The dynamic nature of microservice architectures necessitates robust few-shot anomaly detection (AD) systems to prevent cascading failures. However, current multimodal approaches remain inadequate for cold-start scenarios due to their dependence on extensive training data. The fundamental challenge in few-shot AD lies in two critical aspects: (1) effective feature extraction from intra-modalities, and (2) the alignment of heterogeneous multimodal representations, particularly the distribution discrepancy between discrete token embeddings from logs and continuously evolving representations from traces and metrics. To overcome these challenges, we present FuseGuard, an LLM-enhanced framework that pioneers quality-aware multimodal fusion for few-shot AD. First, our intra-modal feature extraction employs a Dynamic Sparse Correlation Attention mechanism for metrics, Spatio-temporal Encoding for traces, and LLM-enhanced semantic-frequency encoding for logs, enabling adaptive representation of time-evolving patterns. Second, we introduce hierarchical cross-modal alignment via token projection, layer-wise distillation, and consistency learning to preserve modality-specific features while enabling effective knowledge transfer. Finally, a quality-aware fusion mechanism dynamically weights modalities based on uncertainty estimation. Evaluated on three open-source platforms (MSDS, GAIA, TrainTicket) and a production system, FuseGuard's few-shot capability outperforms SOTA by 19.69%-77.07% F1-score across four datasets.

Root cause analysis (RCA) is crucial for the stability and reliability of large-scale microservice architectures. Existing multi-source RCA methods primarily rely on logs, traces, and metrics data to detect anomalies and identify abnormal services and root causes. And most multi-source methods focus only on service-level operations and inter-service dependencies, neglecting transactions and their dynamic changes. Furthermore, these approaches typically address only a subset of the RCA tasks, such as anomaly detection, root cause service localization, or root cause type determination. To address these limitations, we propose MicroTR, a transaction reproduction fault diagnosis framework for multi-source RCA in microservice environments. MicroTR deeply analyzes transaction execution logic and service states, utilizing multi-source data to reproduce the dynamic changes of transaction execution states in knowledge graph. This approach enables efficient and synchronized anomaly detection, root cause service localization, and root cause type determination. Experimental evaluations on two widely-adopted open-source microservice platforms demonstrate that MicroTR outperforms state-of-the-art multi-source methods, achieving an average F1 of 97.3% for anomaly detection, an average Hit@l of 90.8% for root cause service localization, and an average Hit@1 of 89.2% for root cause type determination. These results highlight the effectiveness of reproducing transaction execution states for RCA.

Graph neural networks (GNNs) have proven to be powerful tools for learning from graph-structured data and have achieved great success in many applications. As the sizes of real-world graphs continue to grow, traditional GNN training methods face significant scalability challenges. Recently, disks have gained attention as a cost-effective solution to store large-scale graphs, and several disk-based GNN systems have been proposed to train large-scale graphs on a single machine. However, these systems either overlook the unique data characteristics of GNN workloads when designing cache plans or fail to fully exploit the multilevel hierarchy of storage and computation in system execution, thus resulting in disk I/O bottleneck and resource under-utilization. To address these issues, we present CaliEX, an advanced disk-based GNN system that employs joint optimizations of caching and execution within and across different training stages. CaliEX first designs tailored cache plans and execution policy for both graph topology and features to accelerate neighborhood sampling and feature gathering. Since these two training stages work on different types of data, CaliEX further auto-tunes the cache allocation and pipelines the execution across different stages to improve resource utilization and overall training throughput. Evaluations on multiple GNN models and various large-scale datasets show that CaliEX achieves 3.28 × speedup on average compared to existing disk-based GNN training systems.

As context windows expands, Large Language Models (LLMs) are being more capable of handling long-context tasks. However, long-context inference is hindered by high latency and memory usage due to the linearly growing Key-Value (KV) cache. Prior work has shown that a dynamic subset of the KV cache dominates attention outcomes and selectively loads these subsets instead of the full cache. These methods partition the KV cache into segments (block-wise and token-wise) and identify critical ones for recall. However, for block-wise ones, their recall accuracy is often compromised by semantic inconsistencies among consecutive tokens, and for token-wise ones, they suffer from inefficiency in memory management and offloading. To these ends, we propose Dispenser, a hierarchical KV cache management algorithm inspired by multi-level page tables. Dispenser organizes the KV cache based on token semantic similarity and partitions it into pages and blocks, which enables straightforward integration into modern serving engines such as vLLM. It employs a two-level lookup mechanism to identify and load the most relevant blocks for the current query. Experimental results demonstrate that Dispenser achieves up to a$5.75 \times$speedup in self-attention, reducing inference latency by$2.1 \times$on tasks with long dependencies with negligible accuracy loss.

Microservices architecture has become increasingly popular in modern software systems, yet its complexity also poses challenges for failure diagnosis. Existing literature has deficiencies in multimodal data mining, mainly in two aspects: first, the mining of multimodal data is insufficient, failing to fully exploit the rich information contained in different types of data; second, the analysis of spatiotemporal features of multimodal data is not thorough, failing to fully explore the potential associations of data in the temporal and spatial dimensions. To address these issues, this paper proposes a new method for anomaly detection in microservices. We transform three types of modal data into the wavelet domain and achieve fusion among modalities based on an attention mechanism, fully utilizing the inherent characteristics of multimodal data in the frequency and temporal domains. This fusion process can extract new information that does not exist in the original modalities, thereby enhancing the model's ability to detect anomalies. In addition, we propose a new diffusion probabilistic model (DDPM) based on spatiotemporal graphs, which combines spatiotemporal learning capabilities with the uncertainty measurement of DDPM to generate future samples in a non-autoregressive manner, achieving multi-horizon prediction. Experimental results show that our method significantly improves anomaly detection performance on three public datasets and a real-world production system, demonstrating its effectiveness in microservices anomaly detection.

With the rise of e-commerce and short videos, online recommender systems that can capture users' interests and update new items in real-time play an increasingly important role. In both online and offline recommendation systems, the cold-start problem caused by interaction sparsity has been impacting the effectiveness of recommendations for cold-start items. Many cold-start scheme based on fine-tuning or knowledge transferring shows excellent performance on offline recommendation. Yet, these schemes are infeasible for online recommendation on streaming data pipelines due to different training method, computational overhead and time constraints. Inspired by the above questions, we propose a model-agnostic recommendation algorithm called Popularity-Aware Meta-learning (PAM), to address the item cold-start problem under streaming data settings. PAM divides the incoming data into different meta-learning tasks by predefined item popularity thresholds. The model can distinguish and reweight behavior-related and content-related features in each task based on their different roles in different popularity levels, thus adapting to recommendations for cold-start samples. These task-fixing design significantly reduces additional computation and storage costs compared to offline methods. Furthermore, PAM also introduced data augmentation and an additional self-supervised loss specifically designed for low-popularity tasks, leveraging insights from high-popularity samples. This approach effectively mitigates the issue of inadequate supervision due to the scarcity of cold-start samples. Experimental results across multiple public datasets demonstrate the superiority of our approach over other baseline methods in addressing cold-start challenges in online streaming data scenarios.

E-commerce recommendation platforms often operate across multiple domains, giving rise to Multi-Domain Recommendation (MDR) methods. These methods leverage auxiliary information from other domains to capture comprehensive user preferences and enhance recommendation accuracy. However, cross-domain knowledge transfer often causes domains to capture similar preferences. Additionally, most MDR models optimize for next-item prediction, which promotes greedy strategies focused on immediate gains within individual domains while neglecting the platform-wide profit. These two factors result in vicious competition, as our empirical analysis reveals: Domains recommend overlapping item lists, competing for the same pool of user attention and platform traffic, reducing the overall orders. To address this, we propose the Direct Preference Optimization from Manual Rules (DPOMR) training paradigm for MDR. Inspired by Reinforcement Learning from Human Feedback (RLHF), DPOMR learns user preferences from pairwise preference data generated through manual rules rooted in business expertise. Furthermore, we design a variant of Direct Preference Optimization (DPO) to bypass expensive RL training. Extensive experiments demonstrate the advantages of DPOMR, including: (1) achieving SOTA performance in boosting overall orders(2) showing compatibility with various backbones, and (3) offering robust extendibility to integrate diverse manual rules tailored to specific business needs.

Knowledge distillation is a model compression technique in which a compact "student" network is trained to replicate the predictive behavior of a larger "teacher" network. In logit-based knowledge distillation, it has become the de facto approach to augment cross-entropy with a distillation term. Typically, this term is either a KL divergence that matches marginal probabilities or a correlation-based loss that captures intra- and inter-class relationships. In every case, it acts as an additional term to cross-entropy. This term has its own weight, which must be carefully tuned. In this paper, we adopt a choice-theoretic perspective and recast knowledge distillation under the Plackett–Luce model by interpreting teacher logits as "worth" scores. We introduce *Plackett-Luce Distillation (PLD)*, a weighted list-wise ranking loss. In PLD, the teacher model transfers knowledge of its full ranking of classes, weighting each ranked choice by its own confidence. PLD directly optimizes a single "teacher-optimal" ranking. The true label is placed first, followed by the remaining classes in descending teacher confidence. This process yields a convex and translation-invariant surrogate that subsumes weighted cross-entropy. Empirically, across CIFAR-100, ImageNet-1K, and MS-COCO, PLD achieves consistent gains across diverse architectures and distillation objectives, including divergence-based, correlation-based, and feature-based methods, in both homogeneous and heterogeneous teacher–student pairs.

In modern recommendation systems, leveraging multiple types of user-item interaction behaviors (e.g., click, add-to-cart, and purchase) presents both advantages and challenges. Recent studies organize multi-behavior data into heterogeneous bipartite graphs and used graph neural networks to learn latent representations. However, these methods struggle to model higher-order interactions and capture complex dependencies across various behaviors. In this paper, we propose a novel graph construction method that converts multi-behavior interactions into dual star-expansion hypergraphs by introducing a new type of node called hypernode. Subsequently, we develop StarRec, a hypergraph-based framework for multi-behavior recommendation. StarRec utilizes a spatial-based two-stage intra-behavior message passing strategy and a cross-behavior propagation layer to accurately and efficiently propagate information, modeling both high-order and cross-behavior relationships through the hypergraphs. This approach yields comprehensive representations that enhance recommendation performance. Experimental results on two real-world datasets demonstrate the superiority of StarRec. Our extensive experiments show that StarRec significantly outperforms state-of-the-art methods while maintaining competitive model scalability.

Existing person re-identification (ReID) methods mainly rely on images and videos to match persons across cameras, yet visual data captured by cameras are vulnerable to environmental interferences (e.g. illumination and occlusion) or personal appearance changes, leading to performance degradation under such scenes. Meanwhile, the popularization of Wi-Fi networks has allowed probe requests to be captured for mobile sensing applications such as crowd counting and trajectory estimation. However, the MAC address randomization technique adopted by modern devices breaks the association of probe requests and adversely affects the functionality of these applications. In this paper, we propose MaRPA, the first multimodal training approach that incorporates both videos and Wi-Fi probe requests to simultaneously promote tasks of probe requests association and person ReID. MaRPA first distinguishes among pairwise probe request frames through a contrastive learning model. It then matches video and probe request sequences by exploring their similarities from the position and the vision aspects. Matched videos and probe requests provide complementary information and generate more robust features for both tasks. To evaluate MaRPA, we contribute a new dataset containing synchronous videos and probe requests data for probe requests association and person ReID. Experimental results demonstrate the effectiveness of our approach. For probe requests association, it achieves > 85% discrimination accuracy and > 0.90 V-measure score; for person ReID, it achieves 75.8% mAP and 90.6% Rank-1, improving state-of-the-art video-based ReID methods by over 40%

A robotic locker system is needed where automated storage and retrieval of items are required without the need for staff presence. For example, a robot can provide 7/24 available services of medical items pick-up and return, during the COVID-19 pandemic (or under other emergencies). A robotic locker system is usually equipped with a user-friendly intuitive interface (e.g., a touchscreen); meanwhile, the robot desires a multitask agent that can observe, understand, and operate the locker’s interface to complete many tasks of storing/accessing/shipping items. In this article, we study building a multitask agent for interacting with robotic locker systems, called AgentMario. Without human intervention for a specific task, AgentMario decomposes solving a task into learning basic skills (states or user interfaces) and planning over the skills (finding the next state/interface). When the agent is solving a task, our search algorithm walks on the finite state machine graph and generates the proper plans (operation sequence) for the agent. In experiments, our method accomplishes four diverse tasks of picking-up/storing/dropping-off/shipping items. By employing image recognition and mechanical automation technologies, we implement AgentMario with a robot arm to enable contactless operation over the locker’s interface. Experimental results show that our method outperforms baselines in most tasks by a large margin.

To address the business needs of industrial recommendation systems, an increasing number of Multi-Domain Recommendation (MDR) methods are designed to improve recommendation performance on multiple domains simultaneously. Most MDR methods follow a multi-task learning paradigm, suffering from poor deployability and negative transfer. Due to the great success of large pre-trained models, the pre-train & fine-tune paradigm is attracting increasing attention. The latest methods introduce parameter-efficient fine-tuning techniques like prompt-tuning, showcasing high efficiency and effectiveness. However, these methods neglect the fundamental differences between recommendation and NLP tasks. The inadequate capacity of recommendation models restricts the effectiveness of prompts and adapters. Worse still, traditional natural domain division may group non-identically distributed samples into the same domain, violating the assumption of independent and identically distributed (i.i.d.) data. In this paper, we propose MultiLoRA, a Multi-directional Low Rank Adaptation paradigm for multi-domain recommendation. First we pre-train a universal model using all data samples. Then we conduct multiple domain divisions on the sample space. Under each division, we fine-tune the pre-trained model to obtain a set of domain-specific LoRAs. Finally, we learn a LoRA fusion module to integrate domain-specific preference patterns across multiple divisions. Experimental results on real-world datasets demonstrate notable advantages of MultiLoRA: (1) achieving SOTA performance, (2) showcasing remarkable compatibility, and (3) proving highly efficient, featuring only 2% trainable parameters compared to the backbone.

In Federated Learning, a Central Node (CN) coordinates a group of agents to collectively train a shared neural network.However, due to the inherent information asymmetry, some agents may behave as free riders and exploit the system by reaping rewards or by passively benefiting from the common model without contributing to the training process.Proof-of-Training (PoT) effectively allows the CN to verify that an agent has completed training honestly and correctly.However, this method incurs high costs, including proof generation by the agent, communication expenses, and proof verification by the CN.Conducting Proof-of-Training in each FL round is impractical due to these expenses.To enhance verification efficiency, a feasible strategy is to conduct probabilistic verification, where only a subset of agents is sampled for verification in each FL round.This paper aims to design a new incentive mechanism to motivate the agents behave honestly and potentially mitigate free riders.Our model hinges on two parameters: (i) the reward allocated to the local trainers, namely 𝑅, and (ii) a probability vector, denoted as ì 𝑝, indicating the likelihood of subjecting each agent to PoT scrutiny.We show that it is possible to characterize a set of parameters 𝑅 and ì 𝑝 that minimizes the total CN cost and makes the routine Individually Rational and Incentive Compatible, so that every agent will actively train their local model.Finally, we validate our model through extensive experiments.Our findings show that our characterization of the best reward and validation scheme is correct as they minimize the cost of the training routine without compromising the convergence speed.All our experiments are conducted on various datasets, demonstrating the wide applicability of our results.

Cross-Domain Recommendation (CDR) is a promising technique to alleviate data sparsity by transferring knowledge across domains. However, the negative transfer issue in the presence of numerous domains has received limited attention. Most existing methods transfer all information from source domains to the target domain without distinction. This introduces harmful noise and irrelevant features, resulting in suboptimal performance. Although some methods decompose user features into domain-specific and domain-shared components, they fail to consider other causes of negative transfer. Worse still, we argue that simple feature decomposition is insufficient for multi-domain scenarios. To bridge this gap, we propose TrineCDR, the TRIple-level kNowledge transferability Enhanced model for multi-target CDR. Unlike previous methods, TrineCDR captures single domain and targeted cross-domain embeddings to serve multi-domain recommendation. For the latter, we identify three fundamental causes of negative transfer, ranging from micro to macro perspectives, and correspondingly enhance knowledge transferability at three different levels: the feature level, the interaction level, and the domain level. Through these efforts, TrineCDR effectively filters out noise and irrelevant information from source domains, leading to more comprehensive and accurate representations in the target domain. We extensively evaluate the proposed model on real-world datasets, sampled from Amazon and Douban, under both dual-target and multi-target scenarios. The experimental results demonstrate the superiority of TrineCDR over state-of-the-art cross-domain recommendation methods.

The item cold-start problem is crucial for online recommender systems, as the success of the cold-start phase determines whether items can transition into popular ones. Prompt learning, a powerful technique used in natural language processing (NLP) to address zero- or few-shot problems, has been adapted for recommender systems to tackle similar challenges. However, existing methods typically rely on content-based properties or text descriptions for prompting, which we argue may be suboptimal for cold-start recommendations due to 1) semantic gaps with recommender tasks, 2) model bias caused by warm-up items contribute most of the positive feedback to the model, which is the core of the cold-start problem that hinders the recommender quality on cold-start items. We propose to leverage high-value positive feedback, termed pinnacle feedback as prompt information, to simultaneously resolve the above two problems. We experimentally prove that compared to the content description proposed in existing works, the positive feedback is more suitable to serve as prompt information by bridging the semantic gaps. Besides, we propose item-wise personalized prompt networks to encode pinnaclce feedback to relieve the model bias by the positive feedback dominance problem. Extensive experiments on four real-world datasets demonstrate the superiority of our model over state-of-the-art methods. Moreover, PROMO has been successfully deployed on a popular short-video sharing platform, a billion-user scale commercial short-video application, achieving remarkable performance gains across various commercial metrics within cold-start scenarios.

Federated learning (FL) becomes a promising machine learning paradigm. The impact of heterogeneous hardware specifications and dynamic states on the FL process has not yet been studied systematically. This paper presents the first large-scale study of this impact based on real-world data collected from 136k smartphones. We conducted extensive experiments on our proposed heterogeneity-aware FL platform namelyFLASH, to systematically explore the performance of state-of-the-art FL algorithms and key FL configurations in heterogeneity-aware and -unaware settings, finding the following. (1) Heterogeneity causes accuracy to drop by up to 9.2% and convergence time to increase by 2.32×. (2) Heterogeneity negatively impacts popular aggregation algorithms, e.g., the accuracy variance reduction brought byq-FedAvgdrops by 17.5%. (3) Heterogeneity does not worsen the accuracy loss caused by gradient-compression algorithms significantly, but it compromises the convergence time by up to 2.5×. (4) Heterogeneity hinders client-selection algorithms from selecting wanted clients, thus reducing effectiveness. e.g., the accuracy increase brought by the state-of-the-art client-selection algorithm drops by 73.9%. (5) Heterogeneity causes the optimal FL hyper-parameters to drift significantly. More specifically, the heterogeneity-unaware setting favors looser deadline and higher reporting fraction to achieve better training performance. (6) Heterogeneity results in non-trivial failed clients (more than 10%) and leads to participation bias (the top 30% of clients contribute 86% of computations). Our FLASH platform and data have been publicly open sourced.

Click-through rate (CTR) prediction, whose purpose is to predict the probability of a user clicking on an item, plays a pivotal role in recommender systems. Capturing users’ accurate preferences from their historical interactions (e.g., clicks) is an essential step for handling this task and has aroused wide concern in both academia and industry. However, most of the previous methods focus on the users with abundant clicks and ill-serve the users who rarely click or purchase items. Though the ratio of these long-tailed users may be small on popular platforms, such as Amazon and Taobao, they are the majority on the newborn e-commerce company like Lazada. To extract the interests of long-tailed users, several works attempt to integrate the side information, such as demographic features. Nevertheless, these features are usually not available and may even lead to privacy concerns. Therefore, how to utilize the noisy and limited clicks becomes the key challenge.In this paper, we propose a novel model called Hierarchical Interest Modeling (HIM). It hierarchically utilizes long-tailed users’ limited behaviors and captures their preferences from both personalized and group-wise perspectives. HIM consists of two main components, including User Behavior Pyramid (UBP) and User Behavior Clustering (UBC). The UBP module utilizes additional negative feedback to reduce the noises in positive feedback, thus obtaining reliable user personalized representations. Then, the UBC module automatically discovers latent user groups with self-supervised reconstruction loss and learns another interest representation for each user in a group-wise aspect. Extensive experiments on both public and industrial datasets verify the superiority of HIM compared with the state-of-the-art baselines. Moreover, HIM has already been deployed on Lazada recommendation scenario and gains 3.38% on CTR prediction on average on the online A/B test. Our codes are available in https://github.com/xiaojin-nj/HIM.

Audiences cangain an immersive experience watching videos from multiple angles (a.k.a. viewpoints). Free Viewpoint Video (FVV) is developed to enable users to choose their preferred viewpoints during the play of a video. However, users may experience a delay if video frames of the chosen viewpoint cannot be timely loaded, or synthesized from multiple video streams of neighboring viewpoints. To address this problem, we present Edge-FVV, an edge-assisted FVV system that employs edge caches to reduce the delay in streaming the requested FVV from the server to client users. We first analyze the capacity and delay at edge caches when answering FVV requests. Next, we propose two types of machine learning algorithms that allocate the users’ requests to appropriate edge caches. Our evaluation shows that two types of proposed algorithms outperform benchmarks by 4.2-7.4% and 4.6-6.8%, respectively, in reducing the delay for FVV requests.

Recommender systems across many Internet services have become a critical part of online businesses, as consumers would refer to them before making decisions. However, the lack of explicit ratings for items on many services makes it challenging to capture user preferences and item characteristics. Both academia and the industry have drawn attention to rating predications as a fundamental problem in recommendation systems. With the emergence of social networks, social recommender systems have been proposed to utilize the relationship between users and items to alleviate the data sparsity problem for rating predictions. However, they either concentrate on the opinion mining for each user and item, or consider the connections between users only. In this paper, we present an effective framework, Triple-hierarchical Attention Graph-based social rating prediction (TAG), to exploit the social relationships between users, the user-item interest relationships, the correlation relationships between items, and reviews for rating predictions. In order to consider opinions from reviews and these complex relationships, we first employ two triple-hierarchical attention to extract user and item features from reviews. We then design an inductive GNN, which generates effective embedding for users and items. Experiments over Yelp show that TAG outperforms state-of-the-art methods across RMSE, MAE, and NDCG metrics.

The convolutional neural network (CNN) has achieved great success in fulfilling computer vision tasks despite large computation overhead against efficient deployment. Channel pruning is usually applied to reduce the model redundancy while preserving the network structure, such that the pruned network can be easily deployed in practice. However, existing channel pruning methods require hand-crafted rules, which can result in a degraded model performance with respect to the tremendous potential pruning space given large neural networks. In this article, we introduce differentiable annealing indicator search (DAIS) that leverages the strength of neural architecture search in the channel pruning and automatically searches for the effective pruned model with given constraints on computation overhead. Specifically, DAIS relaxes the binarized channel indicators to be continuous and then jointly learns both indicators and model parameters via bi-level optimization. To bridge the non-negligible discrepancy between the continuous model and the target binarized model, DAIS proposes an annealing-based procedure to steer the indicator convergence toward binarized states. Moreover, DAIS designs various regularizations based on a priori structural knowledge to control the pruning sparsity and to improve model performance. Experimental results show that DAIS outperforms state-of-the-art pruning methods on CIFAR-10, CIFAR-100, and ImageNet.

Using widely deployed Internet of Things (IoT) sensors to perceive the environmental distribution is crucial in many IoT applications, such as intelligent healthcare and smart home. As using traditional sensors will lead to high costs and maintenance, it is important to design the next-generation IoT sensor to reduce the cost of ubiquitous deployment. For this purpose, we propose a novel IoT system based on low-cost and fully passive meta-material sensors. Specifically, the meta-material sensors can sense multiple environmental conditions such as temperature and humidity levels, and transmit back the information by signal reflection, simultaneously. With the information contained in the received signals, a wireless receiver can obtain detailed environmental distributions. However, it is not trivial to achieve high sensing accuracy in the meta-material sensor based IoT system because the structure of the meta-materials, the deployment positions of sensors, and the reconstruction function for environmental distributions need to be jointly optimized. To handle this challenge, we propose an algorithm to design the meta-material based IoT system with the help of a deep learning approach. Simulation results verify that the proposed algorithm effectively maximizes the sensing accuracy. Experimental evaluations also show that the proposed scheme can obtain humidity distribution with an accuracy of over 93%.

On-demand food delivery service has widely served people's daily demands worldwide, e.g., customers place over 40 million online orders in Meituan food delivery platform per day in Q3 of 2021. Predicting the food preparation time (FPT) of each order accurately is very significant for the courier and customer experience over the platform. However, there are two challenges, namely incomplete label and huge uncertainty in FPT data, to make the prediction of FPT in practice. In this paper, we apply probabilistic forecasting to FPT for the first time and propose a non-parametric method based on deep learning. Apart from the data with precise label of FPT, we make full use of the lower/upper bound of orders without precise label, during feature extraction and model construction. A number of categories of meaningful features are extracted based on the detailed data analysis to produce sharp probability distribution. For probabilistic forecasting, we propose S-QL and prove its relationship with S-CRPS for interval-censored data for the first time, which serves the quantile discretization of S-CRPS and optimization for the constructed neural network model. Extensive offline experiments over the large-scale real-world dataset, and online A/B test both demonstrate the effectiveness of our proposed method.

In future cellular systems, wireless localization and sensing functions will be built-in for specific applications, e.g., navigation, transportation, and healthcare, and to support flexible and seamless connectivity. Driven by this trend, the need for fine-resolution sensing solutions and centimeter-level localization accuracy arises, while the accuracy of current wireless systems is limited by the quality of the propagation environment. Recently, with the development of new materials, reconfigurable intelligent surfaces (RISs) provide an opportunity to reshape and control the electromagnetic characteristics of the environment, which can be utilized to improve the performance of wireless sensing and localization. In this tutorial, we will first review the background and motivation for utilizing wireless signals for sensing and localization. Next, we will introduce how to incorporate RIS into applications of sensing and localization, including key challenges and enabling techniques, and then, some case studies will be presented. Finally, future research directions will also be discussed.

Indoor localization has drawn much attention owing to its potential for supporting location based services. Among various indoor localization techniques, the received signal strength (RSS) based technique is widely researched. However, in conventional RSS based systems where the radio environment is unconfigurable, adjacent locations may have similar RSS values, which limits the localization precision. In this paper, we present MetaRadar, which explores reconfigurable radio reflection with a surface/plane made of metamaterial units for multi-user localization. By changing the reflectivity of metamaterial, MetaRadar modifies the radio channels at different locations, and improves localization accuracy by making RSS values at adjacent locations have significant differences. However, in MetaRadar, it is challenging to build radio maps for all the radio environments generated by metamaterial units and select suitable maps from all the possible maps to realize a high accuracy localization. To tackle this challenge, we propose a compressive construction technique which can predict all the possible radio maps, and propose a configuration optimization algorithm to select favorable metamaterial reflectivities and the corresponding radio maps. The experimental results show a significant improvement from a decimeter-level localization error in the traditional RSS-based systems to a centimeter-level one in MetaRadar.

Semantic segmentation is a process of partitioning an image into segments for recognizing regions of humans and objects, which can be widely applied in scenarios such as healthcare and safety monitoring. To avoid privacy violation, using radio frequency (RF) signals instead of photos for semantic segmentation has gained increasing attention. However, traditional human and object recognition by using RF signals is a passive signal collection and analysis process without changing the radio environment. The recognition accuracy is restricted significantly by unwanted multi-path fading, and/or the limited number of independent channels between RF transceivers. This paper introduces MetaSketch, a novel RF-sensing system that performs semantic recognition and segmentation for humans and objects by making the radio environment reconfigurable. A metamaterial-based reconfigurable intelligent surface is incorporated to diversify the information carried by RF signals. Using compressive sensing techniques, MetaSketch reconstructs a point cloud consisting of the reflection coefficients of humans and objects at different spatial points, and recognizes the semantic meaning of the points by using symmetric multilayer perceptron groups. Our evaluation results show that MetaSketch is capable of generating favorable radio environments, extracting exact point clouds, and labeling the semantic meaning of the points with an average error rate of less than 1% in an indoor space.

In the coming 6G communications, the internet of things (IoT) will be a fundamental enabler for ubiquitous environment perception, which requires the IoT sensors to consume near-zero power and have the lowest cost. For this purpose, the IoT sensors are expected to perform simultaneous sensing and transmission, so that energy and hardware costs due to signal modulation can be saved. In this paper, we propose the concept of meta-IoT, i.e., the IoT with sensors composed of specially designed meta-materials, which can achieve simultaneous sensing and transmission without supplied power. The basic idea of meta-IoT sensors is that the signal reflection on the sensors is sensitive to environmental conditions, which can be captured by a wireless receiver. In order to optimize the sensing systems with meta-IoT sensors, we establish the mathematical model of meta-IoT sensors’ sensing and transmission and then jointly optimize the sensors’ structure and the environment estimation at the receiver. We design and implement a practical meta-IoT sensing system for monitoring temperature and humidity levels. Simulation results show that the proposed technique can obtain the optimal sensor structure, and the experimental results verify that the designed meta-IoT sensing system achieves low measurement errors.

As a widely used localization and sensing technique, radars will play an important role in future wireless networks. However, the wireless channels between the radar and the targets are passively adopted by traditional radars, which limits the performance of target detection. To address this issue, we propose to use the reconfigurable intelligent surface (RIS) to improve the detection accuracy of radar systems due to its capability to customize channel conditions by adjusting its phase shifts, which is referred to as MetaRadar. In such a system, it is challenging to jointly optimize both radar waveforms and RIS phase shifts in order to improve the multi-target detection performance. To tackle this challenge, we design a waveform and phase shift optimization (WPSO) algorithm to effectively solve the multi-target detection problem, and also analyze the performance of the proposed MetaRadar scheme theoretically. Simulation results show that the detection performance of the MetaRadar scheme is significantly better than that of the traditional radar schemes.

In the coming 6G communications, the internet of things (IoT) serves as a key enabler to collect environmental information and is expected to achieve ubiquitous deployment. However, it is challenging for traditional IoT sensors to meet this expectation because of their requirements of power supplies and frequent maintenance, which are due to their power-demanding sense and transmit modules. To address this challenge, we propose a meta-IoT sensing system, where the IoT sensors are based on specially designed meta-materials. The meta-IoT sensors achieve simultaneous sensing and transmission by physical reflection and require no power supplies. In order to design a meta-IoT sensing system with optimal sensing accuracy, we jointly consider the sensing and transmission of meta-IoT sensors and propose efficient algorithms to optimize the meta-IoT structure and the sensing function at the receiver. As an example, we apply the meta-IoT system to sensing environmental temperature and humidity levels. Simulation results show that by using the proposed algorithm, the sensing accuracy can be largely increased.

Indoor wireless simultaneous localization and mapping (SLAM) is considered as a promising technique to provide positioning services in future 6G systems. However, the accuracy of traditional wireless SLAM system heavily relies on the quality of propagation paths, which is limited by the uncontrollable wireless environment. In this paper, we propose a novel SLAM system assisted by a reconfigurable intelligent surface (RIS) to address this issue. By configuring the phase shifts of the RIS, the strength of received signals can be enhanced to resist the disturbance of noise. However, the selection of phase shifts heavily influences the localization and mapping phase, which makes the design very challenging. To tackle this challenge, we formulate the RIS-assisted indoor SLAM optimization problem and design an error minimization algorithm for it. Simulations show that the RIS assisted SLAM system can decrease the positioning error by at least 31% compared with benchmark schemes.

Recently, deep learning models have been widely explored in recommender systems. Though having achieved remarkable success, the design of task-aware recommendation models usually requires manual feature engineering and architecture engineering from domain experts. To relieve those efforts, we explore the potential of neural architecture search (NAS) and introduce AMEIR for Automatic behavior Modeling, interaction Exploration and multi-layer perceptron (MLP) Investigation in the Recommender system. Specifically, AMEIR divides the complete recommendation models into three stages of behavior modeling, interaction exploration, MLP aggregation, and introduces a novel search space containing three tailored subspaces that cover most of the existing methods and thus allow for searching better models. To find the ideal architecture efficiently and effectively, AMEIR realizes the one-shot random search in recommendation progressively on the three stages and assembles the search results as the final outcome. The experiment over various scenarios reveals that AMEIR outperforms competitive baselines of elaborate manual design and leading algorithmic complex NAS methods with lower model complexity and comparable time cost, indicating efficacy, efficiency, and robustness of the proposed method.

Federated learning (FL) is an emerging, privacy-preserving machine learning paradigm, drawing tremendous attention in both academia and industry. A unique characteristic of FL is heterogeneity, which resides in the various hardware specifications and dynamic states across the participating devices. Theoretically, heterogeneity can exert a huge influence on the FL training process, e.g., causing a device unavailable for training or unable to upload its model updates. Unfortunately, these impacts have never been systematically studied and quantified in existing FL literature.

Driven by the increasingly serious air pollution problem, nowadays different systems can be used to achieve the monitoring task of air quality index (AQI) in urban areas. In this article, we design a novel unmanned aerial vehicle-aided (UAV-aided) AQI monitoring system, called AQ360, which detects the air quality level from the 360-degree aerial panoramic images taken by the onboard camera. Specifically, we first present our own AQI recognition approach based on the physical form of the haze pictures, where the AQI is jointly decided by the images captured along six directions over the target location. Then, we study the UAV placement problem of selecting UAV's flight altitude and 2-D coordinates during the monitoring process. The objective is to save the system energy consumption while maintaining the accuracy of estimating AQI distribution. For practical considerations, we implement and evaluate the proposed system in real-world scenarios. The results show that our system can provide a lower AQI recognition error compared with existing vision-based monitoring approaches, and energy consumption is also reduced when applying for large-area tasks.

Using RF signals for wireless sensing has gained increasing attention. However, due to the unwanted multi-path fading in uncontrollable radio environments, the accuracy of RF sensing is limited. Instead of passively adapting to the environment, in this paper, we consider the scenario where an intelligent metasurface is deployed for sensing the existence and locations of 3D objects. By programming its beamformer patterns, the metasurface can provide desirable propagation properties. However, achieving a high sensing accuracy is challenging, since it requires the joint optimization of the beamformer patterns and mapping of the received signals to the sensed outcome. To tackle this challenge, we formulate an optimization problem for minimizing the cross-entropy loss of the sensing outcome, and propose a deep reinforcement learning algorithm to jointly compute the optimal beamformer patterns and the mapping of the received signals. Simulation results verify the effectiveness of the proposed algorithm and show how the size of the metasurface and the target space influence the sensing accuracy.

The 360-degree video streaming system delivers a monocular panoramic video surrounding the user, and the user can change the viewing direction of mobile devices to see different parts of the video through the “viewport”. Due to the limited network bandwidth, playbacks of high-resolution 360-degree videos often suffer from rebuffering, while too much bandwidth is wasted in delivering those out-of-viewport parts that the user never watches. In this article, we present an Ensemble Prediction and Allocation based Streaming System, named as EPASS360, for delivering high Quality of Experience (QoE) 360-degree videos. The prediction model takes advantages of ensemble learning, providing high accuracy on the prediction of viewports. The allocation model divides a video into tiles, and allocates high resolution to tiles where a user's viewpoint may appear in the future by solving the QoE-aware optimization problem. Trace-driven emulation on real-world datasets shows that EPASS360 enhances the QoE in various scenarios compared to state-of-the-art streaming approaches. Experiments on the head-mounted device and the hand-held device over real-world Internet confirm the high user experience of EPASS360.

The received signal strength (RSS) based technique is extensively utilized for localization in the indoor environments. Since the RSS values of neighboring locations may be similar, the localization accuracy of the RSS based technique is limited. To tackle this problem, in this paper, we propose to utilize reconfigurable intelligent surface (RIS) for the RSS based multi-user localization. As the RIS is able to customize the radio channels by adjusting the phase shifts of the signals reflected at the surface, the localization accuracy in the RIS aided scheme can be improved by choosing the proper phase shifts with significant differences of RSS values among adjacent locations. However, it is challenging to select the optimal phase shifts because the decision function for location estimation and the phase shifts are coupled. To tackle this challenge, we formulate the optimization problem for the RIS-aided localization, derive the optimal decision function, and design the phase shift optimization (PSO) algorithm to solve the formulated problem efficiently. Analysis of the proposed RIS aided technique is provided, and the effectiveness is validated through simulation.

Nowadays, short video feed has attracted billions of mobile users all around the world to interact with content effortlessly, yielding an explosive growth of short video commerce. Typically, users watch full-screen short videos of a few seconds one-by-one in a watch-list generated by recommender systems, skipping those they are not interested in. However, the recommender system at the cloud makes a user-interest-specific decision mostly based on the users' behavior data collected within the application itself (e.g., users' view history), without examining the lower-layer network and communication statistics. When the playback choked due to the limited network bandwidth, the user will probably skip the video, leading to a waste of bandwidth and degradation of the user's quality of experience (QoE). Meanwhile, the excessive number of user requests to video contents raises a heavy computational load and communication cost for the recommender system at the cloud to determine which videos to be recommended and delivered to each user in a real-time manner. The advance of edge computing provides a promising avenue of deploying edge nodes with caches (e.g., household devices) beyond cloud and edge servers, such that the recommender system in the cloud can place popular video contents closer to client users, and meanwhile the contents are delivered to client users with good network condition. In this paper, we propose CFP, a cross-layer recommender system for short video streaming with fine-grained preloading technique at the network edge. CFP jointly optimizes the recommendation effect of the video application and the content preloading efficiency under various network conditions at the network edge. CFP takes a two-stage approach: the cloud server first seeks to perform edge-wise instead of user-interest-specific recommendation with neural collaborative filtering recommender, preloading a list of candidate videos to edge nodes, and each edge node, deploying the GRU with attention, then delivers the proper video contents to the client user device according to the user's preference. Trace-driven emulations demonstrate the efficiency of the proposed CFP scheme.

With the advance of omnidirectional panoramic technology, 360◦ imagery has become increasingly popular in the past few years. To better understand the 360◦ content, many works resort to the 360◦ object detection and various criteria have been proposed to bound the objects and compute the intersection-over-union (IoU) between bounding boxes based on the common equirectangular projection (ERP) or perspective projection (PSP). However, the existing 360◦ criteria are either inaccurate or inefficient for real-world scenarios. In this paper, we introduce a novel spherical criteria for fast and accurate 360◦ object detection, including both spherical bounding boxes and spherical IoU (SphIoU). Based on the spherical criteria, we propose a novel two-stage 360◦ detector, i.e., Reprojection R-CNN, by combining the advantages of both ERP and PSP, yielding efficient and accurate 360◦ object detection. To validate the design of spherical criteria and Reprojection R-CNN, we construct two unbiased synthetic datasets for training and evaluation. Experimental results reveal that compared with the existing criteria, the two-stage detector with spherical criteria achieves the best mAP results under the same inference speed, demonstrating that the spherical criteria can be more suitable for 360◦ object detection. Moreover, Reprojection R-CNN outperforms the previous state-of-the-art methods by over 30% on mAP with competitive speed, which confirms the efficiency and accuracy of the design.

Irregular scene text recognition has attracted much attention from the research community, mainly due to the complexity of shapes of text in natural scene. However, recent methods either rely on shape-sensitive modules such as bounding box regression, or discard sequence learning. To tackle these issues, we propose a pair of coupling modules, termed as Character Anchoring Module (CAM) and Anchor Pooling Module (APM), to extract high-level semantics from two-dimensional space to form feature sequences. The proposed CAM localizes the text in a shape-insensitive way by design by anchoring characters individually. APM then interpolates and gathers features flexibly along the character anchors which enables sequence learning. The complementary modules realize a harmonic unification of spatial information and sequence learning. With the proposed modules, our recognition system surpasses previous state-of-the-art scores on irregular and perspective text datasets, including, ICDAR 2015, CUTE, and Total-Text, while paralleling state-of-the-art performance on regular text datasets.

User profiles are not always visible in E-commerce scenarios, in which case the recommender systems can only summarize users' preferences through sessions of historical records. However, the items in a session might be irrelevant to users' preferences or become the disturbances for modelling the users' portraits, and thus degrade the performance of the recommender systems. In this paper, we propose the preference-aware mask to capture user preferences over the items within the sessions, which adapts to the preference-irrelevant items within the sessions and provides explainable evidence for the recommendation. Evaluation over three real-world datasets verifies that MBTREC performs well on the new-item recommendation task, and outperforms several state-of-the-art recommender systems on the general metrics.

Traffic flow forecasting is of great significance for improving the efficiency of transportation systems and preventing emergencies. Due to the highly non-linearity and intricate evolutionary patterns of short-term and long-term traffic flow, existing methods often fail to take full advantage of spatial-temporal information, especially the various temporal patterns with different period shifting and the characteristics of road segments. Besides, the globality representing the absolute value of traffic status indicators and the locality representing the relative value have not been considered simultaneously. This paper proposes a neural network model that focuses on the globality and locality of traffic networks as well as the temporal patterns of traffic data. The cycle-based dilated deformable convolution block is designed to capture different time-varying trends on each node accurately. Our model can extract both global and local spatial information since we combine two graph convolutional network methods to learn the representations of nodes and edges. Experiments on two real-world datasets show that the model can scrutinize the spatial-temporal correlation of traffic data, and its performance is better than the compared state-of-the-art methods. Further analysis indicates that the locality and globality of the traffic networks are critical to traffic flow prediction and the proposed TSSRGCN model can adapt to the various temporal traffic patterns.

Recently, sequential recommendation has become a significant demand for many real-world applications, where the recommended items would be displayed to users one after another and the order of the displays influences the satisfaction of users. An extensive number of models have been developed for sequential recommendation by recommending the next items with the highest scores based on the user histories while few efforts have been made on identifying the transition dependency and behavior continuity in the recommended sequences. In this paper, we introduce the Adversarial Oracular Seq2seq learning for sequential Recommendation (AOS4Rec), which formulates the sequential recommendation as a seq2seq learning problem to portray time-varying interactions in the recommendation, and exploits the oracular learning and adversarial learning to enhance the recommendation quality. We examine the performance of AOS4Rec over RNN-based and Transformer-based recommender systems on two large datasets from real-world applications and make comparisons with state-of-the-art methods. Results indicate the accuracy and efficiency of AOS4Rec, and further analysis verifies that AOS4Rec has both robustness and practicability for real-world scenarios.

The multi-path transmission techniques enable multiple paths to maximize resource usage and increase throughput in transmission, which have been installed over mobile devices in recent years. For video streaming applications, compared to the single-path transmission, the multi-path techniques can establish multiple subflows simultaneously to extend the available bandwidth for streaming high-quality videos in mobile devices. Existing adaptive video streaming systems have difficulty in harnessing multi-path scheduling and balancing the tradeoff between the quality of experience (QoE) and quality of service (QoS) concerns. In this paper, we propose an actor-critic network based on Periodical Experience Replay for Multi-path video streaming (PERM). Specifically, PERM employs two actor modules and a critic module: the two actor modules respectively assign the path usage of each subflow and select bitrates for the next chunk of the video, while the critic module predicts the overall objectives. We conduct trace-driven emulation and real-world testbed experiment to examine the performance of PERM, and results show that PERM outperforms state-of-the-art multi-path and single path streaming systems, with an improvement of 10%- 15% on the QoE and QoS metrics.

Given high-speed mobile Internet access today, audiences are expecting much higher video quality than before. Video service providers have deployed dynamic video bitrate adaptation services to fulfill such user demands. However, legacy video bitrate adaptation techniques are highly dependent on the estimation of dynamic bandwidth, and fail to integrate the video quality enhancement techniques, or consider the heterogeneous computing capabilities of client devices, leading to low quality of experience (QoE) for users. In this paper, we present a super-resolution based adaptive video streaming (SRAVS) framework, which applies a Reinforcement Learning (RL) model for integrating the video super-resolution (VSR) technique with the video streaming strategy. The VSR technique allows clients to download low bitrate video segments, reconstruct and enhance them to high-quality video segments while making the system less dependent on estimating dynamic bandwidth. The RL model investigates both the playback statistics and the distinguishing features related to the client-side computing capabilities. Trace-driven emulations over real-world videos and bandwidth traces verify that SRAVS can significantly improve the QoE for users compared to the state-of-the-art video streaming strategies with or without involving VSR techniques.

Short-form video feed has become one of the most popular ways for billions of users to interact with content, where users watch short-form videos of a few seconds one-by-one in a session. The common solution to improve the quality of experience (QoE) for short-form video feed is to treat it as a common sequential item recommendation problem and maximize its click-through rate prediction. However, the QoE of short-form video streaming under dynamic network conditions is jointly determined by both recommendation accuracy and streaming efficiency, and thus merely considering recommendation will lead to the degradation of the QoE of the streaming system for the audience. In this paper, we propose SSR, namely the short-form video streaming and recommendation system, which consists of a Transformer-based recommendation module and a reinforcement learning (RL) based bitrate adaptation streaming module. Specifically, we use Transformer to encode the session into a representation vector and recommend proper short-form videos based on the user's recent interest and the timeliness characteristics of short-form video contents. Then, the RL module combines the representation of session and other observations within the playback, and yields the appropriate bitrate allocation for the next short-form video to optimize a given QoE objective. Trace-driven emulations verify the efficiency of SSR compared to several state-of-the-art recommender systems and streaming strategies with at least 10%-15% QoE improvement under various QoE objectives.

Confronted with the severe indoor air pollution nowadays, we propose the usage of multiple robots to detect the indoor air quality (IAQ) cooperatively for fewer sensors and larger sensing area. To acquire the complete real-time IAQ distribution map, we exploit the real statistical data to construct the IAQ data model and adopt Kalman Filter to obtain the estimation of the unmeasured area. Since the movement of the robots affects the estimation accuracy, a proper movement strategy should be planned to minimize the total estimation error. To solve this optimization problem, we design a deep Q-learning approach, which provides sub-optimal movement strategies for real-time robot sensing. By simulations, we verify the adopted IAQ data model and testify the effectiveness of the proposed solution. For application considerations, we have deployed this system in Peking University since Dec. 2018 and developed a website to visualize the IAQ distribution.

Abstract The advances of mobile equipment and localization techniques put forward the accuracy of the location-based service (LBS) in mobile networks. One core issue for the industry to exploit the economic interest of the LBSs is to make appropriate point-of-interest (POI) recommendation based on users’ interests. Today, the LBS applications expect the recommender systems to recommend the accurate next POI in an anonymous manner, without inquiring users’ attributes or knowing the detailed features of the vast number of POIs. To cope with the challenge, we propose a novel attentive model to recommend appropriate new POIs for users, namely Geographical Attentive Recommendation via Graph (GARG), which takes full advantage of the collaborative, sequential and content-aware information. Unlike previous strategies that equally treat POIs in the sequence or manually define the relationships between POIs, GARG adaptively differentiates the relevance of POIs in the sequence to the prediction, and automatically identifies the POI-wise correlation. Extensive experiments on three real-world datasets demonstrate the effectiveness of GARG and reveal a significant improvement by GARG on the precision, recall and mAP metrics, compared to several state-of-the-art baseline methods.

Indoor air pollution has become a growing health risk, but it is challenging to provide low-cost air quality monitoring for the indoor environment. In this article, we present “AirScope,” a mobile sensing system that employs cooperative robots to monitor the indoor air quality. Since the wireless coverage can be incomplete in some indoor areas, AirScope allows the robots to defer uploading the data to the central server by utilizing their own data buffers. In order to guarantee the timeliness of the data in the server, AirScope aims to minimize the average data latency by properly planning the routes of the robots. Such a route planning strategy has to be implemented in a distributed way since the robots that are out of wireless coverage can only make plans on their own. In addition, the cooperation of the robots is also necessary because the aggregation of the robots in a small area increases the average data latency of the other unattended areas. To solve this distributed and cooperative routing planning problem, we propose a solution based on distributed deep Q-learning (DDQL). We evaluate the system performance by simulations and real-world experiments. The results show that AirScope is effective to reduce data latency, where the proposed DDQL is 8% better than the greedy algorithm and 24% better than the random strategy.

Using radio-frequency (RF) sensing techniques for human posture recognition has attracted growing interest due to its advantages of pervasiveness, contact-free observation, and privacy protection. Conventional RF sensing techniques are constrained by their radio environments, which limit the number of transmission channels to carry multi-dimensional information about human postures. Instead of passively adapting to the environment, in this paper, we design an RF sensing system for posture recognition based on reconfigurable intelligent surfaces (RISs). The proposed system can actively customize the environments to provide desirable propagation properties and diverse transmission channels. However, achieving high recognition accuracy requires the optimization of RIS configuration, which is a challenging problem. To tackle this challenge, we formulate the optimization problem, decompose it into two subproblems, and propose algorithms to solve them. Based on the developed algorithms, we implement the system and carry out practical experiments. Both simulation and experimental results verify the effectiveness of the designed algorithms and system. Compared to the random configuration and non-configurable environment cases, the designed system can greatly improve the recognition accuracy.

Benefited from rapid developments of deep learning, 3D shape recognition has become a remarkable subject in computer vision systems.The existing methods of multi-perspective views have shown competitive performance in 3D shape recognition.However, they have not yet fully exploited the information among all views of projection.In this paper, we propose a novel Multi-view Moments Embedding Network(MMEN) for capturing multiple moments information.MMEN obtains the similarity between different views and retains the description of the original view by generating moments matrix for representing the general features of the 3D shape.Additionally, we apply the matrix square-root layer to perform a non-linear scaling to the eigenvalues of the moment embedding matrix.We compare the performance of our proposed network with several state-of-the-art models on the ModelNet datasets, and the results of the average instance/class accuracy demonstrate the promising performance of MMEN on 3D shape recognition.

In this paper, we consider a cellular Internet of UAVs, where UAVs execute multiple sensing tasks continuously and cooperatively through sensing and transmission with the objective to minimize the age of information (AoI). However, the cooperative sensing and transmission is coupled with the trajectories of the UAVs, which makes the trajectory design a challenging problem. To tackle this challenge, we first propose a distributed sense-and-send protocol to coordinate the UAVs. Based on this protocol, we formulate the trajectory design problem for AoI minimization and propose a deep reinforcement learning algorithm to solve it, which we refer to as the compound-action actor-critic (CA2C) algorithm. Simulation results show that the CA2C algorithm outperforms two baseline algorithms for AoI minimization.

In the era of big data, recommender systems have become the key part of many Internet applications. One successful recommendation strategy is to jointly recommend items from different domains where the system can model an accurate portrait of user behaviors. However, it is still challenging to identify the correlation among various domains and make efficient utilization of features from each domain. In this paper, we propose a novel framework, called Domain Adversarial Cross-Domain Recommendation (DACDR), to learn the implicit transitive semantic features among various information relevant domains. The framework automatically retrieves semantic features from both the source and the target domains, and adaptively learns the transitive latent factors to connect the two domains. The user behaviors are then modelled by the learnt latent factors, based on which DACDR can provide an accurate recommendation. Evaluation over real-world dataset verifies that the proposed framework outperforms the state-of-the-art algorithms in terms of F1, NDCG and MRR metrics.

In the era of big data, information on relationships changes along with time, and the graphs of relationships captured at consecutive timestamps form the multiple temporal relational (MTR) network. To identify the relations in the network while preserving the network structure, a common solution is to learn the network representations through network embedding methods, and then build the relations upon the similarity among these representations. However, the existing network embedding methods either focus on a single relation or ignore the correlation between the heterogeneous and homogeneous relations, and thus it is difficult to investigate the multiple temporal features in the network. In this paper, we propose a novel network embedding method, named Homo- Hetero Network Embedding (HHNE), for the MTR networks. The HHNE utilizes the Graph Convolutional Network (GCN) to extract homogeneous features from each temporal relational network and then generates the homo-hetero network embeddings by fusing the single temporal relational features through a Multi- Layer Perceptron (MLP). Therefore, HHNE could capture the multi- dimensional characteristics in the network, including both intra-relation information and inter-relation information. To show the efficiency of HHNE, we conduct experiments in a real-world dataset on predicting new relations in the MTR networks. The result reveals that our method could outperform several legacy network embedding methods and state- of-the-art multi-relational network embedding methods in the task of relation prediction, demonstrating that the proposed embedding method is more suitable for the MTR network.

Due to the significant air pollution problem, monitoring and prediction for air quality have become increasingly necessary. To provide real-time fine-grained air quality monitoring and prediction in urban areas, we have established our own Internet-of-Things-based sensing system in Peking University. Due to the energy constraint of the sensors, it is preferred that the sensors wake up alternatively in an asynchronous pattern, which leads to a sparse sensing dataset. In this paper, we propose a novel approach to predict the real-time fine-grained air quality based on asynchronous sensing. The sparse dataset and the spatial-temporal-meteorological relations are modeled into the correlation graph, in which way the prediction procedures are carefully designed. The advantage of the proposed solution over existing ones is evaluated over the dataset collected by our air quality monitoring system.

Computer-aided detection and diagnosis (CAD) have been applied to many departments of medical institutions, and early detection of diseases can prevent serious health loss. Pulmonary diseases generate negative effects on human health, even leading to death. The chest X-ray is a common examination for diagnosis of pulmonary diseases. The experienced radiologist can quickly infer patients' symptoms by screening the chest X-ray image. While in some developing countries or remote rural areas, due to the lack of experienced radiologists or doctors, patients may be misdiagnosed. Many efforts have been spent on developing an effective auxiliary detection system to provide medical workers with evidence on diseases. In particular, detecting pulmonary complication via chest X-ray images is one of the most challenging tasks. In this paper, we transform the pulmonary complications detection task into a multi-binary classification task for each pulmonary pathology, and propose a new classification model, DenXFPN (for X-ray). DenXFPN combines multiple feature maps at different scales extracted through a densely convolutional neural network. Our model achieves 0.827 on the area under the receiver operating characteristic curve (AUC) metric on average, which outperforms the state-of-the-art results on most of all pathologies in the Chest X-ray14 dataset.

In the past few years, virtual reality (VR) has become an enabling technique, not only for enriching our visual experience but also for providing new channels for businesses. Untethered mobile devices are the main players for watching 360-degree content, thereby the precision of predicting the future viewpoints is one key challenge to improve the quality of the playbacks. In this paper, we investigate the image features of the 360-degree videos and the contextual information of the viewpoint trajectories. Specifically, we design ladder convolution to adapt for the distorted image, and propose LadderNet to transfer the knowledge from the pre-trained model and retrieve the features from the distorted image. We then combine the image features and the contextual viewpoints as the inputs for long short-term memory (LSTM) to predict the future viewpoints. Our approach is compared with several state-of-the-art viewpoint prediction algorithms over two 360-degree video datasets. Results show that our approach can improve the Intersection over Union (IoU) by at least 5% and meeting the requirements of the playback of 360-degree video on mobile devices.

In this paper, we study a multi-lane cooperative platoon scenario, where platoons move cooperatively and communicate with each other by cellular vehicle-to-everything communication. The platoon formation is important and difficult in multi-platoon scenario, for the platoon size, power and resource allocation of each platoon interact with each other and influence those of other platoons. To this end, we propose a two-step resource allocation strategy in consideration of platoon formation, including the resource allocation at the base station and within each platoon, respectively. A branch and bound algorithm is utilized for the resource allocation at the BS. We design a distributed dynamic programming based subchannel allocation and power control algorithm for the joint optimization of platoon size, power and intra-platoon resource allocation. Simulation results evaluate the influence of the penalty factor and latency constraint on the system performance.

Driven by the increasingly serious air pollution problem, the monitoring of air quality has gained much attention in both theoretical studies and practical implementations. In this paper, we present the implementation and optimization of our own air quality sensing system, which provides real-time and fine-grained air quality map of the monitored area. The objective of our optimization problem is to minimize the average joint error of the established real-time air quality map, which involves data inference for the unmeasured data values. A deep Q-learning solution has been proposed for the power control problem to reasonably plan the sensing tasks of the power-limited sensing devices online. A genetic algorithm has been designed for the location selection problem to efficiently find the suitable locations to deploy a limited number of sensing devices. The performance of the proposed solutions are evaluated by simulations, showing a significant performance gain when adopting both strategies.

Reading text in the wild is a very challenging task due to the diversity of text instances and the complexity of natural scenes. Recently, the community has paid increasing attention to the problem of recognizing text instances with irregular shapes. One intuitive and effective way to handle this problem is to rectify irregular text to a canonical form before recognition. However, these methods might struggle when dealing with highly curved or distorted text instances. To tackle this issue, we propose in this paper a Symmetry-constrained Rectification Network (ScRN) based on local attributes of text instances, such as center line, scale and orientation. Such constraints with an accurate description of text shape enable ScRN to generate better rectification results than existing methods and thus lead to higher recognition accuracy. Our method achieves state-of-the-art performance on text with both regular and irregular shapes. Specifically, the system outperforms existing algorithms by a large margin on datasets that contain quite a proportion of irregular text instances, e.g., ICDAR 2015, SVT-Perspective and CUTE80.

Game AI is of great importance as games are simulations of reality. Recent research on game AI has shown much progress in various kinds of games, such as console games, board games and MOBA games. However, the exploration in RTS games remains a challenge for their huge state space, imperfect information, sparse rewards and various strategies. Besides, the typical card-based RTS games have complex card features and are still lacking solutions. We present a deep model SEAT (selection-attention) to play card-based RTS games. The SEAT model includes two parts, a selection part for card choice and an attention part for card usage, and it learns from scratch via deep reinforcement learning. Comprehensive experiments are performed on Clash Royale, a popular mobile card-based RTS game. Empirical results show that the SEAT model agent makes it to reach a high winning rate against rule-based agents and decision-tree-based agent.

Given the increasingly serious air pollution problem, air quality index (AQI) monitoring in urban areas has drawn considerable attention. This paper presents ImgSensingNet, a vision guided aerial-ground sensing system, for air quality monitoring and forecasting by the fusion of haze images taken by the unmanned-aerial-vehicle (UAV) and the AQI data collected by an on-ground wireless sensor network. Specifically, ImgSensingNet first leverages the computer vision technique to tell the AQI scale in different regions from the haze images, where haze-relevant features and a deep convolutional neural network (CNN) are designed for direct learning between haze images and corresponding AQI scale. Based on the learnt AQI scale, ImgSensingNet determines whether to wake up on-ground wireless sensors for small-scale AQI monitoring and inference, which can greatly reduce the energy consumption of the system. An entropy-based model is employed for accurate real-time AQI estimation at un-measured locations and future air quality distribution forecasting. We implement and evaluate ImgSensingNet on two university campuses since Feb. 2018, and has collected 17,630 photos and 2.6 millions of AQI data samples. Experimental results confirm that ImgSensingNet can achieve high estimation accuracy while greatly reduce the battery consumption, compared to other state-of-the-art AQI monitoring approaches.

360-degree videos have gained more popularity in recent years, owing to the great advance of panoramic cameras and head-mounted devices. However, as 360-degree videos are usually in high resolution, transmitting the content requires extremely high bandwidth. To protect the Quality of Experience (QoE) of users, researchers have proposed tile-based 360-degree video streaming systems that allocate high/low bit rates to selected tiles of video frames for streaming over the limited bandwidth. It is challenging to determine which tiles should be allocated with a high/low rate, because (1) the video playbacks include too many features that dynamically change over time when making the rate allocation; (2) most of the state-of-the-art systems focus on a fixed set of heuristics to optimize a specific QoE objective, while users may have various QoE objectives that need to be optimized in different ways. This paper presents a Deep Reinforcement Learning (DRL) based framework for 360-degree video streaming, named DRL360. The DRL360 framework helps improve the system performance by jointly optimizing multiple QoE objectives across a broad set of dynamic features. The DRL-based model adaptively allocates rates for the tiles of the future video frames based on the observations collected by client video players. We compare the proposed DRL360 to the existing systems by trace-driven evaluations as well as conducting a realworld experiment over a wide variety of network conditions. Evaluation results reveal that DRL360 can adapt to all considered scenarios, and outperform the state-of-the-art approaches by 20%-30% on average given different QoE objectives.

Online advertisement (ad) recommendation in the mobile social network (MSN) is an uprising interest of research. Compared to traditional recommendation systems, one of its major difference is the presence of explicit negative feedback from users (e.g., a user does not click an ad, or she/he does not like it). On the other hand, most methods utilize negative sampling (e.g., randomly sampling an item that a user never interacts with to avoid overfitting, that is, she/he is assumed to dislike it) while training conventional recommendation systems. This may lead to a conflict between negative feedback and sampling, as they should be treated differently, but they are considered as the same if traditional methods are directly applied for online ad recommendation. In this paper, we present AdRec, a novel framework of online ad recommendation in MSN to address this conflict. We introduce an auxiliary output and modify the loss function to assign different weights to negative samples and feedbacks. A theoretical analysis is applied to show the efficiency of our design, and experiments on real world datasets demonstrate that our proposed method outperforms several state-of-the-art approaches.

In decentralised cognitive radio (CR) networks, establishing communication sessions between a communicating pair requires them to meet each other on a common channel via a ‘rendezvous’ process. Devising distributed CR rendezvous protocol is a challenging task as cognitive nodes are not necessarily synchronised, and may have different perceptions of channel availability. In this study, the authors present M‐Rendezvous , an order‐optimal rendezvous protocol exploiting the performance gain brought by having multiple radios at cognitive nodes. As a distinguished feature, M‐Rendezvous is a unified rendezvous protocol that can operate in both homogenous case where both of the rendezvous nodes are equipped with only one radio or multiple radios, and heterogeneous case where one of the rendezvous nodes has single radio and the other has multiple radios. In both cases, by rigorous analysis, the authors demonstrate that M‐Rendezvous can guarantee rendezvous over every channel with bounded and order‐minimal delay even when rendezvous nodes have asynchronous clocks and asymmetrical channel perceptions.

Driven by the increasingly serious air pollution problem, the monitoring of air quality has gained much attention in both theoretical studies and practical implementations. In this paper, we present the architecture, implementation, and optimization of our own air quality sensing system, which provides real-time and fine-grained air quality map of the monitored area. As the major component, the optimization problem of our system is studied in detail. Our objective is to minimize the average joint error of the established real-time air quality map, which involves data inference for the unmeasured data values. A deep Q -learning solution has been proposed for the power control problem to reasonably plan the sensing tasks of the power-limited sensing devices online. A genetic algorithm has been designed for the location selection problem to efficiently find the suitable locations to deploy limited number of sensing devices. The performance of the proposed solutions are evaluated by simulations, showing a significant performance gain when adopting both strategies.

Automated Fare Collection (AFC) systems have been globally deployed for decades, particularly in the public transportation network where the transit fee is calculated based on the length of the trip (a.k.a., distance-based pricing AFC systems). Although most messages of AFC systems are insecurely transferred in plaintext, system operators did not pay much attention to this vulnerability, since the AFC network is basically isolated from the public network (e.g., the Internet)-there is no way of exploiting such a vulnerability from the outside of the AFC network. Nevertheless, in recent years, the advent of Near Field Communication (NFC)-equipped smartphones has opened up a channel to invade into the AFC network from the mobile Internet, i.e., by Host-based Card Emulation (HCE) over NFC-equipped smartphones. In this paper, we identify a novel paradigm of attacks, called LessPay, against modern distance-based pricing AFC systems, enabling users to pay much less than what they are supposed to be charged. The identified attack has two important properties: 1) it is invisible to AFC system operators because the attack never causes any inconsistency in the back-end database of the operators; and 2) it can be scalable to affect a large number of users (e.g., 10,000) by only requiring a moderate-sized AFC card pool (e.g., containing 150 cards). To evaluate the efficacy of the attack, we developed an HCE app to launch the LessPay attack; and the real-world experiments demonstrate not only the feasibility of the LessPay attack (with 97.6 percent success rate) but also its low cost in terms of bandwidth and computation. Finally, we propose, implement and evaluate four types of countermeasures, and present security analysis and comparison of these countermeasures on defending against the LessPay attack.

In this paper, we study the platoon cooperation in the multi-lane cooperative platoon scenario, where platoons move cooperatively and communicate with each other by cellular vehicle-to-everything (V2X) communication. The platoon cooperation is important for the interference management and communication reliability enhancement, yet it is difficult, since the platoon formation, subchannel allocation, and power control of each platoon interact with each other and influence those of other platoons. To increase the number of vehicles in the platoon and reduce the power consumption, we propose a two-step resource allocation strategy in consideration of platoon formation, i.e., the resource allocation at the base station (BS) and within each platoon. A branch and bound algorithm is utilized for the resource allocation at the BS. We then design a distributed dynamic programming-based subchannel allocation and power control algorithm for the joint optimization of platoon formation, subchannel allocation, and power control. The simulation results evaluate the impact of the penalty factor and the latency requirement on the system performance.

In this paper, we consider an uplink cellular Internet-of-Things (IoT) network, where a cellular user (CU) can serve as the mobile data aggregator for a cluster of IoT devices. To be specific, the IoT devices can either transmit the sensory data to the base station (BS) directly by cellular communications, or first aggregate the data to a CU through machine-to-machine (M2M) communications before the CU uploads the aggregated data to the BS. To support massive connections, the IoT devices can leverage the unlicensed spectrum for M2M communications, referred to as IoT unlicensed (IoT-U). Aiming to maximize the number of scheduled IoT devices and meanwhile associate each IoT device with the right CU or BS with the minimum transmit power, we first introduce a single-stage formulation that captures these objectives simultaneously. To tackle the NP-hard problem efficiently, we decouple the problem into two subproblems, which are solved by successive linear programming and convex optimization techniques, respectively. The simulation results show that the proposed IoT-U scheme can support more IoT devices than that only using the licensed spectrum.

Rapid development of online social networks further facilitates the expansion of information over the Internet. In many scenarios, several pieces of different or even opposite information could diffuse competitively at the same time. Recently, some messenger APPs such as WeChat arose, where users can send links in their "WeChat Moments (WM)", which is called the messenger-based social network (Msg-SN). The unique characteristics in Msg-SN may lead to great difference on the network topology compared to conventional social networks. It is impossible to find the key opinion leaders with millions of followers to help block the rumors or to locate the source of rumors. Thus, the business often tries to select and inject a set of users in the network with the truth to block negative influence diffusion. We call this problem as the competitive influence blocking (CIB) problem. In this paper, we study the CIB problem in Msg-SN under the competitive linear threshold (CLT) model. We propose a fast heuristic algorithm based on eigenvector centrality to optimize the negative influence reduction by selecting a positive seed set. The experimental results using real-world WeChat Moments data show that our algorithm performs better than the effective CLDAG algorithm and also runs faster.

For a computing platform that is compliant with the Trusted Platform Module (TPM) standard, direct anonymous attestation (DAA) is an appropriate cryptographic protocol for realizing an anonymous subscription system. This approach takes advantage of a cryptographic key that is securely embedded in the platform's hardware, and enables privacy-preserving authentication of the platform. In all of the existing DAA schemes, the platform suffers from significant computational and communication costs that increase proportionally to the size of the revocation list. This drawback renders the existing schemes to be impractical when the size of the revocation list grows beyond a relatively modest size. In this paper, we propose a novel scheme called Lightweight Anonymous Subscription with Efficient Revocation (LASER) that addresses this very problem. In LASER, the computational and communication costs of the platform's signature are multiple orders of magnitude lower than the prior art. LASER achieves this significant performance improvement by shifting most of the computational and communication costs from the DAA's online procedure (i.e., signature generation) to its offline procedure (i.e., acquisition of keys/credentials). We have conducted a thorough analysis of LASER's performance related features. We have implemented LASER on a laptop with an on-board TPM. To the best of our knowledge, this is the first implementation of a DAA scheme on an actual TPM cryptoprocessor that is compliant with the most recent TPM specification, viz., TPM 2.0.

Recent advance in Internet-of-Things (IoT) brings consumer- level smart mobile robot to our life. Indoor navigation is one of the most critical challenges for mobile robots. Existing approaches using wireless signal fingerprinting (e.g., WiFi fingerprint), computer vision techniques, require extensive war-driving of the indoor environment to collect sufficient environmental data. In this paper, we present SIGN, a lightweight, visual-tag based, indoor navigation approach that is free of indoor war-driving. The approach deploys a set of coded visual tags in the environment, and allows the robot to autonomously decide the moving direction by recognizing nearby tags and leveraging the geometry information. The proposed approach is robust to the change of the environment such as unexpected obstacles. Experiments in two indoor spaces under various scenarios show that SIGN helps the mobile robot using the off-the- shelf camera to self-navigate in indoor environment with the deployment of coded visual tags.

Mobile sensing is challenging in 3D space, as there are many inaccessible places where people rarely venture. Unmanned aerial vehicle (UAV), commonly known as drone, has greatly extended the scope of mobile sensing in 3D space, and pushed forward a variety of 3D mobile sensing applications, such as aerial photo- or video-graphy, 3D wireless signal survey, and air quality monitoring. However, the short battery life of drones has largely restricted the wide adoption of these applications. In this paper, we study the trajectory planning problem for optimizing the flight route in a given sensing space. We first divide the 3D space into an infinite three-dimensional network of observation locations (OLs), and model the sensing scope as a finite subgraph of 3D OL network. We formulate the problem as finding the optimal trajectory in the sensing scope. We propose an algorithm that finds trajectory in each divided 3D grid of the sensing scope by generating a nearly optimal dominating path, and finding the minimum dominating set in the dominating path. Then, we concatenate obtained trajectories in 3D grids to a nearly optimal trajectory in the sensing scope. Experimental results show that the proposed algorithm takes 24% less time to complete sensing the given space, and during the battery life it can cover 19% more sensing scope, than existing solutions.

WeChat is the largest mobile instant messaging service in China, where users can send messages to friends or post them over their walls (a.k.a. friend circle, or WeChat Moments). Interactive web apps are quite attractive for businesses, institutes, or individuals to promote products or events. In this paper, we analyze the diffusion statistics of interactive web apps in WeChat and conduct an empirical measurement study over a dataset with 54 million users and 20 thousand web apps crawled. We discover the lifecycle of interactive web apps varies drastically, which is largely dependent on the content, date, time upon the first release, and the social influence of viewers and senders. Meanwhile, we develop a model based on the matrix factorization method to extract latent features of interactive web apps and an app lifecycle model that characterizes how the features affect apps' lifecycle, achieving the mean absolute error (MAE) of 2.32 days in predicting app's lifecycle. Our results hold the promise of helping businesses to promote their marketing information dissemination through long-lived interactive web apps at the right timing and with the appropriate content.

Online video service has become an emerging application of Internet, playing an important and indispensable role in our daily life. Aiming at relieving the heavy burden on CDN servers, many video service providers deploy a hybrid CDN-P2P system. To minimize the cost of the "last mile delivery" of CDN servers, the system should be able to dispatch video files that receive a large amount of view requests during peak hours to P2P network in advance. However, to accurately predict whether a video will gain popularity is difficult due to the uncertainty of people's viewing tendency. In this paper, we reveal the correlation between the popularity of videos in the daytime and the popularity in peak hours at night based on statistics collected in a real-world large commercial VoD system. Based on our findings, we propose Adaptive Time-Dependent Push Strategy (ATDPS), a scalable push strategy that implements adaptive time-dependent techniques in the hybrid CDN-P2P system. A deep neural network is leveraged to predict the demand of hot videos during peak hours at night. Besides, the system adaptively adjusts the time-dependent strategy of pushing the content of hot videos to the P2P network according to the seed scarcity of the videos in different time periods. Simulations over historical data and pilot deployment on smart routers show that our ATDPS can significantly decrease the addressed bandwidth consumption at peak hours.

Driven by the increasingly serious air pollution problem, the monitoring of fine-grained air quality index (AQI) in urban areas has drawn considerable attention. In this paper, we design a novel algorithm to recommend the placement of sensors for energy- efficient AQI monitoring in urban three-dimensional (3D) space. Specifically, we first propose an entropy- based semi-supervised learning (ESSL) model to estimate the AQI distribution of unobserved locations, using the sparse historical spatial-temporal data and other features, including 3D coordinates, wind speed and weather conditions. Based on ESSL, we then design an entropy minimization ranking (EMR) algorithm to recommend the best sensor locations for AQI monitoring. Through the emulation on a fine-grained AQI dataset, the results demonstrate our scheme can provide energy- efficient solutions by using the least number of sensors to achieve higher accuracy than other existing approaches.

Machine reading comprehension has gained attention from both industry and academia. It is a very challenging task that involves various domains such as language comprehension, knowledge inference, summarization, etc. Previous studies mainly focus on reading comprehension on short paragraphs, and these approaches fail to perform well on the documents. In this paper, we propose a hierarchical match attention model to instruct the machine to extract answers from a specific short span of passages for the long document reading comprehension (LDRC) task. The model takes advantages from hierarchical-LSTM to learn the paragraph-level representation, and implements the match mechanism (i.e., quantifying the relationship between two contexts) to find the most appropriate paragraph that includes the hint of answers. Then the task can be decoupled into reading comprehension task for short paragraph, such that the answer can be produced. Experiments on the modified SQuAD dataset show that our proposed model outperforms existing reading comprehension models by at least 20% regarding exact match (EM), F1 and the proportion of identified paragraphs which are exactly the short paragraphs where the original answers locate.

Decentralizing content delivery to edge devices has become a popular solution for saving the bandwidth consumption of CDN when the CDN bandwidth is expensive. One successful realization is the hybrid CDN-P2P VoD system, where a client is allowed to request video content from a number of seeds (seed clients) in the P2P network. However, the seed scarcity problem may arise for a video resource when there are an insufficient number of seeds to satisfy requests to the video. To alleviate this problem, many commercial VoD systems have employed a video push mechanism that directly sends the recent scarce video resources to randomly-chosen seeds to serve more requests. However, the current video push mechanism fails to consider which videos will become scarce in the future, or differentiate the uploading capability of different seeds. In this paper, we propose Proactive-Push, a video push mechanism that lowers the bandwidth consumption of CDN by predicting future scarce videos and proactively sending them to competent seeds with strong uploading capabilities. Proactive-Push trains neural network models to correctly predict 80% of future scarce video resources, and identify over 90% of competent seeds. We evaluate Proactive-Push using a trace-driven emulation and a real-world pilot deployment over a commercial VoD system. Results show that Proactive-Push can further reduce the proportion of direct download from CDN by 21%, and save the CDN bandwidth cost at peak time by 18%.

Given significant air pollution problems, air quality index (AQI) monitoring has recently received increasing attention. In this paper, we design a mobile AQI monitoring system boarded on the unmanned-aerial-vehicles, called ARMS, to efficiently build fine-grained AQI maps in real-time. Specifically, we first propose the Gaussian plume model on the basis of the neural network (GPM-NN), to physically characterize the particle dispersion in the air. Based on GPM-NN, we propose a battery efficient and adaptive monitoring algorithm to monitor AQI at the selected locations and construct an accurate AQI map with the sensed data. The proposed adaptive monitoring algorithm is evaluated in two typical scenarios, a 2-D open space like a roadside park, and a 3-D space like a courtyard inside a building. The experimental results demonstrate that our system can provide higher prediction accuracy of AQI with GPM-NN than other existing models, while greatly reducing the power consumption with the adaptive monitoring algorithm.

Recently, owing to the advances in the self-interference cancellation technology, the in-band full-duplex (FD) capability has been demonstrated at Wi-Fi range. However, the simultaneous uplink (UL) and downlink (DL) transmission may lead to inter-user interference (IUI) and result in decoding failure. Spectrum efficiency should also be considered in the construction process of the FD transmission. In this paper, we propose a hybrid half-duplex/FD MAC protocol based on a two-fold RTS/CTS contention resolution mechanism, in order to fully exploit the channel access opportunities provided by the simultaneous UL and DL transmissions. The noteworthy features of the proposed protocol lie in the following two aspects. First, the protocol provides the flexibility for the AP to decide the probability of constructing FD transmission, and then it adopts a second-fold of RTS/CTS mechanism to prevent the constructed transmission from being affected by the IUI. The second-fold contention and the probability of constructing FD transmission are optimized separately to maximize the spectrum efficiency given different transmission demands. Simulation results show that the proposed MAC protocol achieves higher capacity compared with previous works, and the hybrid characteristic enables the FD Wi-Fi networks to meet with different system requirements.

With the increasing demand for vehicular data transmission, limited dedicated cellular spectrum becomes a bottleneck to satisfying the requirements of all cellular vehicle-to-everything (V2X) users. To address this issue, unlicensed spectrum is considered to serve as the complement to support cellular V2X users. In this paper, we study the coexistence problem of cellular V2X users and vehicular ad hoc network (VANET) users over the unlicensed spectrum. To facilitate the coexistence, we design an energy sensing-based spectrum sharing scheme, where cellular V2X users are able to access the unlicensed channels fairly while reducing the data transmission collisions between cellular V2X and VANET users. In order to maximize the number of active cellular V2X users, we formulate the scheduling and resource allocation problem as a two-sided many-to-many matching with peer effects. We then propose a dynamic vehicle-resource matching algorithm and present the analytical results on the convergence time and computational complexity. Simulation results show that the proposed algorithm outperforms existing approaches in terms of the performance of the cellular V2X system when the unlicensed spectrum is utilized.

To make every user conveniently have access to his or her most interested jobs and candidates (recommendation items) in the current employment market, the recruitment networks need to meet the demand of fast and accurate recommendation. But a key challenge is that the total items may have a large quantity in the big data scenarios. And another problem is that the personalization of different users is diverse. In order to handle these challenges, this paper proposes a mining and prediction system for job and candidate recommendation with contextual online learning. It predicts a proper item by utilizing the feedback reward of previous users in the nearby context region. Besides that, we introduce a Monte-Carlo Tree Search (MCTS) method in which the similar items can be amalgamated into a cluster to reduce the computing load. Our algorithm can achieve sublinear regret and space complexity. Finally, some experiments are conducted to test our algorithm based on a large database from \emph{Work4} (the global leader in social and mobile recruiting), which can show the outstanding performance of our algorithm when compared with other existing algorithms.

People connect to each other over conventional online social networks (OSNs) based on many parameters (common interests, experiences, locations), while the anonymous social networks (ASNs) recommend candidate friends to a user mainly by the location proximity at a coarse-granularity. In this paper, we formulate a fine-grained trajectory-matching prediction problem for friend recommendation in ASNs-what is the likelihood for two users to encounter with each other in the future based on their historical trajectory data? We define the serendipity of two trajectories in both spatial and temporal domains to quantify the similarity between two users' trajectories, and propose an algorithm that recommends candidate friends to a user by determining the similarity of their trajectories. Experiments show that our proposed algorithm can predict the encounter of users quite accurately and it outperforms the conventional algorithms in terms of the precision and consumed time.

Recently, the in-band full-duplex (FD) capability has been demonstrated at Wi-Fi range. However, the simultaneous uplink (UL) and downlink (DL) transmission may lead to inter-user interference (IUI). In this paper, we propose a hybrid MAC protocol, in which the AP decides the probability of constructing FD transmission. The protocol also adopts a second fold of RTS/CTS mechanism to prevent the constructed transmission from being affected by the IUI. The second fold RTS/CTS mechanism and the probability for FD transmission are optimized respectively to maximize the expected spectrum efficiency. Simulation results show that the proposed MAC protocol achieves higher capacity compared to a half-duplex counterpart in terms of both UL and DL throughput.

Recently, mobile devices have been used to carry sensors to monitor air quality index (AQI), and help construct an AQI map in 2-dimensional (2D) areas. In this paper, we design a novel 3-dimensional (3D) AQI monitoring system, called Arms (AQI realtime monitoring system), to efficiently build realtime fine-grained 3D AQI maps, with the help of unmanned-aerial- vehicles (UAVs). Based on the data monitored by Arms, a novel dispersion model, namely Adaptive Gaussian Plume Model (AGPM) is proposed to predict the distribution of AQI. Moreover, the adaptive monitoring techniques, i.e., complete and optimized monitoring, are designed to effectively produce and maintain realtime AQI maps, while greatly reducing the measurement efforts. Experimental results verify that Arms can provide higher predicting accuracy of AQI with the proposed AGPM than other existing models. In addition, the whole system's battery consumption can be greatly reduced.

The state of art protocols in neighbor discovery in wireless sensor networks can be divided into two categories: the quorum based, and the co-primality based protocols, which are confirmed by simulations to have a small "theoretical" latency according to their wake-up schedule designs. However, these works fail to consider the collision of neighbor discovery beacons, when multiple pairs of nodes search for discovery simultaneously, which could lead to a greater "practical" latency. In this paper, we seek to reduce such practical latency in neighbor discovery protocols caused by the collision of neighbor discovery beacons by a dynamic slot-length control mechanism that allows each node to autonomously vary its slot length based on the detection of beacon collisions. We develop a real-world testbed of neighbor discovery on Android smartphones by implementing a few classic neighbor discovery protocols in literature, and evaluate their performance with and without the proposed slot-length control. Experimental results show that the slot-length control can help reduce the practical latency of neighbor discovery by more than 15% under both types of neighbor discovery protocols.

Driving navigation is challenging in enclosed areas, e.g., urban canyon areas, due to loss of GPS signals, or poor availability of landmarks. Many leader-follower navigation systems are independent of GPS signals or landmarks: a leader device pre-collects sensory signals of landmarks along a pathway to build a reference trace; and the follower device compares the signals at his current location against the ones in the reference trace to get navigated. However, such navigation systems are subject to the volatility of the sensory data, e.g., image landmarks or WiFi signals may change over time. This requires labor-intensive updates of sensory signals along the pathway. In this paper, we propose, Trail-Tracker, a leader-follower driving navigation system that is free of the volatility of these sensory data. Specifically, Trail-Tracker creates the trajectory segments by fusing the visual and inertial data captured by smartphone sensors, and it compares one's trajectory segment against the leader's for navigation, instead of directly comparing the series of volatile sensory data recorded in their devices. Trail-Tracker is infrastructure-free and robust to the change of environment. We implemented Trail-Tracker on smartphones, and evaluated it in a street canyon area and on a public dataset. Our experimental results show that the final spatial errors during navigation were 2.9% of the whole journey, with a low latency of about 100ms per frame.

Businesses are interested in marketing over the mobile social network (MSN) during holiday seasons to expand their holiday sales. Understanding the “holiday syndrome” - how people behave during holidays - over the MSN is important to create a successful marketing campaign that delights customers. In this paper, we conduct an empirical measurement study of WeChat Moments (the most popular social network of the mobile messaging app WeChat in China) during the holiday season of Chinese Spring Festival (with 137 million users involved and 329 thousand applications crawled), and present a comprehensive view of the MSN's impact on the social ties among users, user interests, as well as users' migration patterns before, during, and after the holiday. Our research findings suggest that the MSN is predominantly used during holiday seasons for holiday-atmosphere building and experience sharing. It is revealed that there exist strong correlations between the timing and popular topics, and between holiday migration and regional distribution. Our results hold the promise of helping businesses to promote their marketing information dissemination to targeted groups of customers, at the right region, with appealing words, during the holiday season.

Vehicle-to-everything (V2X) communications enable the information exchange between the vehicle and the infrastructure, pedestrian, device, or any other entity that may affect the vehicle. V2X is known as a critical component for the vision of connected and autonomous vehicles in the future, with the goal of improving safety, saving energy, optimizing the traffic, etc. Many stake holders (e.g., 3GPP, IEEE) have announced the draft standards or technical reports that detail new opportunities of V2X-enabled vehicles for the cellular and automotive industries. However, the security issues in V2X communications receive little attention from industry and academia communities. In this paper, we describe how adversaries can exploit the security vulnerabilities to degrade the performance of V2X communications and evaluate the likelihood of V2X specific attacks in undermining the road safety. Our investigation reveals that the existing security mechanisms fall short of addressing the key security threats, and we also discuss countermeasures by adding a security sub-layer for V2X communication protocols to provide V2X users with privacy, authentication, and confidentiality.

Thanks to the rapid development of information technology, the size of a wireless network is becoming larger and larger, which makes spectrum resources more precious than ever before. To improve the efficiency of spectrum utilization, game theory has been applied to study efficient spectrum sharing for a long time. However, the scale of wireless networks in existing studies is relatively small. In this paper, we introduce a novel game called aggregative game and use it to model spectrum sharing in large-scale, heterogeneous, and dynamic networks. Meanwhile, the massive usage of the spectrum leads to easier divulgence of privacy of spectrum users, which calls for privacy and truthfulness guarantees. In a large decentralized scenario, each user has no priori about other users’ channel access decisions, which forms an incomplete information game. A “weak mediator,” e.g., the base station or licensed spectrum regulator, is introduced and it turns the incomplete spectrum sharing game into a complete one. This is essential in reaching a Nash equilibrium (NE). By utilizing past channel access experience, we propose an online learning algorithm to improve the utility of each user. We show that the learning algorithm achieves an NE over time and provides no regret guarantee for each user. Specifically, our mechanism admits an approximateex-postNE, and is joint differentially private and incentive-compatible. Efficiency of the approximate NE is evaluated, and innovative scaling law results are disclosed. We also provide simulation results to verify our analysis.

Many web applications provide secondary authentication methods, i.e., secret questions (or password recovery questions), to reset the account password when a user's login fails. However, the answers to many such secret questions can be easily guessed by an acquaintance or exposed to a stranger that has access to public online tools (e.g., online social networks); moreover, a user may forget her/his answers long after creating the secret questions. Today's prevalence of smartphones has granted us new opportunities to observe and understand how the personal data collected by smartphone sensors and apps can help create personalized secret questions without violating the users’ privacy concerns. In this paper, we present aSecret-Question based Authenticationsystem, called “Secret-QA”, that creates a set of secret questions on basic of people's smartphone usage. We develop a prototype on Android smartphones, and evaluate the security of the secret questions by asking the acquaintance/stranger who participates in our user study to guess the answers with and without the help of online tools; meanwhile, we observe the questions’ reliability by asking participants to answer their own questions. Our experimental results reveal that the secret questions related to motion sensors, calendar, app installment, and part of legacy app usage history (e.g., phone calls) have the best memorability for users as well as the highest robustness to attacks.

Many online social networks have provided a messenger app (e.g., facebook messenger, direct message on Twitter) to facilitate communication between strong- tied friends. Meanwhile, some messenger apps (WeChat) also start to offer social-networking services ("WeChat Moments" (WM), a.k.a. friend circle) that allow users to post pictures, texts, links of webpages, on their walls, which is called the messenger-based social network (Msg-SN). In online social networks, Key Opinion Leaders (KOLs) with millions of followers are easy to identify for helping viral marketing/advertising. However, most users of a messenger app have a small number of friends (e.g., hundreds of friends), which makes it challenging to detect a KOL in Msg-SN by only counting the number of his/her friends. In this paper, we study the influence maximization problem in the Msg-SN of finding the set of most influential KOL nodes that maximize the spread of information. We develop a novel efficient approximation algorithm that calculates the influence by looking at the user's local contribution to the information diffusion process, which scales to large datasets with provable near-optimal performance. Experiment results using the real-world WeChat Moments data (on January 14th, 2016, 100 thousand users) show that our algorithms can identify the set of KOL nodes with a low time complexity.

WeChat is a mobile messaging application that has 549 million active users as of Q1 2015, and “WeChat Moments” (WM) serves its social-networking function that allows users to post/share links of web pages. WM differs from the other social networks as it imposes many restrictions on the information diffusion process to mitigate the information overload. In this paper, we conduct a measurement study on information diffusion in the WM network by crawling and analyzing the spreading statistics of more than 160,000 pages that involve approximately 40 million users. Specifically, we identify the relationship of the number of posted pages and the number of views, the diffusion path length, the similarity and distribution of users' locations as well as their connections with the GDP of the users' province. For each individual WM page, we measure its temporal characteristics (e.g., the life time, the popularity within a time period); for each individual user, we evaluate how many of, or how likely, one's friends will view his posted pages. Our results will help the business to decide when and how to release the marketing pages over WM for better publicity.

With the rapid growth of Internet technologies, cloud computing and social networks have become ubiquitous. An increasing number of people participate in social networks and massive online social data are obtained. In order to exploit knowledge from copious amounts of data obtained and predict social behavior of users, we urge to realize data mining in social networks. Almost all online websites use cloud services to effectively process the large scale of social data, which are gathered from distributed data centers. These data are so large-scale, high-dimension and widely distributed that we propose a distributed sparse online algorithm to handle them. Additionally, privacy-protection is an important point in social networks. We should not compromise the privacy of individuals in networks, while these social data are being learned for data mining. Thus we also consider the privacy problem in this article. Our simulations shows that the appropriate sparsity of data would enhance the performance of our algorithm and the privacy-preserving method does not significantly hurt the performance of the proposed algorithm.

iBeacon is a new technology proposed by Apple using Bluetooth Low Energy (BLE), which helps mobile devices understand their position on a micro-local scale, and facilitates the delivery of location-based content to mobile users. According to the iBeacon protocol, iBeacon transmitters only do one-way broadcast communication, and thus it is difficult to authenticate the legitimacy of the transmitters. In this paper, we focus on detecting the physical attacks against iBeacon transmitters- iBeacon transmitters can be stolen, tampered, faked and reused, which interfere with the legitimate iBeacon transmission, reduce the quality of service and ultimately degrade the user experience. We develop a detection system based on Hidden Markov Model running on the server-side to detect the misbehaving iBeacon transmitters without more energy consuming. Our system achieves 85% detection accuracy on average for all physical attack actions; meanwhile it has a 5% false alarm rate for non-attack situations in our designated trace experiments, and 100% correct binary judgements in the random-trace experiments. To the best of our knowledge, this is the first work that focuses on the iBeacon physical attack problem.

The detection of face-screen distance on smartphone (i.e., the distance between the user face and the smartphone screen) is of paramount importance for many mobile applications, including dynamic adjustment of screen on-off, screen resolution, screen luminance, font size, with the purposes of power saving, protection of human eyesight, etc. Existing detection techniques for face-screen distance depend on external or internal hardware, e.g., an accessory plug-in sensor (e.g., infrared or ultrasonic sensors) to measure the face-screen distance, a built-in proximity sensor that usually outputs a coarse-grained, two-valued, proximity index (for the purpose of powering on/off the screen), etc. In this paper, we present a fine-grained detection method, called "Look Into My Eyes (LIME)", that utilizes the front camera and inertial accelerometer of the smartphone to estimate the face-screen distance. Specifically, LIME captures the photo of the user's face only when the accelerometer detects certain motion patterns of mobile phones, and then estimates the face-screen distance by looking at the distance between the user's eyes. Besides, LIME is able to take care of the user experience when multiple users are facing the phone screen. The experimental results show that LIME can achieve a mean squared error smaller than 2.4 cm in all of experimented scenarios, and it incurs a small cost on battery life when integrated into an SMS application for enabling dynamic font size by detecting the face-screen distance.

The base station (BS) in a multi-channel cognitive radio (CR) network has to broadcast to secondary (or unlicensed) receivers/users on more than one broadcast channels via channel hopping (CH), because a single broadcast channel can be reclaimed by the primary (or licensed) user, leading to broadcast failures. Meanwhile, a secondary receiver needs to synchronize its clock with the BS's clock to avoid broadcast failures caused by the possible clock drift between the CH sequences of the secondary receiver and the BS. In this paper, we propose a CH-based broadcast protocol called SASS, which enables a BS to successfully broadcast to secondary receivers over multiple broadcast channels via channel hopping. Specifically, the CH sequences are constructed on basis of a mathematical construct- the Self-Adaptive Skolem Sequence (SASS). Moreover, each secondary receiver under SASS is able to adaptively synchronize its clock with that of the BS without any information exchanges, regardless of any amount of clock drift.

In urban areas, WiFi is the most widely-deployed portal for users to acquire the broadband access. Meanwhile, phishing AP (access point)-a rogue AP that falsifies the SSID (or even the BSSID) of a legitimate corporate AP-has caused many security problems in commodity WiFi networks. Existing research on the phishing AP detection can be divided into two categories: (1) the hardware-based approach usually deploys sensors (sniffers and/or USB-based wireless adapters) and conducts radio frequency (RF) sensing at a large scale to detect the anomaly at link and physical layers; and (2) the measurement-based approach enables a laptop to determine the legitimacy of a given AP by monitoring the RTT (round trip time) of data and/or control messages. However, these approaches require the additional cost on either the hardware deployment, or periodic statistical measurements. In this paper, we present Trident, a context-based reverse authentication method for detecting phishing AP in commodity WiFi networks, which requires no extra hardware deployment or periodic statistical measurements. Specifically, Trident employs a challenge-response protocol that allows a user to (reversely) authenticate an AP by two steps: (1) sending the AP a few questions regarding three user-context features (time, location, traffic) during the user-AP interaction procedure, and (2) examining the answers returned by the AP to determine its legitimacy. Our experimental results reveal that Trident achieves a high reliability rate of 95% and a detection rate of 98% when users are connecting rogue APs in the commodity WiFi network on campus.

Learning with incomplete data remains challenging in many real-world applications especially when the data is high-dimensional and dynamic. Many imputation-based algorithms have been proposed to handle with incomplete data, where these algorithms use statistics of the historical information to remedy the missing parts. However, these methods merely use the structural information existing in the data, which are very helpful for sharing between the complete entries and the missing ones. For example, in traffic system, some group information and temporal smoothness exist in the data structure. In this paper, we propose to incorporate these structural information and develop structural feature leaning method for learning with incomplete data (SFLIC). The SFLIC model adopt a fused Lasso based regularizer and a group Lasso style regularizer to enlarge the data sharing along both the temporal smoothness level and the feature group level to fill the gap where the data entries are missing. The proposed SFLIC model is a nonsmooth function according to the model parameters, and we adopt the smoothing proximal gradient (SPG) method to seek for an efficient solution. We evaluate our model on both synthetic and real-world highway traffic datasets. Experimental results show that our method outperforms the state-of-the-art methods.

Spectrum security and enforcement is one of the major challenges that need to be addressed before spectrum sharing technologies can be adopted widely. The problem of rogue transmitters is a major threat to the viability of spectrum sharing. One approach for deterring rogue transmissions is to enable receivers to authenticate or uniquely identify transmitters. Although cryptographic mechanisms at the higher layers have been widely used to authenticate transmitters, the ability to authenticate transmitters at the physical (PHY) layer has a number of key advantages over higher layer approaches. In existing schemes, the authentication signal is added to the message signal in such a way that the authentication signal appears as noise to the message signal and vice versa. Hence, existing schemes are constrained by a fundamental tradeoff between the message signal's signal-to-noise ratio (SNR) and the authentication signal's SNR. In this paper, we extend the precoded duobinary signaling (P-DS) technique to devise a new PHY-layer authentication scheme called P-DS for authentication (P-DSA). P-DSA exploits the redundancy introduced by P-DS to embed the authentication signal into the message signal. P-DSA is not constrained by the aforementioned tradeoff between the message and authentication signals. Our results show that P-DSA improves the detection performance compared with the prior art without sacrificing message throughput or increasing transmission power.

Mainstream indoor localization technologies rely on RF signatures that require extensive human efforts to measure and periodically recalibrate signatures. The progress to ubiquitous localization remains slow. In this study, we explore Sextant, an alternative approach that leverages environmental reference objects such as store logos. A user uses a smartphone to obtain relative position measurements to such static reference objects for the system to triangulate the user location. Sextant leverages image matching algorithms to automatically identify the chosen reference objects by photo-taking, and we propose two methods to systematically address image matching mistakes that cause large localization errors. We formulate the benchmark image selection problem, prove its NP-completeness, and propose a heuristic algorithm to solve it. We also propose a couple of geographical constraints to further infer unknown reference objects. To enable fast deployment, we propose a lightweight site survey method for service providers to quickly estimate the coordinates of reference objects. Extensive experiments have shown that Sextant prototype achieves 2-5 m accuracy at 80-percentile, comparable to the industry state-of-the-art, while covering a 150 x 75 m mall and 300 x 200m train station requires a one time investment of only 2-3 man-hours from service providers.

The lack of floor plans is a critical reason behind the current sporadic availability of indoor localization service. Service providers have to go through effort-intensive and time-consuming business negotiations with building operators, or hire dedicated personnel to gather such data. In this paper, we propose Jigsaw, a floor plan reconstruction system that leverages crowdsensed data from mobile users. It extracts the position, size, and orientation information of individual landmark objects from images taken by users. It also obtains the spatial relation between adjacent landmark objects from inertial sensor data, then computes the coordinates and orientations of these objects on an initial floor plan. By combining user mobility traces and locations where images are taken, it produces complete floor plans with hallway connectivity, room sizes, and shapes. It also identifies different types of connection areas (e.g., escalators and stairs) between stories, and employs a refinement algorithm to correct detection errors. Our experiments on three stories of two large shopping malls show that the 90-percentile errors of positions and orientations of landmark objects are about 1~2m and 5~9°, while the hallway connectivity and connection areas between stories are 100 percent correct.

Neighbor discovery is of paramount importance in mobile sensing applications and is particularly challenging if the operating frequencies of mobile devices span multiple channels. In this paper, we formulate the multi-channel neighbor discovery problem and establish a theoretical framework of it, under which we derive the performance bound of any neighbor discovery protocol guaranteeing discovery. We then develop a multi-channel discovery protocol that achieves guaranteed discovery with order-minimum worst-case discovery delay and fine-grained control of energy conservation levels.

Group signatures (GSs) is an elegant approach for providing privacy-preserving authentication. Unfortunately, modern GS schemes have limited practical value for use in large networks due to the high computational complexity of their revocation check procedures. We propose a novel GS scheme called the Group Signatures with Probabilistic Revocation (GSPR), which significantly improves scalability with regard to revocation. GSPR employs the novel notion of probabilistic revocation, which enables the verifier to check the revocation status of the private key of a given signature very efficiently. However, GSPR's revocation check procedure produces probabilistic results, which may include false positive results but no false negative results. GSPR includes a procedure that can be used to iteratively decrease the probability of false positives. GSPR makes an advantageous tradeoff between computational complexity and communication overhead, resulting in a GS scheme that offers a number of practical advantages over the prior art. We provide a proof of security for GSPR in the random oracle model using the decisional linear assumption and the bilinear strong Diffie-Hellman assumption.

The Radio Resource Control (RRC) state machine has been widely studied to improve application performance and reduce the energy consumption of smart phones. We observe that even a smart phone remains in the RRC state, there may still exist some significant performance change if it simultaneously carry on voice and data services. For example, the Round Trip Time (RTT) will get larger when a voice call comes upon, and may get even larger after finishing the voice call. We conduct in-depth study and find out the primary cause of those phenomena - smart phones may get different physical channels even in the same RRC state. In this paper, we define new states according to which physical channel is allocated to smart phones, then discover a fine-grained state machine which is hidden in the physical layer of user plane, which can explain those phenomena very well. We construct the hidden fine-grained state machine for two carriers, one only supports 3G network in most area and the other supports 4G network. The state machine can help us analyze the interference of voice to data. Using the fine-grained state machine, we also offer some suggestions on how to avoid those performance loss both from the perspective of carriers and users.

The idea of in-band full-duplex (FD) communications revives in recent years owing to the significant progress in the self-interference cancellation and hardware design techniques, which offers the potential to double spectral efficiency. However, the adaptations from lower to upper layers are highly demanded in the design of FD communication systems. In this paper, we first propose a novel medium access control (MAC) protocol on a single channel using FD techniques that allows transmitters to monitor the channel usage while transmitting, and backoff when collision happens. Specifically, imperfect sensing brought by residual self-interference (RSI) in the physical layer is taken into account in the design of the protocol, and throughput is analytical derived. Then, we extend the protocol to multichannel scenario and propose a multichannel selection mechanism based on the rate and occupancy history of each channel for FD users. Simulation results show the effectiveness of the channel selection protocol and indicate that the total throughput of the proposed FD-MAC protocol can significantly outperforms the greedy channel selection strategy based on the CSMA access mechanism.

In cognitive radio (CR) networks, “TTR”, a.k.a. time-to-rendezvous, is one of the most important metrics for evaluating the performance of a channel hopping (CH) rendezvous protocol, and it characterizes the rendezvous delay when two CRs perform channel hopping. There exists a trade-off of optimizing the average or maximum TTR in the CH rendezvous protocol design. On one hand, the random CH protocol leads to the best “average” TTR without ensuring a finite “maximum” TTR (two CRs may never rendezvous in the worst case), or a high rendezvous diversity (multiple rendezvous channels). On the other hand, many sequence-based CH protocols ensure a finite maximum TTR (upper bound of TTR) and a high rendezvous diversity, while they inevitably yield a larger average TTR. In this paper, we strike a balance in the average-maximum TTR trade-off for CR rendezvous by leveraging the advantages of both random and sequence-based CH protocols. Inspired by the neighbor discovery problem, we establish a design framework of creating a wake-up schedule whereby every CR follows the sequence-based (or random) CH protocol in the awake (or asleep) mode. Analytical and simulation results show that the hybrid CH protocols under this framework are able to achieve a greatly improved average TTR as well as a low upper-bound of TTR, without sacrificing the rendezvous diversity.

In the dynamic spectrum access (DSA) paradigm for cognitive radio networks (CRNs), one of the commonly used Medium Access Control (MAC) schemes is designed on basis of the popular carrier sensing multiple access with collision avoidance. However, this proposal suffers from two major problems that may significantly decrease the system performance: (1) collision among the secondary users (SUs) can hardly be detected, thus leading to the secondary transmission failures, and (2) SUs cannot abort transmission when collision occurs, making the long collision duration possible. In this paper, we propose a new cognitive MAC protocol for efficient DSA based on full-duplex CRNs (FD-CRNs), where SUs are able to perform simultaneous spectrum sensing and data transmission owing to full-duplex techniques. Specifically, SUs can detect the collision during transmission, so as to reduce the collision time and improve secondary network performance. Analytical results include the derivations of key design parameters such as the collision ratio with the PU, spectrum usage ratio, optimal contention window size, and the performance comparisons with the conventional DSA in half-duplex CRNs (HD-CRNs), which are further confirmed by simulation results.

In this paper, we present TapLock as a smartphone password system that exploits the finger tap events on capacitive touch screens for increasing the password's resilience to shoulder-surfing attacks (where the password input by a user can be easily observed by a bystander over the user's shoulder). TapLock captures the size and the axis length of the finger touch area on the phone screen for creating a password, which cannot be easily observed by a shoulder surfer. Our user study shows that TapLock has several advantages over existing smartphone password systems, including its strong attack resilience, small authentication delay, and haptic input feedback that improves the usability.

Nearest neighbor based nonparametric regression is a classic data-driven method for traffic flow prediction in intelligent transportation systems (ITS). Performances of those models depend heavily on the similarity or distance metric used to search nearest neighborhood. Metric learning algorithms have been developed to learn the distance metrics from data in recent years. In real-world transportation application, multiple forecasting tasks are set since there are lots of road sections and detector points in the traffic network. Previous works tend to learn only one global metric to be used for all the tasks or learn multiple local metrics for each task which may lead to under-fitting or over-fitting problem. To balance these two kinds of methods and improve the generalization of learned metrics, we propose a common metric learning algorithm under the intuition that homogenous tasks tend to have similar local metrics. Then the learned common metrics are used in common metric KNN (CM-KNN) for traffic flow prediction. Experimental results show that our algorithm to learn common metrics are reasonable and CM-KNN method for traffic flow prediction outperforms other competing methods.

Ensemble learning of neural network is a learning paradigm where ensembles of several neural networks show improved generalization capabilities that outperform those of single networks. For deep learning of multi-layer neural networks, ensemble learning is still applicable. In addition, characteristics of deep neural networks can provide potential opportunities to improve the performance of traditional neural network ensembles. In this paper, we propose an ensemble criterion of deep neural networks that is based on the reconstruction error and present two strategies to solve the most important issues in ensemble learning of neural networks: component dataset sampling and output averaging. Component training datasets are selected according to the reconstruction error instead of random bootstrap sampling or re-weighting. Moreover, for each testing instance, we can compute the reconstruction error yielded by the sub-model simultaneously with the output. The reconstruction error is used as the weights in output averaging. From the perspectives of prediction interval and confidence interval, we demonstrated that smaller reconstruction error could ensure smaller prediction interval. We also incorporate the famous structure ensemble approach “Dropout” into the proposed approach to achieve the best performance. We conduct experiments on classification and regression datasets to validate the effectiveness of our approach.

he prevalence of smart devices has promoted the popular- ity of mobile applications (a.k.a. apps) in recent years. A number of interesting and important questions remain unan- swered, such as why a user likes/dislikes an app, how an app becomes popular or eventually perishes, how a user selects apps to install and interacts with them, how frequently an app is used and how much traffic it generates, etc. This paper presents an empirical analysis of app usage behaviors collected from millions of users of Wandoujia, a leading An- droid app marketplace in China. The dataset covers two types of user behaviors of using over 0.2 million Android apps, including (1) app management activities (i.e., installa- tion, updating, and uninstallation) of over 0.8 million unique users and (2) app network traffic from over 2 million unique users. We explore multiple aspects of such behavior data and present interesting patterns of app usage. The results provide many useful implications to the developers, users, and disseminators of mobile apps.

Neighbor discovery plays a crucial role in the formation of wireless sensor networks and mobile networks where the power of sensors (or mobile devices) is constrained. Due to the difficulty of clock synchronization, many asynchronous protocols based on wake-up scheduling have been developed over the years in order to enable timely neighbor discovery between neighboring sensors while saving energy. However, existing protocols are not fine-grained enough to support all heterogeneous battery duty cycles, which can lead to a more rapid deterioration of long-term battery health for those without support. Existing research can be broadly divided into two categories according to their neighbor-discovery techniques — the quorum based protocols and the co-primality based protocols. In this paper, we propose two neighbor discovery protocols, called Hedis and Todis, that optimize the duty cycle granularity of quorum and co-primality based protocols respectively, by enabling the finest-grained control of heterogeneous duty cycles. We compare the two optimal protocols via analytical and simulation results, which show that although the optimal co-primality based protocol (Todis) is simpler in its design, the optimal quorum based protocol (Hedis) has a better performance since it has a lower relative error rate and smaller discovery delay, while still allowing the sensor nodes to wake up at a more infrequent rate.

The popularity of QR code clearly indicates the strong demand of users to acquire (or pull) further information from interested sources (e.g., a poster) in the physical world. However, existing information pulling practices such as a mobile search or QR code scanning incur heavy user involvement to identify the targeted posters. Meanwhile, businesses (e.g., advertisers) are also interested to learn about the behaviors of potential customers such as where, when, and how users show interests in their offerings. Unfortunately, little such context information are provided by existing information pulling systems. In this paper, we present Contextual-Code (C-Code) - an information pulling system that greatly relieves users' efforts in pulling information from targeted posters, and in the meantime provides rich context information of user behavior to businesses. C-Code leverages the rich contextual information captured by the smartphone sensors to automatically disambiguate information sources in different contexts. It assigns simple codes (e.g., a character) to sources whose contexts are not discriminating enough. To pull the information from an interested source, users only need to input the simple code shown on the targeted source. Our experiments demonstrate the effectiveness of C-Code design. Users can effectively and uniquely identify targeted information sources with an average accuracy over 90%.

With the booming exploitation of WiFi networks based on the conventional CSMA/CA access scheme, the frequent long collision period becomes unbearable. To better utilize the WiFi spectrum, in this poster, we propose a novel WiFi protocol with the assistance of full-duplex (FD) technique that allows users to sense the spectrum while transmitting, and stop transmission once collision is detected. Analytical and simulated results show that the average collision length is sharply reduced and the normalized throughput can be significantly improved by the proposed FD-WiFi protocol compared with the conventional CSMA/CA.

Given the enormous demands for location based applications and service, localization technologies, which estimate accurate locations of the mobile users, have been developed rapidly outdoors (e.g., GPS) and indoors (e.g., WiFi fingerprinting). However, in half-open areas where existing studies are rarely conducted, either the outdoor or indoor localization technique fails to achieve a satisfactory performance due to the short of signals. In this paper, we propose a hybrid localization method tailored for the use in half-open areas. Specifically, we present two individual probabilistic localization techniques, which are extended from conventional GPS and WiFi fingerprinting. Moreover, our hybrid approach combines the locations estimated by the two techniques, and modifies the estimation by an enhanced Kalman filter leveraging the user movement capacity as well as the location probability. The experiment results show our hybrid localization method outperforms the conventional GPS and WiFi fingerprinting based methods in half-open areas.

Two players wishing to communicate are placed each in a room with N telephones connecting the two rooms. The players do not know how the telephones are interconnected. In each round, each player picks up a phone and says “hello” until when they hear each other. The problem is to devise an algorithm minimising the delay to establish communication. The above problem, called the Telephone Coordination Game, also termed as the Telephone Problem, is of fundamental importance in distributed algorithm design. In this paper, we investigate a generalised version where among N telephones, only a subset can establish communication between the two players. We are interested in devising the deterministic strategy achieving bounded rendezvous delay and minimising the worst-case rendezvous delay. Specifically, we first establish the lower-bound of worst-case rendezvous delay. We then characterise the structure of the phone pick sequences that can guarantee rendezvous without any prior coordination. Assuming each player has a globally unique ID, we further devise a deterministic strategy that (1) guarantees rendezvous between the players regardless of their telephone labeling functions and their relative time difference and (2) approaches the performance bound within a constant factor proportional to the ID length.

Recent advances in spectrum access technologies, such as cognitive radios, have made spectrum sharing a viable option for addressing the spectrum shortage problem. However, these advances have also contributed to the increased possibility of "hacked" or "rogue" radios causing harm to the spectrum sharing ecosystem by causing significant interference to other wireless devices. One approach for countering such threats is to employ a scheme that can be used by a regulatory entity (e.g., FCC) to uniquely identify a transmitter by authenticating its waveform. This enables the regulatory entity to collect solid evidence of rogue transmissions that can be used later during an adjudication process. We coin the term Blind Transmitter Authentication (BTA) to refer to this approach. Unlike in the existing techniques for PHY-layer authentication, in BTA, the entity that is authenticating the waveform is not the intended receiver. Hence, it has to extract and decode the authentication signal "blindly" with little or no knowledge of the transmission parameters. In this paper, we propose a novel BTA scheme called Frequency offset Embedding for Authenticating Transmitters (FEAT). FEAT embeds the authentication information into the transmitted waveform by inserting an intentional frequency offset. Our results indicate that FEAT is a practically viable approach and is very robust to harsh channel conditions. Our evaluation of FEAT is based on theoretical bounds, simulations, and indoor experiments using an actual implementation.

Adverse Drug Reactions (ADRs) has become a worldwide problem that draws the attention of people from all racial and ethnic groups. The number of deaths caused by ADRs has greatly increased and led to many drug withdrawals in the last decades. Recent research findings indicate that most ADRs can be effectively prevented to some extent by using computer-aided information technologies. Though many spontaneous reporting systems (SRSs) have been built to enhance the pharma-covigilance, the ADRs data is still very sparse because the large amount of reports obtained from consumers contains insufficient hints to identify a possible causal relationship between an adverse event and drug. Based on this motivation, we developed Adverse-Tracking, a spontaneous reporting system of ADRs via crowd-sourcing. Our proposed system interacts with consumers through a Q&A interface and collects the ADR reports. The decision tree support vector machine (DTSVM) based on the genetic algorithm is used in our system to automate the Q&A procedure. We carried out experiments to evaluate the performance at Peking University First Hospital. As demonstrated by the results, our system is an efficient tool to track and discover adverse events in the consumers' reports of ADRs, which facilitates the detection of “signal”.

Mainstream indoor localization technologies rely on RF signatures that require extensive human efforts to measure and periodically re-calibrate. Although recent crowdsourcing based work has started to address the issue, incentives are still lacking for wide user adoption. Thus the progress to ubiquitous localization remains slow. In this paper, we explore an alternative approach that leverages environmental physical features such as store logos or wall posters. A user uses a smartphone to obtain relative position measurements to such static reference points for the system to triangulate the user location. We study the principle of such localization, determine the suitable sensor, and devise guidelines for the user to choose reference points for better accuracy. To enable fast deployment, we propose a lightweight site survey method for service providers to quickly estimate the coordinates of reference points. We incorporate and enhance image matching algorithms with a heuristic technique to automatically identify chosen reference points at high accuracy. Extensive experiments have shown that the prototype achieves 4-5m accuracy at 80-percentile, comparable to the industry state-of-the-art, while covering a 150×75m mall and 300×200m train station requires a one time investment of only 2-3 man-hours from service providers.

The lack of floor plans is a critical reason behind the current sporadic availability of indoor localization service. Service providers have to go through effort-intensive and time-consuming business negotiations with building operators, or hire dedicated personnel to gather such data. In this paper, we propose Jigsaw, a floor plan reconstruction system that leverages crowdsensed data from mobile users. It extracts the position, size and orientation information of individual landmark objects from images taken by users. It also obtains the spatial relation between adjacent landmark objects from inertial sensor data, then computes the coordinates and orientations of these objects on an initial floor plan. By combining user mobility traces and locations where images are taken, it produces complete floor plans with hallway connectivity, room sizes and shapes. Our experiments on 3 stories of 2 large shopping malls show that the 90-percentile errors of positions and orientations of landmark objects are about 1~2m and 5~9°, while the hallway connectivity is 100% correct.

Existing code designs for display-camera based visual communication all have an all-or-nothing behavior, i.e., they assume the entire code must be decoded. However, diverse operational conditions due to device hardware diversity (in camera resolution and frame rate) and distance range motivate more scalable designs. In this paper, we borrow the notion of hierarchical modulation from traditional RF communication, and design Strata, a layered coding scheme for visual communication. Strata can support a range of frame capture resolutions and rates, and deliver information rates correspondingly. Strata embeds information at multiple granularity into the same code area spatially or the same frame interval temporally. It ensures all layers are decodable independently, by controlling the amount of interference between adjacent layers. Further, our design is recursive and extends readily to generate more layers. Compared with existing codes, it significantly extends the operational range, though at the expense of less capacity than a single-layer code.

In cognitive radio (CR) networks, a pair of CR nodes have to ``rendezvous'' on a common channel for link establishment. Channel hopping (CH) protocols have been proposed for creating rendezvous over multiple channels to reduce the possibility of rendezvous failures caused by the detection of primary user signals. Rendezvous within a minimal bounded time over multiple channels is a challenging problem in heterogeneous CR networks where two CR nodes may have asynchronous clocks, different sensing capabilities, no common universal channel set, and heterogeneous channel index systems. In this paper, we present a systematic approach using group theory for designing CH protocols that guarantee the maximum number of rendezvous channels and the minimal time-to-rendezvous (TTR) in heterogeneous environments. We derive the minimum upper bound of TTR, and propose two types of rendezvous protocols that are independent of environmental heterogeneity. Analytical and simulation results show that these protocols are resistant to rendezvous failures under various network conditions.

Neighbor discovery is of paramount importance in mobile sensing applications that rely heavily on data timely collected and shared among nearby users. Guaranteed discovery with bounded latency and supporting heterogenous duty cycles to provide fine-grained control of energy conservation levels are among the most crucial requirements in the design of efficient neighbor discovery protocols. While simultaneously satisfying these two requirements is non-trivial, the situation is exacerbated if the operating frequencies of mobile devices span multiple channels and discovery occurs only if nodes switch to the same channel. In this paper, we formulate this problem as heterogeneous multi-channel neighbor discovery problem and establish a theoretical framework of the problem, under which we derive the performance bound of any neighbor discovery protocol. Based on the theoretical results, we then develop Mc-Dis (Multi-channel Discovery), a novel multi-channel discovery protocol that (1) achieves guaranteed discovery with order-minimal worst-case discovery delay and (2) supports almost all duty cycles to provide fine-grained control of energy conservation levels.

Due to intermittent connectivity and uncertain node mobility, opportunistic message forwarding algorithms have been widely adopted in delay tolerant networks (DTNs). While existing work proposes practical forwarding algorithms in terms of increasing the delivery rate and decreasing data overhead, little attention has been drawn to the control overhead induced by the algorithms. The control overhead could, however, make the forwarding algorithms infeasible when the network size scales. In this paper, we are interested in increasing scalability by reducing control overhead, while retaining the state-of-the-art forwarding performances. The basic idea is to use locality-sensitive hashing to map each node as a hash-code, and use these hash-codes to compute the pair-wise similarity that guides the forwarding decisions. The proposed SOFA algorithms have reduced control overhead and competitive forwarding performance, which are verified by extensive real trace-driven simulations.

We present VeLoc, a smartphone-based vehicle localization approach that tracks the vehicle's parking location without GPS or WiFi signals. It uses only the embedded accelerometer and gyroscope sensors. VeLoc harnesses constraints imposed by the map and landmarks (e.g., speed bumps) recognized from inertial data, employs a Bayesian filtering framework to estimate the location of the vehicle. We have conducted experiments in three parking structures of different sizes and configurations, using three vehicles and three kinds of driving styles. We find that VeLoc can always localize the vehicle within 10m, which is sufficient for the driver to trigger a honk using the car key.

Recently, cardiovascular disease (CVD) has become one of the leading death causes worldwide, and it contributes to 41% of all deaths each year in China. This disease incurs a cost of more than 400 billion US dollars in China on the healthcare expenditures and lost productivity during the past ten years. It has been shown that the CVD can be effectively prevented by an interdisciplinary approach that leverages the technology development in both IT and electrocardiogram (ECG) fields. In this paper, we present WE-CARE , an intelligent telecardiology system using mobile 7-lead ECG devices. Because of its improved mobility result from wearable and mobile ECG devices, the WE-CARE system has a wider variety of applications than existing resting ECG systems that reside in hospitals. Meanwhile, it meets the requirement of dynamic ECG systems for mobile users in terms of the detection accuracy and latency. We carried out clinical trials by deploying the WE-CARE systems at Peking University Hospital. The clinical results clearly showed that our solution achieves a high detection rate of over 95% against common types of anomalies in ECG, while it only incurs a small detection latency around one second, both of which meet the criteria of real-time medical diagnosis. As demonstrated by the clinical results, the WE-CARE system is a useful and efficient mHealth (mobile health) tool for the cardiovascular disease diagnosis and treatment in medical platforms.

Cardiovascular disease (CVD), principally heart disease and stroke, has become the worldwide leading killer for people of all racial and ethnic groups. In China, this disease contributes 41% to all deaths each year, and it costs the country more than 400 billion US dollars in last decade, including health expenditures and lost productivity, which continues to grow as the population size increases. Recent research findings indicate that CVD can be effectively prevented to some extent by an interdisciplinary approach that combines ICT (Information and Communication Technology) and healthcare applications. Based on this motivation, we developed WE-CARE, a Wearable Efficient teleCARdiology systEm using mobile 7-lead ECG devices. Our WE-CARE system surpasses existing resting ECG systems that reside in hospitals owing to its improved mobility brought by wearable and mobile ECG devices. Meanwhile, it outperforms those conventional dynamic 1-lead or 3-lead ECG systems for mobile users in terms of the appropriate ECG information required for clinical proposes. We carried out clinical trials by deploying the WE-CARE systems at People Hospital of Peking University. The results showed that our solution achieves a high detection rate over 95% against common types of anomalies in ECG signals, while its risk alert delay is limited around one second, both of which match the criteria of real-time healthcare monitoring very well. As demonstrated by the results, the WE-CARE system is a useful and efficient tool for the cardiovascular disease prevention and daily monitoring.

We consider the distributed channel allocation problem in an asymmetrical opportunistic spectrum access (OSA) system where each secondary user possibly has different channel reward even in the same channel due to geographic dispersion. We formulate this problem as a Gale-Shapley stable theorem using game theory to optimize the sum reward of all secondary users. It is challenging to achieve the stable matching of user-channel pairs without centralized control and prior knowledge of channel availability statistics. In this paper, we present a novel decentralized order-optimal learning Gale-Shapley scheme (OLGS) in which secondary users learn from their local history data and individually adjust their behaviors in a time-varying OSA system. The proposed scheme eliminates collisions among secondary users by a one-to-one user-channel matching policy. It also achieves stable spectral allocations using learning method without assuming known channel parameters and independent of information exchange among secondary users. Simulation results show that the system regret of the OLGS solution grows with time at the logarithmic order with low complexity.

In decentralized cognitive radio (CR) networks, establishing a link between a pair of communicating nodes requires that the radios "rendezvous” in a common channel—such a channel is called a rendezvous channel—to exchange control information. When unlicensed (secondary) users opportunistically share spectrum with licensed (primary or incumbent) users, a given rendezvous channel may become unavailable due to the appearance of licensed user signals. Ideally, every node pair should be able to rendezvous in every available channel (i.e., maximize the rendezvous diversity) so that the possibility of rendezvous failures is minimized. Channel hopping (CH) protocols have been proposed previously for establishing pairwise rendezvous. Some of them enable pairwise rendezvous over all channels but require global clock synchronization, which may be very difficult to achieve in decentralized networks. Maximizing the pairwise rendezvous diversity in decentralized CR networks is a very challenging problem. In this paper, we present a systematic approach for designing CH protocols that maximize the rendezvous diversity of any node pair in decentralized CR networks. The resulting protocols are resistant to rendezvous failures caused by the appearance of primary user (PU) signals and do not require clock synchronization. The proposed approach, called asynchronous channel hopping (ACH), has two noteworthy features: 1) any pair of CH nodes are able to rendezvous on every channel so that the rendezvous process is robust to disruptions caused by the appearance of PU signals; and 2) an upper bounded time-to-rendezvous (TTR) is guaranteed between the two nodes even if their clocks are asynchronous. We propose two optimal ACH designs that maximize the rendezvous diversity between any pair of nodes and show their rendezvous performance via analytical and simulation results.

In this paper, we present an efficient routing protocol for Mobile Hybrid Wireless Networks (MHWNs), which consists of an infrastructure wireless network and a few mobile ad hoc networks. MHWNs have several advantages over traditional wireless networks (such as cellular networks and WLANs). For example, MHWNs can achieve higher throughput, larger coverage, and better load balancing cross cells. In this paper, we present an efficient routing protocol for MHWNs. The protocol utilizes node location information, moving speed, and remaining battery life for routing decision. The protocol is energy efficient (for mobile nodes) and can find robust routing path. We evaluate its performance by NS-2 simulations. Our results show that the protocol significantly reduces the routing overhead, and the routing path is relatively stable.

In Cognitive Radio (CR) networks, establishing a link between a pair of communicating nodes requires that their radios are able to “rendezvous” on a common channel (a.k.a. a rendezvous channel). When unlicensed (secondary) users opportunistically share spectrum with licensed (primary or incumbent) users, a given rendezvous channel may become unavailable due to the appearance of licensed user signals, which makes rendezvous impossible. Ideally, any node pair should be able to rendezvous over every available channel to minimize the possibility of such rendezvous failures. Channel hopping (CH) protocols have been proposed previously for establishing pairwise rendezvous. Some of them enable pairwise rendezvous over all channels but require global clock synchronization, which is very difficult to achieve in decentralized networks. In this paper, we present a systematic approach, called asynchronous channel hopping (ACH), for designing CH-based rendezvous protocols for decentralized CR networks. The resulting protocols are resistant to rendezvous failures caused by the appearance of primary user signals and do not require clock synchronization. We propose an optimal ACH design that maximizes the rendezvous probability between any pair of nodes, and show its rendezvous performance via simulation results.

In decentralized cognitive radio (CR) networks, enabling the radios to establish a control channel (i.e., "rendezvous" to establish a link) is a challenging problem. The use of a dedicated common control channel simplifies the rendezvous process but may not be feasible in many opportunistic spectrum sharing scenarios due to the dynamically changing availability of all the channels, including the control channel. To address this problem, researchers have proposed the use of channel hopping protocols for enabling rendezvous in CR networks. Most, if not all, of the existing channel hopping schemes only provide ad hoc approaches for generating channel hopping sequences and evaluating their properties. In this paper, we present a systematic approach, based on quorum systems, for designing and analyzing channel hopping protocols for the purpose of control channel establishment. The proposed approach, called Quorum-based Channel Hopping (QCH) system, can be used for implementing rendezvous protocols in CR networks that are robust against link breakage caused by the appearance of incumbent user signals. We describe two synchronous QCH systems under the assumption of global clock synchronization, and two asynchronous channel hopping systems that do not require global clock synchronization. Our analytical and simulation results show that the proposed channel hopping schemes outperform existing schemes under various network conditions.

IEEE 802.22 is the first wireless standard based on cognitive radio (CR) technology. It defines the air interface for a wireless regional area network (WRAN) that uses fallow segments of the TV broadcast bands. CR technology enables unlicensed users in WRANs to utilize licensed (incumbent) spectrum bands on a non-interference basis to incumbent users. The coexistence between incumbent users and unlicensed users is referred to as incumbent coexistence. On the other hand, the coexistence between unlicensed users in different WRAN cells is referred to as self-coexistence. 802.22 defines several inter-base station (BS) dynamic resource sharing mechanisms to enable overlapping cells to share spectrum. However, those mechanisms do not adequately address some of the key issues concerning incumbent and self coexistence. In this paper, we propose an inter-BS coexistence-aware spectrum sharing (CASS) protocol for overlapping 802.22 cells that takes into account coexistence requirements. We show that the proposed protocol outperforms 802.22's self-coexistence solutions using simulation results. To the best of our knowledge, the work presented here is the first systematic study of the self-coexistence problem in the context of 802.22 WRANs.

Establishing a control channel for medium access control is a challenging problem in multi-channel and dynamic spectrum access (DSA) networks. In the design of multi-channel MAC protocols, the use of channel (or frequency) hopping techniques (a.k.a. parallel rendezvous) have been proposed to avoid the bottleneck of a single control channel. In DSA networks, the dynamic and opportunistic use of the available spectrum requires that the radios are able to "rendezvous" -- i.e., find each other to establish a link. The use of a dedicated global control channel simplifies the rendezvous process but may not be feasible in many opportunistic spectrum sharing scenarios due to the dynamically changing availability of all the channels, including the control channel. To address this problem, researchers have proposed the use of channel hopping protocols for enabling rendezvous in DSA networks.

Distributed spectrum sensing (DSS) enables a Cognitive Radio (CR) network to reliably detect licensed users and avoid causing interference to licensed communications. The data fusion technique is a key component of DSS. We discuss the Byzantine failure problem in the context of data fusion, which may be caused by either malfunctioning sensing terminals or Spectrum Sensing Data Falsification (SSDF) attacks. In either case, incorrect spectrum sensing data will be reported to a data collector which can lead to the distortion of data fusion outputs. We investigate various data fusion techniques, focusing on their robustness against Byzantine failures. In contrast to existing data fusion techniques that use a fixed number of samples, we propose a new technique that uses a variable number of samples. The proposed technique, which we call Weighted Sequential Probability Ratio Test (WSPRT), introduces a reputation-based mechanism to the Sequential Probability Ratio Test (SPRT). We evaluate WSPRT by comparing it with a variety of data fusion techniques under various network operating conditions. Our simulation results indicate that WSPRT is the most robust against the Byzantine failure problem among the data fusion techniques that were considered.

Denial-of-Service (DoS) attacks pose a major threat to the availability of wireless ad hoc networks. Fault tolerant operation of wireless ad hoc networks will depend on the placement of DoS countermeasures in sufficiently robust form. In this paper, we describe a novel type of DoS attack called the Stasis Trap attack, and propose a technique for detecting such an attack. Stasis Trap attack has two distinguishing characteristics-it has a cross-layer design, and is stealthy. The Stasis Trap attack has a cross-layer design in that it is launched from the MAC layer but its aim is to degrade the end-to-end throughput of flows at the transport layer by exploiting TCP's congestion-control mechanism. Specifically, an adversary launches a Stasis Trap attack against neighboring nodes by periodically preempting the wireless channel in order to cause large variations in the round trip time (RTT) of TCP flows. Channel preemptions are carried out by manipulating the back-off mechanism of the Distributed Coordinating Function of the 802.11 MAC protocol. The periodic preemptions induce large RTT variations in the TCP flows that are within the transmission range of the adversary. This in turn causes a significant drop in the throughput of those flows, thereby creating a "stasis trap" around the adversary that entangles TCP flows. The aforementioned attack severely degrades end-to-end throughput but has very little effect on MAC-layer throughput, and hence it is very hard to detect at the MAC layer, which is its point of attack. In this sense, this attack is stealthy. To detect the Stasis Trap attack, we propose a minimax robust decentralized detection framework with robust hypothesis testing.