With the commercialization of private data, location privacy trading in Mobile Crowd Sensing (MCS) has become a fascinating research topic. In consideration of location-dependent sensing tasks, mobile workers take risks at location privacy disclosure when reporting their actual locations. Existing work fail to take workers' diverse privacy protection and trading into account. This paper proposes a novel trading framework with personalized differential privacy guarantee, referred to asLeaper, to bridge the gap between location privacy protection and task allocation efficiency. In particular,Leaperoutputs a personalized obfuscated range for each worker and further obfuscates his location based on a perturbation set within this range by incorporating differential privacy and$k$-anonymity techniques, and thus improves the efficiency of task allocation. Moreover,Leaperquantifies each worker's location privacy loss and compensates him with reasonable payment by running auction in a cost-effective way. Through real-world datasets, our evaluations and analysis demonstrate thatLeaperindeed guarantees all desired properties of personalized differential privacy, truthfulness, individual rationality and budget feasibility.

Sequential recommenders aim to enhance prediction accuracy by leveraging user interaction sequences, with transformer-based models showing particularly strong performance. Among them, cold-start sequential recommenders are particularly challenging because these models typically require extensive historical data to perform optimally. Some works attempt to address this issue by enhancing the adaptive ability of the sequence recommenders with meta-learning approaches. However, they are unsuitable for enhancing the popular Transformer-based sequence recommenders: MAML-based models cannot adapt the large number of parameters of Transformers, while transition-based and metric-based meta-learning models rely on unique architectures that are incompatible with Transformer-based frameworks. Also, they usually lack mechanisms to recognize and cater to multiple interests within short interaction sequences. To address these limitations, we propose MESA, a meta-modulation plugin module specifically designed to enhance the cold-start recommendation of Transformer-based sequential recommender systems. (1) We design a meta-modulation method to directly modulate the parameters in Transformer-based sequence encoders, thus enabling the model to adapt more effectively to new users in cold-start scenarios. (2) Additionally, MESA integrates the Mixture of Experts (MoE) mechanism, which refines sequence representations by utilizing multiple experts, each focusing on different aspects of user interests. This structure enhances the personalization of the recommendation by effectively handling diverse user interests within the sequences. Experiments demonstrate the effectiveness of MESA in cold-start scenarios. Our codes are available here : https://github.com/Mushroom-cat/MESA .

Graph Contrastive Learning (GCL) has recently garnered significant attention for enhancing recommender systems. Most existing GCL-based methods perturb the raw data graph to generate views, performing contrastive learning across these views to learn generalizable representations. However, most of these methods rely on data- or model-based augmentation techniques that may disrupt interest consistency. In this paper, we propose a novel interest-aware augmentation approach based on diffusion models to address this issue. Specifically, we leverage a conditional diffusion model to generate interest-consistent views by conditioning on node interaction information, ensuring that the generated views align with the interests of the nodes. Based on this augmentation method, we introduce DiffCL, a graph contrastive learning framework for recommendation. Furthermore, we propose an easy-to-hard generation strategy. By progressively adjusting the starting point of the reverse denoising process, this strategy further enhances effective contrastive learning. We evaluate DiffCL on three public real-world datasets, and results indicate that our method outperforms state-of-the-art techniques, demonstrating its effectiveness.

User trajectory publication has promoted various location-based applications like user travel recommendation. However, possible privacy leakages have hindered more inclusive trajectory data analysis and utilization. Privacy-preserving trajectory synthesis is a popular approach to address the above privacy issues. Existing methods unavoidably produce low trajectory utility since they usually apply perturbed versions of human moving patterns. Worse still, they cannot adaptively adjust this synthesis according to the varying granularity demands of different users. This paper proposes a novel adaptive trajectory synthesis framework with generated data, namelyADGTrace. Our model achieves privacy preservation without introducing additional noise while maintaining high adaptation.ADGTracedirectly synthesizes artificial trajectories that share the similar patterns with real ones through agenerative and selectiveoptimization process. Additionally, we present a grid granularity alignment strategy to achieve adaptive trajectory synthesis, satisfying varying user demands. Extensive experiments on real-world datasets demonstrate the superiority ofADGTraceover the state-of-the art methods under various utility metrics, maintaining strong attack resilience.

Aggregating noisy labels from mobile crowdsourcing (MCS) to recover true labels is a fundamental yet challenging problem, especially due to the sparsity and unreliability of crowd-contributed data. While most prior work addresses only single-label scenarios, real-world MCS applications often require robust solutions for both single-label and multi-label tasks, where each instance may be associated with multiple categories. In this paper, we propose ATHENA, a novel approach that leverages self-supervision signals inherent in MCS data for effective label aggregation. Firstly, we propose a graph transformer model that can learn from the MCS topology and features. Then, we propose self-supervision signals inherently included in the dataset to help aggregate the labels. To address the unique challenges of multi-label aggregation, we further extend our approach toATHENA+, introducing a label message passing (LMP) module that explicitly models correlations and dependencies among labels. We conducted extensive experiments on multiple single-label and multi-label classification datasets, comparing the proposed models with state-of-the-art methods. Our results demonstrate that ATHENA and ATHENA+ are highly effective in aggregating labels and obtain much better performance than existing methods.

Face authentication has become an increasingly attractive and prevalent technology in human-computer interaction. Recent works have explored radio frequency (RF) signals for illumination-robust and privacy-preserving face authentication. However, these approaches require all users to undergo compulsory prior registration and cannot effectively handle unregistered users, which restricts their practical applicability in real-world scenarios. In this paper, we present ammWave-basedmulti-user face authentication system,m3FacePass, which performs zero-shot face authentication in complex multi-user scenarios using a commercial off-the-shelf (COTS) mmWave radar. First, m3FacePass collects mmWave signals and reconstructs spatial mappings by generating 3D heatmaps. Based on the 3D heatmaps,m3FacePassdetects and separates faces in multi-user scenarios through template matching. Then, unique facial features are extracted and transformed to a hypersphere manifold, which reserves feature space for unregistered users. By introducing dummy classifiers in the authentication model,m3FacePassoptimizes decision boundaries between registered and unregistered users. Furthermore,m3FacePassenhances its generalization ability for zero-shot authentication by incorporating pseudo unknowns during model training. Extensive experiments in real-world environments demonstrate thatm3FacePassachieves an authentication accuracy of 96.6% for registered users and 91.1% for unregistered users in multi-user scenarios.

As a powerful tool to alleviate the data sparsity and cold-start problems in traditional recommender systems, cross-domain recommendation hinges on addressing two fundamental questions: how to transfer knowledge and what to transfer. Regarding the two questions, existing methods have limitations, such as restricted domain connections, inadequate representation disentanglement, and insufficient knowledge transfer. To overcome these challenges, we propose a novel model, KDCLM, which integrates sophisticated knowledge distillation and contrastive learning mechanisms within a multi-view graph architecture. The proposed model comprises two views—a local view and a global view—both of which construct multiple graphs based on user–item interactions to establish richer domain connections. Specifically, the local view incorporates two contrastive learning mechanisms: one for aligning domain-invariant representations and another for differentiating domain-specific representations, which jointly achieve effective representation disentanglement. In addition, we employ knowledge distillation between the global heterogeneous user–item interaction graph and the homogeneous user–user and item–item relationship graphs to facilitate sufficient knowledge transfer. Through extensive experiments on real-world cross-domain recommendation tasks, our proposed KDCLM model demonstrates significant improvements over current state-of-the-art methods. We release our source code at https://github.com/fanydan/KDCLM .

Multimodal recommendation aims to enhance user interest modeling by leveraging informative item multimodal contexts. Though existing GNN-based works have achieved notable success, they typically rely solely on the observed useritem interaction records, while ignoring suboptimal items that can reflect latent user interest. The inadequate records can lead to the insufficient modeling of user interest. Moreover, interest misalignment of cross levels is a prevalent challenge in accurate user modeling, while noisy modality features will further aggravate this problem. In this work, we propose a novel Latent Interest Discovery and Alignment Representation Learning Framework For Multimodal Recommendation (IDARec for short) to mine latent user interest and enhance interest alignment of cross levels via modality denoising. By utilizing rich mutlimodal features, we construct the potential user-item interaction graph and augment original one with it. To denoise modality features for better interest alignment, we adopt information bottleneck principles to extract the minimal and sufficient statistic. Extensive experiments are conducted on three real-world datasets, and the results demonstrate the effectiveness of IDARec.

Face authentication has become an increasingly attractive and prevalent technology in human-computer interaction. Recent works have explored radio frequency (RF) signals for illumination-robust and privacy-preserving face authentication. However, these approaches require all users to undergo compulsory prior registration and cannot effectively handle unregistered users, which restricts their practical applicability in real-world scenarios. In this paper, we present a mmWave-based multiuser face authentication system,$m^{3}$FacePass, which performs zero-shot face authentication in complex multi-user scenarios using a commercial off-the-shelf (COTS) mm Wave radar. First,$m^{3}$FacePass collects mmWave signals and reconstructs spatial mappings by generating 3D heatmaps. Based on the 3D heatmaps,$m^{3}$FacePass detects and separates faces in multi-user scenarios through template matching. Then, unique facial features are extracted and transformed to a hypersphere manifold, which reserves feature space for unregistered users. By introducing dummy classifiers in the authentication model,$\boldsymbol{m}^{\mathbf{3}}$FacePass optimizes decision boundaries between registered and unregistered users. Furthermore,$\boldsymbol{m}^{\mathbf{3}}$FacePass enhances its generalization ability for zero-shot authentication by incorporating pseudo unknowns during model training. Extensive experiments in realworld environments demonstrate that$\boldsymbol{m}^{3}$FacePass achieves an authentication accuracy of 96.6% for registered users and 91.1% for unregistered users in multi-user scenarios.

Social recommendation systems leverage both user-user (u-u) social relations and user-item (u-i) collaborative interactions to improve recommendation quality. Despite their effectiveness, existing models often struggle with task-irrelevant information and misalignment between social and collaborative signals and the downstream recommendation task, leading to suboptimal performance. To address these limitations, we propose a novel framework for Effective and Consistent Information Extraction for Social Recommendation (ECSR). Our approach focuses on two key modules: (1) a task-irrelevant information discarding module that filters out noisy signals from both social relations and user-item interactions, and (2) a task-relevant information alignment module that captures both shared and view-specific task-relevant information, ensuring alignment with the recommendation objective. By integrating them into a unified form, our method extracts minimal and sufficient statistics, which significantly enhance the model's ability to predict user preferences. We validate ECSR on three real-world social recommendation datasets, demonstrating that it consistently outperforms state-of-the-art baselines.

Designing effective negative sampling strategies is crucial for training Multi-Modal Recommendation (MMRec) models, as it helps address the issues of sparse user-item interactions and facilitates the learning of high-dimensional modality features. However, most existing methods randomly sample non-interacted items as negative ones, which frequently result in easy negatives. They limit the model's ability to accurately capture user preferences. In this paper, we propose to Generate Difficulty-aware Negative Samples via conditional diffusion for MMRec (denoted as GDNSM). Leveraging the rich semantic and contextual information from multi-modal features, our method generates hard negative samples with varying difficulty levels, tailored to user preferences. They force the model to learn finer-grained distinctions between positive and negative samples, enhancing its ability to inferring user preferences. To avoid unstable training, we design a dynamic difficulty scheduling mechanism that schedules the negative samples from easy to hard for model training, ensuring both stability and effectiveness. Extensive experiments on three real-world datasets demonstrate that the effectiveness of our models.

The integration of social information into recommender systems (RSs) has gained significant popularity for enhancing recommendation performance and user experience. However, this practice introduces substantial privacy risks, particularly concerning the leakage of sensitive social relationships. While prior research has primarily focused on user-level and interaction-level privacy risks, the social relation-level privacy risks remain largely unexplored. To fill this gap, we investigate social privacy risks through membership inference attacks (MIA) and propose a Social relation-level MIA (SMIA) framework. Two key challenges arise: (1) the adversary can only access the recommended item IDs, which provide indirect and limited information about social relationships, and (2) extracting socially relevant preferences from recommendation results is inherently difficult. To tackle the first challenge, we leverage shadow models to transform sparse item IDs into dense features, enabling adversaries to effectively utilize recommendation outputs. For the second challenge, SMIA employs a dual-branch learning approach that disentangles social and behavioral preferences. Therefore, we can extract socially relevant signals from the disentangled preferences.Extensive experiments on real-world datasets demonstrate that both social and general RSs are highly vulnerable to such attacks, highlighting the urgent need for robust privacy protection mechanisms. To defend against these attacks, we introduce a Socially Adversarial Learning (SAL) defense mechanism that selectively obscures sensitive social information in user representations during training, effectively reducing privacy leakage. We further evaluate the effectiveness of our defense and discuss future directions for developing privacy-preserving mechanisms in social RSs.

With the rapid developments of Internet of Thing (IoT) technologies, side-channel sound sensing has become a key research area. Unlike traditional sound-sensing methods that rely on direct acoustic signal recording, side-channel sound-sensing methods utilize various indirect emissions from electronic devices, such as mechanical vibrations, electromagnetic leakage, etc., to infer sound content, making it preferred in many application scenarios. Recently, many works related to side-channel sound sensing have been proposed and drawn much attention from not only academia but also industry. In this article, we present a comprehensive survey of various side-channel sound-sensing methods. Specifically, we first review the commonly sensed object-state characteristics in side-channel sound-sensing methods. Then, we introduce the widely exploited hardware infrastructure, and signal processing techniques, which are the basis of side-channel sound sensing. After that, we provide a categorization introduction of emerging side-channel sound-sensing methods, and review the common application scenarios. Finally, we provide a thoughtful analysis of the countermeasures, challenges, and future directions in this field. With this survey, we aim to summarize the latest research results in the field of side-channel sound sensing and provide insights and inspiration for future research works.

As one of the most essential accessories, headsets have been widely used in common online conversations. The metal coil vibration patterns of headset speakers/microphones have been proven to be highly correlated with the speaker-produced/microphone-received sound. This paper presents an online conversation eavesdropping system,RFSpy, which uses only one RFID tag attached on a headset to alternately sense metal coil vibrations of headset speaker and microphone for eavesdropping on speaker-produced and microphone-received sound. In some accessible scenarios, assuming attackers secretly attach a small, battery-free RFID tag under one ear cushion of an eavesdropped user’s headset without being noticed. Meanwhile, RFID readers are camouflaged as decorations placed in/out of rooms to transmit and receive RF signals. When the eavesdropped user talks with other users online through the headset,RFSpyfirst activates the RFID tag to capture the metal coil vibration patterns of headset speaker and microphone upon RF signals. Then,RFSpyreconstructs sound spectrograms from the RF signal-based vibration patterns for not only trained words but also untrained (i.e., out-of-vocabulary) words utilizing designed SSR network. Finally,RFSpyconverts the sound spectrograms to conversation content through sound recognition API. Extensive experiments demonstrate thatRFSpycan eavesdrop on online conversations with out-of-vocabulary words effectively.

The technology of facial expression reconstruction has paved the way for various face-centric applications such as virtual reality (VR) modeling, human-computer interaction, and affective computing. Existing vision-based solutions present challenges in privacy leakage and poor lighting conditions. In this paper, we introduce a nonintrusive facial expression reconstruction system,mm3DFace, which uses a millimeter wave (mmWave) radar to reconstruct facial expressions in a privacy-preserving and passive manner.mm3DFacefirst captures and pre-processes mmWave signals reflected by a human face, and extracts intricate facial geometric features using a ConvNeXt model integrated with triple loss embedding. Subsequently,mm3DFacederives pose-invariant facial representations utilizing region-divided affine transformation, and further generates individual facial shapes with 68 facial landmarks. Then, dynamic facial expressions with 3D facial avatars are reconstructed to exhibit realistic facial expressions. Finally,mm3DFaceenables micro-expression recognition with mmWave signals, which ensures the capability of describing tiny facial changes. Through extensive real-world experiments involving 15 participants,mm3DFaceachieves a normalized mean error of 3.94%, a mean absolute error of 2.30 mm, and a 3D-mean absolute error of 4.10 mm in tracking 68 facial landmarks, which demonstrates the efficacy and practicality ofmm3DFacein real-world 3D facial reconstruction scenarios.

Federated learning participants have two identities: model trainers and model users. As model users, participants care most about the performance of the final model on their own distributions, which is called Personal Model Performance (PMP). This makes training a single global model to accommodate all participants impractical because the data distributions of participants are heterogeneous. As model trainers, due to high training costs, participants are reluctant to contribute models if incentives are not enough. With the combination of the above two reasons, we propose a dual-identity double auction as an incentive mechanism in personalized federated learning, allowing directional selection between model users and model trainers, both of which are served by FL participants. Within the double auction framework, we devise a reinforcement learning-based model selection method. This method selects a set of models for each buyer to bid on. The bought models are aggregated to be a personalized model to achieve higher PMP. Additionally, we implement a transaction partition-based approach for determining clearing prices and winning pairs. We address the challenge of the unavailability of private yet essential data distribution information, the coupled influence of model selection and auction results on PMP, and more utility improvement ways of multi-demand dual-identity participants. Finally, our double auction optimizes the PMP of all participants and ensures the truthfulness of multi-demand dual-identity participants, which is harder compared with single-demand single-identity participants.

The proliferation of smart mobile devices has catalyzed the growth of Mobile CrowdSourcing (MCS) as a distributed problem-solving paradigm. MCS platforms heavily rely on advanced truth inference techniques to extract reliable information from diverse and potentially noisy crowd-contributed data. Existing truth inference models often made simplified assumptions about workers or tasks, employing complex Bayesian models or stringent data aggregation methods. These approaches tend to be task-specific, primarily limited to categorical labeling, making adaptations to other mobile computing scenarios labor-intensive. To address these limitations, we introduce the Bipartite Attention-driven Truth (BAT), a versatile approach tailored for mobile computing environments. BAT utilizes an Attributed Bipartite Graph (ABG) to holistically model the MCS process, with workers and tasks as nodes connected by edges representing answer-specific attributes. The approach employs a bipartite graph neural network with an innovative attention mechanism to assess the importance of different answers. BAT extends beyond categorical tasks to support numerical ones by incorporating novel feature representations and model extensions. Theoretical analyses clarify the link between answer similarity and worker expertise. Extensive experiments using diverse real-world datasets demonstrate BAT's superior performance compared to state-of-the-art categorical and numerical truth inference models, highlighting its effectiveness in mobile computing scenarios.

User authentication is evolving with expanded applications and innovative techniques. New authentication approaches utilize RF signals to sense specific human characteristics, offering a contactless and nonintrusive solution. However, these RF signal-based methods struggle with challenges in open-world scenarios, i.e., dynamic environments, daily behaviors with unrestricted postures, and identification of unauthorized users with security threats. In this paper, we present an open-world user authentication system, OpenAuth, which leverages a commercial off-the-shelf (COTS) mmWave radar to sense unrestricted human postures and behaviors for identifying individuals. First, OpenAuth utilizes a MUSIC-based neural network imaging model to eliminate environmental clutter and generate environment-independent human silhouette images. Then, the human silhouette images are normalized to consistent topological structures of human postures, ensuring robustness against unrestricted human postures. Next, fine-grained body features are extracted from these environment-independent and posture-independent human silhouette images using a metric learning model. To eliminate potential security threats that arise from unauthorized users, OpenAuth synthesizes data placeholders for enhancing unauthorized user identification. Finally, a k-NN-based authentication model is constructed to authenticate users' identities. Experiments in real environments show that the proposed OpenAuth achieves an average authentication accuracy of 93.4% and false acceptance rate (FAR) of 1.8% in open-world scenarios.

Multi-access edge computing has become an effective paradigm to provide offloading services for computation-intensive and delay-sensitive tasks on vehicles. However, high mobility of vehicles usually incurs spatio-temporal load-imbalances among edge servers. Therefore, task migration is employed to maintain dynamic workload balancing by transmitting excessive tasks from overloaded to underloaded servers. Recent studies adopt deep reinforcement learning approaches to generate offloading and migration decisions based on current observations of systems. However, we argue that the migration direction is highly dependent on vehicular movements, and task migration towards the wrong direction could lead to additional delays. Therefore, we emphasize the importance of guiding task migration via exploring prospective trajectories of vehicles. We propose a Mobility-Aware Cooperative Multi-Agent (MCMA) deep reinforcement learning approach to make vehicle-by-vehicle decisions in multi-edge computation offloading scenarios. A two-stage decision framework is designed to solve the joint optimization problem of computation offloading and resource allocation. Additionally, an Informer-based multi-step vehicular trajectory prediction module is incorporated to enhance the capability of forecasting vehicular movements. Extensive experiments and analysis are conducted on synthetic and realistic scenarios, showing that our approach consistently outperforms both heuristic and DRL-based methods. The simulation scenarios and source codes are publicly available here.

User cold-start recommendation presents a significant challenge for recommender systems, affecting their overall effectiveness. Meta-learning-based methods have been introduced to address this issue. These methods treat the user cold-start recommendation problem as a few-shot learning task, where each user represents a unique task. The objective is to acquire shared initialization parameters that can be effectively applied across all cold-start users. Subsequently, these shared parameters are fine-tuned into personalized parameters using individual interaction data. Recent studies argue that shared parameters are unsuitable for all users with an implicit grouping distribution of user preference. Therefore, they propose adaptive-initialization-based methods, which first differentiate tasks based on user preferences and then generate task-adaptive initialization parameters using task representations. However, both the meta-learning and adaptive-initialization-based manners ignore discovering the adaptive capability of update strategies in the process of transferring initialization parameters to personalized parameters. Instead, they rely on task-shared optimization strategies, leading the model to fall into an overfitting or underfitting situation. In response to this, we propose a dual-adaptive update strategies-enhanced meta-optimization framework (DAUS) for user cold-start recommendation. First, we integrate dual-adaptive update strategies to enhance the adaptive capability of transferring initialization parameters. This involves incorporating both task-adaptive optimization hyperparameters and objectives. Second, we design a multifaceted task encoder , which can provide diverse task information to differentiate between tasks, including explicit task features (task relevance, training signals) and other implicit task information. Extensive experiments based on three real-world datasets demonstrate that our DAUS outperforms the state-of-the-art methods. The source code is available at https://github.com/XuHao-bit/DAUS .

The need for an adaptive congestion control (CC) service is crucial due to the heterogeneity of systems and the diversity of applications. Traditional CC methods often fail to adaptively balance throughput and delay, struggling to meet the varied demands of different network applications. In this work, we introduceAuto, a novel CC service that employs Multi-Objective Reinforcement Learning (MORL) to transcend these limitations. Unlike conventional approaches,Autooptimizes policies within a single model to cater to all potential preferences for balancing throughput and delay, making it ideal for diverse and heterogeneous network environments. To enhance operational transparency, we developed an interpretation algorithm that translates MORL into a human- readable decision tree, essential for service computing where clarity and interpretability are crucial. Furthermore,Autoallows users to explicitly set flow priorities and target sending rates, meeting varied application demands. Our extensive evaluations show thatAutonot only consistently outperforms existing CC methods in diverse network conditions but also exhibits robustness to stochastic packet loss and rapid network changes. These capabilities establishAutoas a pioneering solution for next-generation congestion control in networking services.

Designed to establish potential relations and distill high-order representations, graph-based recommendation systems continue to reveal promising results by jointly modeling ratings and reviews. However, existing studies capture simple review relations, failing to (1) completely explore hidden connections between users (or items), (2) filter out redundant information derived from reviews, and (3) model the behavioral association between rating and review interactions. To address these challenges, we propose a review-enhanced hierarchical contrastive learning, namely ReHCL. First, ReHCL constructs topic and semantic graphs to fully mine review relations from different views. Moreover, a cross-view graph contrastive learning is used to achieve enhancement of node representations and extract useful review knowledge. Meanwhile, we design a neighbor-based positive sampling to capture the graph-structured similarity between topic and semantic views, further performing efficient contrast and reducing redundant noise. Next, we propose a cross-modal contrastive learning to match the rating and review representations, by exploring the association between ratings and reviews. Lastly, these two contrastive learning modes form a hierarchical contrastive learning task, which is applied to enhance the final recommendation task. Extensive experiments verify the superiority of ReHCL compared with state-of-the-arts.

User authentication is evolving with expanded application scenarios and innovative techniques. New authentication approaches utilize RF signals to sense specific human behaviors and characteristics, such as faces, specific gestures, etc., offering a contactless and nonintrusive solution. However, these RF signal-based methods struggle with challenges in open-world scenarios, i.e., dynamic environments, daily behaviors with unrestricted postures, and identification of unauthorized users with security threats. In this paper, we present an open-world user authentication system, OpenAuth, which leverages a commercial off-the-shelf (COTS) mmWave radar to sense unrestricted human postures and behaviors for identifying individuals. First, OpenAuth utilizes a MUSIC-based neural network imaging model to eliminate environmental clutter and generates environment-independent human silhouette images. Then, the human silhouette images are normalized to consistent topological structures of human postures, ensuring robustness against unrestricted human postures. Based on the environment-independent and posture-independent human silhouette images, OpenAuth further extracts fine-grained body features through a metric learning model for user authentication. To eliminate potential security threats that arise from frequent accesses by unauthorized users, OpenAuth synthesizes data placeholders for enhancing the applicability of unauthorized user identification. Finally, a k-NN-based authentication model is constructed based on the extracted body features to authenticate users' identities. Experiments in real environments show that the proposed OpenAuth achieves an average authentication accuracy of 93.4 % and false acceptance rate (FAR) of 1.8% in open-world scenarios.

Crowdsourcing has become a popular paradigm for collecting large-scale labeled datasets by leveraging numerous annotators. However, these annotators often provide noisy labels due to varying expertise. Truth inference aims to infer accurate consensus labels from noisy crowdsourced annotations. Existing approaches rely heavily on hand-engineered assumptions or ground truth data, limiting their applicability. To address this, we propose GOVERN, a graph contrastive learning framework for truth inference without such external supervision. GOVERN employs a novel graph data augmentation strategy to generate views capturing worker coordination patterns. A contrastive objective then encourages invariant representations across views, enabling the discovery of features related to the hidden consensus. Further, a label correction method based on k-nearest neighbors refines noisy pseudo-labels to supervise model training. Comprehensive experiments on 9 real-world datasets demonstrate that GOVERN outperforms state-of-the-art truth inference techniques.

In cross-silo federated learning (FL), organizations cooperatively train a global model with their local data. The organizations, however, may be heterogeneous in terms of data distributions. In such cases, FL might produce a biased global model that is not optimal for each organization. Then each organization faces several fundamental questions: should I join FL or just remain alone? If joining FL, which organizations should I cooperate with? In this work, we formulate a coalition formation game in cross-silo FL to help organizations choose proper cooperators. We first build an estimation method to predict personal model performance for each organization before FL starts, and we treat performance improvement as individual utility. With estimated utilities, we design a distributed coalition formation algorithm to find stable coalition structures and optimize social welfare at the same time. Our simulations based on MNIST and FMNIST datasets show that the estimation model can predict the sign of the utility correctly with a probability of 0.9 and has an average relative error of $30 \%$. With the above errors, the obtained coalition structure performs well from both perspectives of real social welfare and individual satisfaction.

POI recommendation aims to learn diverse user preferences based on their historical behavioral trajectories and to recommend locations that align with user interests. In this scenario, discerning behavioral patterns and preferences from user check-in sequences plays a crucial role. In recent study, Markov Chain-based methods mainly focus on modeling transition relation between items in a sequence, RNN-based and attention-based methods pay great attention to capture sequence patterns and user’s preferences. However, existing methods neglect the significance of the user’s current intent in next POI recommendation. In our work, we propose a novel Intent-Aware Cross Attention for next POI Recommendation (ICARec) to provide intent insight into the user’s short-term trajectory for better and accurate recommendation. We not only modeling the long/short-term user preference by segmented check-in sequences, but also design an intent cross-attention module which enables interactions between the user’s intent and their most recent check-ins. In addition, to enhance the pairwise independence of intents, we adopt an auxiliary loss function to disentangle intents, endowing them with greater interpretability by ensuring that each intent is represented as an independent and distinct construct within the model. Extensive experiments on two real-world datasets validate the superior performance of our model.

Eavesdropping on human sound is one of the most common but harmful ways to threaten personal privacy. As one of the most essential accessories, headsets have been widely used in common online conversations, such as online calls, video meetings, etc. The metal coil vibration patterns of headset speakers/microphones have been proven to be highly correlated with the speaker-produced/microphone-received sound content. This paper presents an online conversation eavesdropping system, RFSpy, which uses only one RFID tag attached on a headset to alternately sense the metal coil vibrations of headset speaker and microphone for eavesdropping on speaker-produced and microphone-received sound. In some accessible scenarios, such as meeting rooms, offices, etc., assuming attackers secretly attach a small, battery-free RFID tag under one ear cushion of an eavesdropped user's headset without being noticed. Meanwhile, RFID readers are camouflaged as decorations placed in/out of rooms to transmit and receive RF signals. When the eavesdropped user talks with other users online by using the headset, RFSpy first activates the RFID tag attached on the headset to capture the metal coil vibration patterns of headset speaker and microphone upon RF signals. Then, RFSpy reconstructs sound spectrograms from the RF signal-based vibration patterns for not only trained words but also untrained (i.e., out-of-vocabulary) words by utilizing a designed Sound Spectrogram Reconstruction (SSR) network. Finally, RFSpy converts the sound spectrograms to conversation content through a sound recognition API. Extensive experiments in real environments demonstrate that RFSpy can eavesdrop on online conversations with out-of-vocabulary (OOV) words effectively.

Wireless powered mobile edge computing combines the benefits of wireless power transfer and mobile edge computing, enabling mobile devices (MDs) to overcome energy and computational constraints by obtaining energy from hybrid access point (HAP) and offloading computation tasks to HAP. However, given the devices' half-duplex nature, conflicts arise between time allocation and task offloading. Current research lacks a comprehensive examination of the joint impact of task offloading and time allocation on long-term delay. Furthermore, most existing centralized solutions may encounter issues such as dimensionality explosion and so on. This paper thoroughly investigates the task offloading problem in wireless powered mobile edge computing systems, focusing on minimizing long-term task completion delay under delay and energy constraints. To address this problem, we reformulate the task offloading process as a bi-level Markov decision process and convert it into an optimization problem of finding the optimal policy. Subsequently, we introduce a Bi-level Actor-Critic-based Task Offloading Approach (BiAC-TOA), where MDs and HAP leverage centrally trained agents for decisions on task offloading and time allocation in a decentralized manner. Finally, a series of experiments confirm the superiority of our proposed approach.

Graph-based social recommendation improves the prediction accuracy of recommendation by leveraging high-order neighboring information contained in social relations. However, most of them ignore the problem that social relations can be noisy for recommendation. Several studies attempt to tackle this problem by performing social graph denoising, but they suffer from 1) adaptability issues for other graph-based social recommendation models and 2) insufficiency issues for user social representation learning. To address the limitations, we propose a model-agnostic graph denoising module (denoted as MADM) which works as a plug-and-play module to provide refined social structure for base models. Meanwhile, to propel user social representations to be minimal and sufficient for recommendation, MADM further employs mutual information maximization (MIM) between user social representations and the interaction graph and realizes two ways of MIM: contrastive learning and forward predictive learning. We provide theoretical insights and guarantees from the perspectives of Information Theory and Multi-view Learning to explain its rationality. Extensive experiments on three real-world datasets demonstrate the effectiveness of MADM.

Information networks generally exhibit three characteristics, namely dynamicity, heterogeneity, and node attribute diversity. However, most existing network embedding approaches only consider two of the three when embedding each node into low-dimensional space. Adding to such an existing approach a technique of processing the remaining characteristic can easily cause incompatibility. One solution to process the three characteristics together is to treat the dynamic heterogeneous attributed network (DHAN) as a temporal sequence of heterogeneous attributed network (HAN) snapshots. For example, existing graph convolutional networks (GCNs)-based DHAN embedding approaches embed the HAN snapshots to get static representations offline, and then dynamically capture temporal dependencies between adjacent snapshots online to maintain fresh representations of the DHAN. However, those approaches encounter the convergence problem when stacking multiple convolutional layers to capture more topological information. Some other existing approaches dynamically update the representations of HAN snapshots online, neglecting the efficiency requirement of online scenarios and the temporal dependencies between snapshots. To address the two issues, we propose a new framework called Dynamic Heterogeneous Attributed Network Embedding (DHANE), consisting of a static model MGAT and a dynamic model NICE. MGAT captures more topological information while maintaining GCN convergence by performing metagraph-based attention in each convolutional layer. NICE preserves network freshness while reducing the computational load of the update by only examining network changes and updating their embedding representations. Extensive experiments show that DHANE achieves up to 27× speedup and 9.1-26.4% higher accuracy on several real dynamic heterogeneous attributed networks for online classification.

As the metaverse continues to expand, it becomes increasingly critical to have human-centric networks that are both efficient and high-performing to optimize the user experience. Network modeling plays a fundamental role in optimizing and allocating resources efficiently, and configuring networks to satisfy the demands of diverse applications and users. Recently, traditional queuing theory-based approaches to network modeling have given way to machine learning-based methods. These methods rely on vast amounts of data for building precise models. Although high-precision simulators are ubiquitous, data collection is still an expensive and time-consuming process, resulting in a data bottleneck. In this paper, we propose a weakly supervised learning approach to modeling networks for human-centric networking in the metaverse. Specifically, we identify that queuing theory-based labels can be used to design the supervision signal at a very low cost. Therefore, we propose an approach that combines the inaccurate network modeling obtained from queuing theory-based approaches with an efficient and precise network model through only a small amount of simulation data. To make it a reality, we propose a novel neural network model that combines the powerful graph neural network and transformers. Additionally, we propose several additional supervision signals and a training algorithm to build a better network model. Experimental results demonstrate that our approach reduces the burden of data collection while achieving prediction accuracy comparable to results from large amounts of expensive simulation data. Furthermore, our approach exhibits superior generalization ability.

Sequential recommendation is a critical part of the flourishing online applications by suggesting appealing items on users’ next interactions, where global dependencies among items have proven to be indispensable for enhancing the quality of item representations toward a better understanding of user dynamic preferences. Existing methods rely on pre-defined graphs with shallow Graph Neural Networks to capture such necessary dependencies due to the constraint of the over-smoothing problem. However, this graph representation learning paradigm makes them difficult to satisfy the original expectation because of noisy graph structures and the limited ability of shallow architectures for modeling high-order relations. In this paper, we propose a novel Graph Diffusion Representation-enhanced Attention Network for sequential recommendation, which explores the construction of deeper networks by utilizing graph diffusion on adaptive graph structures for generating expressive item representations. Specifically, we design an adaptive graph generation strategy via leveraging similarity learning between item embeddings, automatically optimizing the input graph topology under the guidance of downstream recommendation tasks. Afterward, we propose a novel graph diffusion paradigm with robustness to over-smoothing, which enriches the learned item representations with sufficient global dependencies for attention-based sequential modeling. Moreover, extensive experiments demonstrate the effectiveness of our approach over state-of-the-art baselines.

Desirable information processing in space-terrestrial integrated vehicle networks (STINs) handles data distributed in different satellites while transmitting, where efficient modeling time-varying resources is critical. Existing works are not applicable to STINs, however, because they lack the joint consideration of different movement patterns and fluctuating loads. In this paper, we propose theTime-Varying Resource Graph (TVRG)to model dynamic resources in STINs, by leveraging the advantages of software-defined networking in flexible resource management. Firstly, we propose theSTIN mobility modelto uniformly model different movement patterns in STINs. Then, we propose alayered Resource Modeling and Abstraction (RMA)approach, where evolutions of node resources are modeled as Markov processes, by encoding predictable topologies and influences of fluctuating loads as states. Besides, we propose the low-complexity domain resource abstraction algorithm by defining two mobility-based and load-aware partial orders on resource abilities. Finally, we formulate theTVRG-based Processing on the Way (TPoW)problem for data flows with processing requirements and multiple sources. We propose aMulti-level Processing on the Way (MPoW)approach with a bounded approximation ratio, realizing adaptive matching of resources and demands of processing and transmission. To evaluate the RMA approach, we propose aTVRG-based Routing (TR)algorithm for time-sensitive and bandwidth-intensive data flows, with the multi-level on-demand scheduling ability. Comprehensive simulation results demonstrate that our RMA-TR and MPoW outperform most related schemes by decreasing nearly 40% bandwidth consumption with the shortest end-to-end delay.

Gait-based user authentication schemes have been widely explored because of their ability of non-invasive sensing and avoid replay attacks. However, existing gait-based user authentication methods are environment-dependent. In this paper, we present an environment-independent gait-based user authentication system,RFPass, which can identify different individuals leveraging RFID signals. Specifically, we find that Doppler shift of RF signals can describe environment-independent gait features for different individuals. InRFPass, when a user walks through theRFPasssystem, RF signals are first collected by a deployed RFID tag array. Then,RFPassremoves environmental interference from the collected RF signals through a proposed Multipath Direction of arrival (DoA) Signal Select (MDSS) algorithm, and further constructs the environment-independent gait profile. Afterwards, environment-independent gait features are extracted from the constructed gait profile by a proposed CNN-RNN model. Based on the extracted gait features, a hierarchical classifier is trained for user authentication and spoofer detection. Extensive experiments in different real environments demonstrate thatRFPasscan achieve environment-independent gait-based user authentication.

Acoustic target tracking has shown great advantages for device-free human-machine interaction over vision/RF-based mechanisms. However, existing approaches for portable devices solely track a single target, incapable of the ubiquitous and highly challenging multi-target situations such as double-hand multimedia controlling and multi-player gaming. In this paper, we proposeAMT$^+$, a pioneering smartphone MIMO system to achieve centimeter-level multi-target tracking. The challenge of multi-target occlusion is effectively addressed by employing multiple speaker-microphone pairs. However, the unique challenge raised by MIMO is the superposition of multi-source signals due to the cross-correlation among speakers. Initially, we tackle this challenge by designing a weak cross-correlation signal to reduce interference passively. InAMT$^+$, we’ve further integrated self-interference cancellation for active minimize interference. The most distinguishing advantage ofAMT$^+$lies in the elimination of the raised multipath effect, which is commonly ignored in previous work by hastily assuming targets as particles.AMT$^+$employs Doppler filtering over delay subtraction for echo suppression. Further, by non-particle target reflections modeling results, we introduce a distance-projection-based method for continuous target identification and tracking. Implemented on commercial smartphones,AMT$^+$achieves on average 0.54 cm, 1.37 cm, and 2.13 cm errors for single, double, and triple target tracking respectively, and on average 97.0% classification accuracy for 14 controlling gestures.

Deep learning-based recommender systems have achieved remarkable success in recent years. However, these methods usually heavily rely on labeled data (i.e., user-item interactions), suffering from problems such as data sparsity and cold-start. Self-supervised learning, an emerging paradigm that extracts information from unlabeled data, provides insights into addressing these problems. Specifically, contrastive self-supervised learning, due to its flexibility and promising performance, has attracted considerable interest and recently become a dominant branch in self-supervised learning-based recommendation methods. In this survey, we provide an up-to-date and comprehensive review of current contrastive self-supervised learning-based recommendation methods. Firstly, we propose a unified framework for these methods. We then introduce a taxonomy based on the key components of the framework, including view generation strategy, contrastive task, and contrastive objective. For each component, we provide detailed descriptions and discussions to guide the choice of the appropriate method. Finally, we outline open issues and promising directions for future research.

Review-based recommender systems explore semantic aspects of users’ preferences by incorporating user-generated reviews into rating-based models. Recent works have demonstrated the potential of review information to improve the recommendation capacity. However, most existing studies rely on optimizing review-based representation learning part, thus failing to explicitly capture the fine-grained semantic aspects, and also ignoring the intrinsic correlation between ratings and reviews. To address these problems, we propose a multi-aspect graph contrastive learning framework, named MAGCL, with three distinctive designs: (i) a multi-aspect representation learning module, which projects semantic relations to different subspaces by decoupling review information, and then obtains high-order decoupled representations in each aspect via graph encoder. (ii) the contrastive learning module performs graph contrastive learning to capture the correlation between rating and review patterns, which utilize unlabeled data to generate self-supervised signals and, in turn, relieve the data sparsity problem of supervision signals. (iii) the multi-task learning module conducts joint training to learn high-order structure-aware yet self-discriminative node representations by combining recommendation task and self-supervised task, which helps alleviate the over-smoothing problem. Extensive experiments are conducted on four real-world review datasets and the results show the superiority of the proposed framework MAGCL compared with several state of the arts. We also provide further analysis on multi-aspect representations and graph contrastive learning to verify the advantage of proposed framework.

Cross-domain recommendation (CDR), which leverages information collected from other domains, has been empirically demonstrated to effectively alleviate data sparsity and cold-start problems encountered in traditional recommendation systems. However, current CDR methods, including those considering time information, do not jointly model the general and current interests within and across domains, which is pivotal for accurately predicting users’ future interactions. In this article, we propose a Contrastive learning-enhanced Multi-View interest learning model (CMVCDR) for cross-domain sequential recommendation. Specifically, we design a static view and a sequential view to model uses’ general interests and current interests, respectively. We divide a user’s general interest representation into a domain-invariant part and a domain-specific part. A cross-domain contrastive learning objective is introduced to impose constraints for optimizing these representations. In the sequential view, we first devise an attention mechanism guided by users’ domain-invariant interest representations to distill cross-domain knowledge pertaining to domain-invariant factors while reducing noise from irrelevant factors. We further design a domain-specific interest-guided temporal information aggregation mechanism to generate users’ current interest representations. Extensive experiments demonstrate the effectiveness of our proposed model compared with state-of-the-art methods.

Recent years have witnessed enormous research efforts on WiFi sensing to enable intelligent services of Internet of Things. However, due to the omni-directional broadcasting manner of WiFi signals, the activity semantic underlying the signals can be leaked to adversaries for surveillance, as demonstrated by our previous work. In this paper, we further extend the attack capability ofActListenerto impersonation attack, which could eavesdrop on users’ behavioral uniqueness imperceptibly using a WiFi infrastructure in any location of user sensing area. In particular,ActListener detects each human activityand converts the eavesdropped signals to that by legitimate devices based on our proposed signal propagation models. To extract noise-resilient individual behavioral uniqueness from converted CSI of WiFi signals, we further add user identification models into the substitute model set for training the signal pattern calibration generative model. Experimental results demonstrate thatActListenercould achieve over 80% accuracy in activity semantics retrieval and impersonation by using the converted signals.

As the most important incremental component in the advent of the 6G era, Low-Earth-Orbit (LEO) satellite networks are becoming increasingly instrumental, and their integration with Software-Defined Networking (SDN) is progressively recognized as a potent strategy for evolving toward truly service-centric networks, where networks are flexiblely reconstructed based on the service demands. Within such networks, the SDN controllers are responsible for network management by making service-aware resource orchestration. Hence, the placement and assignment of controllers emerge as one of the most critical aspects of the network management service, which becomes particularly challenging when confronted with the unique complexities posed by LEO satellite networks, characterized by their highly dynamic topology and unpredictable load fluctuations. In this paper, for the first time, we tackle the issue of controller placement and assignment with a focus on delivering network management services. Firstly, we formulate theadaptive controller placement and assignmentproblem. Then, we propose thecontrol relation graph (CRG)to capture the control overhead. Next, we present theCRG-based controller placement and assignmentalgorithm and thesliding window based traffic prediction method. Thelookahead-based improvementalgorithm is designed to further decrease management costs. Finally, we conduct a series of theoretical analyses including time complexities. Extensive emulation results demonstrate that our algorithms outperform related schemes in terms of response time and load balancing.

User cold-start recommendation is one of the most challenging problems that limit the effectiveness of recommender systems. Meta-learning-based methods are introduced to address this problem by learning initialization parameters for cold-start tasks. Recent studies attempt to enhance the initialization methods. They first represent each task by the cold-start user and interacted items. Then they distinguish tasks based on the task relevance to learn adaptive initialization. However, this manner is based on the assumption that user preferences can be reflected by the interacted items saliently, which is not always true in reality. In addition, we argue that previous approaches suffer from their adaptive framework (e.g., adaptive initialization), which reduces the adaptability in the process of transferring meta-knowledge to personalized RSs. In response to the issues, we propose a task-difficulty-aware meta-learning with adaptive update strategies (TDAS) for user cold-start recommendation. First, we design a task difficulty encoder, which can represent user preference salience, task relevance, and other task characteristics by modeling task difficulty information. Second, we adopt a novel framework with task-adaptive local update strategies by optimizing the initialization parameters with task-adaptive per-step and per-layer hyperparameters. Extensive experiments based on three real-world datasets demonstrate that our TDAS outperforms the state-of-the-art methods. The source code is available at https://github.com/XuHao-bit/TDAS.

Typhoons, formidable natural phenomena, typically unleash a trail of destruction, inflicting severe wind damage, floods, and even triggering tsunamis in coastal regions. Therefore, accurate prediction of typhoon intensity carries immense significance, both in theory and practical applications. Convolutional Neural Networks (CNNs) have shown superior capability in modelling spatial and temporal data. However, conventional convolutional operators are very sensitive to rotations, and is not good at modelling hierarchical structures. Since typhoon intensity data are typical spatiotemporal data that possess a distinctive rotational structure and a multi-layered hierarchy, conventional CNN based models fall short in capturing high-order spatial information, thereby limiting the accuracy of predictions. To address the limitations of conventional convolutional operators, we introduce a typhoon intensity prediction model called Multi-scale Spin Convolutional Neural Network (MS-CNN). Our model rotates the convolution kernel approximately to better model the rotating horizontal structure of the typhoons. Additionally, it employs a fine-grained multi-scale architecture to capture the hierarchical structure of typhoons. We conducted a series of comprehensive experiments using typhoon track dataset in the Western North Pacific. The results demonstrate that the superior performance of our MS-CNN model compared to other state-of-the-art models, marking a substantial advancement in typhoon intensity prediction tasks.

Textual reviews have been widely utilized in recommender systems because text reviews contain rich user preference information. Recent studies have increasingly incorporated textual reviews into user-item graphs as auxiliary information to learn node representations, notably enhancing recommendation performance. However, most existing review-based recommendations could not effectively exploit correlations between ratings and reviews, and suffer from noisy interactions which are further amplified during neighborhood aggregation. To address such limitations, we propose a new graph contrastive learning model for review-based recommendations in this paper. We construct a user-item graph view using both ratings and reviews. In addition, we design two graph views with ratings and reviews, respectively. Through contrastive learning based on these three views, our model manages to generate rich supervision signals for both user and item nodes. Our approach effectively explores intrinsic correlations between heterogeneous rating and review data, which enhance the robustness against interaction noises. A comprehensive experimental study on five benchmark datasets demonstrates that our model outperforms state-of-the-art methods.

Most existing collaborative filtering-based recommendation models only use a single type of interactive data. However, in real-world scenarios, there is more than one type of user interaction behavior. Although numerous recommendation models already use multi-behavior to make recommendation, there are still two limitations for them: i) the scarcity of supervised interaction data under the target behavior; ii) unable to obtain high-order collaborative relation due to over-smoothing. In order to solve the above problems, we propose a multi-behavior recommendation model, D ual C ontrastive L earning (DCL), based on contrastive learning. In DCL, a graph neural network is used to learn the local representations of users and items under multiple behaviors, while a hypergraph neural network is used to capture the global item dependency. In particular, we design two contrastive learning strategies to reinforce the quality of representations. Behavior-wise contrastive learning captures the knowledge that can be transferred between different behaviors. As well as item-wise contrastive learning captures the dependencies between item representations from different perspectives. The effectiveness of our method is verified on three real-world datasets, and the recommendation performance of DCL is superior to the various state-of-the-art recommendation models. At the same time, we also verify the robustness of our model for users with sparse interactions.

Predicting user behavior based on their interactions poses a great challenge in the realm of sequential recommendation. This challenge primarily stems from the erratic and periodic nature of user behavior. Recent approaches leverage attention mechanisms to capture users’ long- and short-term interests by analyzing their past interactions, and have achieved notable improvements of recommendation performance. However, none of these methods take into account semantic subsequences, which are indicative of a user’s focused activity over a specific period within the sequence. Incorporating semantic subsequences can significantly enhance the attention mechanism’s ability to capture users’ short-term interests.In this paper, we introduce the Semantic Subsequences Recognizer for Sequential Recommendation (SSR4Rec), comprising two distinct modules tailored for modeling long-term and short-term interests, respectively. For short-term interest modeling, we present a novel LSTM network that intelligently identifies semantic subsequences within sequences. It then extracts semantically coherent subsequences to create a representation of short-term interests. Meanwhile, for long-term interest modeling, we employ a modified BERT model to generate long-term interest representations. Our extensive experiments on three benchmark datasets demonstrates that SSR4Rec outperforms other state-of-the-art sequential models such as Locker and STOSA.

As a popular location-based service, next point-of-interest (POI) recommendation predicts users’ next movements based on recent visits. Existing works mostly focus on individual sequential preference mining, ignoring the crucial crowd transition patterns under the effects of corresponding spatio-temporal (ST) contexts. Intuitively, users also follow crowd transition rules. In order to better exploit the extensive ST-specific collaborative signals among users, we propose a novel next POI recommender, including both ST-adaptive crowd-enhanced preference and user-specific multi-semantic interest modeling. We firstly introduce user-agnostic region-and timeslot-level graphs to capture ST-specific crowd transition patterns. As they imply fine-grained general preferences and function as prior meta knowledge, we employ a meta gated recurrent network to make an adaptive prediction for specific ST-context in a meta-learned unified way. Moreover, in modeling user-specific interest, we extract multi-semantic correlations from graph-augmented personal trajectories to obtain high-quality preference representation. Extensive experiments on real-world datasets show the superiority of our proposed model against seven state-of-the-art methods.

Performance analysis is of great importance for management and optimization of space-terrestrial integrated networks (STINs). Traditional approaches to network performance analysis are often based on idealized assumptions that are deviated from the real network environment. This leads to the fact that these models are usually inefficient and restricted in real-world STINs with complicated behavior and even dynamic capacity. In this paper, we propose a network performance analysis approach EAGLE based on heterogeneous graph neural networks. Firstly, we propose a powerful computer network representation model that can preserve all of the information in computer networks. It represents different components of computer networks as a set of heterogeneous nodes and edges, and finally constructs a heterogeneous graph. Then, we obtain the topological representation for the routers in the network through a bandwidth-aware network embedding model. Based on this heterogeneous graph, we propose a heterogeneous GNN model to accurately predict network KPIs because it can completely capture the rich topological and attribute information of computer networks. Experimental results demonstrate that EAGLE can accurately model different networks, and outperforms both traditional methods and the latest neural network-based methods.

Recent years have witnessed the emerging market of 3D facial reconstruction that supports numerous face-driven scenarios including modeling in virtual reality (VR), human-computer interaction, and affective computing applications. Current mainstream approaches rely on vision for 3D facial reconstruction, which may encounter privacy concerns and suffer from obstruction scenes and bad lighting conditions. In this paper, we present a nonintrusive 3D facial reconstruction system, mm3DFace, which leverages a millimeter wave (mmWave) radar to reconstruct 3D human faces that continuously express facial expressions in a privacy-preserving and passive manner. Based on the pre-processed mmWave signals, mm3DFace first extracts facial geometric features that capture subtle changes in facial expressions through a ConvNeXt model with triple loss embedding. Then, mm3DFace derives distance and orientation-robust facial shapes with 68 facial landmarks using region-divided affine transformation. mm3DFace next reconstructs facial expressions through a designed regional amplification method and finally generates 3D facial avatars that continuously express facial expressions. Extensive experiments involving 15 participants in real-world environments show that mm3DFace can accurately track 68 facial landmarks with 3.94% normalized mean error, 2.30mm mean absolute error, and 4.10mm 3D-mean absolute error, which is effective and practical in real-world 3D facial reconstruction.

Service placement constitutes a prominent subject in edge computing, given its pivotal role in mitigating service latency. However, conventional heuristic placement strategies encounter difficulties in coping with the intricate dynamics of constantly evolving real-world settings, attributable to the non-stationary nature of service demand and time-varying network conditions. To tackle this challenge, deep reinforcement learning (DRL) techniques have received substantial attention. These approaches harness dynamic edge environments, encompassing cloud, edge, terminal devices, and wireless communication channels, to acquire placement policies through interactive learning. Nevertheless, a significant drawback of these learning-based approaches lie in their frequent necessity for retraining when confronted with novel edge environments, thereby resulting in inefficiencies in dynamic service placement across heterogeneous environments. To overcome this limitation, this paper proposes an innovative recurrent neural network (RNN)-based meta-reinforcement learning (meta-RL) technique. This technique capitalizes on prior historical experiences to expedite the learning of new policies in unfamiliar situations. Extensive simulation results are presented to illustrate the commendable performance of our proposed scheme.

Federated learning (FL) has been widely used in edge computing that enables artificial intelligence at the network edge as a distributed machine learning paradigm. In contrast to traditional cloud-based distributed training, the heterogeneity in edge computing may cause federated learning taking long training time. In this paper, we adapt control parameter (i.e., local epoch size) across devices to minimize wall-clock convergence time with joint consideration of resource heterogeneity and statistical heterogeneity. To analyze the influence of statistical heterogeneity, we derive a convergence upper bound for synchronous FL algorithm and establish the relationship between the number of training rounds and local epoch size under heterogeneous data distribution. Based on the convergence bound, we can solve the non-convex problem of minimizing FL training time with accuracy constraint and obtain near-optimal local epoch size. We develop a scheduling algorithm that estimates the statistical heterogeneity in initial training rounds and subsequently guides adaptive local training across devices. Practically, we evaluate our algorithm in a variety of heterogeneous scenarios. Extensive simulation results demonstrate that our algorithm performs high convergence speed over wall-clock time and spends less time reaching target accuracy compared with benchmark approaches.

The issue of user cold-start poses a long-standing challenge to recommendation systems, due to the scarce interactions of new users. Recently, meta-learning based studies treat each cold-start user as a user-specific few-shot task and then derive meta-knowledge about fast model adaptation across training users. However, existing solutions mostly do not clearly distinguish the concept of new users and the concept of novel preferences, leading to over-reliance on meta-learning based adaptability to novel patterns. In addition, we also argue that the existing meta-training task construction inherently suffers from the memorization overfitting issue, which inevitably hinders meta-generalization to new users. In response to the aforementioned issues, we propose a preference learning decoupling framework, which is enhanced with meta-augmentation (PDMA), for user cold-start recommendation. To rescue the meta-learning from unnecessary adaptation to common patterns, our framework decouples preference learning for a cold-start user into two complementary aspects: common preference transfer, and novel preference adaptation. To handle the memorization overfitting issue, we further propose to augment meta-training users by injecting attribute-based noises, to achieve mutually-exclusive tasks. Extensive experiments on benchmark datasets demonstrate that our framework achieves superior performance improvements against state-of-the-art methods. We also show that our proposed framework is effective in alleviating memorization overfitting.

Next Point-of-Interest (POI) recommendation is an essential part of the flourishing location-based applications, where the demands of users are not only conditioned by their recent check-in behaviors but also by the critical influence stemming from geographical dependencies among POIs. Existing methods leverage Graph Neural Networks with the aid of pre-defined POI graphs to capture such indispensable correlations for modeling user preferences, assuming that the appropriate geographical dependencies among POIs could be pre-determined. However, the pre-defined graph structures are always far from the optimal graph topology due to noise and adaptability issues, which may decrease the expressivity of learned POI representations as well as the credibility of modeling user preferences. In this paper, we propose a novel Adaptive Graph Representation-enhanced Attention Network (AGRAN) for next POI recommendation, which explores the utilization of graph structure learning to replace the pre-defined static graphs for learning more expressive representations of POIs. In particular, we develop an adaptive POI graph matrix and learn it via similarity learning with POI embeddings, automatically capturing the underlying geographical dependencies for representation learning. Afterward, we incorporate the learned representations of POIs and personalized spatial-temporal information with an extension to the self-attention mechanism for capturing dynamic user preferences. Extensive experiments conducted on two real-world datasets validate the superior performance of our proposed method over state-of-the-art baselines.

Summary When large‐scale content‐based publish/subscribe systems face dynamic workloads, it is challenging to stabilize event delivery latency. In this article, we propose a latency‐aware parallelism framework (Lap) to address this challenge. Specifically, we propose a lightweight parallelism method called PhSIH for event matching algorithms. In addition, we design a reactive parallelism degree adjustment (RPDA) mechanism in the backpressure way to determine the parallelism degree. We implement Lap in Apache Kafka and evaluate the parallelism effect of PhSIH and the adaptability of RPDA on trace data. The experiment results demonstrate that PhSIH achieves linear speedup on three existing algorithms and RPDA possesses a desirable adaptability to the dynamic workloads.

The trading of social media data has attracted wide research interests over years. In particular, the trading for Web browsing histories, when being applied to targeted advertising, produces tremendous economic value for data consumers. However, the disclosure of entire browsing histories, even in form of anonymous data sets, poses a huge threat to user privacy. Although some existing solutions have investigated privacy-preserving outsourcing of social media data, unfortunately, they neglected the impact on the data consumer’s utility. In this article, we propose CEATSE, a correlated data trading framework for various kinds of private Web browsing histories. CEATSE first models the correlation among multiple dimensional features, and then generates the optimal feature clustering scheme. Combined with this scheme, CEATSE next incorporates a correlated data perturbation strategy on each feature cluster, in order to balance the privacy-utility tradeoff. It then quantifies each chosen data contributor’s privacy loss on optimal feature clusters. Through real-data-based experiments, our analysis and evaluation results demonstrate CEATSE indeed achieves user privacy protection, the data consumer’s accuracy requirement, and truthfulness, individual rationality as well as budget balance.

Behavior prediction based on historical behavioral data have practical real-world significance. It has been applied in recommendation, predicting academic performance, etc. With the refinement of user data description, the development of new functions, and the fusion of multiple data sources, heterogeneous behavioral data which contain multiple types of behaviors become more and more common. In this paper, we aim to incorporate heterogeneous user behaviors and social influences for behavior predictions. To this end, this paper proposes a variant of Long-Short Term Memory (LSTM) which can consider context information while modeling a behavior sequence, a projection mechanism which can model multi-faceted relationships among different types of behaviors, and a multi-faceted attention mechanism which can dynamically find out informative periods from different facets. Many kinds of behavioral data belong to spatio-temporal data. An unsupervised way to construct a social behavior graph based on spatio-temporal data and to model social influences is proposed. Moreover, a residual learning-based decoder is designed to automatically construct multiple high-order cross features based on social behavior representation and other types of behavior representations. Qualitative and quantitative experiments on real-world datasets have demonstrated the effectiveness of this model.

Multi-access Edge Computing has come forth as a promising paradigm to provide low-latency computing service to mobile end users. Its basic idea is to deploy computation resources at the edge of core networks such as wireless access points, and then users can offload their tasks to nearby edge nodes for processing. Plenty of works have well studied the task offloading problem, aiming to reduce task completion delays. Also, a few recent works have focused on task dispatching among edge nodes to balance their workloads and improve resource utilization. In this work, we jointly consider the task offloading and dispatching problem in an edge computing system with interconnected access points. Furthermore, we assume both end devices and access points are rational, which only care about their own benefits. To solve the joint problem, we firstly formulate it as a multi-leader multi-follower Stackelberg game, and rigorously prove the existence of a Stackelberg equilibrium. Then, we propose two algorithms for task offloading and dispatching, respectively. Extensive simulations are conducted to show the superiority of our proposed approach. We also demonstrate that an upper bound with a constant approximation ratio is achieved by our approach.

Graph Convolutional Networks (GCNs) have been widely used for collaborative filtering, due to their effectiveness in exploiting high-order collaborative signals. However, two issues have not been well addressed by existing studies. First, usually only one kind of information is utilized, i.e., user preference in user-item graphs or item dependency in item-item graphs. Second, they usually adopt static graphs, which cannot retain the temporal evolution of the information. These can limit the recommendation quality. To address these limitations, we propose to mine three kinds of information (user preference, item dependency, and user behavior similarity) and their temporal evolution by constructing multiple discrete dynamic heterogeneous graphs (i.e., a user-item dynamic graph, an item-item dynamic graph, and a user-subseq dynamic graph) from interaction data. A novel network (PDGCN) is proposed to learn the representations of users and items in these dynamic graphs. Moreover, we designed a structural neighbor aggregation module with novel pooling and convolution operations to aggregate the features of structural neighbors. We also design a temporal neighbor aggregation module based on self-attention mechanism to aggregate the features of temporal neighbors. We conduct extensive experiments on four real-world datasets. The results indicate that our approach outperforms several competing methods in terms of Hit Ratio (HR) and Normalized Discounted Cumulative Gain (NDCG). Dynamic graphs are also shown to be effective in improving recommendation performance.

Textual reviews contain rich semantic information that is useful for making better recommendation, as such semantic information may indicate more fine-grained preferences of users. Recent efforts make considerable improvement on recommendation by integrating textual reviews in rating-based recommendations. However, there still exist major challenges on integrating textual reviews for recommendation. On the one hand, most existing works focus on learning a single representation from reviews but ignoring complex relations between users (or items) and reviews, which may fail to capture user preferences and item attributes together. On the other hand, these works independently learn latent representations from ratings and reviews while omitting correlations between rating-based features and review-based features, which may harm recommendation performance. In this article, we capture the aspect-aware relations by constructing heterogeneous graphs from reviews. Furthermore, we propose a new recommendation model, namely AHOR, to jointly distill rating-based features and review-based features, which are derived from ratings and reviews, respectively. To explore the multi-hop connectivity information between users, items, and aspects, a novel graph neural network is introduced to learn aspect-aware high-order representations. Experiments based on public datasets show that our approach outperforms state-of-the-art methods. We also provide detailed analysis on the high-order signals and the aspect importance to show the interpretability of our proposed model.

User cold-start scenarios pose great challenges to recommendation systems in accurately capturing user preferences with sparse interaction records. Besides incorporating auxiliary information to enrich user/item representations, recent studies under the schema of meta-learning focus on quickly adapting personalized recommendation models based on cold-start users’ scarce interactions. The majority of meta-learning based recommendation methods follow a bi-level optimization paradigm and learn globally shared initialization across all cold-start recommendation tasks. In addition, to further facilitate the ability of fast adaptation, existing methods have made efforts to tailor task-specific prior knowledge by identifying the individual characteristics of each task. However, we argue that multi-view commonalities between existing users and cold-start users are also essential for precisely distinguishing new tasks, but not comprehensively modeled in previous studies. In this article, we propose a multifaceted relation-aware meta-learning approach namely MeCM for user cold-start recommendation, which enhances task-adaptive initialization customization by extracting multiple views of task relevance. We design a dual customization framework consisting of two successive phases including cluster-level customization and task-level customization. Specifically, MeCM first extracts multifaceted semantic relations between tasks and refines task commonalities into task clusters maintained with memory networks (MNs). Globally learned fast weights corresponding to task clusters are queried to perform cluster-level customization. Then task-level customization is triggered based on contextual information of the target task via interaction-wise encoding. Extensive experiments on real-world datasets demonstrate the superior performance of our model over state-of-the-art meta-learning-based recommendation methods.

Many remote sensing applications, such as forest fire monitoring, need to send a large volume of data to the ground with low delay. Therefore, the cooperation transmission, which relies on cooperation among satellites to achieve continuous transmission, emerges as an indispensable technique. Most existing work cannot minimize the delay through dynamic cooperation transmission. In this paper, we investigate how to minimize the delay in remote sensing satellite networks based on cooperation transmission, where cooperation hotspots refer to the satellites with ground-satellite links to the Earth Stations (ESs). First, we propose the cooperation capability model to quantify capabilities of cooperation hotspots. Then, we formulate the satellite cooperation transmission problem and prove its NP-hardness. To solve the problem, we propose the delay-minimized cooperation transmission scheme. Both CCT and DCT algorithms adapt well to the dynamic topology and time-varying available resources. Finally, we formally analyze the approximation ratios and the time complexities of both algorithms. We also prove that the DCT always setups loop-free paths. NS2-based simulation results demonstrate that our schemes have good scalability, and both CCT and DCT algorithms reduce the end-to-end delay on average by more than 21.77%, and significantly improve throughput, packet loss rate and flow completion time.

The controller provisioning, which adjusts the number, locations, and members of satellite controllers adaptive to the dynamic network load and topology, fundamentally impacts the performance of software-defined satellite networks (SDSNs). An ideal provisioning strategy should achieve a low total control overhead throughout the entire satellite operation period, which is extremely challenging since the network loadcan only be predicted in a short time scale. Existing methods can hardly achieve this goal for they greedily configure controllers in each time slot, where switches have to frequently migrate from one controller to another. In this paper, we focus on achievingglobally optimized strategieswith onlycurrent network load information. We first propose a comprehensive control overhead model and formulate theControllerProvisioningProblem (CPP)in SDSNs as a non-convex integer programming problem. To solve the problem, we propose an approximate algorithm named AROA by introducing a regularization framework and based on randomized rounding. We theoretically derive its competitive ratio. To produce strategies in time for future large satellite constellations, we further propose a more efficient heuristic algorithm HROA. Evaluations on our built simulation system show that our proposed methods significantly outperform related schemes in control overhead, latency, and scalability.

Due to the urgent emergence of computation-intensive intelligent applications on end devices, edge computing has been put forward as an extension of cloud computing, to satisfy the low-latency requirements of these applications. To process heterogenous computation tasks on an edge node, the corresponding services should be placed in advance, including installing softwares and caching databases/libraries. Considering the limited storage space and computation resources on the edge node, services should be elaborately selected and deployed on the edge node and its computation resources should be carefully allocated to placed services, according to the arrivals of computation workloads. The joint service placement and computation resource allocation problem is particularly complicated, in terms of considering the stochastic arrivals of tasks, the additional latency incurred by service migration, and the waiting time of unprocessed tasks. Benefiting from deep reinforcement learning, we propose a novel approach based on parameterized deep Q networks to make the joint service placement and computation resource allocation decisions, with the objective of minimizing the total latency of tasks in a long term. Extensive simulations are conducted to evaluate the convergence and performance achieved by our proposed approach.

Traditional recommendation systems are faced with two long-standing obstacles, namely data sparsity and cold-start problems, which promote the emergence and development of Cross-Domain Recommendation (CDR). The core idea of CDR is to leverage information collected from other domains to alleviate the two problems in one domain. Since the early 2010s, many efforts have been engaged for cross-domain recommendation. Recently, with the development of deep learning and neural networks, a large number of methods have emerged. However, there is a limited number of systematic surveys on CDR, especially regarding the latest proposed methods as well as the recommendation scenarios and recommendation tasks they address. In this survey article, we first proposed a two-level taxonomy of cross-domain recommendation that classifies different recommendation scenarios and recommendation tasks. We then introduce and summarize existing cross-domain recommendation approaches under different recommendation scenarios in a structured manner. We also organize datasets commonly used. We conclude this survey by providing several potential research directions about this field.

The commoditization of private data has become an attractive research topic with the emergence of Big Data era. In this paper, we study the trading of high-dimensional private data with differential privacy guarantee. We proposeCheap, which is a novel Correlated data trading framework for High-dimEnsionAl Private data.Cheapfirst models data correlations among high-dimensional user attributes, and builds an initial attribute clustering scheme. Combined with this scheme,Cheapdevises a novel data perturbation mechanism by solving optimal attribute clustering (OAC) problem, in order to improve data utility of traded data and further generate a privacy-preserving high-dimensional dataset with close joint distribution with the original one. It then quantifies privacy loss based on near-optimal attribute cluster scheme due to the NP-hardness of theOACproblem, and further compensates data owners by running auction in a cost-effective way. We evaluate the performance ofCheaponUserBehaviordataset andObesitydataset, respectively. Our evaluation and analysis demonstrate thatCheapwell balances data utility and privacy protection, and achieves all desired economic properties of budget balance, individual rationality and truthfulness.

With the development of 5G, edge computing has raised as a promising technology to satisfy the requirements of computation-intensive and delay-sensitive applications. In this work, we try to propose a task offloading strategy for end users, with considering their individual rationality and collective rationality at the same time. Specially, a user only with individual rationality aims to minimize the completion time of its own task, while a user only with collective rationality aims to minimize the total task completion time achieved by the system. The problem is particularly difficult, as there exist essential conflicts between the individual utility of each user and the collective utility of the system, which cannot be optimized simultaneously. To overcome the difficulties, we first reformulate the problem as a coalition formation game. Then, we propose an iterative algorithm, in which each user can make its task offloading decision in a decentralized way. Additionally, we rigorously prove the properties achieved by our algorithm in terms of stability, optimality, and convergence rate. Extensive simulations are also conducted to validate the performance of our algorithm compared with baselines.

Session-based recommendation (SBR) aims to predict which item will be clicked next for the current session. Many studies have shown the advantages of utilizing graph neural networks (GNN) to learning complicated item relations in session-based recommendations. Most existing methods only utilize the item IDs to model the sequential characteristics for the current session while ignoring the inherent features of items, such as category. In some sessions, all items belong to the same category while in other sessions each item belongs to a different category. It is nontrivial to capture the inter-category and intra-category item relations effectively under this circumstance. In light of this insight, we propose Category-Aware Graph Neural Network (CAGNN) for session-based recommendation. We first construct two graphs to learn inter-category and intra-category item relations over all sessions. Then we fuse the item representations in the same category and get category representations and apply graph attention network to it to learn both item and category relations. Finally, we generate representations for each session and predict the next click. Extensive experiments on two real-world datasets show that our CAGNN model is better than most state-of-the-art baselines.

With the development of smart indoor environments, user authentication becomes an essential mechanism to support various secure accesses. Although recent studies have shown initial success on authenticating users with human activities or gestures using WiFi, they rely on predefined body gestures and perform poorly when meeting undefined body gestures. This work aims to enable WiFi-based user authentication with undefined body gestures rather than only predefined body gestures, i.e., realizing a gesture-independent user authentication. In this paper, we first explore physiological characteristics underlying body gestures, and find that statistical distributions under WiFi signals induced by body gestures can exhibit invariant individual uniqueness unrelated to specific body gestures. Inspired by this observation, we propose a user authentication system, which utilizes WiFi signals to identify individuals in a gesture-independent manner. Specifically, we design an adversarial learning-based model, which suppresses specific gesture characteristics, and extracts invariant individual uniqueness unrelated to specific body gestures, to authenticate users in a gesture-independent manner. Extensive experiments in indoor environments show that the proposed system is feasible and effective in gesture-independent user authentication.

The continuously increasing time spent on car trips in recent years brings growing attention to the physical and mental health of drivers on roads. As one of the key vital signs, the heartbeat is a critical indicator of drivers' health states. Most existing studies on heartbeat monitoring either require sensor attachment or could only provide sketchy heart rates. Moreover, most approaches require the subject to remain stationary or a quiet measuring environment, which is hard to apply to dynamic driving environments. In this paper, we propose a contactless cardiac cycle monitoring system, mmECG, which leverages Commercial-Off-The-Shelf mmWave radar to estimate the fine-grained heart movements of drivers in moving vehicles. By exploring the principle of mmWave signal-based sensing, we first perform studies in static environments and find the fine-grained heart movements, represented as stages of atria and ventricles in repetitive cardiac cycles, can be captured by the FMCW-based mmWave radar as phase changes in signals. Whereas in driving environments, such phase changes are caused and influenced by not only the heartbeat of drivers but also driving operations and vehicle dynamics. To further extract the minute heart movements of drivers and eliminate other influences in phase changes, we construct a movement mixture model to represent the phase changes caused by different movements, and further design a hierarchy variational mode decomposition (VMD) approach to extract and estimate the essential heart movement in mmWave signals. Finally, based on the extracted phase changes, mmECG reconstructs the cardiac cycle by estimating fine-grained movements of atria and ventricles leveraging a template-based optimization method. Experimental results involving 25 drivers in real driving scenarios demonstrate that mmECG can accurately estimate not only heart rates but also cardiac cycles of drivers in real driving environments.

In the paper we focus on a promising research problem of data trading, under the scenario that data items can be reproduced easily and inexpensively. Apart from a Bayesian optimal mechanism based data trading approach, we also propose a prior-free data trading approach to organize the data trading process between selfish data owners and share-averse data consumers, with the goal of maximizing revenue of data owners and meanwhile determining the optimal number of data copies. Rigorous theoretical analysis and extensive experiment results are offered to verify the effectiveness of proposed methods in terms of sum of valuations, revenue, individual rationality and incentive compatibility.

Gait-based user authentication schemes have been widely explored because of their ability of non-invasive sensing and avoid replay attacks. However, existing gait-based user au-thentication methods are environment-dependent. In this paper, we present an environment-independent gait-based user authen-tication system, RFPass, which can identify different individuals leveraging RFID signals. Specifically, we find that Doppler shift of RF signals can describe environment-independent gait features for different individuals. In RFPass, when a user walks through the RFPass system, RF signals are first collected by a deployed RFID tag array. Then, RFPass removes environmental interfer-ence from the collected RF signals through a proposed Multipath Direction of arrival (DoA) Signal Select (MDSS) algorithm. Next, we construct an environment-independent gait profile to describe the user's walking movements. Afterward, environment-independent gait features are extracted by a proposed CNN-RNN model. Based on the extracted gait features, a trained model is constructed for user authentication and spoofer detection. Extensive experiments in different real environments demonstrate that RFPass can achieve environment-independent gait-based user authentication.

Next Point-of-Interest (POI) recommendation plays a critical role in many location-based applications as it provides personalized suggestions on attractive destinations for users. Since users' next movement is highly related to the historical visits, sequential methods such as recurrent neural networks are widely used in this task for modeling check-in behaviors. However, existing methods mainly focus on modeling the sequential regularity of check-in sequences but pay little attention to the intrinsic characteristics of POIs, neglecting the entanglement of the diverse influence stemming from different aspects of POIs. In this paper, we propose a novel Disentangled Representation-enhanced Attention Network (DRAN) for next POI recommendation, which leverages the disentangled representations to explicitly model different aspects and corresponding influence for representing a POI more precisely. Specifically, we first design a propagation rule to learn graph-based disentangled representations by refining two types of POI relation graphs, making full use of the distance-based and transition-based influence for representation learning. Then, we extend the attention architecture to aggregate personalized spatio-temporal information for modeling dynamic user preferences on the next timestamp, while maintaining the different components of disentangled representations independent. Extensive experiments on two real-world datasets demonstrate the superior performance of our model to state-of-the-art approaches. Further studies confirm the effectiveness of DRAN in representation disentanglement.

Researchers have proposed many novel methods to detect abnormal taxi trajectories. However, most of the existing methods usually adopt a counting-based strategy, which may cause high false positives due to imprecisely identifying diverse trajectories as anomalies and therefore, they need the support of large-scale historical trajectories to work properly. To improve detection precision and efficiency, in this article, we propose STR, an online abnormal taxi trajectory detection method based on spatio-temporal relations. The basic principle behind STR is that given the displacement from the source point to a testing point, if the driving time and driving distance are not within the normal ranges, the point is identified as anomalous. To learn the two normal ranges for driving time and driving distance, STR defines two spatio-temporal models which characterize the relationship between displacement and driving distance/driving time. To improve detection efficiency, STR reduces the number of models that need to be learned by making full use of the similarity of transportation modes in different time periods and neighboring areas. The effectiveness and performance of STR are evaluated on real-world taxi trajectories. The experiment results show that compared with counting-based methods, STR achieves greater precision by reducing false positives. Furthermore, STR is more efficient than its counterparts and is suitable for online detection.

Prediction tasks about students have practical significance for both student and college. Making multiple predictions about students is an important part of a smart campus. For instance, predicting whether a student will fail to graduate can alert the student affairs office to take predictive measures to help the student improve his/her academic performance. With the development of information technology in colleges, we can collect digital footprints that encode heterogeneous behaviors continuously. In this article, we focus on modeling heterogeneous behaviors and making multiple predictions together, since some prediction tasks are related and learning the model for a specific task may have the data sparsity problem. To this end, we propose a variant of Long-Short Term Memory (LSTM) and a soft-attention mechanism. The proposed LSTM is able to learn the student profile-aware representation from heterogeneous behavior sequences. The proposed soft-attention mechanism can dynamically learn different importance degrees of different days for every student. In this way, heterogeneous behaviors can be well modeled. In order to model interactions among multiple prediction tasks, we propose a co-attention mechanism based unit. With the help of the stacked units, we can explicitly control the knowledge transfer among multiple tasks. We design three motivating behavior prediction tasks based on a real-world dataset collected from a college. Qualitative and quantitative experiments on the three prediction tasks have demonstrated the effectiveness of our model.

The task of next Point-of-Interest (POI) recommendation aims at recommending a list of POIs for a user to visit at the next timestamp based on his/her previous interactions, which is valuable for both location-based service providers and users. Recent state-of-the-art studies mainly employ recurrent neural network (RNN) based methods to model user check-in behaviors according to user’s historical check-in sequences. However, most of the existing RNN-based methods merely capture geographical influences depending on physical distance or successive relation among POIs. They are insufficient to capture the high-order complex geographical influences among POI networks, which are essential for estimating user preferences. To address this limitation, we propose a novel Graph-based Spatial Dependency modeling (GSD) module, which focuses on explicitly modeling complex geographical influences by leveraging graph embedding. GSD captures two types of geographical influences, i.e., distance-based and transition-based influences from designed POI semantic graphs. Additionally, we propose a novel Graph-enhanced Spatial-Temporal network (GSTN), which incorporates user spatial and temporal dependencies for next POI recommendation. Specifically, GSTN consists of a Long Short-Term Memory (LSTM) network for user-specific temporal dependencies modeling and GSD for user spatial dependencies learning. Finally, we evaluate the proposed model using three real-world datasets. Extensive experiments demonstrate the effectiveness of GSD in capturing various geographical influences and the improvement of GSTN over state-of-the-art methods.

Due to the explosion of mobile devices and the evolution of wireless communication technologies, novel applications with intensive computation demands and low-latency requirements have arisen. Edge computing has been proposed as an extension of cloud computing, which moves computation workloads from remote cloud to network edge. Cooperating edge computing and cloud computing can significantly reduce the latency of computation tasks. However, considering the heterogeneity and stochastic arrivals of tasks and the limited computation and communication resources on the edge, task offloading and resource allocation are two joint crucial problems in an edge-cloud orchestrated computing system. In this paper, we propose an online task offloading and resource allocation approach for edge-cloud orchestrated computing, with the aim to minimize the average latency of tasks over time. We first build system models to analyze the latency and energy consumption incurred under different computing modes and formally formulate the joint problem as a mixed-integer optimal decision problem. Then, we employ Lyapunov optimization and duality theory to decompose the problem into a set of subproblems, which can be solved in a semi-decentralized way. We also formally analyze that our approach can achieve near-optimal performance. Extensive simulations are conducted to verify the superiority of our approach.

Existing Space-Terrestrial Integrated Network (STIN) applications collect all data from multiple satellites and terrestrial nodes to the specific analyze center on the earth for processing, which wastes lots of network resources. To save these resources, we propose a novelprocessing-while-transmittingpattern in the SDN-based STIN architecture. Through a logically centralized control plane, it cooperatively processes a complex task on appropriate nodes during data transmission. Here, the key point is to jointly determine the transmission path and place subtasks adaptive to data distributions, heterogeneous link costs, task characteristics, the dynamic topology, and network resources. In this paper, we firstly formulate theTransmission-cost-minimized joint Routing and Tasks placement Problem (TRTP)in time-varying STINs. We prove it is NP-hard and has no Polynomial-Time Approximation Scheme (PTAS). To solve the problem, we propose theJoint Routing and Task Placement (JRTP)algorithm. It first converts the time-varying STIN to a stable graph to cope with the network dynamics, according to the topology and resources during task processing. Then, it jointly decides the routing and task placement through atask-topology graph model, which converts the TRTP problem on the stable graph to the classic shortest path problem. We prove that the performance of JRTP is bounded in cases when transmission resources are sufficient and further improve it through the idea of reinforcement. The experimental results show that our processing pattern can significantly decrease the transmission cost and delay, and our algorithms outperform most related ones.

With the commoditization of private data, data trading in consideration of user privacy protection has become a fascinating research topic. The trading for private web browsing histories brings huge economic value to data consumers when leveraged by targeted advertising. And the online pricing of these private data further helps achieve more realistic data trading. In this paper, we study the trading and pricing of multiple correlated queries on private web browsing history data at the same time. We propose CTRADE, which is a novel online data CommodiTization fRamework for trAding multiple correlateD queriEs over private data. CTRADE first devises a modified matrix mechanism to perturb query answers. It especially quantifies privacy loss under the relaxation of classical differential privacy and a newly devised mechanism with relaxed matrix sensitivity, and further compensates data owners for their diverse privacy losses in a satisfying manner. CTRADE then proposes an ellipsoid-based query pricing mechanism according to a given linear market value model, which exploits the features of the ellipsoid to explore and exploit the close-optimal dynamic price at each round. In particular, the proposed mechanism produces a low cumulative regret, which is quadratic in the dimension of the feature vector and logarithmic in the number of total rounds. Through real-data based experiments, our analysis and evaluation results demonstrate that CTRADE balances total error and privacy preferences well within acceptable running time, indeed produces a convergent cumulative regret with more rounds, and also achieves all desired economic properties of budget balance, individual rationality, and truthfulness.

Non-parallel text style transfer aims to rephrase a sentence with another style while reserving its content relying on non-parallel data. Most existing methods can be divided into two groups: 1) separating content and style of the input text and 2) directly modeling the style transfer process. To the best of our knowledge, all these existing works lack fine-grained supervisory signals during training, which leads to difficulty in achieving a good balance between content preservation and style satisfaction. However, the study on supervisors which could provide fine-grained supervisory signals for training transfer models has received relatively less attention. Thus, we propose a self-attentional discriminator and a training strategy for training an attentional transfer model by leveraging the fine-grained supervisory signals from the proposed discriminator. Specifically, our discriminator provides token-wise style/content weights by performing self-attention between the sentence vector and the token embeddings, which forms a shortcut in back-propagation leading to more accurate gradients. The style/content weights also pose a better content alignment constraint and improve the interpretability of the training procedure by identifying stylized tokens. The training of our transfer model is end-to-end via Gumbel-Softmax with the pre-trained discriminator. Experiments on two datasets with automatic and human evaluations as well as theoretical and empirical analysis demonstrate the effectiveness of our method.1

Sequential recommendation which aims to predict a user's next interaction based on his/her previous behaviors, has attracted great attention. Recent studies mainly employ deep recurrent neural networks or self-attention networks to capture dynamic user preferences. However, existing methods merely focus on modeling users' clear interests in interacted items. We argue that for an interaction, the user may also have ambiguous interests in items that are semantically related to the interacted one. For comprehensively capturing user preferences, it is beneficial to discover potential interests from historical interactions at a broader itemset level. Therefore, in this paper, we propose a knowledge graph enhanced sequential recommendation model namely KGIE, which focuses on enhancing user interest modeling with knowledge-enriched itemsets by incorporating the knowledge graph. Specifically, in addition to item-level interest modeling with interacted items, we further construct knowledge-enriched itemsets that are extracted via high-order knowledge associations with the interacted items. For capturing personalized itemset-level interests, we design an attentive aggregation unit to combine item embeddings considering both inherent and contextual personalization signals. Furthermore, to balance the contributions of both two levels of interest modeling, we adaptively learn high-level preference representations with a gating fusion unit. Extensive experiments on three real-world datasets demonstrate the superior performance beyond state-of-the-art methods and recommendation interpretability of our model.

Cross-domain recommendation aims to leverage the rich interaction information in the source domain to predict interactions between cold-start users and items in the target domain. Since reviews contain users' preferences and items' attributes, many review-based cross-domain recommendation methods are proposed. However, existing methods cannot either 1) select important words and reviews from multiple reviews of users/items, or 2) learn a unified representation space for different domains without enough overlapping users. To address these problems, we propose a Hierarchical Attention model trained with Random Back-Transfer for cross-domain recommendation (HARBT). Specifically, the hierarchical attention extracts text information related to a given user or item which leads to an accurate interaction prediction. The random back-transfer works as a data augmentation algorithm to utilize data of users and items which are in the same domain for better matching of representations in different domains. Extensive experiments on real-world datasets show that our approach outperforms state-of-the-art methods significantly.

User interests are significant components in recommendation systems. Modeling user interests based on users' historical behaviors is a challenging problem, and many recommendation models have been proposed for user interests modeling, such as long-term and short-term interests modeling. In the real world, users' interests always change over time, however, existing models rarely consider users' interest changes. The purpose of this research is to apply graph neural networks to capture users' interest changes. This research first conducts data analysis on two public datasets, and results show that there are considerable amounts of users with a trend of interest changes. Based on this analysis, we construct user-category dynamic differential graphs, and we design a novel neural network based on dynamic differential graphs to learn users' interest changes representations from dynamic differential graphs. The learned representations are integrated with long-term and short-term interest representations to get users' final representations and make recommendations by getting scores with items. Different types of experiments are conducted to evaluate the performance of our proposed model, and experiment results show that the proposed model outperforms other baseline models.

Acoustic target tracking has shown great advantages for device-free human-machine interaction over vision/RF based mechanisms. However, existing approaches for portable devices solely track single target, incapable for the ubiquitous and highly challenging multi-target situation such as double-hand multimedia controlling and multi-player gaming. In this paper, we propose AMT, a pioneering smartphone MIMO system to achieve centimeter-level multi-target tracking. Targets' absolute distance are simultaneously ranged by performing multi-lateration locating with multiple speaker-microphone pairs. The unique challenge raised by MIMO is the superposition of multisource signals due to the cross-correlation among speakers. We tackle this challenge by applying Zadoff-Chu(ZC) sequences with strong auto-correlation and weak cross-correlation. The most distinguishing advantage of AMT lies in the elimination of target raised multipath effect, which is commonly ignored in previous work by hastily assuming targets as particles. Concerning the multipath echoes reflected by each non-particle target, we define the novel concept of primary echo to best represent target movement. AMT then improves tracking accuracy by detecting primary echo and filtering out minor echoes. Implemented on commercial smartphones, AMT achieves on average 1.13 cm and 2.46 cm error for single and double target tracking respectively and on average 97% accuracy for 6 controlling gestures recognition.

In the era of big data, data is an extremely important and valuable asset. Data trading is significantly essential to unlocking the power of AI/ML and gaining competitive advantages. Different from a general concept of data sharing, data trading makes it possible for both data consumers to specify what data they want and data owners to determine whether or not as well as how to trade their data. Existing studies ignore a few important characteristics, e.g., difficulty on accurate valuation for every data item, correlated valuation for data items, and privacy concern on disclosing valuation information. To this end, we propose an iterative combinatorial auction based data trading approach (ICADT) to uncover the value of correlated mobile crowdsensing data on the fly without direct elicitation of private valuation information. ICADT is an efficient ascending price-based auction mechanism which proceeds in rounds and determines allocation of data items and trading prices iteratively. Both rigorous theoretical analysis and extensive simulations demonstrate good properties of ICADT, e.g., convergence, individual rationality, optimality on system efficiency.

Air pollution is an important environmental issue of increasing concern, which impacts human health. Accurate air quality prediction is crucial for avoiding people suffering from serious air pollution. Most of the prior works focus on capturing the temporal trend of air quality for each monitoring station. Recent deep learning based methods also model spatial dependencies among neighboring stations. However, we observe that besides geospatially adjacent stations, the stations which share similar functionalities or consistent temporal patterns could also have strong dependencies. In this paper, we propose an Attentive Temporal Graph Convolutional Network (ATGCN) to model diverse inter-station relationships for air quality prediction of citywide stations. Specifically, we first encode three types of relationships among stations including spatial adjacency, functional similarity, and temporal pattern similarity into graphs. Then we design parallel encoding modules, which respectively incorporate attentive graph convolution operations into the Gated Recurrent Units (GRUs) to iteratively aggregate features from related stations with different graphs. Furthermore, augmented with an attention-based fusion unit, decoding modules with a similar structure to the encoding modules are designed to generate multi-step predictions for all stations. The experiments on two real-world datasets demonstrate the superior performance of our model beyond state-of-the-art methods.

Abstract Data trading has attracted increasing attention over the years as a cost-effective business paradigm, probably producing a tremendous amount of economic value. However, the study of query-based trading in the user data market is still in the initial stage. To design a practical user data trading mechanism, we have to consider three major challenges: privacy concern, compensation cost minimization and revenue maximization in a Bayesian environment. By jointly considering these challenges, we propose a profit-maximizing mechanism for user data trading with personalized differential privacy, called READ, which comprised two components, READ-COST for cost minimization and READ-REV for revenue maximization. Especially, READ adopts personalized differential privacy to satisfy each data owner’s diverse privacy preferences. READ-COST greedily selects the most cost-effective data owner to achieve the sub-optimal data query cost. Given this query cost, READ-REV calculates the maximum expected revenue in a Bayesian setting. Through rigorous theoretical analysis and real-data based experiments, we demonstrate that READ achieves all desired properties and approaches the optimal profit.

Abstract Human–computer interaction through touch screens plays an increasingly important role in our daily lives. Besides smartphones and tablets, laptops are the most prevalent mobile devices for both work and leisure. To satisfy the requirements of some applications, it is desirable to re-equip a typical laptop with both handwriting and drawing capability. In this paper, we design a virtual writing tablet system, VPad, for traditional laptops without touch screens. VPad leverages two speakers and one microphone, which are available in most commodity laptops, to accurately track hand movements and recognize writing characters in the air without additional hardware. Specifically, VPad emits inaudible acoustic signals from two speakers in a laptop and then analyzes energy features and Doppler shifts of acoustic signals received by the microphone to track the trajectory of hand movements. Furthermore, we propose a state machine-based trajectory optimization method to correct the unexpected trajectory and employ a stroke direction sequence model based on probability estimation to recognize characters users write in the air. Experimental results show that VPad achieves the average error of 1.55 cm for trajectory tracking and the accuracy over 90% of character recognition merely through built-in audio devices on a laptop.

With the explosion of mobile smart devices, many computation intensive applications have emerged, such as interactive gaming and augmented reality. Mobile-edge computing (EC) is put forward, as an extension of cloud computing, to meet the low-latency requirements of the applications. In this article, we consider an EC system built in an ultradense network with numerous base stations. Heterogeneous computation tasks are successively generated on a smart device moving in the network. An optimal task offloading strategy, as well as optimal CPU frequency and transmit power scheduling, is desired by the device user to minimize both task completion latency and energy consumption in a long term. However, due to the stochastic task generation and dynamic network conditions, the problem is particularly difficult to solve. Inspired by reinforcement learning, we transform the problem into a Markov decision process. Then, we propose an attention-based double deep Q network (DDQN) approach, in which two neural networks are employed to estimate the cumulative latency and energy rewards achieved by each action. Moreover, a context-aware attention mechanism is designed to adaptively assign different weights to the values of each action. We also conduct extensive simulations to compare the performance of our proposed approach with several heuristic and DDQN-based baselines.

Nowadays most metro advertising systems schedule advertising slots on digital advertising screens to achieve the maximum exposure to passengers by exploring passenger demand models. However, our empirical results show that these passenger demand models experience uncertainty at fine temporal granularity (e.g., per min). As a result, for fine-grained advertisements (shorter than one minute), a scheduling based on these demand models cannot achieve the maximum advertisement exposure. To address this issue, we propose an online advertising approach, called FineUDM, based on the uncertain passenger demand modeling for both entering passengers and exiting passengers. FineUDM combines coarse-grained statistical demand modeling and fine-grained real-time demand modeling by leveraging historical passenger demands, real-time card-swiping records, and passenger mobility patterns. Based on this uncertain demand model, it schedules advertising time online based on robust receding horizon control to maximize the advertisement exposure. We evaluate the proposed approach based on an one-month sample from our 530 GB real-world metro fare dataset with 16 million cards. The results show that our approach provides a 61.5 percent lower traffic prediction error and 20 percent improvement on advertising efficiency on average.

Among various recommendation methods, latent factor models are usually considered to be state-of-the-art techniques, which aim to learn user and item embeddings for predicting user-item preferences. When applying latent factor models to the recommendation with implicit feedback, the quality of embeddings always suffers from inadequate positive feedback and noisy negative feedback. Inspired by the idea of NSVD that represents users based on their interacted items, this article proposes a dual-embedding based deep latent factor method for recommendation with implicit feedback. In addition to learning a primitive embedding for a user (resp. item), we represent each user (resp. item) with an additional embedding from the perspective of the interacted items (resp. users) and propose attentive neural methods to discriminate the importance of interacted users/items for dual-embedding learning. We design two dual-embedding based deep latent factor models, DELF and DESEQ, for pure collaborative filtering and temporal collaborative filtering (i.e., sequential recommendation), respectively. The novel attempt of the proposed models is to capture each user-item interaction with four deep representations that are subtly fused for preference prediction. We conducted extensive experiments on four real-world datasets. The results verify the effectiveness of user/item dual embeddings and the superior performance of our methods on item recommendation.

Crowd flow prediction is a vital problem for an intelligent transportation system construction in a smart city. It plays a crucial role in traffic management and behavioral analysis, thus it has raised great attention from many researchers. However, predicting crowd flows timely and accurately is a challenging task that is affected by many complex factors such as the dependencies of adjacent regions or recent crowd flows. Existing models mainly focus on capturing such dependencies in spatial or temporal domains and fail to model relations between crowd flows of distant regions. We notice that each region has a relatively fixed daily flow and some regions (even very far away from each other) may share similar flow patterns which show strong correlations among them. In this article, we propose a novel model named Double-Encoder which follows a general encoder–decoder framework for multi-step citywide crowd flow prediction. The model consists of two encoder modules named ST-Encoder and FR-Encoder to model spatial-temporal dependencies and daily flow correlations, respectively. We conduct extensive experiments on two real-world datasets to evaluate the performance of the proposed model and show that our model consistently outperforms state-of-the-art methods.

For the emerging mobility-on-demand services, it is of great significance to predict passenger demands based on historical mobility trips towards better vehicle distribution. Prior works have focused on predicting next-step passenger demands at selected locations or hotspots. However, we argue that multi-step citywide passenger demands encapsulate both time-varying demand trends and global statuses, and hence are more beneficial to avoiding demand-service mismatching and developing effective vehicle distribution/scheduling strategies. Furthermore, we find that adaptations of single-step methods are unable to achieve robust prediction with high accuracy for further steps. In this paper, we propose an end-to-end deep neural network model to the prediction task. We employ an encoder-decoder framework based on convolutional and ConvLSTM units to identify complex features that capture spatiotemporal influence and pickup-dropoff interactions on citywide passenger demands. We introduce a multi-level attention model (global attention and temporal attention) to emphasize the effects of latent citywide mobility regularities and capture relevant temporal dependencies. We evaluate our proposed method using real-world mobility trips (taxis and bikes) and the experimental results show that our method achieves higher prediction accuracy than the state-of-the-art approaches.

This paper demonstrates the feasibility of a side-channel attack to infer keystrokes on touch screen leveraging an off-the-shelf smartphone. Although there exist some studies on keystroke eavesdropping attacks on touch screen, they are mainly direct eavesdropping attacks, i.e., require the device of victims compromised to provide side-channel information for the adversary, which are hardly launched in practical scenarios. In this work, we show the practicability of an indirect eavesdropping attack, KeyListener, which infers keystrokes on QWERTY keyboards of touch screen leveraging audio devices on a smartphone. We investigate the attenuation of acoustic signals, and find that a user's keystroke fingers can be localized through the attenuation of acoustic signals received by the microphones in the smartphone. We then utilize the attenuation of acoustic signals to localize each keystroke, and further analyze errors induced by ambient noises. To improve the accuracy of keystroke localization, KeyListener further tracks finger movements during inputs through phase change and Doppler effect to reduce errors of acoustic signal attenuation-based keystroke localization. In addition, a binary tree-based search approach is employed to infer keystrokes in a context-aware manner. The proposed keystroke eavesdropping attack is robust to various environments without the assistance of additional infrastructures. Extensive experiments demonstrate that the accuracy of keystroke inference in top-5 candidates can approach 90 percent with a top-5 error rate of around 6 percent, which is a strong indication of the possible user privacy leakage of inputs on QWERTY keyboard.

Purchase intentions have a great impact on future purchases and thus can be exploited for making recommendations. However, purchase intentions are typically complex and may change from time to time. Through empirical study with two e-commerce datasets, we observe that behaviors of multiple types can indicate user intentions and a user may have multiple coexisting category-level intentions that evolve over time. In this article, we propose a novel Intention-Aware Recommender System (IARS) which consists of four components for mining such complex intentions from user behaviors of multiple types. In the first component, we utilize several Recurrent Neural Networks (RNNs) and an attention layer to model diverse user intentions simultaneously and design two kinds of Multi-behavior GRU (MGRU) cells to deal with heterogeneous behaviors. To reveal user intentions, we carefully design three tasks that share representations from MGRUs. The next-item recommendation is the main task and leverages attention to select user intentions according to candidate items. The remaining two (item prediction and sequence comparison) are auxiliary tasks and can reveal user intentions. Extensive experiments on the two real-world datasets demonstrate the effectiveness of our models compared with several state-of-the-art recommendation methods in terms of hit ratio and NDCG.

For large-scale spatiotemporal-aware publish/subscribe systems, it is critical to design an efficient forwarding engine to achieve fast matching and maintenance of events and subscriptions. For this goal, we propose a novel data structure called MO-Tree to index both subscriptions and events in a unified way. The design philosophy behind MO-Tree is to keep the data structure concise, which manifests in three aspects: limiting the height of MO-Tree, trading space for time, and avoiding node merging and splitting. The difficulty in designing MO-Tree is how to efficiently index width-variable intervals. We present a multi-level cell-overlapping partition scheme and build a theoretical model to optimize the cell width in each level. To evaluate the performance of MO-Tree, a series of experiments is conducted on real-world trace datasets. The experiment results show MO-Tree significantly outperforms the state-of-the-art in terms of matching speed and maintenance cost.

Prediction tasks about students such as predicting students' academic performances have practical real-world significance at both the student level and the college level. With the rapid construction of smart campuses, colleges not only offer residence and academic programs but also record students' daily life. The digital footprints provide an opportunity to offer better solutions for prediction tasks. In this paper, we aim to propose a general deep neural network which can jointly model student heterogeneous daily behaviors generated from digital footprints and social influence to deal with prediction tasks. To this end, we design a variant of LSTM and a novel attention mechanism to model the daily behavior sequence. The proposed LSTM is able to consider context information (e.g., weather conditions) while modeling the daily behavior sequence. The proposed attention mechanism can dynamically learn the different importance degrees of different days for every student. Based on behavior information, we propose an unsupervised way to construct a social network to model social influence. Moreover, we design a residual network based decoder to model the complex interactions between the features and get the predicted values such as future academic performances. Qualitative and quantitative experiments on two real-world datasets collected from a college have demonstrated the effectiveness of our model.

Multi-access Edge Computing (MEC) comes forth as a promising computing paradigm to meet the low-delay requirements of computation-intensive applications. In this work, we focus on the task offloading and dispatching problem in MEC, where mobile devices (MDs) can decide to execute tasks locally or offload them to access points (APs), and each AP can dispatch its received tasks to other APs. Specially, we consider both APs and MDs are selfish, which aim to minimize their respective task completion delay. The problem is particularly difficult, as there exists computing resource competition among MDs and APs, respectively. Furthermore, the offloading decisions made by MDs and the dispatching decisions made by APs are interactive. To overcome the challenges, we first formulate the problem as a multi-leader multi-follower Stackelberg game, and rigorously prove the existence of a Stackelberg equilibrium. Then, we propose an efficient approach to achieve a Stackelberg equilibrium, which includes a Q-learning based offloading strategy for MDs and a best response based dispatching strategy for APs. We also demonstrate an upper bound of the total completion delay achieved by our approach with a constant approximation ratio. Extensive simulations are also conducted to show the performance of our approach, compared with baselines.

With the commoditization of private data, data trading in consideration of user privacy protection has become a fascinating research topic. The trading for private web browsing histories brings huge economic value to data consumers when leveraged by targeted advertising. In this paper, we study the trading of multiple correlated queries on private web browsing history data. We propose TERBE, which is a novel trading framework for correlaTed quEries based on pRivate web Browsing historiEs. TERBE first devises a modified matrix mechanism to perturb query answers. It then quantifies privacy loss under the relaxation of classical differential privacy and a newly devised mechanism with relaxed matrix sensitivity, and further compensates data owners for their diverse privacy losses in a satisfying manner. Through real-data based experiments, our analysis and evaluation results demonstrate that TERBE balances total error and privacy preferences well within acceptable running time, and also achieves all desired economic properties of budget balance, individual rationality, and truthfulness.

With the explosion of mobile smart devices, many computation intensive applications have emerged, such as interactive gaming and augmented reality. Mobile edge computing is put forward, as an extension of cloud computing, to meet the low-latency requirements of the applications. In this paper, we consider an edge computing system built in an ultra-dense network with numerous base stations, and heterogeneous computation tasks are successively generated on a smart device moving in the network. An optimal task offloading strategy, as well as optimal CPU frequency and transmit power scheduling, is desired by the device user, to minimize both task completion latency and energy consumption in a long-term. However, due to the stochastic computation tasks and dynamic network conditions, the problem is particularly difficult to solve. Inspired by reinforcement learning, we transform the problem into a Markov decision process. Then, we propose an online offloading approach based on a double deep Q network, in which a specific neural network model is also provided to estimate the cumulative reward achieved by each action. We also conduct extensive simulations to compare the performance of our proposed approach with baselines.

With increasing private and sensitive data stored in mobile devices, secure and effective mobile-based user authentication schemes are desired. As the most natural way to contact with mobile devices, finger touches have shown potentials for user authentication. Most existing approaches utilize finger touches as behavioral biometrics for identifying individuals, which are vulnerable to spoofer attacks. To resist attacks for on-touch user authentication on mobile devices, this paper exploits physical characters of touching fingers by investigating active vibration signal transmission through fingers, and we find that physical characters of touching fingers present unique patterns on active vibration signals for different individuals. Based on the observation, we propose a behavior-irrelevant on-touch user authentication system, TouchPass, which leverages active vibration signals on smartphones to extract only physical characters of touching fingers for user identification. TouchPass first extracts features that mix physical characters of touching fingers and behavior biometrics of touching behaviors from vibration signals generated and received by smartphones. Then, we design a Siamese network-based architecture with a specific training sample selection strategy to reconstruct the extracted signal features to behavior-irrelevant features and further build a behavior-irrelevant on-touch user authentication scheme leveraging knowledge distillation. Our extensive experiments validate that TouchPass can accurately authenticate users and defend various attacks.

Crowd sensing has emerged as a compelling paradigm for collecting sensing data over a vast area. It is of paramount importance for crowd sensing systems to provide effective incentive mechanisms. This paper studies the critical problem of maximizing the aggregate data utility under a budget constraint in incentive mechanism design in crowd sensing. This problem is particularly challenging given the redundancy in sensing data, self-interested and strategic user behavior, and private cost information of smartphones users. Most of existing mechanisms do not consider the important performance objective—maximizing the redundancy-aware data utility of sensing data collected from smartphones users. Furthermore, they do not consider the practical constraint on budget. In this paper, we propose an incentive mechanism based on a reverse auction framework. It consists of an approximation algorithm for winning user determination and a critical payment scheme. The approximation algorithm guarantees an approximation ratio for the aggregate data utility at polynomial-time complexity. The critical payment scheme guarantees truthful bidding. The rigorous theoretical analysis demonstrates that our mechanism achieves truthfulness, individual rationality, computational efficiency and budget feasibility.

Business location selection is crucial to the success of businesses. Traditional approaches like manual survey investigate multiple factors, such as foot traffic, neighborhood structure, and available workforce, which are typically hard to measure. In this article, we propose to explore both satellite data (e.g., satellite images and nighttime light data) and urban data for business location selection tasks of various businesses. We extract discriminative features from the two kinds of data and perform empirical analysis to evaluate the correlation between extracted features and the business popularity of locations. A novel neural network approach named R 2 Net is proposed to learn deep interactions among features and predict the business popularity of locations. The proposed approach is trained with a regression-and-ranking combined loss function to preserve accurate popularity estimation and the ranking order of locations simultaneously. To support the location selection for multiple businesses, we propose an approach named AR 2 Net with three attention modules, which enable the approach to focus on different latent features according to business types. Comprehensive experiments on a real-world dataset demonstrate that the satellite features are effective and our models outperform the state-of-the-art methods in terms of four metrics.

The increasing amount of trajectory data facilitates a wide spectrum of practical applications in which large numbers of trajectory range and similarity queries are issued continuously. This calls for high-throughput trajectory query processing. Traditional in-memory databases lack considerations of the unique features of trajectories, while specialized trajectory query processing systems are typically designed for only one type of trajectory queries. This paper introduces GAT, a unified GPU-accelerated framework to process batch trajectory queries with the objective of high throughput. GAT follows the filtering-and-verification paradigm where we develop a novel index GTIDX for effectively filtering invalid trajectories on the CPU, and exploit the massive parallelism of the GPU for verification. To optimize the performance of GAT, we first greedily partition batch queries to reduce the amortized query processing latency. We then apply the Morton-based encoding method to coalesce data access requests from the GPU cores, and maintain a hash table to avoid redundant data transfer between CPU and GPU. To achieve load balance, we group size-varying cells into balanced blocks with similar numbers of trajectory points. Extensive experiments have been conducted over real-life trajectory datasets. The results show that GAT is efficient, scalable, and achieves high throughput with acceptable indexing cost.

Given the increasing popularity, mobile devices are exploited to enhance active driving safety nowadays. Among all safety services provided for vehicles, tracking the rotation angle of steering wheel in real time can monitor the vehicles' dynamics and drivers' behaviors at the same time. In this paper, we propose a steering tracking system, SteerTrack, which tracks the rotation angle of the steering wheel in real time leveraging audio devices on smartphones. SteerTrack seeks a device-free approach for steering tracking without requiring installation of specialized sensors on the steering wheels nor asking drivers to wear sensors on their wrists. Since the steering wheel is operated by a driver's hands, the rotation angle of the steering wheel can be tracked based on movements of the driver's hands. SteerTrack first builds an acoustic signal field inside of a vehicle and then analyzes the echoes reflected from the driver's hands with relative correlation coefficient (RCC) and reference frame to track the movement trajectory of hands under different steering maneuvers. Given the tracked movement trajectory, SteerTrackfurther develops a geometrical transformation-based method for estimating the rotation angle of the steering wheel in 3D driving environments by projecting the steering wheel to a 2D ellipse. Through extensive experiments in real driving environments with five volunteers for several weeks, SteerTrack can achieve an average steering wheel estimation error of 1.48 degree during driving, and 4.61 degree for turns.

Financial fraud detection is an important topic in business intelligence, and neural networks have been effectively applied to construct detection models for this problem. Nevertheless, the timeliness of fitted models degrades over time when they are deployed in online detection systems. To maintain model performance when the labels of new transactions are not available, we propose an incremental virtual learning (IVL) method to update neural networks continually. The basic idea of IVL is to make the output distribution of neural networks smoother in the adversarial direction by unlabeled data. IVL uses local distribution smoothness (LDS) as the loss function at the unsupervised incremental learning stage. When updating a neural network by IVL, unlabeled data can be fed into the neural network periodically, so IVL can be implemented in a real online system without violating time constraints. To evaluate the effectiveness of IVL, experiments are conducted on a real dataset, demonstrating that neural networks augmented by IVL (IVL-NN) perform better than unoptimized neural networks in term of area under the curve (AUC). Furthermore, the standard deviation of the daily AUCs improves up to 19.09%, which indicates that IVL improves the stability of neural networks.

Cooperation among the traffic signals enables vehicles to move through intersections more quickly. Conventional transportation approaches implement cooperation by pre-calculating the offsets between two intersections. Such pre-calculated offsets are not suitable for dynamic traffic environments. To enable cooperation of traffic signals, in this paper, we propose a model, CoLight, which uses graph attentional networks to facilitate communication. Specifically, for a target intersection in a network, CoLight can not only incorporate the temporal and spatial influences of neighboring intersections to the target intersection, but also build up index-free modeling of neighboring intersections. To the best of our knowledge, we are the first to use graph attentional networks in the setting of reinforcement learning for traffic signal control and to conduct experiments on the large-scale road network with hundreds of traffic signals. In experiments, we demonstrate that by learning the communication, the proposed model can achieve superior performance against the state-of-the-art methods.

Predicting the accurate traffic crowd flows is of practical importance for intelligent transportation systems (ITS). However, it is challenging because traffic flows are affected by multiple complex factors, such as spatial and temporal dependencies of regions and external factors. In this paper, we propose a deep hybrid spatio-temporal dynamic neural network, called DHSTNet, to predict both inflows and outflows in every region of a city. More specifically, it consists of four main components, i.e., closeness influence taking the instantaneous variations of traffic flows, period influence regularly identifying daily changes of traffic crowd flows, weekly component identifying the patterns of weekly traffic flows and external component acquiring external factors. We design a branch of deep hybrid recurrent convolutional neural network units to model the first three temporal properties, i.e., closeness, period influence, and weekly influence. The external components are feed into two fully connected neural networks. For different branches, our proposed model assigns different weights and then combines the output of the four components. Experimental results based on two large-scale real-world datasets demonstrate the superiority of our model over the existing state-of-the-art methods.

The increasing volume of spatial-textual data generated from check-ins and reviews facilitates many practical applications. In these applications, similarity joins are the basic operation which further supports a wide range of similarity queries. However, this compute-intensive join operation calls for more efficient and effective algorithm to support real-time queries. Exploiting general purpose GPUs (GPGPUs) is one natural solution. Nevertheless, existing join algorithms utilizing GPGPU lack considerations on unique features of spatial-textual trajectories, especially the textual domain, thus resulting in poor performance. In this paper, we first propose a baseline spatial-textual trajectory similarity join algorithm, which is essentially based on a traditional algorithm for relational joins on GPGPUs. Then, by analyzing the bottleneck of this baseline, we further develop a fine-grained join algorithm which consists of memory access techniques and optimizations. We propose a strategy of flip to ensure coalesced memory accesses, and a batch scheduler for dividing the whole task into batches to fit the global memory while alleviating imbalanced throughput. Extensive experiments have been conducted over real-life datasets and the results show that our fine-grained algorithm performs the best and reduces the latency effectively.

Oceans are important for scientific research and also for global economic and military security. Usually, wireless ad hoc networks are chosen to transform real-time data collected by ocean monitoring sensors (nodes). Due to the random motion of waves or the random direction of the wind, nodes in the network might become detached from the coverage of the network. In this case, the detached nodes can either send the collected data directly to the base station at the cost of consuming more energy or wait for a period of time to rejoin the network with the price of sacrificing the real time of the collected data. In this paper, we model the optimal waiting time for detached nodes before directly sending the data in the dynamic environment of ocean monitoring. For this purpose, we need to address two problems. The first is how to calculate the rate of coverage with a different number and different broadcast radii of nodes. The second is when a node detaches from the coverage of the network, how much time will it need to wait before it rejoins the network. We first establish the motion model of nodes, which is the basis to deduce the probability distribution of a certain time when the detached node rejoins the network. Based on the probability distribution, the waiting time of the detached nodes can be optimally determined, aiming to achieve a good balance between energy consumption and data timeliness. Finally, a series of simulations is conducted to validate the effectiveness of our proposed method.

This paper focuses on the practical problem of detecting taxi anomalous detours. In this paper, we propose a length-adaptive detection approach called LADD to detect if a taxi conducted an anomalous detour by investigating the taxi journey's trajectory. We employ a similarity-based detection strategy, which takes trajectory length into consideration. Our approach can deal with both long and short trajectories by applying weighted similarity on trajectories and using trajectory concatenation or clipping. For quantitative performance comparison, we propose a performance metric, and compare our approach with the state-of-the-art methods on a real-world dataset. The results verify the superior performance of LADD on taxi detour detection.

The matching algorithm is a critical component of the content-based publish/subscribe system, whose performance has direct effects on the QoS of the whole system. Aiming to improve and stabilize the matching performance, we propose a lightweight parallelization method called PhSIH on the basis of three existing algorithms. PhSIH fulfills Parallelization by horizontally Segmenting the Indexing Hierarchy of data structures to support multiple threads performing matching tasks in parallel on a common data structure. PhSIH can adaptively adjust the degree of parallelism according to the changing workloads in order to meet the performance requirement. The main work of PhSIH concerns dynamically adjusting the degree of parallelism and computing a task allocation solution for parallel threads. PhSIH is implemented in Apache Kafka to augment it as a content-based publish/subscribe system, which makes Kafka suitable for real-time fine-grained event dissemination scenarios, such as stock ticks. To evaluate the parallelization effect and adaptability of PhSIH, a series of experiments are conducted based on synthetic and real-world data. The experiment results demonstrate that PhSIH achieves a good parallelization effect on the three existing algorithms and possesses a desirable adaptability that stabilizes the performance of the matching algorithms.

Collaborative Filtering (CF) is among the most successful techniques in recommendation tasks. Recent works have shown a boost of performance of CF when introducing the pairwise relationships between users and items or among items (users) using interaction data. However, these works usually only utilize one kind of information, i.e., user preference in a user-item interaction matrix or item dependency in interaction sequences which can limit the recommendation performance. In this paper, we propose to mine three kinds of information (user preference, item dependency, and user similarity on behaviors) by converting interaction sequence data into multiple graphs (i.e., a user-item graph, an item-item graph, and a user-subseq graph). We design a novel graph convolutional network (PGCN) to learn shared representations of users and items with the three heterogeneous graphs. In our approach, a neighbor pooling and a convolution operation are designed to aggregate features of neighbors. Extensive experiments on two real-world datasets demonstrate that our graph convolution approaches outperform various competitive methods in terms of two metrics, and the heterogeneous graphs are proved effective for improving recommendation performance.

Dredging is the removal of sediment from the bottom of lakes, rivers, harbors, and other water bodies. It is a routine necessity in waterways around the world because the natural process of sand and silt washing downstream results in the sediment gradually filling channels and harbors. However, during the dredging operation, some dredgers do not transport the sediment to the designated area as expected but throw it near the waterway meaning sediment may return to the waterway in a short period. This paper proposes an online dredging operation anomaly detection (DOAD) method to detect this kind of irregular behavior during the dredging operation based on automatic identification system (AIS) data. First, we establish a feature system to extract behavior features from AIS data. Furthermore, we jointly utilize t-distributed stochastic neighbor embedding (t-SNE) with neural networks and a Gaussian mixture model (GMM) to train a detection model in a semi-supervised way. Through the trained model, irregular behaviors can be efficiently detected in real time during the dredging operation. The effectiveness of DOAD is evaluated according to a series of experiments. To the best of our knowledge of the published literature, this work is the first to introduce the application of AIS data to detect irregular behaviors during dredging operations.

Deep learning is popular in many areas, but users must manually specify the resource configuration when submitting deep learning training jobs, usually over-provisioning resources. This kind of unreasonable resource configuration method results in slow training and low resource utilization. Therefore, it would be more convenient and efficient if users only need to specify the quality of service (QoS) for their jobs, and then the resources will be autoconfigured to meet the QoS. To satisfy this demand, we present a QoS-oriented scheduling and autoscaling framework that schedules and autoscales deep learning training jobs in the Kubernetes cluster. This paper focuses on the most important QoS requirement for deep learning training jobs: deadline. The goal of the framework is to guarantee that as many jobs as possible can be accomplished before their specified deadlines. To reach this goal, the framework schedules deep learning jobs by implementing a heuristic scheduling policy based on resource status and job deadline, and autoscales resource configuration by exploiting a characteristic of deep learning jobs: the predictability of training time. This predictability is used to predict whether a job can be accomplished before its deadline and estimate appropriate resource configuration if necessary. We implemented the framework by modifying the default scheduler of Kubernetes and conducted experiments to evaluate its performance. The experiment results show that our scheduling policy can improve the completion rate by 26% when the cluster resources are insufficient, and our autoscaling policy can improve the completion rate to 100% when the cluster resources are sufficient. We also show that the framework improves the utilization of allocated CPUs to 100%. Our proposed framework points to a new way of submitting and managing deep learning training jobs in the cluster.

This paper demonstrates the feasibility of a side-channel attack to infer keystrokes on touch screen leveraging an off-the-shelf smartphone. Although there exist some studies on keystroke eavesdropping attacks on touch screen, they are mainly direct eavesdropping attacks, i.e., require the device of victims compromised to provide side-channel information for the adversary, which are hardly launched in practical scenarios. In this work, we show the practicability of an indirect eavesdropping attack, KeyListener, which infers keystrokes on QWERTY keyboards of touch screen leveraging audio devices on a smartphone. We investigate the attenuation of acoustic signals, and find that a user's keystroke fingers can be localized through the attenuation of acoustic signals received by the microphones in the smartphone. We then utilize the attenuation of acoustic signals to localize each keystroke, and further analyze errors induced by ambient noises. To improve the accuracy of keystroke localization, KeyListener further tracks finger movements during inputs through phase change and Doppler effect to reduce errors of acoustic signal attenuation-based keystroke localization. In addition, a binary tree-based search approach is employed to infer keystrokes in a context-aware manner. The proposed keystroke eavesdropping attack is robust to various environments without the assistance of additional infrastructures. Extensive experiments demonstrate that the accuracy of keystroke inference in top-5 candidates can approach 90% with a top-5 error rate of around 6%, which is a strong indication of the possible user privacy leakage of inputs on QWERTY keyboard.

The trading of social media data has attracted wide research interests over years. Especially the trading for web browsing histories probably produces tremendous economic value for data consumers when being applied to targeted advertising. However, the disclosure of entire browsing histories, even in form of anonymous datasets poses a huge threat to user privacy. Although some existing solutions have investigated privacy-preserving outsourcing of social media data, unfortunately, they neglected the impact on the data consumer's utility. In this paper, we propose PEATSE, a new Privacy-prEserving dAta Trading framework for web browSing historiEs. It takes users' diverse privacy preferences and the utility of their web browsing histories into consideration. PEATSE perturbs users' detailed browsing times on released browsing records to protect user privacy, while balancing the privacy-utility tradeoff. Through real-data based experiments, our analysis and evaluation results demonstrate PEATSE indeed achieves user privacy protection, the data consumer's accuracy requirement, and truthfulness, individual rationality as well as budget balance.

Urban environmental monitoring related to such issues as air pollution and noise helps people understand their living environments and promotes urban construction. It is more and more important nowadays. By crowdsourcing, we can get mobile users at a low cost to collect measurement at different locations. This paper studies how to select optimal mobile users to construct an accurate monitoring map under a limited budget. We extend the noise Gaussian Process model to construct the data utility model. Because the monitoring map is updated in each time slot, we try to maximize the time-averaged data utility under the time-averaged budget constraint. This problem is particularly challenging given the unknown future information and the difficulty of solving the one-slot problem: maximizing a non-monotone sub-modular objective under the budget constraint. To address these challenges, we first make use of Lyapunov optimization to decompose the long-term optimization problem into a series of real-time problems which do not require a priori knowledge about the future information. We then propose a time-efficient online algorithm to solve the NP-hard one-slot problem. As long as the algorithm for the one-slot problem has a competitive ratio e, the time-averaged data utility of our online algorithm has a small gap compared with e times the optimal one. Evaluations based on the real air pollution data in Beijing [2] and real human trajectory data [1] show the efficiency of our approach.

Latent factor models (LFMs) such as matrix factorization have achieved the state-of-the-art performance among various collaborative filtering approaches for recommendation. Despite the high recommendation accuracy of LFMs, a critical issue to be resolved is their lack of interpretability. Extensive efforts have been devoted to interpreting the prediction results of LFMs. However, they either rely on auxiliary information which may not be available in practice, or sacrifice recommendation accuracy for interpretability. Influence functions, stemming from robust statistics, have been developed to understand the effect of training points on the predictions of black-box models. Inspired by this, we propose a novel explanation method named FIA (Fast Influence Analysis) to understand the prediction of trained LFMs by tracing back to the training data with influence functions. We present how to employ influence functions to measure the impact of historical user-item interactions on the prediction results of LFMs and provide intuitive neighbor-style explanations based on the most influential interactions. Our proposed FIA exploits the characteristics of two important LFMs, matrix factorization and neural collaborative filtering, and is capable of accelerating the overall influence analysis process. We provide a detailed complexity analysis for FIA over LFMs and conduct extensive experiments to evaluate its performance using real-world datasets. The results demonstrate the effectiveness and efficiency of FIA, and the usefulness of the generated explanations for the recommendation results.

Given the increasing amount of time people spent on driving, the physical and mental health of drivers is essential to road safety. Breathing patterns are critical indicators of the well-being of drivers on the road. Existing studies on breathing monitoring require active user participation of wearing special sensors or relatively quiet environments during sleep, which are hardly applicable to noisy driving environments. In this work, we propose a fine-grained breathing monitoring system, BreathListener, which leverages audio devices on smartphones to estimate the fine-grained breathing waveform in driving environments. By investigating the data collected from real driving environments, we find that Energy Spectrum Density (ESD) of acoustic signals can be utilized to capture breathing procedures in driving environments. To extract breathing pattern in ESD signals, BreathListener eliminates interference from driving environments in ESD signals utilizing background subtraction and Ensemble Empirical Mode Decomposition (EEMD). After that, the extracted breathing pattern is transformed into Hilbert spectrum, and we further design a deep learning architecture based on Generative Adversarial Network (GAN) to generate fine-grained breathing waveform from the Hilbert spectrum of extracted breathing patterns in ESD signals. Experiments with 10 drivers in real driving environments show that BreathListener can accurately capture breathing patterns of drivers in driving environments.

Multipath profiling is to characterize multipath components of wireless channels, which can be done using Channel State Information (CSI) from WiFi devices. To do so with satisfactory accuracy, recent studies rely on either a large number of receiving antennas or large bandwidth. However, it is difficult for commodity WiFi devices to meet these requirements. In this paper, we propose a scheme, WiZoom, that can perform accurate multipath profiling using single-band CSI from commodity WiFi devices. In order to achieve accurate multipath profiling with limited bandwidth, WiZoom first incorporates the MUltiple SIgnal Classification (MUSIC) algorithm with CSI to estimate ToAs of multipath components, and then combines multiple antennas to improve the resolution of ToA estimation. WiZoom further estimates attenuations and phase shifts for multipath components using the ToAs. So far, multipath components are fully characterized, and all these estimated parameters form the multipath profile. We evaluate the performance of WiZoom using commodity WiFi devices in real environment, and results show that WiZoom achieves high accuracy in multipath profiling.

Abstract The advent of big data era has given rise to the big data trading market because of the potentially enormous economic value. However, designing an effective trading mechanism for the data trading market is still in its infancy. Existing several incentive mechanisms have neglected the important fact that data consumers have both preferences and complex conflicts of interest (CoI) relations among them. In response to the limitations of existing trading mechanisms, we propose DTPCI, a truthful double auction mechanism for a Data Trading market with two unique characteristics of consumers’ Preferences and complex CoI relations among them. However, three major challenges have to be addressed, i.e. diverse market preferences, the complex CoI relations of data consumers and the strategic behaviors of both two sides. To jointly address the three challenges, we propose DTPCI to achieve nonnegative social welfare, which features a group rule and a data trading rule. The group rule generates all conflict-free virtual groups based on the CoI graph. The data trading rule adopts the group buying to share data and expense. Through rigorous theoretical analysis and real-data based experiments, we demonstrate that DTPCI achieves all the desired economic properties.

As metropolises develop, air pollution has become a serious problem, especially in developing countries like China. Many governments and researchers have devoted themselves to tackling and solving this problem. With the proliferation of smartphones, mobile crowdsensing is becoming a promising paradigm for monitoring large-scale environmental phenomena. In a practical crowdsensing system, incentives should be provided to encourage the participation of rational smartphone users, because it incurs various costs on users to collect sensing data. However, monitoring fine-grained air pollution in a large urban area based on crowdsensing will lead to high payments, which makes designing an efficient incentive mechanism a challenging problem. Fortunately, compressive sensing (CS) has been proved as an effective technology to reduce the amount of collected data via exploiting the spatial correlations among sensing data. In this article, we employ CS in the air pollution monitoring application, in which only a sampled set of locations are selected to collect data and provide incentives to the participants, and air pollution concentrations in unselected locations are inferred via CS. We propose an active learning scheme, which iteratively selects valuable locations to collect sensing data. Moreover, an expectation maximization-based algorithm is designed to detect the contexts in which sensing data are collected, and an efficient incentive mechanism is provided to encourage users with low costs participating. Comprehensive simulations are conducted to demonstrate the performance of our proposed scheme.

Air quality has gained much attention in recent years and is of great importance to protecting people’s health. Due to the influence of multiple factors, the limited air quality monitoring stations deployed in cities are unable to provide fine-grained air quality information. One cost-effective way is to infer air quality with records from existing monitoring stations. However, the severe data sparsity problem (e.g., only 0.2% data are known) leads to the failure of most inference methods. We observe that remote sensing data are of high quality and have a strong correlation with the air quality. Therefore, we propose to integrate remote sensing data and ubiquitous urban data for the air quality inference. But there are two main challenges, i.e., data heterogeneity and incompleteness of the remote sensing data. To address the challenges, we propose a two-stage approach. In the first stage, we infer and predict air quality conditions of some places leveraging the remote sensing data and meteorological data with two proposed ANN-based methods, respectively. This stage significantly alleviates the data sparsity problem. In the second stage, the records and estimated air quality data are put in a tensor. A tensor decomposition method is applied to complete the tensor. The features extracted from urban data are classified into the spatial features (i.e., road features and POI features) and the temporal features (i.e., meteorological features) as the constraints to further address the data sparsity problem. In addition, an iterative training framework is proposed to improve the inference performance. Experiments on a real-world dataset show that our approach outperforms state-of-the-art methods, such as U-Air.

To prevent users privacy from leakage, more and more mobile devices employ biometric-based authentication approaches, such as fingerprint, face recognition, voiceprint authentications, and so on, to enhance the privacy protection. However, these approaches are vulnerable to replay attacks. Although the state-of-art solutions utilize liveness verification to combat the attacks, existing approaches are sensitive to ambient environments, such as ambient lights and surrounding audible noises. Toward this end, we explore liveness verification of user authentication leveraging users mouth movements, which are robust to noisy environments. In this paper, we propose a lip reading-based user authentication system, LipPass, which extracts unique behavioral characteristics of users speaking mouths through acoustic sensing on smartphones for user authentication. We first investigate Doppler profiles of acoustic signals caused by users' speaking mouths and find that there are unique mouth movement patterns for different individuals. To characterize the mouth movements, we propose a deep learning-based method to extract efficient features from Doppler profiles and employ softmax function, support vector machine and support vector domain description to construct multi-class identifier, binary classifiers and spoofer detectors for mouth state identification, user identification and spoofer detection, respectively. Afterward, we develop a balanced binary tree-based authentication approach to accurately identify each individual leveraging these binary classifiers and spoofer detectors with respect to registered users. Through extensive experiments involving 48 volunteers in four real environments, LipPass can achieve 90.2% accuracy in user identification and 93.1% accuracy in spoofer detection.

Urban air pollution has attracted much attention these years for its adverse impacts on human health. While monitoring stations have been established to collect pollutant statistics, the number of stations is very limited due to the high cost. Thus, inferring fine-grained urban air quality information is becoming an essential issue for both government and people. In this paper, we propose a generic neural approach, named ADAIN, for urban air quality inference. We leverage both the information from monitoring stations and urban data that are closely related to air quality, including POIs, road networks and meteorology. ADAIN combines feedforward and recurrent neural networks for modeling static and sequential features as well as capturing deep feature interactions effectively. A novel attempt of ADAIN is an attention-based pooling layer that automatically learns the weights of features from different monitoring stations, to boost the performance. We conduct experiments on a real-world air quality dataset and our approach achieves the highest performance compared with various state-of-the-art solutions.

Stock price prediction has always been a hot but challenging task due to the complexity and randomness in stock market. Investors and researchers usually derive a great number of factors from original data such as historical stock price, company profit, or textual data collected from social media. Normally these factors are then fed into models like linear regression, SVM or neural networks to make a prediction. Even though the number of factors are considerable, most of them have relatively weak correlations with future stock price. During training process, these factors not only result in additional computation but sometimes even be harmful to the performance of prediction. In this paper, we propose a novel multi-input LSTM model which is capable of extracting valuable information from low-correlated factors and discarding their harmful noise by employing extra input gates controlled by the convincing factors called \emph{mainstream}. We also introduce several new factors including the prices of other related stocks to improve the prediction accuracy. The experimental results on the stock data from China stock market demonstrate the effectiveness of the proposed approach compared with the state-of-the-art methods.

This paper focuses on predicting rating scores of new restaurants listed in online restaurant review platforms. Most existing works rely on customer reviews to make an prediction. However, in practice, the customer reviews for new restaurants are always missing. In this paper, we mine useful features from the information of restaurants as well as highly available urban data to tackle this problem. We propose a deep-learning based approach called MR-Net to model both endogenous and exogenous factors in a unified manner and capture deep feature interaction for rating score prediction. Extensive experiments on real world data from Dianping show that our approach achieves better performance than various baseline methods. To the best of our knowledge, it is the first work that predicts rating scores for new restaurants without the knowledge of customer reviews.

The increasing amount of trajectory data facilitates a wide spectrum of practical applications. In many such applications, large numbers of trajectory range and similarity queries are issued continuously, which calls for high-throughput trajectory query processing. Traditional in-memory databases lack considerations of the unique features of trajectories, thus suffering from inferior performance. Existing trajectory query processing systems are typically designed for only one type of trajectory queries, i.e., either range or similarity query, but not for both. Inspired by the massive parallelism on GPUs, in this paper, we develop a GPU-accelerated framework, named GAT, to support both types of trajectory queries (i.e., both range and similarity queries) with high throughput. For similarity queries, we adopt the Edit Distance on Real sequence (EDR) as the similarity measure which is accurate and robust to noise in real-world trajectories. GAT employs a GPU-friendly index called GTIDX to effectively filter invalid trajectories for both range and similarity queries, and exploits the GPU to perform parallel verifications. To accelerate the verification process on the GPU, we apply the Morton-based encoding method to reorganize trajectory points and facilitate coalesced data accesses for individual point data in global memory, which reduces the global memory bandwidth requirement significantly. We also propose a technique of grouping size-varying cells into balanced blocks with similar numbers of trajectory points, to achieve load balancing among the Streaming Multiprocessors (SMs) of the GPU. We conduct extensive experiments to evaluate the performance of GAT using two real-life trajectory datasets. The results show that GAT is scalable and achieves high throughput with acceptable indexing cost.

With the prosperity of the location-based social networks, next Point-of-Interest (POI) recommendation has become an important service and received much attention in recent years. The next POI is dynamically determined by the mobility pattern and various contexts associated with user check-in sequence. However, exploring spatial-temporal mobility patterns and incorporating heterogeneous contextual factors for recommendation are challenging issues to be resolved. In this paper, we introduce a novel neural network model named TMCA (Temporal and Multi-level Context Attention) for next POI recommendation. Our model employs the LSTM-based encoder-decoder framework, which is able to automatically learn deep spatial-temporal representations for historical check-in activities and integrate multiple contextual factors using the embedding method in a unified manner. We further propose the temporal and multi-level context attention mechanisms to adaptively select relevant check-in activities and contextual factors for next POI preference prediction. Extensive experiments have been conducted using two real-world check-in datasets. The results verify (1) the superior performance of our proposed method in different evaluation metrics, compared with several state-of-the-art methods; and (2) the effectiveness of the temporal and multi-level context attention mechanisms on recommendation performance.

This paper studies the problem of time series forecasting. A time series is defined as a sequence of data points listed in time order. Many real-life time series data are driven by multiple latent components which occur at different frequencies. Existing solutions to time series forecasting fail to identify and discriminate these frequency-domain components. Inspired by the recent advent of signal processing and speech recognition techniques that decompose a time series signal into its time-frequency representation - a scalogram (or spectrogram), this paper proposes to explicitly disclose frequency-domain information from a univariate time series using wavelet transform, towards improving forecasting accuracy. Based on the transformed data, we leverage different neural networks to capture local time-frequency features and global long-term trend simultaneously. We further employ the attention mechanism to fuse local and global features in an effective manner. The experimental results on real time series show that our proposed approach achieves better performance than various baseline methods.

Human-computer interaction based on touch screens plays an increasing role in our daily lives. Besides smartphones and tablets, laptops are the most popular mobile devices used in both work and leisure. To satisfy requirements of many emerging applications, it becomes desirable to equip both writing and drawing functions directly on laptop screens. In this paper, we design a virtual writing tablet system, VPad, for traditional laptops without touch screens. VPad leverages two speakers and one microphone, which are available in most commodity laptops, for trajectory tracking without additional hardware. It employs acoustic signals to accurately track hand movements and recognize characters user writes in the air. Specifically, VPad emits inaudible acoustic signals from two speakers in a laptop. Then VPad applies Sliding-window Overlap Fourier Transformation technique to find Doppler frequency shift with higher resolution and accuracy in real time. Furthermore, we analyze frequency shifts and energy features of acoustic signals received by the microphone to track the trajectory of hand movements. Finally, we employ a stroke direction sequence model based on possibility estimation to recognize characters users write in the air. Our experimental results show that VPad achieves the average trajectory tracking error of only 1.55cm and the character recognition accuracy of above 90% merely through two speakers and one microphone on a laptop.

Emerging non-volatile memory (NVM) technologies promise persistence, byte-addressability, low power consumption and high density. The potential of NVM implies that it can improve persistence performance and availability for high-performance computing tasks in data centers. However, NVM suffers from limited write endurance; skewed writes can extremely curtail the lifetime of NVM. Although several wear-leveling algorithms have been proposed to address the wear-out problem, based on estimation of write counts, they come with limitations in accuracy and compatibility with existing hardware and softwares. In this paper, we propose several software-based ways of monitoring NVM writes and obtaining the write counts, which are more accurate and non-intrusive for existing programs. We compare our proposed monitoring approaches in the aspects of granularity and portability; we conduct extensive experiments to evaluate them and the results show that our proposed methods can obtain good accuracy with an affordable time overhead.

Data persistence refers to an characteristic that data needs to outlive its creator. In recent years, NVM (Non-volatile Memory), a new type of computer memory supporting memory-like byte-addressable access and disk-like persistence, became a promising technique for facilitating data persistence in memory and its management. So far NVM has been supported in many programming languages such as C, C++ and Java. Meanwhile, it has not yet been well supported in JavaScript, a popular scripting language for software development. This paper presents JSNVM, an extension to JavaScript's runtime and execution engine, to support data persistence in JavaScript using NVM. JSNVM consists of (1) a JavaScript persistent object pool that serves as a persistent heap in which persistent objects are created and managed. This pool is also enhanced for guaranteeing data safety and consistency; and (2) a set of JavaScript persistent APIs that provide programmers with a support in creating, managing, and accessing persistent data in an easy-to-use and safe manner. We have implemented JSNVM and evaluated it against two database-supported data persistence styles (i.e., MongoDB's object store and indexedDB's binary store) on micro-benchmarks and real-world applications. The evaluation results show that compared with MongoDB's object store, JSNVM can achieve a 1.6× speedup; when applied to access binary data, JSNVM can achieve a 24.6× speedup over indexedDB's binary store, denoting that JSNVM can enhance performance of JavaScript applications in practice. JSNVM is planned to be publicly available by the end of 2018.

In spite of their convenience and popularity, dockless shared bikes pose several challenges to operations and city management, e.g., unbalanced supply and demand across a city, and harmful congestions in pedestrian walkways. A step towards addressing these challenges is to find whether there exist periodical patterns in dockless shared bike demands. A periodical pattern of dockless shared bike demand is a time-dependent demand profile that repeats over a time period and frequently appear in different areas across a city. Mining periodical patterns of dockless shared bike demands, however, is very challenging because of data noises and different demand scales in different areas. In this paper, we propose a two-stage method for mining the periodical patterns of dockless shared bike demands. In the first stage, we determine the areas which have periodical dockless shared bike demands. And in the second stage, we introduce the concept of magnitude-oblivious demand to handle the issue on the different scales in different areas and propose an algorithm to compute the magnitude-oblivious periodic patterns. We conduct experiments with real data in Shanghai, China, which show that 12.4% of spatial areas in Shanghai have periodicity in bike demands, and we report 157 magnitude-oblivious periodical patterns in Shanghai. We also present several case studies which show our approach produces meaningful and useful patterns. Interestingly, we find that the areas with a similar geography often share the same periodical patterns of dockless shared bike demands.

A distributed cluster provides a common computation platform to efficiently run different types of jobs, such as real-time and batch jobs that have different QoS requirements. One challenge of a distributed cluster is to find a scheduling strategy that can reduce the overtime ratio of real-time jobs as much as possible while also improving the completion time of batch jobs, aiming to promote QoS even though the resources in the cluster are stretched. To address this issue, many efficient scheduling methods have been proposed. However, most existing approaches are naive and coarse-grained in means of either killing batch jobs to preempt resources for real-time jobs or reserving some resources in advance for real-time jobs to minimize the overtime ratio of real-time jobs, which prolongs the completion time of batch jobs and reduces the resource utilization of the cluster. In this paper, we propose UpPreempt, a fine-grained preemptive scheduling strategy for container-based clusters. When scheduling real-time jobs, UpPreempt considers the deadline of jobs and the resource usage of existing batch jobs. Performing resource preemption from multiple batch jobs is the basic idea of UpPreempt. The set of batch jobs to be preempted and the amount of resources taken from each job are finely determined. In this way, UpPreempt greatly alleviates the effect of preemption on the batch jobs in terms of completion time and avoids reserving resources for real-time jobs. We implement UpPreempt in YARN to evaluate its performance. The evaluation with various workloads shows that our proposed scheduling strategy can achieve a good trade-off between the overtime ratio of real-time jobs and the completion time of batch jobs without reducing the resource utilization of the cluster.

Among various recommendation methods, latent factor models are usually considered to be state-of-the-art techniques, which aim to learn user and item embeddings for predicting user-item preferences. When applying latent factor models to recommendation with implicit feedback, the quality of embeddings always suffers from inadequate positive feedback and noisy negative feedback. Inspired by the idea of NSVD that represents users based on their interacted items, this paper proposes a dual-embedding based deep latent factor model named DELF for recommendation with implicit feedback. In addition to learning a single embedding for a user (resp. item), we represent each user (resp. item) with an additional embedding from the perspective of the interacted items (resp. users). We employ an attentive neural method to discriminate the importance of interacted users/items for dual-embedding learning. We further introduce a neural network architecture to incorporate dual embeddings for recommendation. A novel attempt of DELF is to model each user-item interaction with four deep representations that are subtly fused for preference prediction. We conducted extensive experiments on real-world datasets. The results verify the effectiveness of user/item dual embeddings and the superior performance of DELF on item recommendation.

To prevent users' privacy from leakage, more and more mobile devices employ biometric-based authentication approaches, such as fingerprint, face recognition, voiceprint authentications, etc., to enhance the privacy protection. However, these approaches are vulnerable to replay attacks. Although state-of-art solutions utilize liveness verification to combat the attacks, existing approaches are sensitive to ambient environments, such as ambient lights and surrounding audible noises. Towards this end, we explore liveness verification of user authentication leveraging users' lip movements, which are robust to noisy environments. In this paper, we propose a lip reading-based user authentication system, LipPass, which extracts unique behavioral characteristics of users' speaking lips leveraging build-in audio devices on smartphones for user authentication. We first investigate Doppler profiles of acoustic signals caused by users' speaking lips, and find that there are unique lip movement patterns for different individuals. To characterize the lip movements, we propose a deep learning-based method to extract efficient features from Doppler profiles, and employ Support Vector Machine and Support Vector Domain Description to construct binary classifiers and spoofer detectors for user identification and spoofer detection, respectively. Afterwards, we develop a binary tree-based authentication approach to accurately identify each individual leveraging these binary classifiers and spoofer detectors with respect to registered users. Through extensive experiments involving 48 volunteers in four real environments, LipPass can achieve 90.21% accuracy in user identification and 93.1% accuracy in spoofer detection.

With the increasingly wide adoption of crowdsensing services, we can leverage the crowd to obtain labeled data instances for training machine learning models. In this paper, we focus on the critical problem that which data instances should be collected to maximize the performance of the trained model under the budget limit. Solving this problem is nontrivial because of the unclear relationship between the performance of the trained model and the data collection process, NP-hardness of the problem and the online arrival of workers. To overcome these challenges, we first propose a crowdsensing framework with multiple rounds of data collecting and model training. The framework is based on the stream-based batch-mode active learning. According to the framework, we come up with a novel data utility model to measure the contribution of a data batch to the performance of the learning model. The data utility model combines uncertainty and weighted density to measure the contribution of one instance. Finally, we propose an online algorithm to select a data batch in each round. The algorithm achieves fairness, computational efficiency and a competitive ratio 0.1218 when the ratio of the largest contribution of one data instance to the optimal offline total data utility is infinitely small. Through evaluations based on a real data set, we demonstrate the efficiency of our data utility model and our online algorithm.

Dockless shared bikes, which aim at providing a more flexible and convenient solution to the first-and-last mile connection, come into China and expand to other countries at a very impressing speed. The expansion of shared bike business in new cities brings many challenges among which, the most critical one is the parking chaos caused by too many bikes yet insufficient demands. To allow possible actions to be taken in advance, this paper studies the problem of detecting parking hotspots in a new city where no dockless shared bike has been deployed. We propose to measure road hotness by bike density with the help of the Kernal Density Estimation. We extract useful features from multi-source urban data and introduce a novel domain adaption network for transferring hotspots knowledge learned from one city with shared bikes to a new city. The extensive experimental results demonstrate the effectiveness of our proposed approach compared with various baselines.

Vehicular ad hoc network (VANET) has been widely recognized as a promising solution to enhance driving safety, by keeping vehicles well aware of the nearby environment through frequent beacon message exchanging. Due to the dynamic of transportation traffic, especially for those scenarios where the density of vehicles is high, the naive beaconing scheme where vehicles send beacon messages at a fixed rate with a fixed transmission power can cause severe channel congestion. In this paper, we investigate the risk of rear-end collision model and define a danger coefficient ρ to characterize the danger threat of each vehicle being in a rear-end collision. We then propose a fully-distributed beacon congestion control scheme, referred to as ABC, which guarantees each vehicle to actively adapt a minimal but sufficient beacon rate to avoid a rear-end collision based on individual estimates of ρ. In essence, ABC adopts a TDMA-based MAC protocol and solves a NP-hard optimal distributed beacon rate adapting (DBRA) problem with a greedy heuristic algorithm, in which a vehicle with a higher ρ will be assigned with a higher beacon rate while keeping the total required beacon demand lower than the channel capacity. We conduct extensive simulations to demonstrate the efficiency of ABC design in different traffic density and a large variety of underlying road topologies.

Given the increasing popularity, mobile devices are exploited to enhance active driving safety nowadays. Among all safety services provided for vehicles, tracking the rotation angle of steering wheel in real time can monitor the vehicles' dynamics and drivers' behaviors at the same time. In this paper, we propose a steering tracking system, SteerTrack, which tracks the rotation angle of steering wheel in real time leveraging audio devices on smartphones. SteerTrack seeks a device-free approach for steering tracking without requiring installation of specialized sensors on steering wheels nor asking drivers to wear sensors on their wrists. Since the steering wheel is operated by a driver's hands, the rotation angle of steering wheel can be tracked based on movements of the driver's hands. SteerTrack first builds an acoustic signal field inside of a vehicle and then analyzes the echoes reflected from the driver's hands with relative correlation coefficient(RCC) and reference frame to track the movement trajectory of hands under different steering maneuvers. Given the tracked movement trajectory, SteerTrack further develops a geometrical transformation-based method for estimating the rotation angle of steering wheel in 3D driving environments by projecting the steering wheel to a 2D ellipse. Through extensive experiments in real driving environments with 5 volunteers for several weeks, SteerTrack can achieve an average error of 4.61 degree for estimating the rotation angle of steering wheel.

Recently, dockless shared bike services have achieved great success and reinvented bike sharing business in China. When expanding bike sharing business into a new city, most start-ups always wish to find out how to cover the whole city with a suitable bike distribution. In this paper, we study the problem of inferring bike distribution in new cities, which is challenging. As no dockless bikes are deployed in the new city, we propose to learn insights on bike distribution from cities populated with dockless bikes. We exploit multi-source data to identify important features that affect bike distributions and develop a novel inference model combining Factor Analysis and Convolutional Neural Network techniques. The extensive experiments on real-life datasets show that the proposed solution provides significantly more accurate inference results compared with competitive prediction methods.

Predicting passenger pickup/dropoff demands based on historical mobility trips has been of great importance towards better vehicle distribution for the emerging mobility-on-demand (MOD) services. Prior works focused on predicting next-step passenger demands at selected locations or hotspots. However, we argue that multi-step citywide passenger demands encapsulate both time-varying demand trends and global statuses, and hence are more beneficial to avoiding demand-service mismatching and developing effective vehicle distribution/scheduling strategies. In this paper, we propose an end-to-end deep neural network solution to the prediction task. We employ the encoder-decoder framework based on convolutional and ConvLSTM units to identify complex features that capture spatiotemporal influences and pickup-dropoff interactions on citywide passenger demands. A novel attention model is incorporated to emphasize the effects of latent citywide mobility regularities. We evaluate our proposed method using real-word mobility trips (taxis and bikes) and the experimental results show that our method achieves higher prediction accuracy than the adaptations of the state-of-the-art approaches.

Mobile crowd sensing, also called crowd sensing over smartphones, has been an appealing paradigm for collecting sensory data over a vast urban area, due to advantages of low deployment cost and widely spatial coverage of geographically distributed smartphones or other smart devices. In the paper, we focus on a nontrivial problem of making an agreement between crowdsourcers and smartphone users to find the most efficient assignment of sensing tasks to smartphone users. However, there exist several technical challenges such as the incentive issue to encourage participation of smartphone users, preserving private information and distributed implementation in practice. Existing approaches usually have several limitations, e.g. the absence of proper incentives, the assumption of a centralized auctioneer or platform. To this end, we propose a distributed auction framework that explicitly models the interaction between crowdsourcers and smartphone users, achieving the optimal social profit and providing proper incentives to entities without disclosing their privacy as well. We demonstrate that the proposed distributed auction algorithm satisfies a lot of good properties, including optimality of social profit, computation efficiency, convergence, individual rationality through both solid theoretical analysis and extensive experiments.

It is of significant importance to provide incentives to smartphone users in mobile crowd sensing systems. Recently, a number of auction-based incentive mechanisms have been proposed. However, an auction-based incentive mechanism may unexpectedly release the location privacy of smartphone users, which may seriously reduce the willingness of users participating in contributing sensing data. In an auction-based incentive mechanism, even if the location of a user is not enclosed in his/her bid submitted to the platform, the location information may still be inferred by an adversary by using the prices of the tasks required by the user. We take an example to show how an attack can recover the location information of a smartphone user by merely knowing his/her bid. To defend against such an attack, we propose a method to protect location privacy in auctions for mobile crowd sensing systems. This method encrypts prices in a bid so that the adversary cannot access and hence the location privacy of users can be protected. In the meanwhile, however, the auction can proceed properly, i.e. the platform can select the user offering the lowest price for each sensing task or the platform can choose users with budget constraint. We demonstrate the effectiveness of our proposed method with theoretical analysis and simulations.

We consider the crucial problem of maximizing the social welfare of a vehicular participatory sensing system, where the system's social welfare is measured by the amount of sensing data delivered to a central platform through a vehicular ad hoc network. The key to the problem is to control network stability since both network congestion and idleness will slump system social welfare. However, several great challenges exist. First, limited vehicle-to-vehicle (V2V) link capacity and vehicle buffer size will lead to heavy network congestion when each individual vehicle blindly injects too much data into the network hoping to get more rewards. Second, the highly dynamic network topology and stochastic inter-vehicle contacts have a serious impact on the performance of multi-hop data transmission. Third, vehicles need to be practically rewarded based on their sensing and transmission cost, which, however, greatly vary among vehicles. To tackle the aforementioned challenges, we propose a distributed backpressure control approach, the first work to the best of our knowledge, to maximize the social welfare while balancing network stability for a vehicular participatory sensing system. Combining vehicular network properties and Lyapunov optimization techniques, individualized strategies are developed for each participant to control its sensing rate, make its own routing decisions, and set its own price for data relaying. Formally proved by rigorous theoretical analysis, the social welfare achieved by the proposed approach is comparative to the optimum performance. In addition, extensive data-driven simulations based on real taxi GPS traces have been conducted, and the results confirm the efficacy of the proposed algorithm.

Real-time driving behavior monitoring is a corner stone to improve driving safety. Most of the existing studies on driving behavior monitoring using smartphones only provide detection results after an abnormal driving behavior is finished, not sufficient for driver alerting and avoiding car accidents. In this paper, we leverage built-in audio devices on smartphones to realize early recognition of inattentive driving events including Fetching Forward, Picking up Drops, Turning Back, and Eating or Drinking. Through empirical studies of driving traces collected in real driving environments, we find that each type of inattentive driving event exhibits unique patterns on Doppler profiles of audio signals. This enables us to develop an Early Recognition system, ER, which can recognize inattentive driving events at an early stage and alert drivers timely. ER employs machine learning methods to first generate binary classifiers for every pair of inattentive driving events, and then develops a modified vote mechanism to form a multi-classifier for all four types of inattentive driving events, for atypical inattentive driving events along with other driving behaviors. It next turns the multi-classifier into a gradient model forestto achieve early recognition of inattentive driving. Through extensive experiments with eight volunteers driving for about two months, ER can achieve an average total accuracy of 94.80 percent for inattentive driving recognition and recognize over 80 percent inattentive driving events before the event is 50 percent finished.

When vehicle road-level localization cannot satisfy people's need for convenience and safety driving, lane-level localization becomes a corner stone in Intelligent Transportation System. Existing works of tracking vehicles on lane-level mostly depend on pre-deployed infrastructures and additional hardwares. In this paper, we utilize smartphones to sense driving conditions for vehicle lane-level localization on highways. By analyzing driving traces collected from real driving environments, we find that each type of lane-change has its unique pattern on the vehicle's lateral acceleration. Based on this observation, we propose a Lane-Level Localization (L3) system, which can perform real-time vehicle localization on lane-level only using smartphones when vehicles are driving on highways. Our system first uses embedded sensors in smartphones to capture the patterns of lane-change behaviors. Then, a Finite State Machine is employed to track vehicles on lane-level leveraging the patterns. Extensive experiments demonstrate that L3is accurate and robust in real driving environments. The experimental results show that, on average, L3achieves the accuracy of 91.49 percent on lane change detection and 90.31 percent on lane-level localization.

Auctions have been adopted by many major cloud providers, such as Amazon EC2. Unfortunately, only simple auctions have been implemented. Such simple auction has serious limitations, such as being unable to accept elastic user demands and having to allocate different types of VMs independently. These limitations create a big gap between the real needs of cloud users and the available services of cloud providers. In response to the limitations of the existing auction mechanisms, this paper proposes a novel online auction mechanism for IaaS clouds, with the unique features of an elastic model for inputting time-varying user demands and a unified model for requesting heterogeneous VMs together. However, several major challenges should be addressed, such as NP hardness of optimal VM allocation, time-varying user demands and potential misreports of private information of cloud users. We propose a truthful online auction mechanism for maximizing the profit of the cloud provider in IaaS clouds, which is composed of a price-based allocation rule and a payment rule. In the allocation rule, the online auction mechanism determines the number of VMs of each type to each user. In the payment rule, by introducing a marginal price function for each type of VMs, the mechanism determines how much the cloud provider should charge each cloud user. With solid theoretical analysis and trace-driven simulations, we demonstrate that our mechanism is truthful, fair and individually rational, and has a polynomial-time complexity. In addition, our auction achieves a competitive ratio for the profit of the cloud provider, compared against the offline optimal one.

Double auction-based pricing model is an efficient pricing model to balance users' and providers' benefits. Existing double auction mechanisms usually require both users and providers to bid with the unit price and the number of VMs. However, in practice users seldom know the exact number of VMs that meets their task requirements, which leads to users' task requirements inconsistent with providers' resource. In this paper, we propose a truthful double auction mechanism, including a matching process as well as a pricing and VM allocation scheme, to bridge users' task requirements and providers' resources in two-sided cloud markets. In the matching process, we design a cost-aware resource algorithm based on Lyapunov optimization techniques to precisely obtain the number of VMs that meets users' task requirements. In the pricing and VM allocation scheme, we apply the idea of second-price auction to determine the final price and the number of provisioned VMs in the double auction. We theoretically prove our proposed mechanism is individual-rational, truthful and budget-balanced, and analyze the optimality of proposed algorithm. Through simulation experiments, the results show that the individual profits achieved by our algorithm are 12.35 and 11.02 percent larger than that of scaleout and greedy scale-up algorithms respectively for 90 percent of users, and the social welfare of our mechanism is only 7.01 percent smaller than that of the optimum mechanism in the worst case.

Benefiting from the pay-per-use pricing model of cloud computing, many companies migrate their services and applications from typical expensive infrastructures to the cloud. However, due to fluctuations in the workload of services and applications, making a cost-efficient VM configuration decision in the cloud remains a critical challenge. Even experienced administrators cannot accurately predict the workload in the future. Since the pricing model of cloud provider is convex other than linear that often assumed in past research, instead of typical scaling out strategy. In this paper, we adopt mix scale strategy. Based on this observation, we model an optimization problem aiming to minimize the VM configuration cost under the constraint of migration delay. Taking advantages of Lyapunov optimization techniques, we propose a mix scale online algorithm which achieves more cost-efficiency than that of scale out strategy. Experimental results shows that the mix scale algorithm saves 30.8% and 31.1% cost where controlling migration delay in a tolerable range under different workload respectively.

The byte-addressable Non-Volatile Memory (NVM) offers fast, fine-grained access to persistent storage. While DRAM and NVM have similar read performance, the write operations of existing NVM materials incur longer latency and lower bandwidth than DRAM. This read-write asymmetry nature of NVM causes two bottlenecks for accessing read-and write-intensive file data: expensive data block lookups via file inner structure and high-latency direct writes to data blocks in NVM. However, existing NVM-based file systems fail to address both bottlenecks well. This paper presents WARP, an adaptive prefetching module designed for NVM-based file systems, which aims to deal with two bottlenecks effectively. WARP employs two acceleration approaches: 1) mapping data blocks into kernel virtual address space to bypass the indirection of file inner structure for read-intensive file data; and 2) allocating DRAM buffer to absorb frequent writes for write-intensive file data. We design a WARP benefit model to identify read-and write-intensive access patterns for file data, and use a successor prediction model to predict future data access based on historical file access traces. With WARP, we are able to prefetch file data according to both file access patterns and traces with consistency guarantee. WARP can be implemented on various NVM-based file systems, and we choose HMVFS for the experiments. The evaluation results show that HMVFS with WARP provides high prefetching accuracy and up to 32%-83% improvement compared with the state-of-the-art NVM-based file systems.

In-memory key/value stores have been widely deployed in many large systems for high throughput and low latency data access. To offer durability and fault tolerance, many of them (e.g., Memcached, Redis) flush data to RAID or SSD in local and remote with primary backup replication (PBR), in which the RAID and network become the bottleneck of throughput and latency. Recently, two promising technologies are emerging, i.e., non-volatile memory (NVM) and remote direct memory access (RDMA). NVMs are integrating into the main memory for their high density, high access speed, low cost and byte addressability. And RDMA allows direct access to the memory of a remote machine without invoking the peer CPU, thus reducing latency. To overcome the limitations of traditional key/value stores, this paper explores the design of a distributed low-latency key/value store on non-volatile main memory by leveraging RDMA. NVM not only eliminates disk IO operations, but also makes fast repli- cation possible. For a PUT operation, we collect modifications (data and metadata) at the local NVM of the primary server and replicate them to the same positions of backup servers by RDMA writes. A prototype distributed key/value store, called NVDS, is designed and implemented. Extensive experiments on the micro benchmark show that NVDS achieves significant latency reduction, compared to existing key/value stores. It replicates a 32bytes key/value PUT operation to two backup servers in less than 2μs and the whole request latency is less than 10μs.

New non-volatile memory (NVM) technologies, e.g., Phase Change Memory (PCM), are emerging with main features such as byte addressability, cheapness and large size, and will be deployed to serve as main memory. For fast processing of big data, block device drivers have been developed for NVM such that traditional file systems (e.g., EXT4) operated on non-volatile main memory. However, the existing block driver blindly caches pages, which incurs unnecessary access delays. To overcome this drawback, this paper develops a novel block device driver, called NVMBD, for byte-addressable non-volatile main memory. It adopts two methods of processing block I/O requests, i.e., traditional block I/O and BMAP. On the one hand, traditional block I/O reads/writes 512B sectors with multiple load/store instructions. On the other hand, BMAP inserts NVM pages into the page cache tree when processing block I/O requests, which removes the page movement between the page cache and the NVM. BMAP involves in the management of page cache, but it is transparent to file systems. BMAP provides file systems with the DAX-like feature, improving the file system performance. Through comprehensive experiments, we demonstrate that the developed block device driver significantly improves the file access performance.

With more and more vehicles equipped with GPS tracking devices, there is increasing interest in building and updating maps using vehicular GPS footprints or traces. Most existing approaches for building maps rely on position traces from highly accurate positioning devices, which are sampled at a high frequency, e.g., 1 Hz. Typically these traces are purposely recorded by survey vehicles. In practice, however, commodity GPS devices have much lower accuracy. In addition, the sampling frequency is low (at around once per minute) in order to reduce communication cost. Building maps from coarse-grained vehicular GPS footprints is challenging due to the inherent noise in commodity GPS devices and the shape complexity of urban roads. In this paper, we propose a novel algorithm called RRA for recognizing urban roads with coarse-grained GPS footprints from probe vehicles moving in urban areas. The algorithm overcomes the challenges by pruning low quality GPS footprints, clustering GPS footprints on the same road segment and applying shape aware B-spline fitting. We have conducted empirical study with a real data set of GPS footprints and evaluation results demonstrate that our RRA algorithm achieves good performance. When there are 800 taxis and the time window for footprints collection is 2 hours, the coverage of roads for RRA is 60% and the rate of false positive is 5%, while the best alternative algorithm KDE Points can hardly recognize any road.

Auctions have been adopted by many major cloud providers, such as Amazon EC2. Unfortunately, only simple auctions have been implemented. Such simple auction has serious limitations, such as being unable to accept elastic user demands and having to allocate different types of VMs independently. These limitations create a big gap between the real needs of cloud users and the available services of cloud providers. In response to the limitations of the existing auction mechanisms, this paper proposes a novel online auction mechanism for IaaS clouds, with the unique features of an elastic model for inputting time-varying user demands and a unified model for requesting heterogeneous VMs together. However, several major challenges should be addressed, such as NP hardness of optimal VM allocation, time-varying user demands and potential misreports of private information of cloud users. We propose a truthful online auction mechanism for maximizing the profit of the cloud provider in IaaS clouds, which is composed of a price-based allocation rule and a payment rule. In the allocation rule, the online auction mechanism determines the number of VMs of each type to each user. In the payment rule, by introducing a marginal price function for each type of VMs, the mechanism determines how much the cloud provider should charge each cloud user. With solid theoretical analysis and trace-driven simulations, we demonstrate that our mechanism is truthful and individually rational, and has a polynomial-time complexity.

Real-time driving behavior monitoring is a corner stone to improve driving safety. Most of the existing studies on driving behavior monitoring using smartphones only provide detection results after an abnormal driving behavior is finished, not sufficient for driver alert and avoiding car accidents. In this paper, we leverage existing audio devices on smartphones to realize early recognition of inattentive driving events including Fetching Forward, Picking up Drops, Turning Back and Eating or Drinking. Through empirical studies of driving traces collected in real driving environments, we find that each type of inattentive driving event exhibits unique patterns on Doppler profiles of audio signals. This enables us to develop an Early Recognition system, ER, which can recognize inattentive driving events at an early stage and alert drivers timely. ER employs machine learning methods to first generate binary classifiers for every pair of inattentive driving events, and then develops a modified vote mechanism to form a multi-classifier for all inattentive driving events along with other driving behaviors. It next turns the multi-classifier into a gradient model forest to achieve early recognition of inattentive driving. Through extensive experiments with 8 volunteers driving for about half a year, ER can achieve an average total accuracy of 94.80% for inattentive driving recognition and recognize over 80% inattentive driving events before the event is 50% finished.

As physical obstacles, vehicles have a significant impact on the efficient propagation of safety-related information in vehicular ad hoc networks (VANETs) by frequently obstructing the LOS link between the source and receivers. Obstructing effect of vehicles will diminish the effective coverage of broadcast as part of vehicles can not decode the broadcast successfully and incur severe impact on road safety. However, this impact has not been addressed by existing protocols. In this paper, we first present the definition of broadcast efficiency (BE) as the metric for measuring the obstructing effect and conclude the optimization issue of propagation. We further propose a distributed algorithm for mitigating this impact that can be embedded in VANETs. This algorithm maximizes the effective coverage of the broadcast of safety-related information and meanwhile satisfies the constraints on both link state and delay by selecting relay according to BE and referential propagation distance. Simulation results demonstrate that the proposed algorithm promotes the efficiency of propagation in dynamic multilane VANETs with varying vehicular distribution.

Understanding air travel choice behavior of air passengers is of great significance for various purposes such as travel demand prediction and trip recommendation. Existing approaches based on surveys can only provide aggregate level air travel choice behavior of passengers and they fail to provide comprehensive information for personalized services. In this paper we focus on modeling individual level air travel choice behavior of passengers, which is valuable for recommendations and personalized services. We employ a probabilistic model to represent individual level air travel choice behavior based on a large dataset of historical booking records, leveraging several key factors, such as takeoff time, arrival time, elapsed time between reservation and takeoff, price, and seat class. However, each passenger has only a limited number of historical booking records, causing a serious data sparsity problem. To this end, we propose a mixed kernel density estimation (mix-KDE) approach for each passenger with a mixture model that combines probabilistic estimation of both regularity of the individual himself and social conformity of similar passengers. The proposed model is trained and evaluated via the expectation-maximization (EM) algorithm with a huge dataset of booking records of over 10 million air passengers from a popular online travel agency in China. Experimental results demonstrate that our mix-KDE approach outperforms the Gaussian mixture model (GMM) and the simple kernel density estimation in the presence of the sparsity issue.

With the development of distributed energy generators and storages, the sustainability of a microgrid comprised of multiple electricity users is significantly increased. Maximizing the efficiency of generated renewable energy is vital to running a sustainable microgrid as it indicates reducing the usage of thermal electricity purchased from the macrogrid. To this end, the excessive renewable energy of a user should be shared with others who are short of energy. Unfortunately, coordinating the transfers of renewable energy among the users in a microgrid is particularly difficult, given the rational nature of users, the stochastic nature of renewable energy and the dynamic nature of energy demand of each user. In this paper, we consider the coupled problem of maximizing the renewable energy efficiency of a sustainable microgrid as well as stimulating rational users to share excessive renewable energy. We propose a near-optimal scheduling algorithm, which determines the amounts of renewable energy transferred among users in an online fashion. We also design an efficient pricing mechanism for the trade of energy among users based on double auction. We rigorously prove that our online scheduling algorithm is approximately optimal and the pricing mechanism guarantees the property of individual rationality of users. Comprehensive simulation results demonstrate the efficacy of our online algorithm and incentive mechanism.

With the proliferation of smartphones, participatory sensing using smartphones provides unprecedented opportunities for collecting enormous sensing data. There are two crucial requirements in participatory sensing, fair task allocation and energy efficiency, which are particularly challenging given high combinatorial complexity, trade-off between energy efficiency and fairness, and dynamic and unpredictable task arrivals. In this paper, we present a novel fair energy-efficient allocation framework whose objective is characterized by min–max aggregate sensing time. We rigorously prove that optimizing the min–max aggregate sensing time is NP hard even when the tasks are assumed as a priori. We consider two allocation models: offline allocation and online allocation. For the offline allocation model, we design an efficient approximation algorithm with the approximation ratio of 2−1m⁠, where m is the number of member smartphones in the system. For the online allocation model, we propose two algorithms: greedy algorithm and Robin-Hood algorithm, which achieve the competitive ratio of at most m and m+1⁠, respectively. The results demonstrate that the approximation algorithm reduces over 81% total sensing time, the online greedy algorithm and Robin-Hood algorithms reduce the total sensing time 73% and 37.5%, respectively. The offline approximation algorithm and online greedy algorithm achieve much better min–max fairness compared to other algorithms.

Delivering data from source vehicles to infrastructures, or convergecast, is a fundamental operation in vehicular networks. However, the network capacity of vehicular network is always limited because of scarce inter-vehicle contacts. Thus, throughput maximization of convergecast in vehicular networks is of great importance. The unique characteristics of vehicular networks, however, present great challenges including frequent connection unavailability and opportunistic contacts. We propose an approach called ConvergeCode for improving the convergecast throughput in vehicular networks, which employs random linear coding for packet delivery. A vehicle randomly combines all received coded data and forwards it to any contacted vehicles. Through extensive empirical study based on the two large datasets of real GPS traces, we make the key observation that significant throughput gain can be achieved by using network coding but a serious fairness issue arises. In this paper, we study the problem of maximizing the throughput of convergecast in vehicular networks at the same time enhancing the fairness among different source nodes. We first formulate the problem of allocating inter-vehicle contacts as a lexicographical max-min multi-source flow problem, and then develop an efficient approximation algorithm with ε-approximation guarantee. Simulations based on real vehicular GPS traces have been performed and results show that the throughput is improved by 74-110 percent while the lexicographical max-min fairness is achieved.

Crowdsourcing to mobile users has emerged as a compelling paradigm for collecting sensing data over a vast area for various monitoring applications. It is of paramount importance for such crowdsourcing paradigm to provide effective incentive mechanisms. State-of-the-art auction mechanisms for crowdsourcing to mobile users are typically deterministic in the sense that for a given sensing job from a crowdsourcer, only a small set of smartphones are selected to perform sensing tasks and the rest are not selected. One apparent disadvantage of such deterministic auction mechanisms is that the diversity with respect to the sensing job is reduced. As a consequence, the quality of the collected sensing data is also decreased. This is due to failure to exploit the intrinsic advantage of the large set of diverse mobile users in a mobile crowdsourcing network. In this paper, we propose a randomized combinatorial auction mechanism for the social cost minimization problem, which is proven to be NP-hard. We design an approximate task allocation algorithm that is near optimal with polynomial-time complexity and use it as a building block to construct the whole randomized auction mechanism. Compared with deterministic auction mechanisms, the proposed randomized auction mechanism increases the diversity in contributing users for a given sensing job. We carry out both solid theoretical analysis and extensive numerical studies and show that our randomized auction mechanism achieves approximate truthfulness, individual rationality, and high computational efficiency.

Accessing to timely and accurate road condition information, especially about dangerous potholes is of great importance to the public and the government. In this paper, we propose a novel scheme, called P3, which utilizes smartphones placed in normal vehicles to sense and estimate the profiles of potholes on urban surface roads. In particular, a P3-enabled smartphone can actively learn the knowledge about the suspension system of the host vehicle without any human intervention and adopts a one degree-offreedom (DOF) vibration model to infer the depth and length of pothole while the vehicle is hitting the pothole. Furthermore, P3 shows the potential to derive more accurate results by aggregating individual estimates. In essence, P3 is light-weighted and robust to various conditions such as poor light, bad weather, and different vehicle types. We have implemented a prototype system to prove the practical feasibility of P3. The results of extensive experiments based on real trace demonstrate the efficacy of the P3 design. On average, P3 can achieve low depth and length estimation error rates of 13 and 16 percent, respectively.

Real-time abnormal driving behaviors monitoring is a corner stone to improving driving safety. Existing works on driving behaviors monitoring using smartphones only provide a coarse-grained result, i.e., distinguishing abnormal driving behaviors from normal ones. To improve drivers’ awareness of their driving habits so as to prevent potential car accidents, we need to consider a fine-grained monitoring approach, which not only detects abnormal driving behaviors but also identifies specific types of abnormal driving behaviors, i.e.,Weaving,Swerving,Sideslipping,Fast U-turn,Turning with a wide radius, andSudden braking. Through empirical studies of the 6-month driving traces collected from real driving environments, we find that all of the six types of driving behaviors have their unique patterns on acceleration and orientation. Recognizing this observation, we further propose a fine-grained abnormalDriving behaviorDetection and iDentification system,$D^{3}$, to perform real-time high-accurate abnormal driving behaviors monitoring using smartphone sensors. We extract effective features to capture the patterns of abnormal driving behaviors. After that, two machine learning methods,Support Vector Machine(SVM) andNeuron Networks(NN), are employed, respectively, to train the features and output a classifier model which conducts fine-grained abnormal driving behaviors detection and identification. From results of extensive experiments with 20 volunteers driving for another four months in real driving environments, we show that$D^{3}$achieves an average total accuracy of 95.36 percent with SVM classifier model, and 96.88 percent with NN classifier model.

In this paper, we investigate the problem of energy balanced data collection in wireless sensor networks, aiming to balance energy consumption among all sensor nodes during the data propagation process. Energy balanced data collection can potentially save energy consumption and prolong network lifetime, and hence, it has many practical implications for sensor network design and deployment. The traditional hop-by-hop transmission model allows a sensor node to propagate its packets in a hop-by-hop manner toward the sink, resulting in poor energy balancing for the entire network. To address the problem, we apply a slice-based energy model, and divide the problem into inter-slice and intra-slice energy balancing problems. We then propose a probability-based strategy named inter-slice mixed transmission protocol and an intra-slice forwarding technique to address each of the problems. We propose an energy-balanced transmission protocol by combining both techniques to achieve total energy balancing. In addition, we study the condition of switching between inter-slice transmission and intra-slice transmission, and the limitation of hops in an intra-slice transmission. Through our extensive simulation studies, we demonstrate that the proposed protocols achieve energy balancing, prolong network lifespan, and decrease network delay, compared with the hop-by-hop transmission and a cluster-based routing protocol under various parameter settings.

With the growth of the economy, the air quality is becoming a serious issue, especially for those developing countries, such as China. Therefore, it is very important for the public and the government to access real-time air quality information. Unfortunately, the limited number of air quality monitoring stations is unable to provide fine-grained air quality information in a huge city, such as Beijing. One cost-effective approach for obtaining fine-grained air quality information is to infer air quality with those measured data at the monitoring stations. However, existing inference techniques have poor performance because of the extreme data sparsity problem (e.g., only 0.2% data are known). We observe that remote sensing has been a high-quality data source about urban dynamics. In this paper, we propose to integrate remote sensing data and ubiquitous urban data for air quality inference. There are two main challenges, i.e., data heterogeneity and incomplete remote sensing data. In response to the challenges, we propose a two-stage inference approach. In the first stage, we use the AOT remote sensing data and the meteorological data to infer the air quality values with an Artificial Neural Network (ANN). After this stage, we significantly reduce the percentage of empty cells in the tensor representing the spatio-temporal air quality values. In the second stage, we propose a tensor decomposition method to infer the complete set of air quality values. We use the spatial features (i.e., road features and POI features) and the temporal features (i.e., meteorological features) as the constraints in the tensor decomposition process. Experiments with real data sets show that our approach has profound performance advantage over the state-of-the-art methods, such as U-Air.

As air pollution is becoming a serious problem in developing nations, governments try to track and solve this problem by monitoring air pollution. With the proliferation of smartphones, mobile crowdsensing becomes a promising paradigm for monitoring fine-grained air pollution in urban areas. As existing studies have shown that pollutant concentrations have inherent spatiotemporal correlations, compressive sensing is an effective technology to reduce the amount of data collected through crowdsensing. In a practical crowdsensing application, incentives are expected by smartphone users for contributing sensing data. However, how to design incentives to collect high- quality sensing data with low costs is difficult in compressive crowdsensing. In this work, we propose an iterative scheme for the process of crowdsensing-based air pollution monitoring, where incentives are updated online according to the distribution of collected sensing data. Comprehensive simulations have been conducted to demonstrate the efficacy of our proposed scheme.

To support mobile users in contributing sensing data for making urban management decisions, in ShanghaiGrid, unified data gathering operations are to be performed. For citywide coverage, public vehicles accept data from surrounding users and hand over to computing center through wireless base stations (BSs) deployed in the city. Meanwhile, several among the vehicles are hired as relays, which assist gathering from others with multicopy and multihop forwarding towards the BSs. However, the budget shared by deploying BSs and hiring relays is limited. We explore how to decide BS deployment and relay-based forwarding for efficient gathering under the budget. The challenge lies in the great uncertainty about collection opportunities of candidate locations and vehicles in future gathering processes. In this paper, we present an empirical approach for the problem. To tackle the challenges, we characterize collection performance as function of temporal data paths towards each candidate, and formulate the problem as a multiobjective optimization problem. To solve it, we reveal regular relations between the candidates and estimate expected importance of them with large set of real vehicular traces; and develop an algorithmic framework for BS deployment and corresponding forwarding strategy. Extensive trace-driven simulations demonstrate the efficacy of the approach.

It is of significant importance to provide incentives to smartphone users in mobile crowd sensing systems. And a number of auction-based incentive mechanisms have been proposed. However, an auction-based incentive mechanism may unexpectedly release the location privacy of smartphone users, which may seriously reduce users' willingness of participating in mobile crowd sensing. In an auction-based mechanism, even if the location of the user is not enclosed in its bid submitted to the platform, the location information may still be inferred by an adversary by using the prices of the tasks required by the user. We show such an attack on a typical auction-based incentive mechanism and reveal that the attack can recover the location information of a smartphone user by merely knowing the bid from the user. To defend against such an attack, we propose P2, a location privacy-preserving auction mechanism for mobile crowd sensing systems. This mechanism encrypts prices in a bid so that the adversary cannot access and hence the location privacy of the user can be protected. In the meanwhile, however, the auction can proceed properly, i.e. the platform can select the user offering the lowest price for each sensing task. We demonstrate the effectiveness of our the proposed mechanism with simulation experiments.

With the development of renewable energy generators and electricity storages, microgrids become a promising technology of the smart grid. Maximizing the usage of renewable energy is vital to running a microgrid as it indicates reduction of the usage of thermal electricity purchased from the macrogrid. To this end, the excessive renewable energy of a user should be transferred to other users who need energy. Unfortunately, coordinating the transfers of renewable energy among the users in the microgrid is particularly difficult due to the stochastic nature of renewable energy, and the dynamic energy demand of each user. In this paper, we consider the problem of maximizing the long-term renewable energy usage by exchanging excessive renewable energy among users in a microgrid. We propose an online control algorithm which determines the amounts of renewable energy transferred among users in an online fashion. We rigorously prove that our online control algorithm is approximately optimal. We have conducted comprehensive simulation results that demonstrate the efficacy of our online algorithm.

Crowdsourcing distributed sensing to smartphones has become an appealing paradigm for harnessing the power of the crowd for collecting and sharing information. Market-driven auctions have been recognized as an effective way to matching sensing service demand and supply. A crowdsourcer acts as an auctioneer and smartphone workers act as bidders who are willing to supply sensing services to crowdsourcers. A number of auction mechanisms have been proposed. Unfortunately, most of them assume there is only one crowdsourcer, which is not true in the real world. In this paper, we consider the design of distributed auctions for a crowdsourced sensing market with multiple crowdsourcers and many smartphone workers. We employ a distributed reverse auction that works in a fully distributed fashion. The mechanism requires no one to release its private information. With extensive simulations, we demonstrate that our distributed mechanism achieves the optimal social welfare, and produces better performance than a competing algorithm.

Noise pollution poses a serious threat to people living in cities today. To alleviate the negative impact of noise pollution, an urban noise mapping can be helpful. In this paper, we present the design of NoiseSense, a crowd sensing system for housing a real-time urban noise mapping service. A major challenge in building such a system is caused by the sparsity problem of the limited noise measurement data from smartphones. To tackle this challenge, we propose a semi-supervised tensor completion algorithm for inferring noise levels for locations without measurements by smartphone users. This algorithm leverages a variety of urban data sources, such as Point of Interests (PoIs), road networks, and check-in data. We implemented the system and developed an APP for smartphone users. We conducted experiments and field study. The experimental results show that the proposed algorithm is superior in inferring noise levels merely with sparse measurements from smartphone users.

With the rapid emergence of mobile devices, smart phones have penetrated into every aspect of people's daily life. The explosive growth of mobile applications makes it difficult for mobile users to find suitable and interesting applications. Mobile app recommendation has been explored by many researchers and some industry solutions are proposed for mobile users. Collaborative filter (CF) is a popular technique in recommendation system, but it requires explicit feedback data like ratings, which are usually difficult to be collected. Many application markets provide keywords search functions and recommend applications with high download counts. However, downloading an application is a vague indicator of whether the user truly likes that application, as the user may probably uninstall that application immediately after it has been installed. Some other industry solutions involve users' personal data such as social networking, which may result in privacy leaks. In this paper, we propose two hybrid models based on collaborative filtering to make mobile app recommendations. We leverage RFD (Recency, Frequency, Duration) model to label the preference for users over applications from users' usage data. The first model, namely, improved item-oriented collaborative filtering (IIOCF), improves the performance of the item-oriented approach by leveraging the latent factor model to discover latent factors among applications. The second model (HLF) is a hybrid model of the latent factor and item-oriented approach. This model sums the predictions of the latent factor model and item-oriented approach, thereby capturing the advantages of both approaches. Our experiment results over 6,568 applications and 25,302 users clearly show that HLF model has better performance than both the item-oriented and latent factor approach.

When vehicle road-level localization cannot satisfy people's need for convenience and safety driving, lane-level localization becomes a corner stone in Intelligent Transportation System. Existing work on tracking vehicles on lane-level mostly depends on pre-deployed infrastructures and additional hardwares. In this paper, we utilize smartphone sensing of driving conditions for vehicle lane-level localization on highways. We analyze the driving traces collected from real driving environments, finding that each type of lane change has its unique pattern on the vehicle's lateral acceleration. Based on this observation, we propose a Lane-Level Localization (L3) system, which can perform real-time vehicle localization on lane-level only using smartphones when vehicles are driving on highways. Our system first uses embedded sensors in smartphones to capture the patterns of lane change behaviors. Then a Gaussian Distribution is employed to track vehicles on lane-level with tolerance of false detections. Extensive experiments demonstrate that L3 is accurate and robust in real driving environments. The experimental results show that, on average, L3 achieves accuracy of 91.49% on lane change detection and 86.94% on lane-level localization.

Mobile crowd sensing (MCS) has become a promising paradigm to perceive the environment with the help of smart phones. A monetary award is an effective method to incentivize participants to contribute good quality data. However, the reward for long-term data collection in the wide area could be unaffordable for a MCS requester. In this paper, we enable data requesters to recruit sensing workers in a group buying way. Requesters with similar data demand can form a group to share the payment and sensing data, which reduces cost and increases the coverage of sensing data. Agents from different groups compete in buying sensing data from sensing workers. We propose TGBA, a Two-phase Group Buying based Auction mechanism for MCS. In phase I, requesters submit bids to their group agent, the group agent decides the winners and clearing prices. In phase II, group agents attend the auction for recruiting workers. TGBA is computationally efficient and possesses good economic properties such as individual rationality, budget balance and truthfulness.

IEEE 802.11p based Dedicated Short Range Communication (DSRC) has been considered as a promising wireless technology for enhancing transportation safety and traffic efficiency. However, with limited literature available, there is lack of understanding about how IEEE 802.11p performs for vehicleto-vehicle (V2V) communications in urban environments. In this paper, we conduct intensive statistical analysis on V2V communication performance, based on the empirical measurement data collected from off-the-shelf IEEE 802.11p-compatible onboard units (OBUs). We have several key insights as follows. First, both line-of- sight (LoS) and non-line-of-sight (NLoS) durations follow power law distributions, which implies that the probability of having long LoS/NLoS conditions can be relatively high. Second, the packet inter-reception (PIR) time distribution follows an exponential distribution in LoS conditions but a power law in NLoS conditions. In contrast, the packet inter-loss (PIL) time distribution in LoS condition follows a power law but an exponential in NLoS condition. Third, the overall PIR time distribution is a mix of exponential distribution and power law distribution. The presented results provide solid ground to validate models, tune VANET simulators and improve communication strategies.

This paper discusses the time-constrained data delivery problem in vehicular ad hoc networks (VANETs). The unique characteristics of the network present great challenges to the issue. First, there are no always-connected forwarding routes between vehicles. Second, there is an intrinsic tradeoff between communication cost and delivery quality. Third, there is great uncertainty about vehicular mobilities. Exploiting vehicular trajectories, we present a constructive approach called TNC to tackle the challenges. In TNC, contact-based data forwarding and communication connections through the mobile network are incorporated. TNC first predicts the time-stamped inter-vehicle contacts and establishes expected contact graph, based on which it then computes the configuration for enhancing the connectivity of the network while introducing minimum number of mobile communication connections. Extensive simulations based on three real vehicular traces collected from 2,000 taxis and 1,400 buses in Shanghai, and 2,500 taxis in Shenzhen have been conducted and results demonstrate the efficacy of our approach.

We consider the crucial problem of maximizing the system-wide performance which takes into account request processing throughput, smartphone user experience and system stability in a participatory sensing system with cooperative smartphones. Three important controls need to be made, i.e., 1) request admission control, 2) task allocation, and 3) task scheduling on smartphones. It is highly challenging to achieve the optimal system-wide performance, given arbitrary unknown arrivals of sensing requests, intrinsic tradeoff between request processing throughput and smartphone user experience degradation, and heterogenous requests. Little existing work has studied this crucial problem of maximizing the system-wide performance of a participatory sensing system as a whole. In response to the challenges, we propose an optimal online control approach to maximize the system-wide performance of a participatory sensing system. Exploiting the stochastic Lyapunov optimization techniques, it derives the optimal online control strategies for request admission control, task allocation and task scheduling on smartphones. The most salient feature of our approach is that the achieved system-wide performance is arbitrarily close to the optimum, despite unpredictable and arbitrary request arrivals. Rigorous theoretical analysis and comprehensive simulation evaluation jointly demonstrate the efficacy of our online control approach.

Participatory regression modeling is a cost-efficient mechanism to establish the relationships among multiple dimensions of sensory data collected from volunteers. Getting an accurate model estimate is challenging for two main reasons. First, with the concern of confidentiality of individual private data, the original data are nearly unavailable; second, low quality data with outliers are inherently embedded in the collected data. In this paper, we propose an innovative scheme, PURE, which can accurately estimate the global regression model without the need for knowing local private data (referred to as blind regression modeling) even when there is a large portion of outliers embedded. The wisdom of PURE is to let individual participants peer judge and further improve the global estimate via negotiations. Meanwhile, during the whole process, all information is exchanged in an aggregated way. By design, PURE is secure and can well protect individual privacy. Furthermore, PURE is a lightweight protocol suitable for mobile devices. Extensive trace-driven simulation results show that PURE can achieve an outstanding accuracy gain of two orders of magnitude even with random outliers near a ratio of 50 percent compared with the state-of-the-art least square estimator.

Mobile advertising in vehicular networks is of great interest with which timely information can be fast spread into the network. Given a limited budget for hiring seed vehicles, how to achieve the maximum advertising coverage within a given period of time is NP-hard. In this paper, we propose an innovative scheme, POST, for mobile advertising in vehicular networks. The POST design is based on two key observations we have found by analyzing three large-scale vehicular traces. First, vehicles demonstrate dynamic sociality in the network; second, such vehicular sociality has strong temporal correlations. With the knowledge, POST uses Markov chains to infer future vehicular sociality and adopts two greedy heuristics to select the most “centric” vehicles as seeds for mobile advertising. Extensive simulations based on three real data sets of taxi and bus traces have been carried out. The results show that POSTcan greatly improve the coverage and the intensity of advertising. For all the three involved data sets, it achieves an average gain of 64 percent comparing with the state-of-art schemes.

Nowadays most metro advertising systems schedule advertising slots on digital advertising screens to achieve the maximum exposure to passengers by exploring passenger demand models. However, our empirical results show that these passenger demand models experience uncertainty at fine temporal granularity (e.g., per min). As a result, for fine-grained advertisements (shorter than one minute), a scheduling based on these demand models cannot achieve the maximum advertisement exposure. To address this issue, we propose an online advertising approach, called EveryoneCounts, based on an uncertain passenger demand model. It combines coarse-grained statistical demand modeling and fine-grained Bayesian demand modeling by leveraging realtime card-swiping records along with both passenger mobility patterns and travel periods within metro systems. Based on this uncertain demand model, it schedules advertising time online based on robust receding horizon control to maximize the advertisement exposure. We evaluate the proposed approach based on an one-month sample from our 530 GB real-world metro fare dataset with 16 million cards. The results show that our approach provides a 61.5% lower traffic prediction error and 20% improvement on advertising efficiency on average.

The proliferation of smartphones has enabled a novel paradigm, participatory sensing, which leverages the smartphones to collect and share data about their surrounding environment. Since the sensing tasks are location-dependent and have time features, it is crucial and challenging to find a proper allocation of sensing tasks to ensure the timeliness of tasks and the quality of sensing data. In this paper, we investigate the heterogeneous sensing task allocation problem aiming at minimizing the total penalty caused by the tardiness of tasks. We prove this problem is NP-hard and propose two hybrid algorithms which combine a heuristic algorithm and two meta-heuristic algorithms respectively. The extensive simulation results show that the proposed hybrid algorithms outperform the meta-heuristic algorithms.

Packet failure classifiers help improve wireless transmission performance by identifying packet failure causes. Since different configurations should be adopted for packet retransmissions according to different packet failure causes, knowing the real-time failure causes can avoid further retransmissions. We have the observation that real-world packet failure causes may interleave in packet level so that adjacent packet failures may occur with different causes. However, existing classifiers introduce a long classification delay, during which the channel condition probably has changed. We propose a packet- level failure classifier, which identifies packet failure causes for each corrupted packet. The classifier characterizes failure patterns of byte-level RSSI and packet-level LQI for packet failure causes of collision and weak link. We have implemented the classifier in TelosB nodes in an indoor environment. The salient feature of the proposed classifier is that the classification delay is reduced to packet-level, as short as 23 ms. Test-bed experiments show that the classifier has a classification accuracy of 93%. Moreover, a throughput improvement of 110% is achieved by avoiding 70% packet retransmissions.

This paper studies the critical problem of maximizing the aggregate data utility under the practical constraint on budget in mobile crowd sourced sensing. This problem is particularly challenging given the redundancy in sensing data, self-interested and strategic user behaviors, private cost information of smartphones and budget constraint. In this paper, we propose a combinatorial auction mechanism based on a redundancy-aware reverse auction framework. It consists of an approximation algorithm for winning bids determination and a critical payment scheme. Our mechanism achieves truthfulness, individual rationality, computational efficiency, budget feasibility and high redundancy-aware data utility.

Participatory sensing has become a compelling and viable paradigm for large scale sensing data collection in recent years, with smartphone workers recruited from a public crowd. Since the quality of the sensing data is directly related to the performance of the workers, it is then crucial to enable effective participation for a large number of workers. In this paper, we propose a decentralized dynamic participation game framework for participatory sensing systems with heterogeneous sensing processes and smartphone workers. Based on economic studies, we characterize the behaviour of workers with the idea of correlated equilibrium. We propose a regret matching based participation algorithm to track the set of correlated equilibria in a distributed manner, where the knowledge of competitors' preference information is not required. Simulation results demonstrate that our algorithm achieves good convergence and effective participation.

It is valuable for the public to get access to real-time noise level information. Unfortunately, it is generally difficult for ordinary people to access real-time noise level information because of limited noise information stations and increased burden of carrying professional noise level meters. Being equipped with a high-quality microphone, a smartphone can potentially serve as a handy noise level meter. However, the straightforward use of sound measurements from smartphones leads to large measurement errors. As a result, it is essential to calibrate a smartphone before it can be used for noise level measurements. Little work has been done on automatic smartphone calibration for noise measurement purposes. In this paper we design a system called iCal for calibrating smartphones for accurate noise level measurements. The system consists of two key components: node-based calibration and crowdsourcing-based calibration. The node-based calibration enables an individual smartphone to do offline calibration, but suffers a slow-start issue. Complementing the node-based calibration, the crowdsourcing-based calibration leverages the power of crowdsourcing to maintain a lookup table, which a smartphone user can consult to find an approximate offset specific to its smartphone model. Thus, the slow-start issue can be effectively mitigated. The salient feature of iCal is human intervention free. We have implemented iCal on the android platform and experimental results show that the calibration error is as low as 3 dbA.

Wireless local area networks (WLANs) are pervasive but crowded nowadays. It is of great importance for access points (APs) to adapt to the changing traffic conditions. Exiting approaches for channel selection largely rely on local channel assessment and adopt greedy selection strategies. They suffer a major limitation that an AP fail to take various traffic demands of clients into account. We have witnessed that wireless sensor networks are increasingly deployed everywhere. A ZigBee sensor operates on the 2.4G radio spectrum which overlaps the spectrum used by most WiFi APs. As a result, a ZigBee sensor is able to sense the traffic of different AP channels. Motivated by this important observation, we present the design, implementation and evaluation of OutSence, a system that enables APs to takes traffic volumes of clients into account. It makes use of channel utilization sensed by ZigBee sensors and allows an AP to select a channel of good performance. The salient feature of OutSence is that it exploits in-situ ZigBee sensors for APs to quickly adapt to short-term traffic variations (e.g., order of minutes). We have fully implemented OutSence on Telos B sensor nodes and off-the-self APs. Extensive experiments have been conducted and conclusive results demonstrate that OutSence effectively improves overall WLAN performance.

This paper studies the critical problem of maximizing the aggregate data utility under budget constraint in mobile crowd sourced sensing. This problem is particularly challenging given the redundancy in sensing data, self-interested and strategic user behaviors, and private cost information of smartphones. Most of existing approaches do not consider the important performance objective - maximizing the redundancy-aware data utility of sensing data collected from smartphones. Furthermore, they do not consider the practical constraint on budget. In this paper, we propose a combinatorial auction mechanism based on a reverse auction framework. It consists of an approximation algorithm for winning bids determination and a critical payment scheme. The approximation algorithm guarantees a constant approximation ratio at polynomial-time complexity. The critical payment scheme guarantees truthful bidding. The rigid theoretical analysis demonstrates that our mechanism achieves truthfulness, individual rationality, computational efficiency, and budget feasibility. Extensive simulations show that the proposed mechanism produces high redundancy-aware data utility.

Crowd sourced sensing over smartphones presents a new paradigm for collecting sensing data over a vast area for real-time monitoring applications. A monitoring application may require different types of sensing data, while under a budget constraint. This paper explores the crucial problem of maximizing the aggregate data utility of heterogeneous sensing tasks while maintaining utility-centric fairness across different tasks under a budget constraint. In particular, we take the redundancy of sensing data into account. This problem is highly challenging given its unique characteristics including the intrinsic trade off between aggregate data utility and fairness, and the large number of smartphones. We propose a fairness-aware distributed approach to solving this problem. To overcome the intractability of the problem, we decompose it to two sub problems of recruiting smartphones under a budget constraint and allocating workloads of sensing tasks. For the first sub problem, we propose an efficient greedy algorithm which has a constant approximation ratio of two. For the second problem, we apply dual based decomposition based on which we design a distributed algorithm for determining the workloads of different tasks on each recruited smartphone. We have implemented our distributed algorithm on a windows-based server and Android-based smartphones. With extensive simulations we demonstrate that our approach achieves high aggregate data utility while maintaining good utility-centric fairness across sensing tasks.

Stimulating both service users and service providers is of paramount importance to mobile crowdsourcing. A few incentive mechanisms have been proposed, but all of them have focused only on one-sided interactions either among service users or among service providers. For the first time, to the best of our knowledge, we investigate the important two-sided online interactions among service users and service providers in mobile crowdsourcing. We model such interactions as online double auctions, explicitly taking the dynamic nature of both users and providers into account We propose a general framework for the design of truthful online double auctions for dynamic mobile crowdsourcing. The framework is expressive and can work with different price schedules. We propose price-ranked online double auctions with four price schedules to implement the framework, which are suitable for different scenarios. With theoretical analysis and extensive simulations we demonstrate that the proposed auctions are strategy-proof, individual rational, and ensure budget balance.

Mobile crowdsourcing to smartphones has emerged as a compelling paradigm for collecting sensing data over a vast area for various monitoring applications. It is of paramount importance for mobile crowdsourcing to provide incentive mechanisms. State-of-the-art auction mechanisms for mobile crowdsourcing are deterministic in the sense that given the real costs of the smartphone users, a fixed set of smartphone users are recruited for performing sensing tasks. This leads to serious issues including reduced diversity of sensing devices and starvation of some users. In this paper, we propose an approximate-truthful randomized combinatorial auction mechanism for the social cost minimization problem, which is NP-hard. We design an approximate task allocation algorithm that is near optimal with polynomial-time complexity and use it as a block to construct the whole randomized auction mechanism. We carry out numerical studies and show that our randomized auction mechanism achieves approximate truthfulness, individual rationality, and high computation efficiency. Moreover, the proposed mechanism increases diversity of devices and prevents starvation of some smartphones.

Spectrum sharing between the licensed primary user (PU) and secondary users (SUs) has been increasingly important. We consider a utility maximization framework for spectrum sharing among cognitive SUs and the PU in multi-hop cognitive radio networks. We propose an efficient distributed algorithm for solving the spectrum allocation problem. Extensive simulations have been performed and the results show that our algorithm achieves much better network utility than other compared algorithms.

Smartphone is widely used in indoor map construction with its build-in sensors. However, the low accuracy problem of build-in sensors always causes the collected user trajectories noisy. The significant problem we face is the low accuracy of walk heading estimated by build-in sensors because of phone heading fluctuation and magnetic field anomaly. This paper presents HiHeading - a high reliable crowdsourcing-based indoor map construction system. HiHeading leverages build-in inertial sensors to construct accurate motion traces. These traces are generated by HiHeading with high accuracy based on the novel ideal of fusing gyroscope and orientation sensor to get reliable walk heading estimation in indoor dead reckoning (DR). To evaluate our system, we have tested it in a middle size indoor office by recording 3 people's walk trajectories during 5 days. We present an evaluation of our system and the experiment result shows 70% of the heading estimation error is lower than 10 degrees.

Real-time abnormal driving behaviors monitoring is a corner stone to improving driving safety. Existing works on driving behaviors monitoring using smartphones only provide a coarsegrained result, i.e. distinguishing abnormal driving behaviors from normal ones. To improve drivers' awareness of their driving habits so as to prevent potential car accidents, we need to consider a finegrained monitoring approach, which not only detects abnormal driving behaviors but also identifies specific types of abnormal driving behaviors, i.e. Weaving, Swerving, Sideslipping, Fast U-turn, Turning with a wide radius and Sudden braking. Through empirical studies of the 6-month driving traces collected from real driving environments, we find that all of the six types of driving behaviors have their unique patterns on acceleration and orientation. Recognizing this observation, we further propose a finegrained abnormal Driving behavior Detection and iDentification system, D3, to perform real-time high-accurate abnormal driving behaviors monitoring using smartphone sensors. By extracting unique features from readings of smartphones' accelerometer and orientation sensor, we first identify sixteen representative features to capture the patterns of driving behaviors. Then, a machine learning method, Support Vector Machine (SVM), is employed to train the features and output a classifier model which conducts fine-grained identification. From results of extensive experiments with 20 volunteers driving for another 4 months in real driving environments, we show that D3achieves an average total accuracy of 95.36%.

Elevated roads are built worldwide to alleviate urban traffic congestions. An elevated road may overlap with the ground surface road. This poses a great challenge to auto navigation systems. It is particularly difficult for auto navigation systems to determine if an vehicle is running on an elevated road because altitude readings from GPS (Global Positioning Systems) receivers are of low accuracy. Without correct positioning of elevated or surface roads, an auto navigation system may recommend wrong routes which may lead to serious traffic accidents or cause drivers' anxiety. In this paper, we design a smartphone-based system called DEEL for detecting road elevation as the vehicle moves on urban roads. HMM-based models are built to characterize the patterns of vehicle dynamics with respect to the elevation of the road that the vehicle is moving on. The system leverages smartphone sensors to sense the instantaneous vehicle dynamics, including the 3D acceleration, the speed, and the number of perceived GPS satellites. Based on the sensed dynamics, it determines whether the vehicle is running on an elevated road or not in an online fashion. We have successfully implemented our system in Android-based smartphones. Extensive experiments demonstrate the system achieves a high accuracy of 92.1% with strong robustness to variations of vehicles, drivers and roads.

Sensing data collection is of great significance in mobile crowd sensing. We consider the problem of online maximization of data utility of the sensing data collected from smartphone users under a time average budget constraint. There are several major challenges, including random and unknown phone contexts, budget constraint and existence of data redundancy. Little work has studied this crucial problem. In this paper we formulate it as an online scheduling problem which determines sensing decisions for smartphones that are distributed over different regions of interest We first propose a centralized online scheduling algorithm based on stochastic optimal control. To address the poor scalability issue of the centralized algorithm, we further propose a distributed online scheduling algorithm based on distributed correlated scheduling. It does not require any priori knowledge of future smartphone contexts, and hence sensing decisions can locally be made by individual smartphones. Rigorous theoretical analysis show that our algorithms can achieve a time average data utility that is within O{1/V) of the theoretical optimum. Extensive simulations demonstrate that our algorithms produce high time average data utility.

When road-level localization cannot satisfy people's need for convenience and safety driving, lane-level localization becomes a corner stone. In this paper, we propose a vehicle Lane-Level Localization (L^3) system, which utilizes smartphone sensors to real-time locate the vehicle on lane-level on highways. The system is based on the observation that each type of lane change has its unique pattern on the vehicle's lateral acceleration. Extensive experiments demonstrate that L^3 is both accurate and robust in real driving environments.

As people increasingly rely on road maps in the digital age, manually maintained maps cannot keep up with the demand for accuracy and freshness, evidenced by the recent iOS map incident and the bidding war for Waze. There are many research works on automatic map inference using GPS data, and some have suggested that Google and Waze automate their map update processes to some degree with user data. However, existing published work focuses on refining road geometry. In reality, connectivity issues at intersections, including missing connections and unmarked turn restrictions, are much more prevalent and also more difficult to infer. In this paper, we report our study on the connectivity issues in the OSM Shanghai map using 21 months of GPS data from over |$10\,000$| taxis. We first adapt a robust map matching algorithm. Then, we propose simple algorithms for detecting missing intersections, turn restrictions and road closures. Empirical results show that our algorithms of connectivity refinement for road maps are effective.

Summary With the increasingly growing amount of service requests from the world‐wide customers, the cloud systems are capable of providing services while meeting the customers' satisfaction. Recently, to achieve the better reliability and performance, the cloud systems have been largely depending on the geographically distributed data centers. Nevertheless, the dollar cost of service placement by service providers (SP) differ from the multiple regions. Accordingly, it is crucial to design a request dispatching and resource allocation algorithm to maximize net profit. The existing algorithms are either built upon energy‐efficient schemes alone, or multi‐type requests and customer satisfaction oblivious. They cannot be applied to multi‐type requests and customer satisfaction‐aware algorithm design with the objective of maximizing net profit. This paper proposes an ant‐colony optimization‐based algorithm for maximizing SP's net profit (AMP) on geographically distributed data centers with the consideration of customer satisfaction. First, using model of customer satisfaction, we formulate the utility (or net profit) maximization issue as an optimization problem under the constraints of customer satisfaction and data centers. Second, we analyze the complexity of the optimal requests dispatchment problem and rigidly prove that it is an NP‐complete problem. Third, to evaluate the proposed algorithm, we have conducted the comprehensive simulation and compared with the other state‐of‐the‐art algorithms. Also, we extend our work to consider the data center's power usage effectiveness. It has been shown that AMP maximizes SP net profit by dispatching service requests to the proper data centers and generating the appropriate amount of virtual machines to meet customer satisfaction. Moreover, we also demonstrate the effectiveness of our approach when it accommodates the impacts of dynamically arrived heavy workload, various evaporation rate and consideration of power usage effectiveness. Copyright © 2014 John Wiley & Sons, Ltd.

3G technology has stimulated a wide variety of high-bandwidth applications on smartphones, such as video streaming and content-rich web browsing. Although having those applications mobile is quite appealing, high data rate transmission also poses huge demand for power. It has been revealed that the tail effect in 3G radio operation results in significant energy drain on smartphones. Recent fast dormancy technique can be utilized to remove tails but, without care, can degrade user experience. In this paper, we propose a novel scheme SmartCut, which effectively mitigates the tail effect of radio usage in 3G networks with little side-effect on user experience. The core idea of SmartCut is to utilize the temporal correlation of packet arrivals to predict upcoming packets, based on which unnecessary high-power-state tails of radio are cut out leveraging the Fast Dormancy mechanism. Both prototype experiment and extensive trace-driven simulation results demonstrate the efficacy of SmartCut design. On average, SmartCut can save up to 43 percent network energy while having little side-effect to user experience.

Touch-screen technique has gained the large popularity in human-screen interaction with modern smartphones. Due to the limited size of equipped screens, scrolling operations are indispensable in order to display the content of interest on screen. While power consumption caused by hardware and software installed within smartphones is well studied, the energy cost made by human-screen interaction such as scrolling remains unknown. In this paper, we analyze the impact of scrolling operations to the power consumption of smartphones, finding that the state-of-art strategy of smartphones in responding a scrolling operation is to always use the highest frame rate which arouses huge computation burden and can contribute nearly 50 percent to the total power consumption of smartphones. In recognizing this significance, we further propose a novel system, energy-efficient engine (E3), which automatically tracks the scrolling speed and adaptively adjusts the frame rate according to user preference. The goal of E3is to guarantee the user experience and minimize the energy consumption caused by scrolling at the same time. Extensive experiment results demonstrate the efficiency of E3design. On average, E3can save up to 60 percent of the energy consumed by CPU and 35 percent of the overall energy consumption.

Multicast is a crucial routine operation for vehicular networks, which underpins important functions such as message dissemination and group coordination. As vehicles may distribute over a vast area, the number of vehicles in a given region can be limited which results in sparse node distribution in part of the vehicular network. This poses several great challenges for efficient multicast, such as network disconnection, scarce communication opportunities and mobility uncertainty. Existing multicast schemes proposed for vehicular networks typically maintain a forwarding structure assuming the vehicles have a high density and move at low speed while these assumptions are often invalid in a practical vehicular network. As more and more vehicles are equipped with GPS enabled navigation systems, the trajectories of vehicles are becoming increasingly available. In this work, we propose an approach called TMC to exploit vehicle trajectories for efficient multicast in vehicular networks. The novelty of TMC includes a message forwarding metric that characterizes the capability of a vehicle to forward a given message to destination nodes, and a method of predicting the chance of inter-vehicle encounter between two vehicles based only on their trajectories without accurate timing information. TMC is designed to be a distributed approach. Vehicles make message forwarding decisions based on vehicle trajectories shared through inter-vehicle exchanges without the need of central information management. We have performed extensive simulations based on real vehicular GPS traces and compared our proposed TMC scheme with other existing approaches. The performance results demonstrate that our approach can achieve a delivery ratio close to that of the flooding-based approach while the cost is reduced by over 80 percent.

Data collection is a crucial operation in wireless sensor networks. The design of data collection schemes is challenging due to the limited energy supply and the hot spot problem. Leveraging empirical observations that sensory data possess strong spatiotemporal compressibility, this paper proposes a novel compressive data collection scheme for wireless sensor networks. We adopt a power-law decaying data model verified by real data sets and then propose a random projection-based estimation algorithm for this data model. Our scheme requires fewer compressed measurements, thus greatly reduces the energy consumption. It allows simple routing strategy without much computation and control overheads, which leads to strong robustness in practical applications. Analytically, we prove that it achieves the optimal estimation error bound. Evaluations on real data sets (from the GreenOrbs, IntelLab and NBDC-CTD projects) show that compared with existing approaches, this new scheme prolongs the network lifetime by 1.5X to 2X for estimation error 5-20 percent.

Content-based publish/subscribe systems have been employed to deal with complex distributed information flows in many applications. It is well recognized that event matching is a fundamental component of such large-scale systems. Event matching searches a space which is composed of all subscriptions. As the scale and complexity of a system grows, the efficiency of event matching becomes more critical to system performance. However, most existing methods suffer significant performance degradation when the system has large numbers of both subscriptions and their component constraints. In this paper, we present Hash Tree (H-Tree), a highly efficient index structure for event matching. H-Tree is a hash table in nature that is a combination of hash lists and hash chaining. A hash list is built up on an indexed attribute by realizing novel overlapping divisions of the attribute's value domain, providing more efficient space consumption. Multiple hash lists are then combined into a hash tree. The basic idea behind H-Tree is that matching efficiencies are improved when the search space is substantially reduced by pruning most of the subscriptions that are not matched. We have implemented H-Tree and conducted extensive experiments in different settings. Experimental results demonstrate that H-Tree has better performance than its counterparts by a large margin. In particular, the matching speed is faster by three orders of magnitude than its counterparts when the numbers of both subscriptions and their component constraints are huge.

This paper focuses on workload allocation among mobile nodes in a mobile crowd sensing system. We take both two important objectives into account, including load balance and sensing data utility maximization. However, workload allocation achieving both objectives is particularly challenging. First, there is an intrinsic tradeoff between load balance and utility maximization. The system should strike a good balance between the two important objectives. Second, the number of mobile users can be large. A simple exhaustive search of workload allocation results can be prohibitively expensive. In this paper, we model workload allocation as a Nash bargaining game. We propose a distributed algorithm to solve the Nash bargaining game and determine the workload to each individual smartphone. It effectively decomposes the complex optimization problem into subproblems, and obtains the workload allocation solution by an iterative procedure imitating the bargaining process. This distributed algorithm can achieve a fair tradeoff between workload balance and data utility maximization, which is provably Pareto-efficient. We have conducted extensive simulations, and the results demonstrate that our algorithm achieves Pareto optimality and fairness between the two important objectives.

Many cities suffer from noise pollution, which compromises people's working efficiency and even mental health. New York City (NYC) has opened a platform, entitled 311, to allow people to complain about the city's issues by using a mobile app or making a phone call; noise is the third largest category of complaints in the 311 data. As each complaint about noises is associated with a location, a time stamp, and a fine-grained noise category, such as "Loud Music" or "Construction", the data is actually a result of "human as a sensor" and "crowd sensing", containing rich human intelligence that can help diagnose urban noises. In this paper we infer the fine-grained noise situation (consisting of a noise pollution indicator and the composition of noises) of different times of day for each region of NYC, by using the 311 complaint data together with social media, road network data, and Points of Interests (POIs). We model the noise situation of NYC with a three dimension tensor, where the three dimensions stand for regions, noise categories, and time slots, respectively. Supplementing the missing entries of the tensor through a context-aware tensor decomposition approach, we recover the noise situation throughout NYC. The information can inform people and officials' decision making. We evaluate our method with four real datasets, verifying the advantages of our method beyond four baselines, such as the interpolation-based approach.

We are interested in delay-constrained data aggregation in delay tolerant vehicular networks, in which contact opportunities are usually scarce and thus become critical resources. Data aggregation has been recognized as an effective technique for reducing communication cost while obtaining useful aggregated information. The unique characteristics of the network present great challenges to the delay-constrained aggregation issue. First, there is no always-connected path from a source node to a destination node. Second, there is an intrinsic tradeoff between communication cost and aggregation quality. In this paper we discuss the delay-constrained data aggregation problem in delay tolerant vehicular networks with the objective of maximizing the amount of information collected, which has not been well studied in the literature. We observe that there are heterogeneity and regularity with node contact patterns. Motivated by this observation, we propose an Efficient tree-based Data Aggregation algorithm called EDA. EDA first constructs a data aggregation tree based on the shortest path tree, and then assigns a waiting time budget to each node on the tree using a dynamic programming algorithm. We have performed extensive simulations on real taxi traces and results show that our EDA scheme incurs much lower transmission overhead while achieving the same performance compared with other schemes.

Stimulating participation from smartphone users is of paramount importance to mobile crowd sourcing systems and applications. A few incentive mechanisms have been proposed, but most of them have made the impractical assumption that smartphones remain static in the system and sensing tasks are known in advance. The existing mechanisms fail when being applied to the realistic scenario where smartphones dynamically arrive to the system and sensing tasks are submitted at random. It is particularly challenging to design an incentive mechanism for such a mobile crowd sourcing system, given dynamic smartphones, uncertain arrivals of tasks, strategic behaviors, and private information of smartphones. We propose two truthful auction mechanisms for two different cases of mobile crowd sourcing with dynamic smartphones. For the offline case, we design an optimal truthful mechanism with an optimal task allocation algorithm of polynomial-time computation complexity of O (n+γ)3, where n is the number of smartphones and γ is the number of sensing tasks. For the online case, we design a near-optimal truthful mechanism with an online task allocation algorithm that achieves a constant competitive ratio of 1:2. Rigorous theoretical analysis and extensive simulations have been performed, and the results demonstrate the proposed auction mechanisms achieve truthfulness, individual rationality, computational efficiency, and low overpayment.

On behalf of the 20th IEEE International Conference on Parallel and Distributed Systems (ICPADS 2014) Organizing Committee, we are very pleased to announce that more than three hundred researchers and contributors from the world submitted their papers to share their research results and new ideas. The objective of this conference to provide a major international forum for scientists, engineers, and users to exchange and share their experiences, new ideas, and latest research results on all aspects of parallel and distributed computing systems.

In this paper, we tackle the problem of stimulating smartphone users to join mobile crowdsourcing applications with smartphones. Different from existing work of mechanism design, we uniquely take into consideration the crucial dimension of location information when assigning sensing tasks to smartphones. However, the location awareness largely increases the theoretical and computational complexity. In this paper, we introduce a reverse auction framework to model the interactions between the platform and the smartphones. We rigorously prove that optimally determining the winning bids is NP hard. In this paper we design a mechanism called TRAC which consists of two main components. The first component is a near-optimal approximate algorithm for determining the winning bids with polynomial-time computation complexity, which approximates the optimal solution within a factor of 1 + ln(n), where n is the maximum number of sensing tasks that a smartphone can accommodate. The second component is a critical payment scheme which, despite the approximation of determining winning bids, guarantees that submitted bids of smartphones reflect their real costs of performing sensing tasks. Through both rigid theoretical analysis and extensive simulations, we demonstrate that the proposed mechanism achieves truthfulness, individual rationality and high computation efficiency.

Acquiring instant vehicle speed is desirable and a corner stone to many important vehicular applications. This paper utilizes smartphone sensors to estimate the vehicle speed, especially when GPS is unavailable or inaccurate in urban environments. In particular, we estimate the vehicle speed by integrating the accelerometer's readings over time and find the acceleration errors can lead to large deviations between the estimated speed and the real one. Further analysis shows that the changes of acceleration errors are very small over time which can be corrected at some points, called reference points, where the true vehicle speed is known. Recognizing this observation, we propose an accurate vehicle speed estimation system, SenSpeed, which senses natural driving conditions in urban environments including making turns, stopping and passing through uneven road surfaces, to derive reference points and further eliminates the speed estimation deviations caused by acceleration errors. Extensive experiments demonstrate that SenSpeed is accurate and robust in real driving environments. On average, the real-time speed estimation error on local road is 1.32mph, and the offline speed estimation error is as low as 0.75mph. Whereas the average error of GPS is 3.1mph and 2.8mph respectively.

Event matching is the process of checking high volumes of events against large numbers of subscriptions and is a fundamental issue for the overall performance of a large-scale distributed publish/subscribe system. Most existing algorithms are based on counting satisfied component constraints in each subscription. As the scale of a system grows, these algorithms inevitably suffer from performance degradation. We present REIN (REctangle INtersection), a fast event matching approach for large-scale content-based publish/subscribe systems. The idea behind REIN is to quickly filter out unlikely matched subscriptions. In REIN, the event matching problem is first transformed into the rectangle intersection problem. Then, an efficient index structure is designed to address the problem by using bit operations. Experimental results show that REIN has a better matching performance than its counterparts. In particular, the event matching speed is faster by an order of magnitude when the selectivity of subscriptions is high and the number of subscriptions is large.

Mobile advertising in vehicular networks is of great interest with which timely information can be fast spread into the network. Given a limited budget for hiring seed vehicles, how to achieve the maximum advertising coverage within a given period of time is NP-hard. In this paper, we propose an innovative scheme, POST, for mobile advertising in vehicular networks. The POST design is based on two key observations we have found by analyzing three large-scale vehicle traces. First, vehicles demonstrate dynamic sociality in the network; second, such vehicular sociality has strong temporal correlations. With the knowledge, POST uses Markov chains to infer future vehicular sociality and adopts one greedy heuristic to select the most “centric” vehicles as seeds for mobile advertising. Extensive trace-driven simulation results show that POST can greatly improve the coverage and the intensity of advertising.

With the proliferation of smartphones, participatory sensing using smartphones provides unprecedented opportunities for collecting enormous sensing data. There are two crucial requirements in participatory sensing, fair task allocation and energy efficiency, which are particularly challenging given high combinatorial complexity, tradeoff between energy efficiency and fairness, and dynamic and unpredictable task arrivals. In this paper, we present a novel fair energy-efficient allocation framework whose objective is characterized by min-max aggregate sensing time. We rigorously prove that optimizing the min-max aggregate sensing time is NP hard even when the tasks are assumed as a priori. We consider two allocation models: offline allocation and online allocation. For the offline allocation model, we design an efficient approximation algorithm with the approximation ratio of 2 - 1/m, where m is the number of member smartphones in the system. For the online allocation model, we propose a greedy online algorithm which achieves a competitive ratio of at most m. The results demonstrate that the approximation algorithm reduces over 81% total sensing time, the greedy online algorithm reduces more than 73% total sensing time, and both algorithms achieve over 3x better min-max fairness.

Wireless sensor networks (WSNs) are gaining popularity in practical monitoring and surveillance applications. Because of the limited energy of sensor nodes, many WSNs work in a low duty cycle mode to effectively extend their network lifetime. However, low duty cycling also decreases transmission efficiency and makes data gathering more challenging. By exploiting the redundancy of in real sensing data, we propose a novel and distributed approach for data gathering in wireless sensor networks, employing the compressed sensing theory. Instead of selecting a fixed sink, all data can be retrieved from an arbitrary node within the network. Moreover, we use sequential observations to dynamically fit the sparsity of various data sets. With extensive simulations, we show that our approach is efficient with tunable accuracy in different node duty cycles.

This paper considers the crucial problem of event detection and localization with sensor networks, which not only needs to detect occurrences but also to determine the locations of detected events and event source signals. It is highly challenging when taking several unique characteristics of real-world events into consideration, such as simultaneous emergence of multiple events, overlapping events, event heterogeneity and stringent requirement on energy efficiency. Most of existing studies either assume the oversimplified binary detection model or need to collect all sensor readings, incurring high transmission overhead. Inspired by spatially sparse event occurrences within the monitoring area, we propose a compressive sensing based approach called CED, targeting at multiple heterogeneous events that may overlap with each other. With a fully distributed measurement construction process, our approach enables the collection of a sufficient number of measurements for compressive sensing based data recovery. The distinguishing feature of our approach is that it requires no knowledge of, and is adaptive to, the number of occurred events which is changing over time. We have validated the signal attenuation event model through testbed experiments with TelosB motes. Extensive simulation results demonstrate that our approach can achieve high detection rate and localization accuracy while incurring modest transmission overhead.

We consider the crucial problem of maximizing the social welfare of a vehicular participatory sensing system which consists of mobile source vehicles that collect sensing data on the move and relay vehicles that forward sensing data to the central sensing platform. Three issues should be taken into consideration, i.e., sensing rate control, flow control and transmission, incentives for vehicles to participate. It is highly challenging to achieve the optimal social welfare, given the arbitrary unknown contact events and the dynamic network formed by mobile vehicles. To tackle the challenges, we propose a fully distributed optimal control algorithm DBC to maximize the social welfare while keeping good network stability. Exploiting the stochastic Lyapunov optimization technique, it derives an optimal control strategy for sensing rate control and flow control. Rigorous theoretical analysis shows the gap between the DBC and the optimum is only O(1/V), where V is a tradeoff parameter between social welfare and network stability. In addition, we have conducted extensive simulations based on real taxi GPS traces, and the results show the efficacy of DBC.

In this paper, we consider the crucial problem of maximizing the profit of a crowd sensing platform which receives sensing requests from various subscribers and completes the requests by leveraging sensing time of participating smartphones. The profit of the platform is defined as the total charges of sensing requests minus the payments to smartphones. It is highly challenging to obtain the maximal profit for the platform, because of stochastic arrivals of sensing requests, dynamic participation of smartphones, and high complexity of optimally allocating requests to smartphones. In response to the challenges, we propose an optimal online control framework which can efficiently utilize the limited sensing time on each smartphone. Based on the stochastic Lyapunov optimization techniques combined with the idea of weight perturbation, our control framework makes crucial online control decisions, such as sensing requests admission and dispatching control, sensing time purchasing control and sensing time allocation control, without requiring any future knowledge about request arrivals. Rigorous mathematical analysis and comprehensive simulation results show that our control framework can achieve a time averaged profit that is arbitrarily close to the optimum, while still maintaining strong system stability.

Radio Frequency IDentification (RFID) systems have rich applications in daily life. A crucial problem in RFID systems is to estimate the cardinality of RFID tags. Most exiting probabilistic RFID cardinality estimation algorithms utilize a certain pattern hidden in the response vector formed by the tag responses to make estimators. In this paper, we argue that finding the patterns is actually not necessary! In this paper, we present a novel approach to RFID cardinality estimation by making the full use of the whole response vector. We characterize the critical relationship between the number of RFID tags and the specific distribution of the bits in the response vector. In this paper, we consider two kinds of responses, i.e., empty / non-empty responses and empty / singleton / collision responses. To cater for RFID systems with a very large number of tags, we also generalize our estimation approach to handle geometrically distributed response vectors. Both rigid theoretical analysis and extensive simulations have been conducted and the conclusive results demonstrate that our approach is more accurate than existing state-of-the-art RFID estimation approaches.

Participatory sensing has gained increasing attention in recent years as it is promising for empowering large-scale monitoring and knowledge discovery, leveraging a crowd of public smartphone workers. In a participatory sensing system, the platform recruits workers to participate in multiple sensing processes. However, sensing processes have limited budgets. A smartphone is only satisfied when it receives a reward large enough to cover its cost caused, e.g., by resource consumption. Considering the rationality of smartphone workers, it is of great importance for the participatory sensing system to satisfy as many workers as possible, in order to stimulate more smartphone participation. In this paper, we propose a general sensing processes participation game framework with heterogenous workers and heterogenous sensing processes. We show that it is NP-hard to find a sensing processes participation solution which maximizes the number of satisfied workers. Inspired by the finite improvement property of the game, we design and implement an algorithm of sensing processes participation, which guarantees to reach a pure Nash equilibrium in polynomial time, and allows workers to change their strategy profiles asynchronously. Simulation results show that our algorithm is effective and efficient.

SUMMARY It is well known that data centers are consuming a large amount of energy that incurs significant financial and environmental costs. Recently, there has been an increasing interest in utilizing green energy for data centers, where green energy sources include solar and wind. This paper studies the crucial problem of maximizing the utilization of green energy through scheduling complex jobs in data centers in order to reduce the use of traditional brown energy. However, it is highly challenging for data centers to make use of green energy. First, the availability of typical green energy is variable to dynamic changes of natural environments, for example, weather. Second, although predictions can be made for the future availability of green energy, it is inevitable that such predictions have errors. Third, jobs are associated with strict deadlines, and it is required that jobs are completed before their deadlines. Finally, because the reliability in a data center relies upon temperature, the awareness of temperature should be taken into account while maximizing the green energy. In this paper, we consider online scheduling of jobs whose arrivals to the data center system dynamically. In addition, we explicitly take the power consumption of switches into account when scheduling jobs onto computing nodes. Two solar energy‐aware algorithms called SEEDMin and SEEDMax have been proposed. Then, we extend SEED to RSEED with the awareness of reliability. To evaluate the effectiveness of the proposed algorithms, comprehensive simulations have been conducted, and the proposed algorithms are compared with other state‐of‐art algorithms. Experimental results demonstrate that both SEEDMin and SEEDMax can significantly increase the utilization of solar energy without violating job deadlines and overall energy budget. The amount of solar energy utilized by SEEDMin and SEEDMax is 33.4%and35.3% larger than that of two traditional scheduling algorithms, MinMin and MinMax, respectively. Also, it can be seen that RSEED greatly improves the reliability by decreasing the temperature. Copyright © 2013 John Wiley & Sons, Ltd.

Geocast in vehicular networks aims to deliver a message to a target geographical region, which is useful for many applications such as geographic advertising. This is a highly challenging task in vehicular network environments due to the rare encounter opportunities and uncertainty caused by vehicular mobility. As more vehicles are equipped with on-board navigation systems, vehicle trajectories are ready for exploitation. We observe that a vehicle has a higher capability of delivering a message to the target region if its own future trajectory or trajectories of those vehicles to be encountered overlap the target region. Motivated by this observation, we develop a message forwarding metric, called coverage capability, to characterize the capability of a vehicle to successfully geocast the message. When calculating the coverage capability, we are facing the major challenge raised by the absence of accurate vehicle arrival time. Through an empirical study using real vehicular GPS traces of 2,600 taxis, we verify that the travel time of a vehicle, which is modeled as a random variable, follows the Gamma distribution. The travel time modeling helps us to make accurate predictions for inter-vehicle encounters. We perform extensive trace-driven simulations and the results show that our approach achieves 37.4 percent higher delivery ratio and 43.1 percent lower transmission overhead comparing with GPSR which is a representative geographic routing protocol.

Efficient identification of tags has been an essential operation for Radio Frequency IDentification (RFID) systems. In this paper, we consider the crucial problem of collecting all tags in a large-scale system through a handheld RFID reader. The reader has to move around due to the limited communication range of tags. We focus on the minimization of power consumption of the reader given the constraint on its movement distance. Two challenges must be addressed. First, the communication range of a tag is dependent on the reader. There is an intrinsic tradeoff between power saving and movement distance. Second, the number of sites at which the reader can collect tags can be numerous and the problem complexity is extremely high. We theoretically prove that the problem of minimizing the energy consumption of the reader is NP Complete (NPC). To solve the problem, we first analytically reveal that the time needed for reading a given number of tags is linearly proportional to the number of tags only. With this insight, we next propose an approach called ePath by constructing an energy-efficient candidate path and then incrementally pruning the path when the tag locations are given. We further relax the assumption on tag locations by extending ePath to exploit the tag distribution density knowledge only. Extensive simulations have been performed, and results show that our approach significantly reduces the power consumption of the reader comparing to an existing approach.

Efficient data delivery is of great importance, but highly challenging for vehicular networks because of frequent network disruption, fast topological change and mobility uncertainty. The vehicular trajectory knowledge plays a key role in data delivery. Existing algorithms have largely made predictions on the trajectory with coarse-grained patterns such as spatial distribution or/and the inter-meeting time distribution, which has led to poor data delivery performance. In this paper, we mine the extensive data sets of vehicular traces from two large cities in China, i.e., Shanghai and Shenzhen, through conditional entropy analysis, we find that there exists strong spatiotemporal regularity with vehicle mobility. By extracting mobility patterns from historical vehicular traces, we develop accurate trajectory predictions by using multiple order Markov chains. Based on an analytical model, we theoretically derive packet delivery probability with predicted trajectories. We then propose routing algorithms taking full advantage of predicted probabilistic vehicular trajectories. Finally, we carry out extensive simulations based on three large data sets of real GPS vehicular traces, i.e., Shanghai taxi data set, Shanghai bus data set and Shenzhen taxi data set. The conclusive results demonstrate that our proposed routing algorithms can achieve significantly higher delivery ratio at lower cost when compared with existing algorithms.

The process of map matching takes a sequence of possibly noisy GPS coordinates from a vehicle trace and estimates the actual road positions---a crucial first step needed by many GPS applications. There has been a plethora of methods for map matching published, but most of them are evaluated on low-noise datasets obtained from a planned route. And comparisons with other methods are very limited. Based on our previous unifying framework used to catalog different mathematical formulas in many published methods, we evaluate representative algorithms using the low-noise dataset from the GIS Cup 2012 and a high-noise dataset collected from Shanghai downtown. Our experiments reveal that global max-weight and global geometrical map matching methods are the most accurate, but each has its weaknesses. We therefore propose a new map matching algorithm that integrates Fréchet distance with global weight optimization, which is more accurate across all sampling intervals.

This paper describes a point-polygon query program we submitted to the ACM SIGSPATIAL Cup 2013. Point-polygon topological relationship query is one of the core functions for commercial spatial databases, and also an active research topic in academia. Spatial indices are the key to achieve top performance. However, different datasets or query patterns require different indices for optimal performance. Based on the patterns of the training dataset, we build a hierarchy of indices, including polygon index, edge index, and interval index, which help find polygons near a point, calculate the distance from a point to a polygon, and determine whether a point is inside a polygon, respectively. Using the provided training dataset, these three indices reduce the computation time of "WITHIN n" query by 90%, 10%, and 50%, respectively. We build a large dataset with more than 1 million samples and 520 polygons by cloning and offsetting the training dataset 15 and 13 times, respectively. Our program finishes the "WITHIN 1000" query in only one second on a 4-core 3.3GHz Xeon Processor.

Vehicular networks have become a promising platform for large-scale urban sensing. On-demand data retrieval is a crucial operation for many applications of vehicular networks. It is particularly challenging, however, to achieve high performance of on-demand data retrieval in sparse vehicular networks. Data replication based on random linear network coding can solve the coupon collection problem but suffers the problem of unnecessary data replications which waste the precious communication opportunities of sparse vehicular networks. With real traces we reveal the existence of community structures in vehicular networks, which causes excessive linearly correlated blocks. Motivated by the important observation, we propose a community-aware data replication scheme based on random linear network coding. To reduce the excessive correlated coded blocks because of community structures, we make probabilistic control on the data replication phase, taking the community structures into account. It is demonstrated through extensive simulations that the community-aware scheme can effectively save up to 50% communication opportunities whiling achieving high performance of on-demand data retrieval.

A hot and primary problem in RFID system is the estimation of RFID tag cardinality and many algorithms have been proposed for estimating RFID cardinality. However, we find that there is a serious problem that has been widely neglected by some of previous works of RFID cardinality estimation. They incorrectly assume that states of different time slots in the same frame are independent of each other. The consequence of such incorrect assumption would lead to low estimation accuracy. To demonstrate how we correct this mistake, we propose an accurate and fast estimating algorithm called AFR based on the pattern of the number of consecutive empty slots before the first non-empty slot. We theoretically derive the expected number and the variance of consecutive empty slots before the first non-empty slot as a function of the number of tags. Based on such theoretical derivation, we determine the best estimation of the number of tags by only looking at the numbers of consecutive empty slots before the first non-empty slot. Simulation results demonstrate that our algorithm makes more accurate estimation of RFID tag cardinality than an existing state-of-the-art algorithm while using shorter estimation time.

There are increasing interests on mobile opportunistic networks which have promising applications. Constructing a mobile backbone can effectively improve the packet delivery performance of a mobile opportunistic network by excluding poor relay nodes and reducing packet collisions. However, it is highly challenging to construct an effective mobile backbone because of the absence of the quantitative relationship between the network performance and the selection of backbone nodes, and expositive search space. As nodes exhibit clear sociality observed in previous studies, We explicitly take such node sociality into account when computing the backbone for mobile opportunistic networks and we incrementally propose three algorithms for computing the mobile backbone. Trace-driven simulations have been conducted and simulation results demonstrate that the sociality-aware algorithms can achieve low delivery delay and high delivery ratio.

Vehicles are becoming powerful mobile sensors, and vehicular networks provide a promising platform to support a wide range of existing large-scale monitoring applications such as road surface monitoring, and etc. In vehicular networks, inter-vehicle contacts are scarce resources for data delivery. This presents a major challenge for monitoring applications with vehicular networks. By analyzing a large dataset of taxi traces collected from around 2,600 taxis in Shanghai, China, we reveal that there is strong correlation with data readings on vehicles. Motivated by this important observation, we propose a compressive sensing based approach called CSM to monitor with vehicular networks. Two key issues must be addressed. First, there is an intrinsic tradeoff between communication cost and estimation accuracy. Second, guaranteed estimation accuracy should be provided over the highly dynamic network. To address the above issues, we first characterize the relationship between estimation error (12 error) and sparsity property of a dataset. Then, we determine two critical parameters: the minimum number of seeds and the minimum transmission hop length for compressive measurements in the network. The selection of the two parameters can reduce the communication cost while guaranteeing the required estimation accuracy. Extensive simulations based on real vehicular GPS traces collected in Shanghai, China have been performed and results demonstrate that CSM achieves much higher estimation accuracy at the same communication cost compared with other alternative schemes.

Given the unique characteristics of vehicular networks, specifically, frequent communication unavailability and short encounter time, packet replication has been commonly used to facilitate data delivery. Replication enables multiple copies of the same packet to be forwarded towards the destination, which increases the chance of delivery to a target destination. However, this is achieved at the expense of consuming extra already scarce bandwidth resource in vehicular networks. Therefore, it is crucial to investigate the fundamental problem of exploiting constrained network capacity with packet replication. We make the first attempt in this work to address this challenging problem. We first conduct extensive empirical analysis using three large datasets of real vehicle GPS traces. We show that a replication scheme that either underestimates or overestimates the network capacity results in poor delivery performance. Based on the observation, we propose a Capacity-Constrained Replication scheme or CCR for data delivery in vehicular networks. The key idea is to explore the residual capacity for packet replication. We introduce an analytical model for characterizing the relationship among the number of replicated copies of a packet, replication limit and queue length. Based on this insight, we derive the rule for adaptive adjustment towards the optimal replication strategy. We then design a distributed algorithm to dictate how each vehicle can adaptively determine its replication strategy subject to the current network capacity. Extensive simulations based on real vehicle GPS traces show that our proposed CCR can significantly improve delivery ratio comparing with the state-of-the-art algorithms.

Vehicular networks consist of highly mobile vehicles communications, where connectivity is intermittent. Due to the distributed and highly dynamic nature of vehicular network, to minimize the end-to-end delay and the network traffic at the same time in data forwarding is very hard. Heuristic algorithms utilizing either contact-level or social-level scale of vehicular mobility have only one-sided view of the network and therefore are not optimal. In this paper, by analyzing three large sets of Global Positioning System (GPS) trace of more than ten thousand public vehicles, we find that pairwise contacts have strong temporal correlation. Furthermore, the contact graph of vehicles presents complex structure when aggregating the underlying contacts. In understanding the impact of both levels of mobility to the data forwarding, we propose an innovative scheme, named ZOOM, for fast opportunistic forwarding in vehicular networks, which automatically choose the most appropriate mobility information when deciding next data-relays in order to minimize the end-to-end delay while reducing the network traffic. Extensive trace-driven simulations demonstrate the efficacy of ZOOM design. On average, ZOOM can improve 30% performance gain comparing to the state-of-art algorithms.

The inaccuracy of manually created digital road maps is a persistent problem, despite their high economic value. We present CrowdAtlas, which automates map update based on people's travels, either individually or crowdsourced. Its mobile navigation app detects significant portions of GPS traces that do not conform to the existing map, as determined by state-of-the-art Viterbi map matching. When there is sufficient evidence collected, map inference algorithms can automatically update the map. The CrowdAtlas server aggregates exceptional traces from users with the navigation app as well as from other, large-scale data sources. From these it automatically generates high quality map updates, which can be propagated to its navigation app and other interested applications. Using CrowdAtlas app, we mapped out a 4.5 km^2 street block in Shanghai in less than half an hour and built a walking/cycling map of the SJTU campus. Using taxi traces collected from Beijing, we contributed completely computer-generated roads for this large, 61 km of missing roads to OpenStreetMap, the first set of open-source map community.

Digital road maps have become essential to many aspects of our lives. Unfortunately, they have persistent quality issues, both in developing countries as well as in developed countries, evidenced by the recent Apple-Google map war. A survey of British drivers showed 26% have been directed by their GPS to go into no-entry areas, and the news periodically reports car accidents caused by or related to digital maps. In addition to correcting existing errors, maps need to be frequently updated to reflect the latest constructions, closures, and reconfigurations. TomTom estimates that roads change by as much as 15% each year. There are also growing demands for other types of maps, including off-road driving, cycling, hiking, and skiing maps. There are services for people to share GPS traces, but none creates navigable maps.

Touch-screen technique has gained the large popularity in human-screen interaction with modern smartphones. Due to the limited size of equipped screens, scrolling operations are indispensable in order to display the content of interest on screen. While power consumption caused by hardware and software installed within smartphones is well studied, the energy cost made by human-screen interaction such as scrolling remains unknown. In this paper, we analyze the impact of scrolling operations to the power consumption of smartphones, finding that the state-of-art strategy of smartphones in responding a scrolling operation is to always use the highest frame rate which arouses huge computation burden and can contribute nearly 50% to the total power consumption of smartphones. In recognizing this significance, we further propose a novel system, Energy-Efficient Engine(E3), which automatically tracks the scrolling speed and adaptively adjusts the frame rate according to individual user preference. The goal of E3 is to guarantee the user experience and minimize the energy consumption caused by scrolling at the same time. Extensive experiment results demonstrate the efficiency of E3 design. On average, E3 can save up to 58% of the energy consumed by CPU and 34% of the overall energy consumption.

Vehicular 3G (third-generation cellular system) users often need to download files from the Internet through the 3G data network, which is crucial in many application scenarios such as digital map update or location-based advertisement. Although the 3G brings larger coverage and instant access to data transfer, it may also incur high cost. We observe that many applications of vehicular 3G users can actually tolerate certain data access latency. In addition, inter-vehicle communications have been practical and can be exploited for inter-vehicle data delivery. Based on these observations, we propose to augment vehicular 3G users by data sharing through inter-vehicle communications. We formulate an optimization problem. The objective is to minimize the cost of 3G data communications, meanwhile maximizing the success probability of downloading all 3G user data. The two-hop transmission process and the bandwidth limitation in vehicular network are both modeled in the optimization problem. To lower the cost of 3G and meet the delivery ratio and delay constraints of data, one single-stage and one multi-stage algorithms are proposed for selection of seed vehicles (who download the data via 3G channel). We have evaluated our algorithm with simulations with real vehicular traces and the results show that our algorithms reduce the 3G cost and achieve good performance of data downloads.

Cloud computing has emerging as a promising pattern for data outsourcing and high-quality data services. However, concerns of sensitive information on cloud potentially causes privacy problems. Data encryption protects data security to some extent, but at the cost of compromised efficiency. Searchable symmetric encryption (SSE) allows retrieval of encrypted data over cloud. In this paper, we focus on addressing data privacy issues using SSE. For the first time, we formulate the privacy issue from the aspect of similarity relevance and scheme robustness. We observe that server-side ranking based on order-preserving encryption (OPE) inevitably leaks data privacy. To eliminate the leakage, we propose a two-round searchable encryption (TRSE) scheme that supports top-$(k)$ multikeyword retrieval. In TRSE, we employ a vector space model and homomorphic encryption. The vector space model helps to provide sufficient search accuracy, and the homomorphic encryption enables users to involve in the ranking while the majority of computing work is done on the server side by operations only on ciphertext. As a result, information leakage can be eliminated and data security is ensured. Thorough security and performance analysis show that the proposed scheme guarantees high security and practical efficiency.

Traffic estimation is crucial to a number of tasks such as traffic management and road engineering. We propose an approach for metropolitan-scale traffic estimation with probe vehicles that periodically send location and speed updates to a monitoring center. In our approach, we use the flow speed on a road link within a time slot to indicate the traffic condition of the road segment at the given time slot, which is approximated by the average value of probe speeds. By analyzing a large data set of two-year probe data collected from a fleet of around 4,000 taxis in Shanghai, China, we find that a set of probe data may contain a lot of spatiotemporal vacancies over both time and space. This raises a serious missing data problem for road traffic estimation, which results from the naturally uneven distribution of probe vehicles over both time and space. Through empirical study based on the data set of real probe data using principal component analysis (PCA), we have observed that there are hidden structures within the traffic conditions of a road network. Inspired by this observation, we propose a compressive sensing-based algorithm for solving the missing data problem, which exploits the hidden structures for computing estimates for road traffic conditions. Different from existing approaches, our algorithm does not rely on complicated traffic models, which usually require costly training with field study and large data sets. With extensive experiments based on the data set of real probe data, we demonstrate that our proposed algorithm performs significantly better than other completing algorithms, including KNN and MSSA. Surprisingly, our algorithm can achieve an estimate error of as low as 20 percent even when more than 80 percent of probe data are missing.

Traffic light sensing aims to detect the status of traffic lights which is valuable for many applications such as traffic management, traffic light optimization, and real-time vehicle navigation. In this work, we develop a system called POVA for traffic light sensing in large-scale urban areas. The system employs pervasive probe vehicles that just report real-time states of position and speed from time to time. POVA has advantages of wide coverage and low deployment cost. The important observation motivating the design of POVA is that a traffic light has a considerable impact on mobility of vehicles on the road attached to the traffic light. However, the system design faces three unique challenges: 1) Probe reports are by nature discrete while the goal of traffic light sensing is to determine the state of a traffic light at any time; 2) there may be a very limited number of probe reports in a given duration for traffic light state estimation; and 3) a traffic light may change its state with a variable interval. To tackle the challenges, we develop a new technique that makes the best use of limited probe reports as well as statistical features of light states. It first estimates the state of a traffic light at the time instant of a report by applying maximum a posterior estimation. Then, we formulate the state estimation of a light at any time into a joint optimization problem that is solved by an efficient heuristic algorithm. We have implemented the system and tested it with a fleet of around 4,000 probe taxis and 2,000 buses in Shanghai, China. Trace-driven experimentation and field study show that nearly 60 percent of traffic lights have an estimation error lower than 19 percent if 20,000 probe vehicles would be employed in the urban area of Shanghai. We further demonstrate that the estimation error rate is as low as 18 percent even when the number of available reports is merely 1 per minute.

Online social networks (OSN) have been increasingly popular and attracted hundreds of millions of users, and they are usually deployed on cluster systems. A crucial problem for scaling online social networks is allocation and replication of user data records in cluster nodes with the objective of reducing access time and minimizing the costs of storage and intra-cluster communication. In these applications, users not only access their own data but also data of their friends. It is preferable that all data required by a user be placed in the same node so that access time can be reduced and communication overhead is small. The inherently complex social interactions between users, however, pose great challenges to the mechanism of data allocation and replication. Analyzing a large real dataset from OSNs, we observe that for over 90% of users, all their interactions are contributed by only 22.03% of their fiends, a Pareto distribution property. Thus, the majority of the interactions of a user are attributed to a small subset of the user's friends. Inspired by this observation, we first build a dynamic weighted social graph which differentiates the importance of social interactions between a user and the user's friends. Using this graph, we design WEPAR, an online partitioning and replication algorithm taking into account both read and write operations. WEPAR tries to place master data copies of users with frequent interactions in the same cluster node, and generates slave data copies for the users who tend to receive relatively more reading requests from a cluster-node. Extensive evaluations based on real datasets show that our approach significantly reduces storage cost and improves write response time with read response time comparable to that of existing algorithms.

To many sensor networks, the robust operation depends on deploying relays to ensure wireless coverage. This paper considers the crucial problem of optimal relay placement for wireless sensor networks in indoor environments. The placement of relays is essential for ensuring communication quality and data collection. A number of existing algorithms have been proposed for ensuring full sensing coverage and network connectivity. These algorithms can hardly be applied to indoor environments because of the complexity of indoor environments, in which a radio signal can be dramatically degraded by obstacles like walls. We firstly theoretically prove that the indoor relay placement problem is NP-hard. We then predict radio coverage of a given relay deployment in indoor environments, and then propose a efficient greedy algorithm for computing the relay deployment locations for required coverage quality. This algorithm is proved to provide a Hnfactor approximation to the theoretical optimum, where Hn= 1 + 1/2 + ⋯ + 1/n = ln(n) + 1, and n is the number of all grid points. Experimental results demonstrate the proposed algorithm achieves better performance than two other algorithms. To our knowledge, our work is the very first that study the optimal relay placement problem for sensor networks in complex indoor environments.

This paper describes a map matching program submitted to the ACM SIGSPATIAL Cup 2012. We first summarize existing map matching algorithms into three categories, and compare their performance thoroughly. In general, global max-weight methods using the Viterbi dynamic programming algorithm are the most accurate but the accuracy varies at different sampling intervals using different weight functions. Our submission selects a hybrid that improves upon the best two weight functions such that its accuracy is better than both and the performance is robust against varying sampling rates. In addition, we employ many optimization techniques to reduce the overall latency, as the scoring heavily emphasizes on speed. Using the training dataset with manually corrected ground truth, our Java-based program matched all 14,436 samples in 5 seconds on a dual-core 3.3 GHz iCore 3 processor, and achieved 98.9% accuracy.

Efficient data delivery in vehicular networks has received increasing attention in recent years. Existing routing protocols for vehicular networks can be loosely divided into two classes: road based routing (RBR) and road oblivious routing (ROR). RBR finds a routing path along roads while ROR does not explicitly forward packets along roads. We have the observation that using either of an RBR algorithm or an ROR algorithm alone in a realistic vehicular network setting leads to deficiency. This results from the fact that network conditions can be different at different locations and evolving over time. Motivated by this observation, this paper proposes an adaptive routing algorithm called RWR that adapts its routing strategy to network dynamics as the packet travels from the source to the destination. Extensive simulations based on a large dataset of real vehicular traces collected from around 2,600 taxis in Shanghai have been conducted. Comparison study shows that RWR produces higher delivery ratio than TSF and GPCR, representative routing algorithms of RBR and ROR, respectively. It achieves low delivery delay at the same time.

Wireless sensor networks have been widely applied to various application domains such as environmental monitoring and surveillance. Because of reliance on the open transmission media, a sensor network may suffer from radio jamming attacks, which is easy to launch but difficult to defend. Attacked by jamming signals, a sensor network may experience corrupted packets and low network throughput. A number of defense techniques have been proposed. However, each defense technique is suitable for only a limited range of network and jamming conditions. This paper proposes an adaptive approach to anti-jamming for sensor networks by combining the strength of state-of-the-art anti-jamming techniques, which enables each node to adaptively select the optimal anti-jamming technique for different jamming conditions. The great challenge is that the sensor network undergoes varying jamming conditions over time. We address this challenge by formulating the anti-jamming problem of the sensor network as a Markov decision process and propose an efficient algorithm for computing the best anti-jamming strategy. By comprehensive simulation experiments, we demonstrate that a sensor network using the derived anti-jamming strategy can well defense from radio jamming attacks and in the meanwhile retain high energy-efficiency.

We have developed an NS-2 simulation framework incorporating a large dataset of real GPS taxi traces collected from around 4000 taxis in Shanghai, China. Extensive simulations have been performed to explore the achievable performance of real vehicular networks. Simulation results show that a real vehicular network has surprisingly poor data delivery performance under wide network configurations, which strongly suggests that the challenging characteristics of vehicular networks, such as unique node mobility, constraints of road topology, need further exploration.

Exploiting the increasing ubiquitous deployment of sensor networks, the paper presents a system called WiBee that utilizes ZigBee sensors to build real-time WiFi radio maps. The design of WiBee is motivated by the observation that a ZigBee radio can sense WiFi frame transmissions although it cannot decode WiFi frames. A sensor passively listens on the wireless channel and estimates the RSS of a WiFi AP at its location. The design of WiBee faces three unique challenges. First, multiple APs may transmit frames concurrently and frame collisions may happen. Second, because of severe resource constraints, a sensor cannot sample the channel at arbitrarily high frequency and hence some frame transmissions may not be sampled. Third, sensor nodes are usually not time synchronized and the on-board clock is inaccurate. To address these challenges, we propose a novel gateway-assisted approach to estimating WiFi RSS values at ZigBee sensors. A light-weight algorithm is designed for identifying the RSS values corresponding to a given AP. It searches the sequence of ZigBee RSS samples for an AP signature sequence. An optimization technique is proposed to address issues of clock drift and time asynchronization. Our extensive experiments on a testbed show that WiBee can achieve low estimation error, short delay and small computation overhead.

We develop a system called POVA for traffic light sensing in large-scale urban areas, where traffic light sensing aims to detect the status of traffic lights which is valuable for many applications such as traffic management, traffic light optimization and real-time vehicle navigation. The system employs pervasive probe vehicles that just report real-time states of position and speed from time to time. The important observation motivating the design of POVA is that a traffic light has a considerable impact on mobility of vehicles on the road attached to the traffic light. However, the system design faces three unique challenges, i.e., discrete probe reports, uneven distribution of reports over time and space, and variable interval of light states. To tackle the challenges, we develop a new technique that makes the best use of limited probe reports as well as statistical features of light states. It first estimates the state of a traffic light at the time instant of a report by applying maximum a posterior (MAP) estimation. Then, we formulate the state estimation of a light at any time into a joint optimization problem that is solved by an efficient heuristic algorithm. Trace-driven experimentation and field study show that the estimation error rate is as low as 21% even when the number of available reports is merely one per minute.

Deploying roadside access points (APs) or an infrastructure can improve data delivery. Our empirical results from real trace driven simulations show that deploying APs produces up to 5× performance gain in delivery ratio and reduces delivery delay by as much as 35% with simple routing. However, we also find that buffer resources at the APs become a critical factor and poor buffer allocation leads to marginal performance gain for inter-vehicle routing. Motivated by this important observation, we investigate the optimal infrastructure-assisted routing for inter-vehicle data delivery. It remains a challenging issue for two major reasons. First, the addition of APs dramatically changes delivery opportunities between vehicles, which has not been well understood by existing work. Second, packet forwarding and buffer allocation are inter-dependent and should be addressed together. To tackle the challenges, we first characterize packet delivery probability as a function of predicted vehicle trajectories and AP locations. Then, we formulate the coexisting problem of packet forwarding and buffer allocation as an optimization problem and show that it is a knapsack problem. We design a global algorithm to solve this optimization problem. For more realistic settings, we propose a distributed algorithm for packet forwarding and buffer allocation in which each vehicle and the APs make decisions locally. Through trace-driven simulations, we demonstrate that the distributed algorithm steadily outperforms other alternative approaches under a wide range of network configurations.

We address the problem of inferring road maps from large-scale GPS traces that have relatively low resolution and sampling frequency. Unlike past published work that requires high-resolution traces with dense sampling, we focus on situations with coarse granularity data, such as that obtained from thousands of taxis in Shanghai, which transmit their location as seldom as once per minute. Such data sources can be made available inexpensively as byproducts of existing processes, rather than having to drive every road with high-quality GPS instrumentation just for map building - and having to re-drive roads for periodic updates. Although the challenges in using opportunistic probe data are significant, successful mining algorithms could potentially enable the creation of continuously updated maps at very low cost.

This paper studies mobile barrier coverage (MBC) surrounding dynamic objects. In the real world, several dynamic objects can benefit from MBC. For example, marching troop can detect any adversary intrusion without blind spot by MBC. However, conventional works only focused on barrier coverage for static objects, which fail when the objects start to move. Issues to address these dynamic-object scenarios, we propose the problem of mobile barrier coverage for dynamic objects. The most challenge is how to effectively maintain MBC when the motion of objects are unpredictable. We propose a fully distributed algorithm for mobile sensor nodes to cooperatively move and maintain the high-quality barrier coverage. The extensive simulations based on large-scale trace data demonstrate the efficiency and efficacy of the proposed algorithm.

Most existing connectivity-based localization algorithms require high node density which is unavailable in many large-scale sparse mobile networks. By analyzing large datasets of real user traces from Dartmouth and MIT, we observe that user mobility exhibits high spatiotemporal regularity and, more importantly, that user mobility is strongly correlated with the user's social encounters (including so called Familiar Strangers). Motivated by these important observations, we propose a distributed localization scheme called SOMA that is particularly suitable for sparse mobile networks. To exploit the correlation between mobility and social encounters, we formulate the localization process as an optimization problem with the objective of maximizing the probability of visiting a sequence of locations when the user witnesses the given social encounters at different time. Employing the Hidden Markov Model (HMM), we design an efficient algorithm based on dynamic programming for solving the optimization problem. SOMA is fully distributed, in which each user only makes use of the connectivity information with other users. Experimental results based on large-scale real traces demonstrate that SOMA achieves much smaller localization error than many state-of-the-art localization schemes, but requires minimal running time.

Retrieving data from mobile source vehicles is a crucial routine operation for a wide spectrum of applications of vehicular networks, such as road surface monitoring and sharing. The key to improving the data retrieval performance is to increase the data availability such that a retrieving node can easily acquire its desired data from the vehicles that it contacts. Network coding has widely been exploited as an effective technique for defusing information over a network. In this paper we explore the exploitation of network coding for improving data availability in vehicular networks. By random linear codes, simple replication is avoided, and instead a node forwards a coded block which is a random combination of all data received by the node. We implement a network coding based approach for improving data availability in vehicular networks. To understand the performance of this approach, we have conducted empirical study with extensive simulations based on real vehicular GPS traces from around 2,000 taxis in Shanghai, China. We make the important observation that in spite of significant improvement up to 300% in data availability, there is a serious issue with linear correlation among the received codes, which degrades the performance of data retrieval success rate. By analyzing the real vehicular traces, we reveal that there is strong community structure with a real vehicular network and then explain that such community structure may contribute to the issue of linear dependence. Then, we point out the opportunities for improving the network coding based approach by developing community aware codes distribution techniques.

Location awareness plays an indispensable role in a wide variety of application domains such as environment monitoring, and vehicle tracking. In this paper we focus on the localization of mobile users in sparse mobile networks which exist in many practical scenarios where users are distributed over a vast area. The unique characteristics of sparse mobile networks present several challenges for accurate localization, such as constant movement and little information from anchors. By analyzing five large datasets of real users traces with entropy analysis from five sites, we make an important observation that there is strong patterns with user mobility. Motivated by this observation, we propose a localization approach called EMP by exploiting mobility patterns of users for localization in sparse mobile networks. EMP implements a range-free distributed algorithm, with which each user collaboratively estimates its current location by fusing two localization sources, i.e., network connectivity with other nodes and mobility patterns. With trace driven simulations, we demonstrate that EMP significantly improves the localization accuracy, comparing with other existing localization approaches.

Recommending good driving paths is valuable to taxi drivers for reducing unnecessary waste in fuel and increasing revenue. Driving only according to personal experience may lead to poor performance. With the availability of large-scale GPS traces collected from urban taxis, we have the curiosity about whether we can discover the hidden knowledge in the trace data for smart driving recommendation. This paper focuses on developing a smart recommender system based on mining large-scale GPS trace datasets from a large number of urban taxis. However, such the trace datasets are in nature complex, large-scale, and dynamic, which makes mining the datasets particularly challenging. We first extract vehicular mobility pattern from the large-scale GPS trace datasets. Then, the optimal driving process is modeled as a Markov Decision Process (MDP). Solving the MDP problem results in the optimal driving strategy that gives smart recommendation for taxi drivers. In essence, the most rewarding driving paths can be derived in the long run. We have conducted extensive trace driven simulations and conclusive results show that our recommendation algorithm can successfully find good driving paths and outperforms other alternative algorithms.

The success of a real-time sensing application with a vehicular network highly depends on the spatiotemporal coverage of sensing data that can be collected from the vehicular network. Deploying broadband wireless base stations is an effective way to collect vehicular sensing data and the deployment of base stations has a great impact on delay-constrained coverage. This paper considers the critical problem of base stations for maximizing delay-constrained coverage of an urban area achieved by the vehicular network. This is particularly challenging. We theoretically prove that the optimal deployment of base stations is NP-hard even when the future vehicular traces are assumed as a priori. In a realistic setting, however, the future vehicular traces cannot be known in advance. Therefore, the challenge is to incorporate high vehicle mobility and compute the base station deployment for maximizing the expected delay-constrained coverage. By mining a large dataset of real vehicular GPS traces, we show that there is strong regularity with vehicle mobility. With this important observation, we formulate a new objective of maximizing the expected sensing coverage. This takes random vehicle mobility into account and exploits the regularity in vehicle mobility. We develop greedy algorithms for base station deployment. The achieved sensing coverage of the proposed algorithm is guaranteed to be larger than (1-1/e) of the theoretical optimum. We have performed extensive simulations based on the real vehicular GPS trace dataset and conclusive results show that our algorithms achieve near optimal coverage of the urban area and significantly outperform alternative algorithms.

This paper considers the problem of optimal relay placement for urban monitoring in wireless vehicular networks. The placement of relays is greatly impacted by vehicle distribution and mobility, which makes it difficult to determine the optimal locations. We theoretically prove that the relay placement problem (RPP) is NP-hard even when the vehicle traces are assumed as a priori knowledge. We first propose an approximate algorithm for the RPP with given vehicle traces (D-RPP). This algorithm is proved to achieve an approximation ratio of (1-1/ e), where e is the natural logarithm base. To solve the RPP without a priori knowledge about future vehicle traces (N-RPP), we first show that there is strong regularity with vehicle mobility by entropy analysis. Then, we propose an algorithm for solving the N-RPP, which exploits regularity extracted from historical traces. Extensive simulations based on real trace datasets show that the D-RPP algorithm produces performance close to the optimum. Keywords-wireless vehicular networks, wireless relays, optimal placement, approximation algorithms.

Traffic sensing is crucial to a number of tasks such as traffic management and city road network engineering. We build a traffic sensing system with probe vehicles for metropolitan scale traffic sensing. Each probe vehicle senses its instant speed and position periodically and sensory data of probe vehicles can be aggregated for traffic sensing. However, there is a critical issue that the sensory data contain spatiotemporal vacancies with no reports. This is a result of the naturally uneven distribution of probe vehicles in both spatial and temporal dimensions since they move at their own wills. This paper proposes a new approach based on compressive sensing to large-scale traffic sensing in urban areas. We mine the extensive real trace datasets of taxies in an urban environment with principal component analysis and reveal the existence of hidden structures with sensory traffic data that underpins the compressive sensing approach. By exploiting the hidden structures, an efficient algorithm is proposed for finding the best estimate traffic condition matrix by minimizing the rank of the estimate matrix. With extensive trace-driven experiments, we demonstrate that the proposed algorithm outperforms a number of alternative algorithms. Surprisingly, we show that our algorithm can achieve an estimation error of as low as 20% even when more than 80% of sensory data are not present.

Mobile terminals with multi-radio devices have become increasingly prevalent. This makes it possible for Internet applications being supported by heterogeneous wireless networks while the terminal is on move. As the user is constantly moving, it is highly desirable that the terminal connects to the best network and retains high performance of Internet connection. Handoff can be made within the same type of network or different types of networks. A vertical handoff may interrupt the ongoing activity but may also bring higher performance. Handoff in such a heterogeneous mobile environment faces several challenges, such as user mobility randomness, handoff overhead and optimality requirement. Existing work often focuses only on the current network condition when making handoff decisions, ignoring user mobility patterns. As a result, a handoff decision good for the present may soon become poor when the user moves to another place. Importantly, the current handoff decision may influence the future performance of the user's connection. This paper proposes an optimal handoff algorithm that explicitly exploits user mobility patterns, with which we can effectively predict further locations of a user. This algorithm can produce optimal handoff decisions in the long run. Employing a comprehensive framework for preference customization, the algorithm supports user customization caring for different user preferences. We conduct extensive real trace driven simulation experiments and comparative study shows our algorithm is better than the typical algorithms.

Efficient data delivery is a great challenge in vehicular networks because of frequent network disruption, fast topological change and mobility uncertainty. The vehicular trajectory knowledge plays a key role in data delivery. Existing algorithms have largely made predictions on the trajectory with coarse-grained patterns such as spatial distribution or/and the inter-meeting time distribution, which has led to poor data delivery performance. In this paper, we mine the extensive trace datasets of vehicles in an urban environment through conditional entropy analysis, we find that there exists strong spatiotemporal regularity. By extracting mobile patterns from historical traces, we develop accurate trajectory predictions by using multiple order Markov chains. Based on an analytical model, we theoretically derive packet delivery probability with predicted trajectories. We then propose routing algorithms taking full advantage of predicted vehicle trajectories. Finally, we carry out extensive simulations based on real traces of vehicles. The results demonstrate that our proposed routing algorithms can achieve significantly higher delivery ratio at lower cost when compared with existing algorithms.

Reliable communications are essential for most applications in wireless sensor networks (WSNs). In traditional approaches, the per-hop and end-to-end (E2E) recovery schemes are widely used. These schemes, however, suffer from low E2E success rate and poor energy efficiency in large-scale real environments. Through empirical studies, in this paper we identify three major problems that hinder the efficient and reliable communications. To address these problems, we propose a novel in-middle recovery scheme and realize it by designing and implementing a proliferation routing. Proliferation routing integrates three core technologies, namely, capability-based path finder, a randomized dispersity, and reproduction. Proliferation routing offers great flexibilities for transmissions. It cannot only be applied with any Medium Access Control (MAC) protocols and routing metrics, but also obtains a desired service quality (i.e., transmission success rate, energy cost, etc.) by controlling the system parameters. To demonstrate the effectiveness of proliferation routing, we thoroughly analyze its performance. We also conduct performance evaluations through implementation experiments as well as simulations. In a specific experimental setup, proliferation routing can increase the E2E transmission success rate up to 80 percent compared with the well-known hop-based routing and flooding.

Intercontact time between moving vehicles is one of the key metrics in vehicular ad hoc networks (VANETs) and central to forwarding algorithms and the end-to-end delay. Due to prohibitive costs, little work has conducted experimental study on intercontact time in urban vehicular environments. In this paper, we carry out an extensive experiment involving thousands of operational taxies in Shanghai city. Studying the taxi trace data on the frequency and duration of transfer opportunities between taxies, we observe that the tail distribution of the intercontact time, that is, the time gap separating two contacts of the same pair of taxies, exhibits an exponential decay, over a large range of timescale. This observation is in sharp contrast to recent empirical data studies based on human mobility, in which the distribution of the intercontact time obeys a power law. By analyzing a simplified mobility model that captures the effect of hot areas in the city, we rigorously prove that common traffic influxes, where large volume of traffic converges, play a major role in generating the exponential tail of the intercontact time. Our results thus provide fundamental guidelines on design of new vehicular mobility models in urban scenarios, new data forwarding protocols and their performance analysis.

Jamming is a serious security threat to a wireless sensor network since the network relies on open wireless radio channel. A jamming attacker launches jamming attacks easily by transmitting high-power signals and all legitimate sensor nodes interfered by jamming signals suffer corrupted packet transmissions. More importantly, the jammer is typically strategic and chooses its jamming strategy in response to the possible defense strategy taken by the sensor network. In this paper we model the interaction between the sensor network and the attacker as a non-cooperative non-zero-sum static game. In such a game, the sensor network has a set of strategies of controlling its probability of accessing the wireless channel and the attacker manipulates its jamming by controlling its jamming probability after sensing a transmission activity. We propose an efficient algorithm for computing the optimal strategies for jamming attack and network defense. A critical issue is that there may exist a number of possible strategy profiles of Nash equilibria. To address this issue, we further propose to choose realistic Nash equilibria by applying Pareto-dominance and risk dominance. Our numerical results demonstrate that the strategies chosen by Pareto-dominance and risk dominance achieve the expected performance. Our results presented in the paper provides valuable defense guidance for wireless sensor networks against jamming attacks.

Inter-contact time between moving vehicles is one of the key metrics in vehicular ad hoc networks (VANETs) and central to forwarding algorithms and the end-to-end delay. Due to prohibitive costs, little work has conducted experimental study on inter-contact time in urban vehicular environments. In this paper, we carry out an extensive experiment involving thousands of operational taxies in Shanghai city. Studying the taxi trace data on the frequency and duration of transfer opportunities between taxies, we observe that the tail distribution of the inter-contact time, that is the time gap separating two contacts of the same pair of taxies, exhibits a light tail such as one of an exponential distribution, over a large range of timescale. This observation is in sharp contrast to recent empirical data studies based on human mobility, in which the distribution of the inter-contact time obeys a power law. By performing a least squares fit, we establish an exponential model that can accurately depict the tail behavior of the inter-contact time in VANETs. Our results thus provide fundamental guidelines on design of new vehicular mobility models in urban scenarios, new data forwarding protocols and their performance analysis.

In this paper, we present our study of extracting a mobility model for vehicular ad hoc networks (VANETs) from a large amount of real taxi GPS trace data. In order to capture characteristics of the urban vehicle network from microscopic to macroscopic aspects, we design three parameters and extract their values from the GPS trace data. Using this mobility model, we can generate the synthetic trace to simulate the movement of taxis in the urban area of a metropolis. The validation is carried through extensive comparisons between the synthetic trace and the real trace. Validation results show that our mobility model has a good approximation to the real scenario.

Intelligent transportation systems have become increasingly important for the public transportation in Shanghai. In response, Shanghai Grid (SG) aims to provide abundant intelligent transportation services to improve the traffic condition. A challenging service in SG is to estimate the real-time traffic condition on surface streets. In this paper, we present an innovative approach SEER to tackle this problem. In SEER, we deploy a cost-effective system of taxi traffic sensors. These taxi sensory data are found to be noisy and very lossy in both time and space. By intensively mining the spatio-temporal correlations along with the evolution of traffic condition, SEER provides wealthy knowledge to setup statistical models for inferring traffic condition when they cannot be directly calculated. As an example, we demonstrate utilizing multichannel singular spectrum analysis (MSSA) to iteratively produce estimates of traffic condition in a metropolitan scale. The optimal window width of MSSA is determined with the basic periodicity found in traffic condition. Moreover, we minimize the number of channels required by MSSA to estimate traffic condition at any location. Given a desired estimation granularity, we optimize the MSSA parameters to minimize the estimation error.

Rapid advancement in wireless communication has made it possible to develop vehicular ad hoc networks, in which a vehicle can communicate with other vehicles via a wireless, multi-hope fashion. A variety of appealing real-world applications can be enabled by VANETs, such as driving safety and urban monitoring. Many location based routing algorithms have been proposed for data delivery in VANETs. Most of them assume that accurate location information is available when needed. In practice, however, such assumption is unrealistic. It incurs considerable cost to retrieve location information. In addition, a vehicle is on the fast move over time, and a location previously obtained may become invalid after certain time. This paper proposes a routing algorithm that is based on a practical location information model. To solve the problem of location inaccuracy and vehicle mobility, we devise a location predictor which estimates the possible location of a vehicle by using history information. Based on the greedy forwarding strategy, the proposed routing differentiates packets in terms of closeness to destination and jump distance. We evaluate the performance of the proposed algorithms with a large real trace of taxi motion in Shanghai. Trace-driven simulation results demonstrate that data delivery performance is improved.

Recently, System-on-Chip (SoC) technology has been adopted to design smaller, lower-power and cheaper tamper-resistant sensor nodes. In these nodes, we find that there exists a lifetime-secure memory fraction which stores the anterior part of the application executable binary code, namely "fingerprint". We propose a key management protocol based on this secure finger- print-FKM. In this protocol, any pair of nodes can build a secret key by combining two raw key elements randomly selected by both nodes from their fingerprints respectively. To further strengthen the security, we also present two multi-dimension grid key reinforcement schemes. To the best of our knowledge, this paper is the first attempt at the use of application executable binary code itself to develop a key management protocol A thorough analysis shows that FKM supports higher security and superior operational properties while consuming less memory resource compared to the existing key establishment schemes.

Body sensor networks (BSNs) for healthcare have more stringent security and context adaptation requirements than required in large-scale sensor networks for environment monitoring. Policy-based management enables flexible adaptive behavior by supporting dynamic loading, enabling and disabling of policies without shutting down nodes. This overcomes many of the limitations of sensor operating systems, such as TinyOS, which do not support dynamic modification of code. Alternative schemes for adaptation, such as network programming, have a high communication cost and suffer from operational interruption. In addition, a policy-driven approach enables fine-grained access control through specifying authorization policies. This paper presents the design, implementation and evaluation of an efficient policy system called Finger which enables policy interpretation and enforcement on distributed sensors to support sensor level adaptation and fine-grained access control. It features support for dynamic management of policies, minimization of resources usage, high responsiveness and node autonomy. The policy system is integrated as a TinyOS component, exposing simple, well-defined interfaces which can easily be used by application developers. The system performance in terms of processing latency and resource usage is evaluated.

Intelligent transportation systems have become increasingly important for the public transportation in Shanghai. In response, ShanghaiGrid (SG) project aims to provide abundant intelligent transportation services to improve the traffic condition. A challenging service in SG is to accurately locate the positions of moving vehicles in real time. In this paper, we present an innovative scheme, hierarchical exponential region organization (HERO), to tackle this problem. In SG, the location information of individual vehicles is actively logged in local nodes which are distributed throughout the city. For each vehicle, HERO dynamically maintains an advantageous hierarchy on the overlay network of local nodes to conservatively update the location information only in nearby nodes. By bounding the maximum number of hops the query is routed, HERO guarantees to meet the real-time constraint associated with each vehicle. A small-scale prototype system implementation and extensive simulations based on the real road network and trace data of vehicle movements from Shanghai demonstrate the efficacy of HERO.

In a realistic sensor network, in particular with a non-uniform deployment, sensor nodes inevitably have varying workloads. This causes a natural problem that some sensor nodes are subject to excessive power consumption and thus become hot. These hot nodes deplete much earlier resulting in system performance degradation. This paper proposes a systematic approach to design a hotness-aware sensor network where each node is able to obtain its own hotness information. Based on these vital information, the system is able to provide various technologies to protect the critical set of hot nodes. More specifically, we design a centralized optimal algorithm to derive the precise hotness of each node. In addition, we develop a completely distributed algorithm to estimate hotness with high accuracy. An effective hotness-aware MAC is developed to offer medium access priority to the nodes with higher hotness to protect and prolong their lifetimes. It is demonstrated, through both theoretical analysis and comprehensive simulations, that our approach is valuable to improving system performance of practical sensor networks.

Body sensor networks (BSNs) have become a promising technology for healthcare, in which biosensors continuously monitor physiological parameters of a user. Distinct from conventional sensor networks for environmental monitoring, such networks need to be adaptive and can therefore be easily managed. In addition, security becomes a necessity. To this end, we design a policy system that implements policy-driven management on the sensor level. Biosensor adaptability is realized through support of dynamic loading, enabling and disabling of policies without shutting down nodes. In addition, fine-grained access control becomes possible through authorization policies on biosensors. Design and implementation details of the policy system are presented. Experimental results demonstrate that the policy system is viable and can accelerate application development of biosensor networks for healthcare.

It has been of significant importance to provision network-wide guaranteed QoS for a wide range of event detection applications in wireless sensor networks (WSNs). This paper investigates solutions to this QoS provision problem. For event detection applications, there are two key performance metrics, i.e., detection probability and detection latency. This paper focuses on dual-objective QoS provision, taking both metrics into account. This is very challenging due to the stringent resource constraint of sensor nodes and unpredictable randomness of physical events. We propose a novel probabilistic approach to provisioning due-objective QoS. Following a unified framework, we design a distributed algorithm that determines the active probability of every sensor node. The probability is minimized while being sufficient for QoS provision. Our approach is flexible and supports different requirements that may be posed by different applications. Theoretical analysis and comprehensive simulation experiments have been conducted, which jointly demonstrate that our approach is able to deliver guaranteed QoS for distributed event detection while prolonging the system lifetime significantly compared with other alternative schemes.

Intelligent transportation systems have become increasingly important for the public transportation in Shanghai. In response, ShanghaiGrid (SG) aims to provide abundant intelligent transportation services to improve the traffic condition. A challenging service in SG is to accurately locate the positions of moving vehicles in real time. In this paper we present an innovative scheme HERO to tackle this problem. In SG, the location information of individual vehicles is actively logged in local nodes which are distributed throughout the city. For each vehicle, HERO dynamically maintains an advantageous hierarchy on the overlay network of local nodes to conservatively update the location information only in nearby nodes. By bounding the maximum number of hops the query is routed, HERO guarantees to meet the real-time constraint associated with each vehicle. Extensive simulations based on the real road network and trace data of vehicle movements from Shanghai demonstrate the efficacy of HERO.

Body sensor networks (BSNs) for healthcare put more emphasis on security and adaptation to changes in context and application requirement. Policy-based management enables flexible adaptive behaviour by supporting dynamic loading, enabling and disabling of policies without shutting down nodes. This overcomes many of the limitations of sensor operating systems, such as TinyOS, which do not support dynamic modification of code. Alternative schemes for network adaptation, such as networking programming, suffer from high communication cost and operational interruption. In addition, the policy-driven approach enables fine-grained access control through specifying authorization policies. This paper presents an efficient policy system called finger which enables policy interpretation and enforcement on distributed sensors to support sensor level adaptation and fine-grained access control. It features support for dynamic management of policies, minimization of resources usage, high responsiveness and node autonomy. The policy system is integrated as a TinyOS component, exposing simple, well-defined interfaces which can easily be used by application developers. The system performance in terms of processing latency and resource usage is evaluated.

A sustainable market-like computational grid has two characteristics: it must allow resource providers and resource consumers to make autonomous scheduling decisions, and both parties of providers and consumers must have sufficient incentives to stay and play in the market. In this paper, we formulate this intuition of optimizing incentives for both parties as a dual-objective scheduling problem. The two objectives identified are to maximize the success rate of job execution and to minimize fairness deviation among resources. The challenge is to develop a grid scheduling scheme that enables individual participants to make autonomous decisions while producing a desirable emergent property in the grid system; that is, the two systemwide objectives are achieved simultaneously. We present an incentive-based scheduling scheme, which utilizes a peer-to-peer decentralized scheduling framework, a set of local heuristic algorithms, and three market instruments of job announcement, price, and competition degree. The performance of this scheme is evaluated via extensive simulation using synthetic and real workloads. The results show that our approach outperforms other scheduling schemes in optimizing incentives for both consumers and providers, leading to highly successful job execution and fair profit allocation.

Surveillance is an important class of applications for wireless senor networks (WSNs), whose central task is to detect events of interest. Existing approaches seriously suffer from blind spots and low energy efficiency. In this paper, we propose a fully distributed algorithm GAP for energy-efficient event detection for surveillance applications. The unique features of GAP are threefold. First, it provides guaranteed detectability for any event occurring in the sensing field. Second, it exposes a convenient interface of the user to specify the desired detectability. Finally, it significantly reduces the duty cycle of each sensor and therefore prolongs system lifetime remarkably. Without relying on costly time synchronization, GAP is a lightweight distributed protocol and is truly scalable to network scale and sensor density. Comprehensive experiments are conducted, which demonstrate the efficacy of the GAP algorithm.

Intelligent transportation systems have become increasingly important for the public transportation in Shanghai. In response, ShanghaiGrid aims to provide abundant intelligent transportation services to improve the traffic condition. A fundamental service in ShanghaiGrid is to locate the nearest desirable vehicles for users. In this paper we propose an innovative protocol ANTS to locate a desirable vehicle close to the querying user. The protocol finely mimics the efficient searching strategy adopted by a lost desert ant in searching for its nest. Taking query locality into account, ANTS can retrieve the nearest vehicles satisfying the query with high probability but incurs small query latency and modest network traffic. ANTS is a fully distributed and robust protocol and therefore has good scalability. Extensive simulations based on the real road network and the trace data of vehicle movements in Shanghai demonstrate the efficacy of ANTS.

In this paper we address the problem of energy-efficient event detection in wireless sensor networks (WSNs). Duty cycling is a fundamental approach to conserving energy in WSNs. However, it brings challenges to event detection in the sense that an event may be undetected or undergo a certain delay before it is detected, in particular when sensors are low duty-cycled. We investigate the fundamental relationship between event detection and energy efficiency. Based on a simplified network model, we quantify event detection performance by deriving the closed forms of detection delay and detectability. We also characterize the intrinsic tradeoff that exists between detection performance and system lifetime, which helps flexible design decisions for WSNs. In addition, we propose a completely localized algorithm, CAS, to cooperatively determine sensor wakeups. Without relying on location information, CAS is easy to implement and scalable to network density. Theoretical bounds of event detection are also studied to facilitate the comparative study. Comprehensive experiments are conducted and results demonstrate that CAS significantly improves detection performance.

Reliable transmission service is in dire need for many applications in wireless sensor networks (WSNs). Most existing routing protocols however, seriously suffer from low end-to-end success rates in real deployments. Through extensive experiments on a test-bed of Mica2 nodes, we identify three key problems that hinder the reliable packet delivery. In order to address these problems and therefore to provide a reliability-oriented transmission service, we propose a novel in-middle recovery mechanism that fills the gap between the traditional per-hop recovery and end-to-end recovery mechanisms. To realize such an idea, we design and implement proliferation routing that leverages randomized dispersity and reproduction. The distinctive feature of proliferation routing is its great flexibility. Not only can it be applied with any medium access control (MAC) protocol and routing metric, but also a desired service quality can be effectively derived by controlling the system parameters. Such a feature is revealed by theoretical analysis and confirmed by implementation and simulation experiments. In a specific experiment setup, proliferation routing can increase the end-to-end transmission success rate up to 70% compared with the well-known hop-based routing and flooding.

The persistent nature of physical events makes it possible to detect events using lowly duty-cycled sensors. However, it raises a serious over-detection problem when every sensor blindly wakes up in each cycle, in particular, if sensor density is high. In this paper, we propose an innovative probabilistic wakeup protocol for energy-efficient event detection in wireless sensor networks. The central idea is to reduce the duty cycle of every sensor via probabilistic wakeup, exploiting the dense deployment of sensor networks. A distinctive feature is that the system ensures that the detection delay of any event occurring anywhere in the sensing field is statistically bounded. In addition, the algorithm exposes a convenient interface for users to define the requirement on detection latency, thereby tuning the intrinsic tradeoff between energy efficiency and event detection performance. The algorithm is a lightweight and completely localized protocol, and introduces minimal communication overhead. Extensive experiments have been conducted and results demonstrate that this algorithm significantly prolongs the system lifetime.

In order to establish trust relationship between service requesters and providers in an open decentralized environment, we propose a novel trust negotiation framework, TOWER, which integrates distributed trust chain construction of trust management and aims to enhance the grid security infrastructure. Our approach leverages attribute-based credentials to support flexible delegation, and dynamically constructs trust chains. A novel TRust chAin based Negotiation Strategy (TRANS) is proposed to establish trust relationship on the fly by gradually disclosing credentials according to various access control policies. Our approach has been successfully implemented as useful components and fundamental security services in the CROWN Grid, and techniques such as trust tickets and policy caching that can greatly increase service efficiency are used. Finally, we evaluate our approach by comprehensive experiments and the results show that it is feasible.

Abstract With the rapid development of high‐speed wide‐area networks and powerful yet low‐cost computational resources, Grid computing has emerged as an attractive computing paradigm. In typical Grid environments, there are two distinct parties, resource consumers and resource providers. Enabling an effective interaction between the two parties (i.e. scheduling jobs of consumers across the resources of providers) is particularly challenging due to the distributed ownership of Grid resources. In this paper, we propose an incentive‐based peer‐to‐peer (P2P) scheduling for Grid computing, with the goal of building a practical and robust computational economy. The goal is realized by building a computational market supporting fair and healthy competition among consumers and providers. Each participant in the market competes actively and behaves independently for its own benefit. A market is said to be healthy if every player in the market gets sufficient incentive for joining the market. To build the healthy computational market, we propose the P2P scheduling infrastructure, which takes the advantages of P2P networks to efficiently support the scheduling. The proposed incentive‐based algorithms are designed for consumers and providers, respectively, to ensure every participant gets sufficient incentive. Simulation results show that our approach is successful in building a healthy and scalable computational economy. Copyright © 2006 John Wiley & Sons, Ltd.

Wireless sensor networks have been widely deployed for monitoring environments of interest. The diffusion stimulus (DS) is a very common and important one in real environments, which is characterized by originating at a source spot and continuously spreading outward. DS-based applications are usually time-sensitive and require high accuracy. It is very challenging, however, for sensor networks to monitor a DS when those sensors could usually monitor one point (the sensing range is zero) only. No existing algorithm is effective and energy-efficient for DS monitoring. In this paper, we propose stimulus-based adaptive sleeping (SAS), to tackle this unique challenge. With SAS, each node independently determines its sleep duration based on its local observations on the stimulus. SAS enables sensors near the stimulus boundary to stay alert to accurately capture the stimulus arrival, and those far away from the stimulus to safely sleep longer for energy efficiency.

Broadcasting is an effective technique to reduce network traffic, and is inherently supported by wireless networks. It thus has been advocated by numerous on-demand data access protocols. In a wireless cellular network, broadcasting can be implemented within a single cell. However, the data owned by different cells could be different. If a client requests a data item available only in a remote cell, an inter-cell data transmission over some wired link is needed, which introduces additional access delay. In this paper, we demonstrate that such delay can be minimized through the use of remote caching. Specifically, we propose a novel cooperative caching scheme, in which each cell dynamically allocates the cache spaces for data from different remote cells. It makes replacement decisions according to several important factors: data item access frequency, cell traffic, and retrieval delay. Simulation results show that the proposed scheme can significantly reduce the response time over the non-cooperative caching scheme under various system configurations.