Quantization is a pivotal technique for enhancing communication efficiency in Federated Learning (FL). Traditional quantization methods often set uniform intervals, may fail to adequately characterize non-uniform data distributions, thus leading to substantial estimation errors and degrated model performance. Non-uniform quantization can better solve the problem. However, when applied to FL, it would bring additional communication overheads for the alignment of parameter distributions among distributed models. To address this issue, we propose Bisection Interval Quantization (BIQ), a novel non-uniform quantization framework for FL with great communication efficiency. In particular, BIQ works by optimizing the interval selection through recursive bisection among distributed clients without extra parameter communication. For scenarios involving amounts of boundary inputs, we further design Weighted Bisection Interval Quantization (WBIQ), which incorporates maximum likelihood estimation to refine boundary value reconstruction to enhance the estimation quality of boundary inputs. Our theoretical analysis rigorously establishes, for the first time under biased quantization conditions, that both BIQ and WBIQ achieve tighter error bounds and enhanced stability. Extensive experiments validate that both BIQ and WBIQ significantly accelerate the convergence of FL model training when compared to the state-of-the-art quantizers under both convex and non-convex settings.

Test-Time Adaptation (TTA) has recently emerged as a promising research direction, enabling vision-language models (VLMs) to adapt to unlabeled test data in zero-shot settings. Among TTA approaches, test-time prompt tuning has shown great potential for enhancing the practical applicability of VLMs. However, existing methods typically either focus on adapting a single modality or apply uniform optimization to both modalities, without explicitly defining modality-specific optimization objectives. Such a one-size-fits-all strategy often results in suboptimal performance under test-time conditions. To address this limitation, we propose Dual-modality Heterogeneous Prompt Tuning (DHPT), a novel framework designed to simultaneously capture fine-grained textual semantics and alleviate domain shift noise in the visual modality. Specifically, we leverage a large language model to provide textual cognition guidance for the text encoder, while on the vision side, we develop a lightweight calibration module that adaptively mitigates domain shift noise across different scales. Furthermore, we introduce a cluster-tight optimization objective that enhances the stability and generalizability of prompt tuning under distribution shifts. Extensive experiments conducted on 11 benchmark datasets demonstrate that DHPT consistently and significantly outperforms existing TTA methods for VLMs.

Local Differential Privacy (LDP) enables massive data collection and analysis while protecting end users' privacy against untrusted aggregators. It has been applied to various data types (e.g., categorical, numerical, and graph data) and application settings (e.g., static and streaming). Recent findings indicate that LDP protocols can be easily disrupted by poisoning or manipulation attacks, where an attacker can leverage injected/corrupted fake users to send crafted data to the aggregator in order to manipulate the final estimate of the aggregator. However, current attacks primarily target static protocols, neglecting the security of LDP protocols in the streaming settings. Our research fills the gap by developing novel fine-grained manipulation attacks to LDP protocols for data streams. By reviewing the attack surfaces in existing algorithms, we introduce a unified attack framework with composable modules, which can manipulate the LDP estimated stream toward a target stream. Our attack framework can adapt to state-of-the-art streaming LDP algorithms with different analytic tasks (e.g., frequency and mean) and LDP models (event-level, user-level, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$w$</tex-math></inline-formula>-event level). We verify our attacks theoretically and validate them through extensive experiments on real-world datasets. Finally, we explore a possible defense mechanism for mitigating our attacks.

Transformers are increasingly becoming the dominant model in the field of computer vision, thereby catalyzing research efforts aimed at unraveling the interpretability of transformers. Existing explanation techniques, whether attention-based or gradient-based, furnish a dependable approach to quantifying the impact of input features on model predictions from the perspective of dissecting self-attention mechanisms. However, current research overlooks the block-to-block constraints, which result in misdirection in attribution. In this work, we propose a block-wise constraints-free interpretation method, Independent Block Level Attribution (IBA), which maintains the relative independence of each block in the model. The IBA reconfigures the model into mutually unaffected class-semantic blocks via class-semantic relevance, each of which performs the attribution computation independently, thus minimizing the influence of inter-block constraints on the model interpretation performance. Extensive perturbation and segmentation experiments unequivocally demonstrate the superiority of our method, showcasing its significant outperformance compared to current interpretation methods. Additionally, we also apply IBA to the text transformer to demonstrate the generalization of our method. Our code is available athttps://github.com/qinanin/TMM-IBA.git.

Graph federated learning enables the collaborative extraction of high-order information from distributed subgraphs while preserving the privacy of raw data. However, graph data often exhibits overlap among different clients. Previous research has demonstrated certain benefits of overlapping data in mitigating data heterogeneity. However, the negative effects have not been explored, particularly in cases where the overlaps are imbalanced across clients. In this paper, we uncover the unfairness issue arising from imbalanced overlapping subgraphs through both empirical observations and theoretical reasoning. To address this issue, we propose FairGFL (FAIRness-aware subGraph Federated Learning), a novel algorithm that enhances cross-client fairness while maintaining model utility in a privacy-preserving manner. Specifically, FairGFL incorporates an interpretable weighted aggregation approach to enhance fairness across clients, leveraging privacy-preserving estimation of their overlapping ratios. Furthermore, FairGFL improves the tradeoff between model utility and fairness by integrating a carefully crafted regularizer into the federated composite loss function. Through extensive experiments on four benchmark graph datasets, we demonstrate that FairGFL outperforms four representative baseline algorithms in terms of both model utility and fairness.

Network topology planning is an essential multi-phase process to build and jointly optimize the multi-layer network topologies in wide-area networks (WANs). Most existing practices target single-phase/layer planning, and are incapable of satisfying all rigorous topological structure constraints (e.g., dual-homing rings) defined by network standards and operators, especially in large-scale networks. These significantly limit their usability and performance in production networks. We consider a general topology planning problem with typical structure constraints over three essential phases (greenfield, reconfiguration, and site expansion) and topological layers (optical, IP, and routing topologies). We present, T3Planner, a novel practical solver to this problem in production. Specifically, we develop a structure-driven encoder based on graph neural network (GNN) for concise structure encoding, and design a new learning framework with optical-centric layer compression/reconstruction and rule-aided reinforcement learning (RL) for fast convergence and high performance. Extensive experiments on nine real topologies demonstrate that T3Planner scales to large optical networks with hundreds of sites, saves 46.6% cost, and supports$3.12\times $more demand when compared to related existing approaches.

EEG-based emotion recognition (EER) has gained significant attention due to its potential for understanding and analyzing human emotions. While recent advancements in deep learning techniques have substantially improved EER, the field lacks a convincing benchmark and comprehensive open-source libraries. This absence complicates fair comparisons between models and creates reproducibility challenges for practitioners, which collectively hinder progress. To address these issues, we introduce LibEER, a comprehensive benchmark and algorithm library designed to facilitate fair comparisons in EER. LibEER carefully selects popular and powerful baselines, harmonizes key implementation details across methods, and provides a standardized codebase in PyTorch. By offering a consistent evaluation framework with standardized experimental settings, LibEER enables unbiased assessments of seventeen representative deep learning models for EER across the six most widely used datasets. Additionally, we conduct a thorough, reproducible comparison of model performance and efficiency, providing valuable insights to guide researchers in the selection and design of EER models. Moreover, we make observations and in-depth analysis on the experiment results and identify current challenges in this community. We hope that our work will not only lower entry barriers for newcomers to EEG-based emotion recognition but also contribute to the standardization of research in this domain, fostering steady development. The library and source code are publicly available athttps://github.com/XJTU-EEG/LibEER.

The advent of 5G wireless technology marks a significant milestone in telecommunications, enhancing consumer and industrial applications through Industry 4.0 technologies. The radio access network (RAN) and its downlink throughput are vital for Internet service providers. However, ensuring 5G RAN downlink throughput reliability requires robust failure diagnosis strategies for quick identification and resolution, posing challenges in cost efficiency, expert trustworthiness, and adaptability. We present 5G RAN Downlink Throughput Abnormality Diagnosis (5GR-DTAD), a diagnostic framework that fusing domain expertise with machine learning techniques, incorporating both feed-forward and long short-term memory (LSTM) neural networks. Experimental results on real-world data from multiple base stations show that 5GR-DTAD outperforms existing methods in precision, recall, and F1 scores by up to 29.85%, 42.28%, and 35.74%, respectively. 5GR-DTAD improves diagnostic accuracy while minimizing reliance on labeled data, offering an adaptable and cost-effective solution for various 5G RAN conditions.

The critical importance of monitoring and recognizing human emotional states in healthcare has led to a surge in proposals for EEG-based multimodal emotion recognition in recent years. However, practical challenges arise in acquiring EEG signals in daily healthcare settings due to stringent data acquisition conditions, resulting in the issue of incomplete modalities. Existing studies have turned to knowledge distillation as a means to mitigate this problem by transferring knowledge from multimodal networks to unimodal ones. However, these methods are constrained by the use of a single teacher model to transfer integrated feature extraction knowledge, particularly concerning spatial and temporal features in EEG data. To address this limitation, we propose a multi-teacher knowledge distillation framework enhanced with a Large Language Model (LLM), aimed at facilitating effective feature learning in the student network by transferring knowledge of extracting integrated features. Specifically, we employ an LLM as the teacher for extracting temporal features and a graph convolutional neural network for extracting spatial features. To further enhance knowledge distillation, we introduce causal masking and a confidence indicator into the LLM to facilitate the transfer of the most discriminative features. Extensive testing on the DEAP and MAHNOB-HCI datasets demonstrates that our model outperforms existing methods in the modality-incomplete scenario. This study underscores the potential application of large models in this field.

In mobile edge computing (MEC), resource scheduling is crucial to task requests’ performance and service providers’ cost, involving multi-layer heterogeneous scheduling decisions. Existing MEC schedulers typically adopt static-timescale scheduling, where scheduling decisions are updated regularly at fixed intervals for all layers. The inflexible updating timescales lead to poor performance in the production networks. In this paper, we propose EdgeTimer, an unprecedented approach that automatically and adaptively determines respective updating timescales of multiple scheduling layers to achieve a better trade-off between the operation cost and service performance. Specifically, we design (i) a three-layer hierarchical deep reinforcement learning (DRL) framework for efficient learning of tightly coupled policies, (ii) a tailored multi-agent DRL algorithm for decentralized scheduling, with the convergence strictly proved, and (iii) a lightweight system defender for deterministic reliability assurance. Furthermore, we apply EdgeTimer to a wide range of Kubernetes scheduling rules, and evaluate it using production traces with different workload patterns. Through extensive trace-driven experiments, we demonstrate that EdgeTimer can significantly decrease the operation cost for service providers without sacrificing the delay performance, thereby improving overall profits, compared with the state-of-the-art approaches.

Federated Learning (FL) succeeds in collaborative and privacy-preserving ML model training among multiple distributed data owners. To maintain a healthy FL ecosystem, it is crucial to estimate the contributions of all participants fairly. Due to provable fairness, Shapley value (SV) is widely used for contribution estimation in FL. However, current studies focus on static scenarios with fixed participants and neglect the dynamic settings with the random joining or leaving of participants in practice. This paper fills the gap by proposing FedDSV, a novel contribution estimation framework for FL with dynamic participation. FedDSV supports flexible weighting mechanisms and is compatible with the SV fairness properties in dynamic scenarios. To reduce the computational complexity, we propose a Monte Carlo variant sampling method (SMC), which can adapt well to dynamic scenarios and approximate the true SVs. To evaluate the effectiveness and efficiency of our proposed approaches, extensive experiments under different settings (e.g., frequency switching, low-quality detection, etc.) are conducted on both i.i.d and non-i.i.d. distributions. Experimental results demonstrate that FedDSV can reflect the real utility contribution of data sources for dynamic FL, and SMC can approximate the exact dynamic SVs with larger similarities in a much shorter time than the state-of-the-art methods.

Network slicing architecture is expected to fulfill network applications with heterogeneous requirements through efficient slice admission control (SAC) policies. Existing SAC approaches entirely rely on current limited observations to make admission decisions, ignoring the potential impact of future demands. The short-sighted behaviors lead to poor service performance and infrastructure providers’ (InPs’) revenue in practice. In this paper, we propose OACR$^{2}$, an online SAC approach based on deep reinforcement learning (DRL) that can exploit predictable future requests to make more precise admission control decisions for the long-term revenue, and reserve proper resources accordingly. Specifically, we design three novel schemes: (i) a requirement predictor based on long short-term memory (LSTM) and a novel input-output way to predict future unforeseen requests, (ii) a DRL admission controller based on the partially observable Markov decision process model to make precise admission decisions without accurate future request information, with the convergence strictly proved, and (iii) a decision defender to guarantee decision reliability. Extensive experiments on real-world traces demonstrate that compared to the No-wait, Wait-queue, and Wait-earliest time approaches, OACR$^{2}$improves InPs’ revenue and acceptance ratio by up to 40.9% and 16.7%, respectively, without sacrificing online inference time (within 0.9 milliseconds).

Multiview clustering (MVC) has been widely studied in machine learning and data mining for its capability of improving clustering performance by fusing the information from multiview data. In the past decade, a large number of MVC methods have made impressive progress, but most of them suffer from computational burdens, especially in large-scale tasks. Binary MVC (BMVC) is proposed to address this issue by representing the large-scale high-dimensional dataset as a group of consensus and low-dimensional binary codes. However, current BMVC-based approaches generate the clustering by executing binary k-means on the obtained binary codes, which fail to capture the embedded geometric information, leading to poor clustering performance. In addition, parameter selection is another "mission impossible" in unsupervised learning tasks including MVC. To tackle these challenges, a framework of multiview clustering via partitioning the signed prototype graph (SPGMVC) is proposed in this work. The SPGMVC framework offers several contributions. First, SPGMVC is designed as a unified framework for MVC. It combines effective technologies, such as consensus binary coding, code compression (CC), signed prototype graph (SPG) partitioning, and prototype-based cluster assignment. Second, SPGMVC partitions the signed graph (SG) based on the relationships between positive and negative edges. By capturing the underlying structure of the data, this partitioning strategy improves clustering accuracy (ACC). CC techniques are applied to reduce the graph's scale, enabling further partitioning and enhancing computational efficiency. Third, SPGMVC employs an alternate minimizing strategy to efficiently handle the optimization problem. This strategy has nearly linear time and space complexity with respect to the data volume, making it suitable for large-scale tasks. Fourth, SPGMVC proposes an automatic parameter selection strategy, eliminating the need for extensive parameter exploration. Comprehensive experiments illustrate the superiority of our model. The implementation of SPGMVC is available at: https://github.com/gepingyang/PSGMVC.

Congestion control (CC) plays a pivotal role in low-latency interactive video streaming such as cloud gaming. However, existing end-to-end CC methods often cause self-induced network queuing. As a result, they may largely delay video frame transmission and undermine the user’s quality of experience. In this paper, we present a new, practical CC algorithm namedPudicathat strives to achieve near-zero queuing delay and high link utilization while respecting cross-flow fairness. Pudica introduces several judicious approaches to utilize the paced frame to probe the bandwidth utilization ratio (BUR) instead of bandwidth itself. By leveraging BUR estimations, Pudica designs a holistic bitrate adjustment policy to balance low queuing, efficiency, and fairness. We conducted thorough and comprehensive evaluations in real production networks. In comparison to the state-of-the-art methods, Pudica reduces the average and tailed frame delay by 3.1$\times$and 5.1$\times$, respectively. Meanwhile, it increases the frame bitrate by 12.1%. Pudica has been deployed in a large-scale cloud gaming platform, currently serving millions of players.

Knowledge distillation (KD), a technique widely employed in computer vision, has emerged as a de facto standard for improving the performance of small neural networks. However, prevailing KD-based approaches in video tasks primarily focus on designing loss functions and fusing cross-modal information. This overlooks the spatial-temporal feature semantics, resulting in limited advancements in model compression. Addressing this gap, our paper introduces an innovative knowledge distillation framework, with the generative model for training a lightweight student model. In particular, the framework is organized into two steps: the initial phase is Feature Representation, wherein a generative model-based attention module is trained to represent feature semantics; Subsequently, the Generative-based Feature Distillation phase encompasses both Generative Distillation and Attention Distillation, with the objective of transferring attention-based feature semantics with the generative model. The efficacy of our approach is demonstrated through comprehensive experiments on diverse popular datasets, proving considerable enhancements in video action recognition task. Moreover, the effectiveness of our proposed framework is validated in the context of more intricate video action detection task. Our code is available at https://github.com/aaai-24/Generative-based-KD.

In mobile edge computing (MEC), resource scheduling is crucial to task requests’ performance and service providers’ cost, involving multi-layer heterogeneous scheduling decisions. Existing schedulers typically adopt static timescales to regularly update scheduling decisions of each layer, without adaptive adjustment of timescales for different layers, resulting in potentially poor performance in practice.We notice that the adaptive timescales would significantly improve the trade-off between the operation cost and delay performance. Based on this insight, we propose EdgeTimer, the first work to automatically generate adaptive timescales to update multi-layer scheduling decisions using deep reinforcement learning (DRL). First, EdgeTimer uses a three-layer hierarchical DRL framework to decouple the multi-layer decision-making task into a hierarchy of independent sub-tasks for improving learning efficiency. Second, to cope with each sub-task, EdgeTimer adopts a safe multi-agent DRL algorithm for decentralized scheduling while ensuring system reliability. We apply EdgeTimer to a wide range of Kubernetes scheduling rules, and evaluate it using production traces with different workload patterns. Extensive trace-driven experiments demonstrate that EdgeTimer can learn adaptive timescales, irrespective of workload patterns and built-in scheduling rules. It obtains up to 9:1 more profit than existing approaches without sacrificing the delay performance.

Data synthesis is a promising solution to share data for various downstream analytic tasks without exposing raw data. However, without a theoretical privacy guarantee, a synthetic dataset would still leak some sensitive information in raw data. As a countermeasure, differential privacy is widely adopted to safeguard data synthesis by strictly limiting the released information. This technique is advantageous yet presents significant challenges in the vertical federated setting, where data attributes are distributed among different data parties. The main challenge lies in maintaining privacy while efficiently and precisely reconstructing the correlation between attributes. In this paper, we propose a novel algorithm called VertiMRF, designed explicitly for generating synthetic data in the vertical setting and providing differential privacy protection for all information shared from data parties. We introduce techniques based on the Flajolet-Martin (FM) sketch for encoding local data satisfying differential privacy and estimating cross-party marginals. We provide theoretical privacy and utility proof for encoding in this multi-attribute data. Collecting the locally generated private Markov Random Field (MRF) and the sketches, a central server can reconstruct a global MRF, maintaining the most useful information. Two critical techniques introduced in our VertiMRF are dimension reduction and consistency enforcement, preventing the noise of FM sketch from overwhelming the information of attributes with large domain sizes when building the global MRF. These two techniques allow flexible and inconsistent binning strategies of local private MRF and the data sketching module, which can preserve information to the greatest extent. We conduct extensive experiments on four real-world datasets to evaluate the effectiveness of VertiMRF. End-to-end comparisons demonstrate the superiority of VertiMRF.

Safety protective gear (SPG) detection based on the machine learning model plays an important role in improving outdoor personnel safety in the electric power industry. However, the detection method of transmitting video to the cloud faces a series of challenges, such as privacy disclosure and high latency. To solve this problem, we present FtlSPG, a federated transfer learning framework for SPG detection. In particular, under the three-layer pyramid architecture of “site-companyCloud-globalServer,” we propose a federated personalized model based on local batch normalization and dynamical weighting for the source domain with labeled video. Moreover, a federated domain adaptation model based on a federated deep adversarial network and model self-training is presented for the target domain with unlabeled video. Finally, we verify the effectiveness of FtlSPG in real-world power companies. Extensive experiments demonstrate that FtlSPG can significantly outperform existing schemes, in terms of privacy protection, detection precision, and response latency.

Knowledge and data dual-driven (KDDD) represents a novel paradigm that leverages the strengths of data-driven methods in feature representation and knowledge transfer, while also incorporating expertise accumulated by domain experts. This integration allows KDDD methods to enhance the interpretability, reliability, and robustness of fault diagnosis (FD) approaches, making them widely studied in the field of industrial equipment (IE) FD. Despite the existence of systematic and valuable reviews on IE FD, there remains a gap in the literature regarding the review of KDDD IE FD methods. Therefore, conducting a comprehensive investigation into KDDD IE FD methods is of utmost importance and necessity. Such an investigation will facilitate readers’ understanding of advanced technologies and enable the rapid design of effective solutions for real-world IE FD problems. In this survey, we first outline the limitations of data-driven and knowledge-based FD methods, highlighting the need for KDDD methods. Subsequently, we delve into the details of how domain knowledge can be effectively integrated with deep learning models. Additionally, we analyze challenges of KDDD methods in real-world IE FD applications, while also discussing novel solutions for prospective research directions. Finally, we conclude this survey, emphasizing the inspiration it offers to researchers interested in advancing IE FD, and its potential to stimulate practical IE FD research.

The fusion of federated learning and differential privacy can provide more comprehensive and rigorous privacy protection, thus attracting extensive interests from both academia and industry. However, facing the system-level challenge of device heterogeneity, most current synchronous FL paradigms exhibit low efficiency due to the straggler effect, which can be significantly reduced by Asynchronous FL (AFL). However, AFL has never been comprehensively studied, which imposes a major challenge in the utility optimization of DP-enhanced AFL. Here, theoretically motivated multi-stage adaptive private algorithms are proposed to improve the trade-off between model utility and privacy for DP-enhanced AFL. In particular, we first build two DP-enhanced AFL frameworks with consideration of universal factors for different adversary models. Then, we give a solid analysis on the model convergence of AFL, based on which, DP can be adaptively achieved with high utility. Through extensive experiments on different training models and benchmark datasets, we demonstrate that the proposed algorithms achieve the overall best performances and improve up to 24% test accuracy with the same privacy loss and have faster convergence compared with the state-of-the-art algorithms. Our frameworks provide an analytical way for private AFL and adapt to more complex FL application scenarios.

Bitrate adaptation (also known as ABR) is a crucial technique to improve the quality of experience (QoE) for video streaming applications. However, existing ABR algorithms suffer from severe traffic wastage, which refers to the traffic cost of downloading the video segments that users do not finally consume, for example, due to early departure or video skipping. In this paper, we carefully formulate the dynamics of buffered data volume (BDV), a strongly correlated indicator of traffic wastage, which, to the best of our knowledge, is the first time to rigorously clarify the effect of downloading plans on potential wastage. To reduce wastage while keeping a high QoE, we present a bandwidth-efficient bitrate adaptation algorithm (named BE-ABR), achieving consistently low BDV without distinct QoE losses. Specifically, we design a precise, time-aware transmission delay prediction model over the Transformer architecture, and develop a fine-grained buffer control scheme. Through extensive experiments conducted on emulated and real network environments including WiFi, 4G, and 5G, we demonstrate that BE-ABR performs well in both QoE and bandwidth savings, enabling a 60.87% wastage reduction and a comparable, or even better, QoE, compared to the state-of-the-art methods.

Mobile 360-degree video streaming has grown significantly in popularity but the quality of experience (QoE) suffers from insufficient and variable wireless network bandwidth. Recently, saliency-driven 360-degree streaming overcomes the buffer size limitation of head movement trajectory (HMT)-driven solutions and thus strikes a better balance between video quality and rebuffering. However, inaccurate network estimations and intrinsic saliency bias still challenge saliency-based streaming approaches, limiting further QoE improvement. To address these challenges, we design a robust saliency-driven quality adaptation algorithm for 360-degree video streaming, RoSal360. Specifically, we present a practical, tile-size-aware deep neural network (DNN) model with a decoupled self-attention architecture to accurately and efficiently predict the transmission time of video tiles. Moreover, we design a reinforcement learning (RL)-driven online correction algorithm to robustly compensate the improper quality allocations due to saliency bias. Through extensive prototype evaluations over real wireless network environments including commodity WiFi, 4G/LTE, and 5G links in the wild, RoSal360 significantly enhances the video quality and reduces the rebuffering ratio, thereby improving the viewer QoE, compared to the state-of-the-art algorithms.

Weakly-supervised action localization aims to recognize and localize action instancese in untrimmed videos with only video-level labels. Most existing models rely on multiple instance learning(MIL), where the predictions of unlabeled instances are supervised by classifying labeled bags. The MIL-based methods are relatively well studied with cogent performance achieved on classification but not on localization. Generally, they locate temporal regions by the video-level classification but overlook the temporal variations of feature semantics. To address this problem, we propose a novel attention-based hierarchically-structured latent model to learn the temporal variations of feature semantics. Specifically, our model entails two components, the first is an unsupervised change-points detection module that detects change-points by learning the latent representations of video features in a temporal hierarchy based on their rates of change, and the second is an attention-based classification model that selects the change-points of the foreground as the boundaries. To evaluate the effectiveness of our model, we conduct extensive experiments on two benchmark datasets, THUMOS-14 and ActivityNet-v1.3. The experiments show that our method outperforms current state-of-the-art methods, and even achieves comparable performance with fully-supervised methods.

The development of cloud and edge computing has enabled the easy access of artificial intelligence (AI) services for massive heterogeneous and resource-constrained devices. Particularly, computation-intensive AI services can be orchestrated and deployed in the cloud or edge according to varying performance and cost requirements. Nonetheless, the improved accessibility of deep learning (DL) model variants and the evolving of computational intelligence paradigms pose great challenges for orchestrating large-scale DL inference services in the cloud-edge continuum. Focusing on cloud or edge-based deployment, existing work on multi-variant service orchestration often has a limited solution space of deployment plans. To address this limitation, we first propose a novel multi-paradigm deployment model (MPDM) for service orchestration, which not only considers the model variants but also allows the co-existence of multiple paradigms for large-scale inference service deployment. The service deployment in the MPDM model is then formulated as a multiobjective optimization problem of seeking a better tradeoff among the system accuracy, service scale, and deployment cost. To solve the multiobjective optimization, we further propose a weighted metric-based constructive heuristic algorithm (WCH), which can efficiently obtain an approximately optimal Pareto frontier. Extensive experimental results have validated the effectiveness and efficiency of WCH, and revealed the impacts of both multi-paradigm deployment and edge-cloud collaborative intelligence (ECCI) paradigm on large-scale DL serving systems.

Emerging intelligent applications based on accurate and timely stream analytics require real-time CNN inference of massive data continuously generated at the pervasive end devices. Due to the resource constraints, neither computing locally at end devices nor transmitting to remote servers is competent for computation-intensive CNN inference on large-volume images in real-time. Therefore, Collaborative Inference (CI), which conducts inference sequentially from the local device to the remote server with compressed intermediate inference data, is rapidly promoted. Due to the essential communication in collaboration, the CI efficiency is sensitive to network conditions, and will degrade under the unpredictable network fluctuations in practice, which may cause a severe delay in CI and degrade the responsiveness of stream analytics. For accurate and timely stream analytics in practical fluctuating networks, we present RTCoInfer, the real-time CI framework with run-time transmission adaption considering the network conditions. Specifically, we propose a novel Switchable CNN integrating CNNs with different compression rates on the partition layer for the run-time transmission adjustment, and construct a real-time controller determining the compression rate to maintain the real-time CI for stream analytics. Extensive experiments show that, compared with state-of-the-art methods, RTCoInfer achieves better efficiency and unprecedented resilience in real-time stream analytics.

Image classification using convolutional neural networks (CNNs) is critical for broader industrial applications like defect detection. To protect sensitive data during the industrial process, increasing institutions are highly interested in training CNN classifiers collaboratively with federated learning (FL). However, the existing FL solutions cannot address the sample deficiency and heterogeneous learning resource issues at different practical institutions. In this article, we present a federated lightweight relation network (FLRN), a lightweight industrial image classifier based on our federated few-shot learning (FFSL) architecture. Results of extensive experiments considering different real-world FFSL scenarios indicate that, unlike the state-of-the-art few-shot learning method relation network (RN), the FLRN performs well on not only FL participants with mutually isolated classes of samples but also external institutions with limited samples from unseen classes. Compared to the RN with the predominating FedAvg-based FL deployment, the FLRN manages to achieve as low as$\text{29.6}\times$less client–cloud communication,$\text{5.2}\times$less computation, and$\text{22.0}\times$less storage costs of clients.

5G wireless networks are expected to satisfy different delay requirements of various traffics by network resource scheduling. Existing scheduling methods perform poorly in practice due to their unrealistic assumption on the access to the full channel state information (CSI) or the explicit mathematical expression of network delay. In this paper, we consider the delay-oriented packet scheduling problem in multi-cell 5G downlink networks with multiple users and traffic types (e.g., FTP, VoIP and video streaming), and formulate it as a partially observable Markov decision process (POMDP). We design a delay-oriented downlink scheduling framework based on deep reinforcement learning (DRL) to autonomously schedule the active traffic flows without the full channel information. Furthermore, a recurrent proximal policy optimization (RPPO) algorithm is proposed to perceive the underlying state and accelerate learning under different time granularities, with the policy gradient theorem under POMDP strictly proved. By incorporating the future traffic information provided by a proposed spatial-temporal prediction algorithm, RPPO can balance the load and achieve lower delay in real-time multi-cell multi-user scenarios. Results of extensive experiments on a realistic 5G simulator demonstrate that our framework significantly outperforms existing approaches in terms of both tail delay and average delay for up to 48% and 41.7%, respectively.

Federated learning (FL) is a promising paradigm that enables collaboratively learning a shared model across massive clients while keeping the training data locally. However, for many existing FL systems, clients need to frequently exchange model parameters of large data size with the remote cloud server directly via wide-area networks (WAN), leading to significant communication overhead and long transmission time. To mitigate the communication bottleneck, we resort to the hierarchical federated learning paradigm of HiFL, which reaps the benefits of mobile edge computing and combines synchronous client-edge model aggregation and asynchronous edge-cloud model aggregation together to greatly reduce the traffic volumes of WAN transmissions. Specifically, we first analyze the convergence bound of HiFL theoretically and identify the key controllable factors for model performance improvement. We then advocate an enhanced design of HiFlash by innovatively integrating deep reinforcement learning based adaptive staleness control and heterogeneity-aware client-edge association strategy to boost the system efficiency and mitigate the staleness effect without compromising model accuracy. Extensive experiments corroborate the superior performance of HiFlash in model accuracy, communication reduction, and system efficiency.

Mobile 360° video streaming has grown significantly in popularity but the quality of experience (QoE) suffers from insufficient wireless network bandwidth. The state-of-the-art solutions are limited by the temporal correlation assumption. Recent studies are aware of the potential of saliency to further QoE improvement, but several fundamental challenges about saliency judgment, saliency acquirement, and quality adaptation are still not fully addressed. To solve these challenges, we present SalientVR, a saliency-driven mobile 360° video streaming system integrated with gaze information. We design (i) a precise gaze-driven saliency judging criterion for mobile VR viewers, (ii) two pragmatic gaze-driven, tile-level saliency acquiring methods based on cross-user similarity and a specific content-aware deep neural network respectively, and (iii) a lightweight saliency-aware quality adaptation algorithm with a motion-assisted online correction, which is robust to wireless bandwidth vagaries and saliency bias. Moreover, we contribute a gaze-annotated dataset and a gaze-driven quality assessment metric for 360° videos. By extensive prototype evaluations (based on dataset tests and user studies), compared to alternatives, SalientVR significantly enhances the video quality and reduces the rebuffering ratio over 4G/LTE network emulations and in the wild, which achieves a 43.68% QoE improvement.

Local differential privacy (LDP) is promising for private streaming data collection and analysis. However, existing few LDP studies over streams either apply to finite streams only or may suffer from insufficient protection. This paper investigates this problem by proposing LDP-IDS, a novel w-event LDP paradigm to provide practical privacy guarantee for infinite streams. By constructing a unified error analysis, we adapt the existing budget division framework in centralized differential privacy (CDP) for LDP-IDS, which however incurs prohibitive noise and expensive communication cost. To this end, we propose a novel and extensible framework of population division and recycling, as well as online adaptive population division algorithms for LDP-IDS. We provide theoretical guarantees and demonstrate, through extensive discussions, that our proposed framework not only achieves significant reduction in utility loss and communication overhead, but also enjoys great compatibility for varied analytic tasks and flexibility of incorporating ideas of many existing stream algorithms. Extensive experiments on synthetic and real-world datasets validate the high effectiveness, efficiency, and flexibility of our proposed framework and methods.

Video object detection is a fundamental technology of intelligent video analytics for Internet of Things (IoT) applications. However, even with extraordinary detection accuracy, predominating solutions based on deep convolutional neural networks (DCNNs) cannot achieve real-time online object detection on video streams with a low end-to-end (E2E) response latency and therefore cannot be applied to proliferating latency-sensitive IoT applications like autonomous driving requiring large-scale intelligent video analytics. To address this issue, we present EC2Detect, an edge-cloud collaborative real-time online video object detection method. Specifically, we propose a tracking-assisted object detection architecture based on edge-cloud collaboration with keyframe selection, where the accurate but heavy object detection is conducted by the Cloud on sparse keyframes adaptively selected according to their semantic variation, and the lightweight object tracking is used to localize and identify objects in other frames at edge devices. Extensive experiments of our real-world prototype demonstrate that, EC2Detect significantly outperforms state-of-the-art methods in terms of processing speed (up to$4.77\times $faster), E2E latency (up to$8.12 \times $lower), and edge-cloud bandwidth occupation ($17 \times $lower) with an acceptable mAP, which can effectively support large-scale intelligent video analytics in practice. Source code of EC2Detect is available athttps://github.com/ECCDetect/ECCDetect.

Federated learning (FL) is capable of analyzing tremendous data from smart edge devices in Industrial Internet of Things (IIoTs), empowering numerous industrial applications. However, the increasing privacy concerns and deployment costs of IIoT environment have been posing new challenges for FL. This article proposes PCFed, a novel privacy-enhanced and communication-efficient FL framework to provide higher model accuracy with rigorous privacy guarantees and great communication efficiency. In particular, we develop a sampling-based intermittent communication strategy via a PID (proportional, integral, and derivative) controller on the cloud server to adaptively reduce the communication frequency. In addition, we design a budget allocation mechanism to balance the tradeoff between model accuracy and privacy loss. Then, we develop PCFed+, an enhanced variant for PCFed, with further consideration of infinite data streams on edge servers. Extensive experiments demonstrate that both PCFed and PCFed+ can significantly outperform existing schemes, in terms of communication efficiency, privacy protection, and model accuracy.

An edge-cloud collaborative intelligent (ECCI) platform is of great significance for the agile development and rapid deployment of ECCI applications, which are essential for realizing smart industry in the era of Industry 4.0. However, the existing platforms lack considering the high real-time latency demand of industrial operations, which severely hinders the development of smart industry and may even lead to severe industrial accidents. To effectively reduce the response latency of industrial applications, in this article, we propose an ECCI platform IndustEdge. It takes time-sensitive networking as the deterministic transport for the link layer, and provides an extensible ECCI orchestration component to reduce the system level latency. Furthermore, IndustEdge has an ECCI algorithm library for different collaborative modes and provides the complete life cycle management for ECCI applications. We implement platforms for both the real-world prototype and emulated-world emulation, and conduct two case studies to evaluate the effectiveness of IndustEdge.

Edge Intelligence (EI) aims at addressing concerns like response latency risen by the conflict between predominating Cloud-based deployments of computationally intensive AI applications and the expensive uploading of explosive end data. Convolutional Neural Networks (CNNs) leading the latest flourish of AI inevitably suffer from the aforementioned conflict. There emerge increasing EI-driven attempts on fast CNN inference with high accuracy in the End-Edge-Cloud (EEC) collaborative computing paradigm, where, however, neither model compression approaches for on-device inference nor collaborative inference methods across devices can effectively achieve the trade-off between latency and accuracy of End-to-End (E2E) inference. In this article, we present CNNPC that jointly partitions and compresses CNNs for fast inference with high accuracy in collaborative EEC systems. We implemented CNNPC (source code available athttps://github.com/IoTDATALab/CNNPC) and evaluated its performance within extensive real-world EEC scenarios. Experimental results demonstrate that, compared with state-of-the-art single-end and collaborative approaches, without obvious accuracy loss, collaborative inference based on CNNPC is up to$1.6\times$and$5.6\times$faster, and requires as low as$4.30\%$and$6.48\%$communications, respectively. Besides, when determines the optimal strategy, CNNPC requires as low as$0.1\%$actual compression operations that the traversal method (the only viable method providing the theoretically optimal strategy) requires.

Federated learning (FL) is an emerging privacy-preserving paradigm that enables multiple participants collaboratively to train a global model without uploading raw data. Considering heterogeneous computing and communication capabilities of different participants, asynchronous FL can avoid the stragglers effect in synchronous FL and adapts to scenarios with vast participants. Both staleness and non-IID data in asynchronous FL would reduce the model utility. However, there exists an inherent contradiction between the solutions to the two problems. That is, mitigating the staleness requires to select less but consistent gradients while coping with non-IID data demands more comprehensive gradients. To address the dilemma, this paper proposes a two-stage weighted$K$asynchronous FL with adaptive learning rate (WKAFL). By selecting consistent gradients and adjusting learning rate adaptively, WKAFL utilizes stale gradients and mitigates the impact of non-IID data, which can achieve multifaceted enhancement in training speed, prediction accuracy and training stability. We also present the convergence analysis for WKAFL under the assumption of unbounded staleness to understand the impact of staleness and non-IID data. Experiments implemented on both benchmark and synthetic FL datasets show that WKAFL has better overall performance compared to existing algorithms.

With the increasing popularity of crowdsourcing services, high-dimensional crowdsourced data provides a wealth of knowledge. Nonetheless, unprecedented privacy threats to participants have emerged, due to complex correlations among multiple attributes and the vulnerabilities of untrusted crowdsourcing servers. Differential privacy-based paradigms have been proposed to release privacy-preserving datasets with statistical approximation. Nonetheless, most existing schemes are limited when facing highly correlated attributes, and cannot prevent privacy threats from untrusted crowdsourcing servers. To address this issue, we propose two novel solutions, namelyLoCopandDR_LoCop, which guarantee local differential privacy based on the randomized response technique while synthesizing and releasing high-dimensional crowdsourced data with high data utility. Particularly,LoCopleverages copula theory to synthesize high-dimensional crowdsourced data via univariate marginal distribution and attribute dependence. Univariate marginal distribution is estimated by the Lasso-based regression algorithm from aggregated privacy-preserving bit strings. Dependencies among attributes are modeled as multivariate Gaussian copula. Based onLoCop, the enhanced solutionDR_LoCopnot only takes advantage of C-vine copula to reflect conditional dependencies among high-dimensional attributes, but also achieves dimension reduction. Extensive experiments on real-world datasets demonstrate that our solutions substantially outperform the state-of-the-art techniques in terms of both data utility and computational overhead.

The densified deployment of heterogeneous networks coexisting with a variety of overlapping cells has emerged as a viable solution for next generation wireless networks. Despite numerous advantages, the heterogeneity and denseness also raise complicated handover management issue. Nonetheless, most existing handover methods generally depend on one or more objective attributes, and rarely consider the subjective demands of personalized users and specific applications that demand differentiated services. Through decomposing the control plane and data plane, software defined network(SDN) offers a flexible architectural paradigm to overcome these challenges. In this article, we first develop an SDN-driven handover architecture that is capable of perceiving global network status and requirements from various perspectives, including the physical layer, users, and applications. Then, a context-aware multi-criteria handover mechanism is developed in the SDN edge to provide differentiated services. Considering the numerous complicated factors, the handover decision is made based on a hierarchical fuzzy inference system to process diverse attributes and vague requirements described in natural language. Finally, we evaluate the performance of our proposed scheme through a combination of extensive simulations and real-world experiments. The results demonstrate that our solution outperforms the baseline handover schemes, more efficiently providing differentiated services with respect to throughput, bandwidth cost, and application satisfaction, and is efficient and feasible in practice.

In Internet-of-Things (IoT)-driven smart-world systems, real-time crowdsourced databases from multiple distributed servers can be aggregated to extract dynamic statistics from a larger population, thus providing more reliable knowledge for our society. Particularly, multiple distributed servers in a decentralized network can realize real-time collaborative statistical estimation by disseminating statistics from their separate databases. Despite no raw data sharing, the real-time statistics could still expose the data privacy of crowdsourcing participants. For mitigating the privacy concern, while the traditional differential privacy (DP) mechanism can be simply implemented to perturb the statistics in each timestamp and independently for each dimension, this may suffer a great utility loss from the real-time and multidimensional crowdsourced data. Also, the real-time broadcasting would bring significant overheads in the whole network. To tackle the issues, we propose a novel privacy preserving and communication-efficient decentralized statistical estimation algorithm (DPCrowd), which only requires intermittently sharing the DP protected parameters with one-hop neighbors by exploiting the temporal correlations in real-time crowdsourced data. Then, with further consideration of spatial correlations, we develop an enhanced algorithm, DPCrowd+, to deal with multidimensional infinite crowd-data streams. Extensive experiments on several data sets demonstrate that our proposed schemes DPCrowd and DPCrowd+ can significantly outperform existing schemes in providing accurate and consensus estimation with rigorous privacy protection and great communication efficiency.

Latent Dirichlet Allocation (LDA) is a popular topic modeling technique for hidden semantic discovery of text data and serves as a fundamental tool for text analysis in various applications. However, the LDA model as well as the training process of LDA may expose the text information in the training data, thus bringing significant privacy concerns. To address the privacy issue in LDA, we systematically investigate the privacy protection of the main-stream LDA training algorithm based on Collapsed Gibbs Sampling (CGS) and propose several differentially private LDA algorithms for typical training scenarios. In particular, we present the first theoretical analysis on the inherent differential privacy guarantee of CGS based LDA training and further propose a centralized privacy-preserving algorithm (HDP-LDA) that can prevent data inference from the intermediate statistics in the CGS training. Also, we propose a locally private LDA training algorithm (LP-LDA) on crowdsourced data to provide local differential privacy for individual data contributors. Furthermore, we extend LP-LDA to an online version as OLP-LDA to achieve LDA training on locally private mini-batches in a streaming setting. Extensive analysis and experiment results validate both the effectiveness and efficiency of our proposed privacy-preserving LDA training algorithms.

Latency-aware service placement is promising in reducing the overall service response latency of proliferating edge-cloud collaborative smart manufacturing systems. However, intuitive latency estimators used by existing service placement approaches cannot accurately depict the nonlinear end-to-end (E2E) latency of multihop microservices with complex dependencies, which is severely hindering the effectiveness of latency-aware service placement. To address this issue, in this article, we present a microservice placement mechanism for edge-cloud collaborative smart manufacturing (MPCSM), where a microservice placement algorithm latency-aware edge-cloud collaborative placement supported by an accurate data-driven E2E latency estimation method is proposed. We build a real-world collaborative prototype, and conduct a case study on semiconductor manufacturing to elaborate the construction of our latency estimator. Results of extensive experiments demonstrate that the error of our E2E latency estimator is up to 10× less than that of existing ones, and the overall service latency with MPCSM is up to 10× less than that with existing service placement approaches.

The proliferation of mobile smart devices with ever improving sensing capacities means that human-centric Mobile Crowdsensing Systems (MCSs) can economically provide a large scale and flexible sensing solution. The use of personal mobile devices is a sensitive issue, therefore it is mandatory for practical MCSs to preserve private information (the user's true identity, precise location, etc.) while collecting the required sensing data. However, well intentioned privacy protection techniques also conceal autonomous, or even malicious, behaviors of device owners (termed as self-interested), where the objectivity and accuracy of crowdsensing data can therefore be severely threatened. The issue of data quality due to untruthful reporting in privacy-preserving MCSs has been yet to produce solutions. Bringing together game theory, algorithmic mechanism design, and truth discovery, we develop a mechanism to guarantee and enhance the quality of crowdsensing data without jeopardizing the privacy of MCS participants. Together with solid theoretical justifications, we evaluate the performance of our proposal with extensive real-world MCS trace-driven simulations. Experimental results demonstrate the effectiveness of our mechanism on both enhancing the quality of the crowdsensing data and eliminating the motivation of MCS participants, even when their privacy is well protected, to report untruthfully.

The emerging edge-cloud collaborative Deep Learning (DL) paradigm aims at improving the performance of practical DL implementations in terms of cloud bandwidth consumption, response latency, and data privacy preservation. Focusing on bandwidth efficient edge-cloud collaborative training of DNN-based classifiers, we present CDC, a Classification Driven Compression framework that reduces bandwidth consumption while preserving classification accuracy of edge-cloud collaborative DL. Specifically, to reduce bandwidth consumption, for resource-limited edge servers, we develop a lightweight autoencoder with a classification guidance for compression with classification driven feature preservation, which allows edges to only upload the latent code of raw data for accurate global training on the Cloud. Additionally, we design an adjustable quantization scheme adaptively pursuing the tradeoff between bandwidth consumption and classification accuracy under different network conditions, where only fine-tuning is required for rapid compression ratio adjustment. Results of extensive experiments demonstrate that, compared with DNN training with raw data, CDC consumes 14.9× less bandwidth with an accuracy loss no more than 1.06%, and compared with DNN training with data compressed by AE without guidance, CDC introduces at least 100% lower accuracy loss.

The real-time query of massive surveillance video data plays a fundamental role in various smart urban applications such as public safety and intelligent transportation. Traditional cloud-based approaches are not applicable because of high transmission latency and prohibitive bandwidth cost, while edge devices are often incapable of executing complex vision algorithms with low latency and high accuracy due to restricted resources. Given the infeasibility of both cloud-only and edge-only solutions, we present SurveilEdge, a collaborative cloud-edge system for real-time queries of large-scale surveillance video streams. Specifically, we design a convolutional neural network (CNN) training scheme to reduce the training time with high accuracy, and an intelligent task allocator to balance the load among different computing nodes and to achieve the latency-accuracy tradeoff for real-time queries. We implement SurveilEdge on a prototype1with multiple edge devices and a public Cloud, and conduct extensive experiments using real-world surveillance video datasets. Evaluation results demonstrate that SurveilEdge manages to achieve up to 7× less bandwidth cost and 5.4× faster query response time than the cloud-only solution; and can improve query accuracy by up to 43.9% and achieve 15.8× speedup respectively, in comparison with edge-only approaches.

Latent Dirichlet Allocation (LDA) is a popular topic modeling technique for discovery of hidden semantic architecture of text datasets, and plays a fundamental role in many machine learning applications. However, like many other machine learning algorithms, the process of training a LDA model may leak the sensitive information of the training datasets and bring significant privacy risks. To mitigate the privacy issues in LDA, we focus on studying privacy-preserving algorithms of LDA model training in this paper. In particular, we first develop a privacy monitoring algorithm to investigate the privacy guarantee obtained from the inherent randomness of the Collapsed Gibbs Sampling (CGS) process in a typical LDA training algorithm on centralized curated datasets. Then, we further propose a locally private LDA training algorithm on crowdsourced data to provide local differential privacy for individual data contributors. The experimental results on real-world datasets demonstrate the effectiveness of our proposed algorithms.

It has been widely understood that differential privacy can guarantee rigorous privacy against adversaries with arbitrary prior knowledge. However, recent studies demonstrate that this may not be true for correlated data, and indicate that three factors could influence privacy leakage: the data correlation pattern, prior knowledge of adversaries, and sensitivity of the query function. This poses a fundamental problem: what is the mathematical relationship between the three factors and privacy leakage? In this paper, we present a unified analysis of this problem. A new privacy definition, named prior differential privacy (PDP), is proposed to evaluate privacy leakage considering the exact prior knowledge possessed by the adversary. We use two models, the weighted hierarchical graph and the multivariate Gaussian model, to analyze discrete and continuous data, respectively. We demonstrate that positive, negative, and hybrid correlations have distinct impacts on privacy leakage. Considering general correlations, a closed-form expression of privacy leakage is derived for continuous data, and a chain rule is presented for discrete data. Our results are valid for general linear queries, including count, sum, mean, and histogram. Numerical experiments are presented to verify our theoretical analysis.

High-dimensional crowdsourced data collected from numerous users produces rich knowledge about our society; however, it also brings unprecedented privacy threats to the participants. Local differential privacy (LDP), a variant of differential privacy, is recently proposed as a state-of-the-art privacy notion. Unfortunately, achieving LDP on high-dimensional crowdsourced data publication raises great challenges in terms of both computational efficiency and data utility. To this end, based on the expectation maximization (EM) algorithm and Lasso regression, we first propose efficient multi-dimensional joint distribution estimation algorithms with LDP. Then, we develop a local differentially private high-dimensional data publication algorithm (LoPub) by taking advantage of our distribution estimation techniques. In particular, correlations among multiple attributes are identified to reduce the dimensionality of crowdsourced data, thus speeding up the distribution learning process and achieving high data utility. Extensive experiments on real-world datasets demonstrate that our multivariate distribution estimation scheme significantly outperforms existing estimation schemes in terms of both communication overhead and estimation speed. Moreover, LoPub can keep, on average, 80% and 60% accuracy over the released datasets in terms of support vector machine and random forest classification, respectively.

RPL, an IPv6 routing protocol for Low power Lossy Networks (LLNs), is considered to be the de facto routing standard for the Internet of Things (IoT). However, more and more experimental results demonstrate that RPL performs poorly when it comes to throughput and adaptability to network dynamics. This significantly limits the application of RPL in many practical IoT scenarios, such as an LLN with high-speed sensor data streams and mobile sensing devices. To address this issue, we develop BRPL, an extension of RPL, providing a practical approach that allows users to smoothly combine any RPL Object Function (OF) with backpressure routing. BRPL uses two novel algorithms, QuickTheta and QuickBeta, to support time-varying data traffic loads and node mobility respectively. We implement BRPL on Contiki OS, an open-source operating system for the Internet of Things. We conduct an extensive evaluation using both real-world experiments based on the FIT IoT-LAB testbed and large-scale simulations using Cooja over 18 virtual servers on the Cloud. The evaluation results demonstrate that BRPL not only is fully backward compatible with RPL (i.e., devices running RPL and BRPL can work together seamlessly), but also significantly improves network throughput and adaptability to changes in network topologies and data traffic loads. The observed packet loss reduction in mobile networks is, at a minimum, 60 and up to 1,000 percent can be seen in extreme cases.

The heavy multimedia traffic produced by mobile users poses great challenges for the mobile network operators, especially in the areas with large user densities but limited cellular network capacities (e.g. India). Recently, many studies demonstrate that exploiting the device-to- device(D2D) content sharing in offline Mobile Social Networks is a promising solution to cellular data offloading. However, such approaches are based on either unrealistic assumptions, or limited data analytics caused by small data size (e.g. hundreds of MSN users) or single-dimensional feature (e.g. human mobility only), which severely restricts their applications in practice. To address this issue, this paper performs the first large-scale data measurement and multi-feature analytics of D2D content sharing. Specifically, by using Apache Spark over a 20-server cluster, we analyze the behaviors of 30 million users (with 40 billion D2D transmissions and 16 million content files) of Xender, a leading global D2D sharing platform. Several important features are studied, including performance basics, content properties, location relations, meeting dynamics, and social characteristics. Furthermore, as a proof-of-concept study of our analytics, we also develop a multi-feature learning based framework, which demonstrates the large potentials of predicting and recommending D2D sharing activities using machine learning methods.

Wireless Sensor Networks with Mobile Sinks (WSN-MSs) are considered a viable alternative to the heavy cost of deployment of traditional wireless sensing infrastructures at scale. However, current state-of-the-art approaches perform poorly in practice due to their requirement of mobility prediction and specific assumptions on network topology. In this paper, we focus on lowdelay and high-throughput opportunistic data collection in WSN-MSs with general network topologies and arbitrary numbers of mobile sinks. We first propose a novel routing metric, Contact-Aware ETX (CA-ETX), to estimate the packet transmission delay caused by both packet retransmissions and intermittent connectivity. By implementing CA-ETX in the defacto TinyOS routing standard CTP and the IETF IPv6 routing protocol RPL, we demonstrate that CA-ETX can work seamlessly with ETX. This means that current ETX-based routing protocols for static WSNs can be easily extended to WSN-MSs with minimal modification by using CA-ETX. Further, by combing CA-ETX with the dynamic backpressure routing, we present a throughput-optimal scheme Opportunistic Backpressure Collection (OBC). Both CA-ETX and OBC are lightweight, easy to implement, and require no mobility prediction. Through test-bed experiments and extensive simulations, we show that the proposed schemes significantly outperform current approaches in terms of packet transmission delay, communication overhead, storage overheads, reliability, and scalability.

Mobile Crowdsourcing is a promising service paradigm utilizing ubiquitous mobile devices to facilitate large-scale crowdsourcing tasks (e.g., urban sensing and collaborative computing). Many applications in this domain require Device-to-Device (D2D) communications between participating devices for interactive operations such as task collaborations and file transmissions. Considering the private participating devices and their opportunistic encountering behaviors, it is highly desired to establish secure and trustworthy D2D connections in a fast and autonomous way, which is vital for implementing practical Mobile Crowdsourcing Systems (MCSs). In this paper, we develop an efficient scheme, Trustworthy Device Pairing (TDP), which achieves user-transparent secure D2D connections and reliable peer device selections for trustworthy D2D communications. Through rigorous analysis, we demonstrate the effectiveness and security intensity of TDP in theory. The performance of TDP is evaluated based on both real-world prototype experiments and extensive trace-driven simulations. Evaluation results verify our theoretical analysis and show that TDP significantly outperforms existing approaches in terms of pairing speed, stability, and security.

As a typical cyber-physical system (CPS), smart water distribution networks require monitoring of underground water pipes with high sample rates for precise data analysis and water network control. Due to poor underground wireless channel quality and long-range communication requirements, high transmission power is typically adopted to communicate high-speed sensor data streams, posing challenges for long-term sustainable monitoring. In this article, we develop the first sustainable water sensing system, exploiting energy harvesting opportunities from water flows. Our system does this by scheduling the transmission of a subset of the data streams, whereas other correlated streams are estimated using autoregressive models based on the sound-velocity propagation of pressure signals inside water networks. To compute the optimal scheduling policy, we formalize a stochastic optimization problem to maximize the estimation reliability while ensuring the system’s sustainable operation under dynamic conditions. We develop data transmission scheduling (DTS), an asymptotically optimal scheme, and FAST-DTS, a lightweight online algorithm that can adapt to arbitrary energy and correlation dynamics. Using more than 170 days of real data from our smart water system deployment and conducting in vitro experiments to our small-scale testbed, our evaluation demonstrates that Fast-DTS significantly outperforms three alternatives, considering data reliability, energy utilization, and sustainable operation.

Energy Harvesting Wireless Sensor Networks (EH-WSNs) have been attracting increasing interest in recent years. Most current EH-WSN approaches focus on sensing and networking algorithm design, and therefore only consider the energy consumed by sensors and wireless transceivers for sensing and data transmissions respectively. In this paper, we incorporate CPU-intensive edge operations that constitute in-network data processing (e.g. data aggregation/fusion/compression) with sensing and networking; to jointly optimize their performance, while ensuring sustainable network operation (i.e. no sensor node runs out of energy). Based on realistic energy and network models, we formulate a stochastic optimization problem, and propose a lightweight on-line algorithm, namely Recycling Wasted Energy (RWE), to solve it. Through rigorous theoretical analysis, we prove that RWE achieves asymptotical optimality, bounded data queue size, and sustainable network operation. We implement RWE on a popular IoT operating system, Contiki OS, and evaluate its performance using both real-world experiments based on the FIT IoT-LAB testbed, and extensive trace-driven simulations using Cooja. The evaluation results verify our theoretical analysis, and demonstrate that RWE can recycle more than 90% wasted energy caused by battery overflow, and achieve around 300% network utility gain in practical EH-WSNs.

In this paper, we study the problem of multi-resource fairness in systems with multiple users. Each user requires to run one or more complex jobs that consist of multiple interconnected tasks. A job is considered finished when all its corresponding tasks have been executed in the system. Tasks can have different resource requirements. Because of special demands on particular hardware or software, tasks can have placement constraints limiting the type of machines they can run on. We develop User-Dependence Dominant Resource Fairness (UDRF), a generalized version of max-min fairness that combines graph theory and the notion of dominant resource shares to ensure multi- resource fairness between users with complex jobs. UDRF satisfies several desirable properties including strategy proofness, which ensures that users do not benefit from misreporting their true resource demands. We propose an offline algorithm that computes optimal UDRF allocation while the scheduling process can be to be decentralize across multiple schedulers. But optimality comes at a cost, especially for systems where schedulers need to make thousands of online scheduling decisions per second. Therefore, we develop a lightweight online algorithm that closely approximates UDRF. Large-scale simulations driven by Google cluster- usage traces show that UDRF achieves better resource utilization and throughput compared to the current state-of-the-art in multi-resource fair allocation.

Security plays a vital role in promoting the practicality of Wireless Body Sensor Networks (BSNs), which provides a promising solution to precise human physiological status monitoring. A fundamental security issue in BSN is key management, including establishment and maintenance of the key system. However, current BSN key management solutions are either designed for specific phases of a BSN's life-time or restricted to strong assumptions such as homogeneous BSN composition, pre-deployed key materials, and existing secure path, which limits their applications in real-world BSNs. In this paper, we develop the Systematic Key Management (SKM) for practical BSNs, where basic human interactions are conducted for non-predeployed secure BSN initialization, and authenticated key agreement is achieved using lightweight non-pairing certificateless public key cryptography. We construct a BSN prototype consisting of self-designed motes and Android phones to evaluate the real-world performance of SKM. Through extensive simulations and test-bed experiments, we demonstrate that our lightweight SKM scheme manages to provide high security guarantee while outperforming state-of-the-art approaches in terms of both computation and storage efficiency.

The use of sensor-enabled smart phones is considered to be a promising solution to large-scale urban data collection. In current approaches to mobile phone sensing systems (MPSS), phones directly transmit their sensor readings through cellular radios to the server. However, this simple solution suffers from not only significant costs in terms of energy and mobile data usage, but also produces heavy traffic loads on bandwidth-limited cellular networks. To address this issue, this paper investigates cost-effective data collection solutions for MPSS using hybrid cellular and opportunistic short-range communications. We first develop an adaptive and distribute algorithm OptMPSS to maximize phone user financial rewards accounting for their costs across the MPSS. To incentivize phone users to participate, while not subverting the behavior of OptMPSS, we then propose BMT, the first algorithm that merges stochastic Lyapunov optimization with mechanism design theory. We show that our proven incentive compatible approaches achieve an asymptotically optimal gross profit for all phone users. Experiments with Android phones and trace-driven simulations verify our theoretical analysis and demonstrate that our approach manages to improve the system performance significantly (around 100%) while confirming that our system achieves incentive compatibility, individual rationality, and server profitability.

The papers in this special section provide the opportunity for researchers, practitioners, and application developers to review and discuss the state-of-the-art and trends of MCS (mobile crowd sensing)techniques and applications or propose new solutions. The ubiquitous sensor-rich mobile devices (e.g., smartphones, wearable devices, and smart vehicles) have been playing an increasing important role in the evolution of the Internet of Things (IoTs), which bridges the digital space and physical space at a societal scale. Their powerful computing/communication capacities, huge population, and inherent mobility make mobile-device networks a much more flexible and cost-effective IoT solution than static sensor networks.

It is predicted that billions of intelligent devices and networks, such as wireless sensor networks (WSNs), will not be isolated but connected and integrated with computer networks in future Internet of Things (IoT). In order to well maintain those sensor devices, it is often necessary to evolve devices to function correctly by allowing device management (DM) entities to remotely monitor and control devices without consuming significant resources. In this paper, we propose a lightweight RESTful Web service (WS) approach to enable device management of wireless sensor devices. Specifically, motivated by the recent development of IPv6-based open standards for accessing wireless resource-constrained networks, we consider to implement IPv6 over low-power wireless personal area network (6LoWPAN)/routing protocol for low power and lossy network (RPL)/constrained application protocol (CoAP) protocols on sensor devices and propose a CoAP-based DM solution to allow easy access and management of IPv6 sensor devices. By developing a prototype cloud system, we successfully demonstrate the proposed solution in efficient and effective management of wireless sensor devices.

Cooperative communication has been shown to have great potential in improving wireless link quality. Incorporating cooperative communications in multi-hop wireless networks has been attracting a growing interest. However, most current research focuses on either centralized solutions or schemes limited to specific network problems. In this paper, we propose a distributed framework that uses Network Utility Maximization (NUM) to optimize the following joint objectives: flow control, routing, scheduling, and relay assignment; for multi-hop wireless cooperative networks with general flow and cooperative relay patterns. We define two special graphs, Hyper Forwarding Graphs (HFG) and Hyper Conflict Graphs (HCG), to represent all possible cooperative routing policies and interference relations among the cooperative relays respectively. Based on HFG and HCG, a stochastic mixed-integer non-linear programming problem is formulated. We then propose lightweight algorithms to solve these in a fully distributed manner, and derive the theoretical performance bounds of these proposed algorithms. Simulation results verify our theoretical analysis and reveal the significant performance gains of our framework, in terms of throughput, flexibility, and scalability. To our knowledge, this is the first distributed cross-layer optimization framework for multi-hop wireless cooperative networks with general flow and cooperative relay patterns.

Understanding the optimal usage of fluctuating renewable energy in wireless sensor networks (WSNs) is complex. Lexicographic max-min (LM) rate allocation is a good solution but is nontrivial for multihop WSNs, as both fairness and sensing rates have to be optimized through the exploration of all possible forwarding routes in the network. All current optimal approaches to this problem are centralized and offline, suffering from low scalability and large computational complexity—typically solving O(N2) linear programming problems forN-node WSNs. This article presents the first optimal distributed solution to this problem with much lower complexity. We apply it to solar-powered wireless sensor networks (SP-WSNs) to achieve both LM optimality and sustainable operation. Based on realistic models of both time-varying solar power and photovoltaic-battery hardware, we propose an optimization framework that integrates a local power management algorithm with a global distributed LM rate allocation scheme. The optimality, convergence, and efficiency of our approaches are formally proven. We also evaluate our algorithms via experiments on both solar-powered MICAz motes and extensive simulations using real solar energy data and practical power parameter settings. The results verify our theoretical analysis and demonstrate how our approach outperforms both the state-of-the-art centralized optimal and distributed heuristic solutions.

Cooperative communication mechanisms have been proposed as an effective way of exploiting the spatial diversity to improve the quality of wireless transmissions. To the best of our knowledge, a number of research efforts have been paid to study how to employ diversity to the network layer routing design, realizing the minimum energy expenditure in the data transmission. However, there is a lack of a systematic strategy for evaluating the existing schemes. To address this issue, we first develop a taxonomy to summarize the existing energy-efficient cooperative routing algorithms and compare their pros and cons. In particular, we focus on the relay set selection strategies, which have great impact on energy saving. To fairly compare the performance of those schemes, we conduct theoretical analysis and derive three theorems to instruct energy-efficient cooperative routing. Our extensive experiments validate our findings. Our research summarizes the state-of-art research development and lay out future directions in this area.

Future smart cities will require sensing on a scale hitherto unseen. Fixed infrastructures have limitations regarding sensor maintenance, placement and connectivity. Employing the ubiquity of mobile phones is one approach to overcoming some of these problems. Here, mobility and social patterns of phone owners can be exploited to optimize data forwarding efficiency. The question remains, how can we stimulate phone owners to serve as data relays? In this paper, we combine network science principles and Lyapunov optimization techniques, to maximize global social profit across this hybrid sensor and mobile phone network. Sensor data packets are produced and traded (transmitted) over a virtual economic network using a lightweight social-economic-aware backpressure algorithm, combining rate control, routing, and resource pricing. Phone owners can get benefits through relaying sensor data. Our algorithm is fully distributed and makes no probabilistic/stochastic assumptions regarding mobility, topology, and channel conditions, nor does it require prediction. The global social profit achieved by our algorithm can perform close to (or better than) an ideal algorithm with perfect prediction- proven by rigorous theoretical analysis. Simulation results further demonstrate that the proposed algorithm outperforms pure backpressure and social-aware schemes; highlighting the advantage of building systems combining communication with other types of networks.

Recent advances in solar harvesting technologies pave the way for sustainable environmental-monitoring applications in the emerging solar powered wireless sensor networks (SP-WSNs). The complexities associated with the low-resourced, highly-dynamic, and vulnerable sensor nodes operating in potentially unattended or hostile environments require a high degree of self-management and automation. Guided by autonomic communication principles, this paper presents AutoSP-WSN, a novel distributed framework to achieve sustainable data collection while also optimizing end-to-end network performance for SP-WSNs. Initially, we present the energy-aware support component that provides reliable energy monitoring and prediction. This drives the power management component, which is adaptive to time-varying solar power, avoiding battery exhaustion as well as maximizing the per-node utility. Finally, to demonstrate the key design issues of the network protocol component, we propose two self-adaptive network protocols, a routing protocol SP-BCP and a rate control scheme PEA-DLEX. We show that the individual components seamlessly highly integrate as a whole, and the AutoSP-WSN framework exhibits the properties of context-awareness, distributed operation, self-configuration, self-optimization, self-protection and self-healing. Through extensive experiments on a real SP-WSN platform, and hardware-driven simulations, we show that the proposed schemes achieve substantial improvements over previous work, in terms of reliability, sustainable operation, and network utility.

Accurately measuring the available bandwidth information is critical for providing QoS assurance, especially for the bandwidth-limited 802.11-based wireless networks. However, the shared nature of wireless medium and IEEE 802.11 MAC pose great challenges for estimating the bandwidth accurately. This paper tends to tackle this issue. In particular, we first formally define the available bandwidth in IEEE 802.11 network by considering its unique characteristics. We then present our solution, Passive Available Bandwidth Estimation (PABE). In PABE, the effective link capacity is analyzed by considering the random factors in transmission, and the available channel idle time is estimated by passively monitoring the medium based on a new, lower threshold bandwidth obtained during the normal operations of IEEE 802.11. Our approach incurs very low cost to the network without any explicit message overhead. Through extensive simulation, our data validate that our approach consistently achieves much better performance than other existing algorithms in term of estimation accuracy.

Admission control plays an important role in providing Quality of Service (QoS) guarantees for wireless mesh networks (WMNs). Multipath routing can improve network performance in reliability and load balancing. However, when the multipath routing are adopted in 802.11-based WMNs, the transmission with bandwidth assurance is facing rigorous challenges. In this paper, a novel joint design of multipath routing and admission control protocol is presented, named MRAC. In MRAC, the multipath routing with bandwidth assurance is formulated as an optimization problem based on the analysis of available bandwidth and the bandwidth consumption. Based on the formulation, a heuristic solution is proposed to admit the data session through two parallel paths with bandwidth assurance. Through extensive simulations, the effectiveness of the MRAC is demonstrated in term of satisfying bandwidth requirement.