Leveraging social homophily to enhance user preference modeling, social recommendation has become a cornerstone of modern recommender systems. However, the raw social network contains inherent unreliability as it teems with noise---misclicks, bot-generated and transient ties---while many meaningful links remain unobserved. In this study, we propose DRSoRec, a dual-rectification model to rectify the raw social networks by simultaneously removing noisy signals and preserving useful information. Specifically, the invariant social rationale discovery module distills each user's influential core social circle of the current recommendation, whereas the adaptive social connection refinement module employs a mixture-of-experts structure learner to prune spurious edges and uncover latent links. A contrastive optimization objective is designed to align and mutually enhance these two modules, and the refined user representations are fused with collaborative representations generated from interactions for the final recommendation. Experiments on three public datasets confirm that DRSoRec consistently gains over state-of-the-art baselines.

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

With the development of blockchain technology, Blockchain-based Crowdsensed Data Trading (BCDT) has emerged as an attractive data exchange paradigm. Although it addresses security issues in data transactions, most recent research primarily focuses on offline scenarios, overlooking the critical importance of enabling real-time online data trading, where it suffers from dynamic worker participation and potential malicious attacks. In this paper, we propose a Blockchain-based Secure and Fair Online Incentive Mechanism (BSFOIM), which primarily incorporates a smart contract called BSFOIMToken, designed to function in online scenarios. In particular, we first introduce a multi-stage auction combined with a time discount factor in BSFOIM to quantify the contribution of workers in completing sensing tasks. Meanwhile, to ensure sensing data quality and worker selection fairness, we propose a Fairness-based Truth Discovery Mechanism (FTDM) with two core modules: a fine-grained reputation system to identify reliable workers and filter out malicious ones, and an upper confidence bound algorithm to optimize worker selection and avoid local optima. Finally, we implement these functions in BSFOIMToken and deploy a prototype on the Ethereum blockchain, demonstrating its practicality and robust performance. Rigorous theoretical and comprehensive experimental tests have proven their adherence to truthfulness, budget feasibility and individual rationality.

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

As necessary information about whether cooperation can be reached, rewards should be determined in advance in Vertical Federated Learning (VFL). To determine reasonable rewards, participant contributions should be estimated precisely. We propose a Vertically Federated Contribution Estimation (VF-CE) method. VF-CE calculates Mutual Information (MI) between distributed features and the label using a neural network trained via VFL itself. Note that compensation for CE is low as it only covers computation costs, and reward for real VFL training is high as it needs to cover training costs as well as participants' contributions to model performance and the resulting business benefits. Because MI presents a strong positive correlation with the final model performance, contributions to model performance can be estimated based on contributions to MI. We integrate a scalar-level attention mechanism in MI neural network. The attention weights of participants are treated as their contributions. We find that attention weights can effectively measure contribution redundancy, as its Spearman correlation coefficient with Shapley value is as high as 0.963. We demonstrate that VF-CE also satisfies properties of balance, zero element, and symmetry concerning fairness, which are hallmark properties of Shapley value. Compared with existing work, we consider contribution redundancy precisely, efficiently output approximated Shapley values through one MI calculation instead of 2 n where n is the number of participants, and introduce no extra privacy risk except the inherent risk in VFL, i.e., gradient transmission.

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

Autonomous driving is a hot topic within both academic and industrial domains. Critical to its advancement is the high performance of used machine learning models such as image recognition, lane detection, and danger prediction models. Sharing daily driving data is essential for the continuous enhancement of these predictive models. However, a significant challenge arises in balancing data sharing with the need to protect sensitive driving information. Federated learning (FL) is a popular mechanism for learning models from different vehicles without leaking private local data. However, FL often lacks robustness, leading to suboptimal models when local data comes from highly heterogeneous distributions. In this paper, we propose a novel FL framework with data-free knowledge distillation to address the above problems. Each vehicle extracts local hyper-knowledge including intermediate layer representations and soft predictions during local training. The hyper-knowledge is transferred to the FL server and aggregated to guide the next round of training. By this way, we can acquire better local models that perform well w.r.t. corresponding vehicle’s distribution and a better global model that can be used by future new vehicles without history driving data. Compared with existing knowledge distillation methods, we do not need public data to distill knowledge, which avoids privacy leakage when a real public dataset is shared and high data generation costs when a virtual dataset is shared. The experiments based on traffic sign recognition verify our advancement compared to baselines.

Policy network parameter sharing is a commonly used technique in advanced deep multi-agent reinforcement learning (MARL) algorithms to improve learning efficiency by reducing the number of policy parameters and sharing experiences among agents. Nevertheless, agents that share the policy parameters tend to learn similar behaviors. To encourage multi-agent diversity, prior works typically maximize the mutual information between trajectories and agent identities using variational inference. However, this category of methods easily leads to inefficient exploration due to limited trajectory visitations. To resolve this limitation, inspired by the learning of pre-trained models, in this paper, we propose a novel Contrastive Trajectory Representation (CTR) method based on learning distinguishable trajectory representations to encourage multi-agent diversity. Specifically, CTR maps the trajectory of an agent into a latent trajectory representation space by an encoder and an autoregressive model. To achieve the distinguishability among trajectory representations of different agents, we introduce contrastive learning to maximize the mutual information between the trajectory representations and learnable identity representations of different agents. We implement CTR on top of QMIX and evaluate its performance in various cooperative multi-agent tasks. The empirical results demonstrate that our proposed CTR yields significant performance improvement over the state-of-the-art methods.

Nowadays, Federated learning (FL) is popular as it achieves distributed model training while allowing data to stay locally. It trains a global model by aggregating a selected set of local models from participants' local data. However, the global model may not perform well for all participants, especially when participants' data distributions are non-IID. Participants actually care more about the Personal Model Performance (PMP), i.e., the model performance on their own data distribution, instead of the model performance on all data. In this paper, we design a model selection method to assign a personalized set of models for each participant to maximize PMP. We first propose a model selection metric, that is model similarity. We prove theoretically that selecting models similar to a participant's own local model can make the aggregated model closer to the ideal one. Then we design a DRL-based model selection method to maximize PMP for each participant. By careful design and dimension reduction of actions and states, our TD3-based model selection method achieves the highest PMP compared with baselines. Moreover, it has a transfer ability, which means a model selection agent trained on a dataset, e.g., MNIST, works well on another similar dataset, e.g., FMNIST.

Semantic communication powered by artificial in-telligence is carried out vigorously to further improve communication efficiency. The knowledge base (KB), as a critical component of semantic communication systems, guides devices to do semantic coding/encoding. However, mismatched KBs hinder semantic alignment between the transceiver and the receiver, which brings severe semantic error. In this work, we design a semantic knowledge base synchronization (SKBS) framework based on federated knowledge distillation for KB establishment and dynamic evolution. In the SKBS, we use the mutual distil-lation mechanism to learn knowledge from heterogeneous local KBs. Meanwhile, the global KB is compressed to improve the synchronization efficiency. Moreover, a filtering method for KB parameters with noise is applied to mitigate the effects of noise for KB synchronization. The experiment results demonstrate that our proposed approach can assist in establishing a universal global KB and improve the accuracy of multi-user semantic communication while reducing the communication cost during KB synchronization.

With the rapid development of intelligent driving and the Internet of Vehicles, network security in vehicles has received wide attention. In this paper, we study the problem of abnormal ECU sourcing in the Controller Area Network (CAN) which is a typical and widely used in-vehicle communication protocol. We find that the simple clock-based fingerprints adopted by many related methods cannot work effectively when environmental interference exists. This is because interference makes the measured clock offset deviate significantly from the real value. To overcome the above limitation, we propose an Interference-Tolerant abnormal ECU Sourcing (ITAS) approach based on a multi-dimensional clock fingerprint. ITAS decomposes the measured clock offset, constructs a multi-dimensional clock fingerprint, and maps fingerprints to respective ECUs to help abnormal ECU sourcing. The performance evaluation based on real vehicle CAN bus data collected from a Honda Civic demonstrates the strong anti-interference capability of the proposed ITAS with an over 96% accuracy for abnormal ECU sourcing.

In this paper, a repeated coalition formation game (RCFG) with dynamic decision-making for physical layer security (PLS) in wireless communications with intelligent reflecting surfaces (IRSs) has been investigated. In the considered system, one central legitimate transmitter (LT) aims to transmit secret signals to a group of legitimate receivers (LRs) under the threat of a proactive eavesdropper (EV), while there exist a number of third-party IRSs (TIRSs) which can choose to form a coalition with either legitimate pairs (LPs) or the EV to improve their respective performances in exchange for potential benefits (e.g., payments). Unlike existing works that commonly restricted to friendly IRSs or malicious IRSs only, we study the complicated dynamic ally-adversary relationships among LPs, EV and TIRSs, under unpre-dictable wireless channel conditions, and introduce a RCFG to model their long-term strategic interactions. Particularly, we first analyze the existence of Nash equilibrium (NE) in the formulated RCFG, and then propose a switch operations-based coalition selection along with a deep reinforcement learning (DRL)-based algorithm for obtaining such equilibrium. Simulations examine the feasibility of the proposed algorithm and show its superiority over counterparts.

The trade-off between privacy and accuracy presents a challenge for current federated learning (FL) frameworks, hindering their progress from theory to application. The main issues with existing FL frameworks stem from a lack of interpretability and targeted privacy protections. To cope with these, we proposed Disentangled Federated Learning for Privacy (DFLP) which employes disentanglement, one of interpretability techniques, in private FL frameworks. Since sensitive properties are client-specific in nature, our main idea is to turn this feature into a tool that strikes the balance between data privacy and FL model performance, enabling the sensitive attributes to be private. DFLP disentangles the client-specific and class-invariant attributes to mask the sensitive attributes precisely. To our knowledge, this is the first work that successfully integrates disentanglement and the nature of sensitive attributes to achieve privacy protection while ensuring high FL model performance. Extensive experiments validate that disentanglement is an effective method for accuracy-aware privacy protection in FL frameworks.

In recent years, COVID-19 has spread rapidly around the world, leading to a global pandemic, which has become an unprecedented crisis for almost every country in the world. In this paper, we propose a novel federated learning (FL) algorithm to train a sensitivity-specificity-variable COVID-19 diagnosis model. By FL, patients' data stays at each hospital locally, and thus the privacy of patients is reserved. However, the commonly used FL algorithms, such as FedAvg cannot perform COVID-19 diagnosis efficiently because they did not consider the impact of noise and heterogeneity in the chest X-ray (CXR) data of different hospitals. Moreover, they commonly assumed that hospitals would voluntarily participate in FL without payments. To this end, our FL algorithm integrates a novel data selection module to distinguish participants having data with low noise, high representative distribution, and a payment scheme to incentivize each participant according to their contributions. Our contribution evaluation method is based on the Shapley value method widely applied in coalitional games. Compared to the existing works, our solution does not need to train models repeatedly, which significantly reduces the time and computation resource consumption, while achieving a competitive performance as shown in experiments.

Coded distributed computing(CDC) has shown great potentials to solve the unexpected delay caused by stragglers and communication load in distributed computing. We propose a novel learning auction to allocate computing resource efficiently in a CDC scenario. The user demand types are usually het-erogeneous according to different variation trends of the value with finish time and workload, which can be modeled by deep learning. As the goal of social welfare maximizationthe platform would allocate computing resources according to inferred value functions of users. Due to the uncertain finish time and nonlinear structures of deep learning models, the considered optimization problem is non-convex. We then reformulate the non-convex optimization problem into a mixed integer program(MIP). After analyzing the inference error caused by deep learning, a payment rule referred to VCG is designed to achieve incentive alignment and individual rationality. Besides, experiments have been performed to show the superiority of our mechanism.

In this paper, a multi-layer edge computing frame-work for the virtual machine (VM) placement and computation offloading in industrial Internet of Things (IIoT) is proposed. Unlike most existing works, we focus on addressing the temporal dependency among tasks in an IIoT task flow, and consider that there is a stringent requirement on its completion time (including the transmission time, computation time and waiting time). For striking a balance between the system completion time and the energy consumption while satisfying the storage capacity of edge servers (ESs), completion deadline of time-sequential task flows, and placement requirements of VMs, we design a many-to-one matching game (MGVDA) to jointly determine the optimal VM placement and task offloading decisions. Finally, we prove that the resulted matching game solution is effective and stable. Simulation results examine the efficiency of the proposed MGVDA and show its superiority over the counterparts.

Federated Learning (FL) is a framework where multiple parties can train a model jointly without sharing private data. Private information protection is a critical problem in FL. However, the communication overheads of existing solutions are too heavy for IoT devices in resource-constrained environments. Additionally, they cannot ensure robustness when IoT devices become offline. In this paper, Democratic Federated Learning (DemoFL) is proposed, which is a privacy-preserving FL framework that has sufficiently low communication overheads. DemoFL involves a consensus module to ensure the system is robust. It also utilizes a tree structure to reduce the time communication overheads and realizes high robustness without reducing accuracy. The proposed algorithm reduces the communication complexity of aggregation at training by M $M$ times, M $M$ being a controllable parameter. Sufficient experiments have been conducted to evaluate the efficiency of the proposed method. The experimental results also demonstrate the practicality of the proposed framework for IoT devices in unstable environments.

Coded distributed computing(CDC) has shown great potentials to solve the unexpected delay caused by stragglers in distributed computing. In this paper, we focus on the auction design for efficient resource allocation in CDC. Specifically, we aim to design a learning auction mechanism to handle heterogeneous user demands and also to free users from the complexity of specifying valuations for resource combinations, which increases exponentially with the resource dimensions. The user demand type is heterogeneous according to different variation trends of the value with finish time and workload, which is modeled by deep learning. The platform would allocate resources according to the user value function. Then users do not need to consider the complex relationship between uncertain finish time and resource configuration in CDC. Due to the inference error of the learning model and the complexity of calculating uncertain finish time, the considered social welfare optimization problem is a non-linear and non-convex integer problem. Even worse, the typical VCG-based payment scheme cannot guarantee truthfulness with the inference error. In response to these difficulties, we transform the social welfare optimization problem into a mixed integer programming problem which already has efficient solutions. The social welfare gap caused by the inference error is analyzed theoretically. The relationship between the utility regret of reporting truthfully and the inference error is also analyzed. We prove that our mechanism satisfies incentive alignment and individual rationality. Extensive experiments show the superiority of our mechanism compared with existing ones.

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

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

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

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

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

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

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

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

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

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

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

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

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