Low-Rank Adaptation (LoRA) has emerged as a prominent solution to mitigate the communication and computation costs in federated fine-tuning of Large Language Models (LLMs).However, we observe that even within lowrank adapters, a substantial portion of parameters manifest negligible updates during federated training, leading to redundant communication and wasted local computation.To address this, we propose GMFL, a plug-andplay layer freezing mechanism designed to seamlessly integrate with existing federated fine-tuning frameworks.Specifically, the server monitors the global update magnitude of each LoRA layer to dynamically generate freezing masks.These masks are updated periodically with a fixed freezing rate, ensuring stable convergence by robustly identifying "saturated" layers.Theoretical analysis confirms the convergence of GMFL, where the freezing mechanism yields a bounded error that scales with client heterogeneity.Extensive experiments across multiple tasks (GLUE, Commonsense Reasoning, Math Reasoning and General Generation) demonstrate that GMFL reduces communication overhead and lowers computational costs while preserving the performance of the underlying federated fine-tuning methods.Our work provides a practical, versatile solution for deploying large-scale federated LLM fine-tuning in resource-constrained environments.

Recent advances in Meta-learning for Black-Box Optimization (MetaBBO) have shown the potential of using neural networks to dynamically configure evolutionary algorithms (EAs), enhancing their performance and adaptability across various BBO instances. However, they are often tailored to a specific EA, which limits their generalizability and necessitates retraining or redesigns for different EAs and optimization problems. To address this limitation, we introduce ConfigX, a new paradigm of the MetaBBO framework that is capable of learning a universal configuration agent (model) for boosting diverse EAs. To achieve so, our ConfigX first leverages a novel modularization system that enables the flexible combination of various optimization sub-modules to generate diverse EAs during training. Additionally, we propose a Transformer-based neural network to meta-learn a universal configuration policy through multitask reinforcement learning across a designed joint optimization task space. Extensive experiments verify that, our ConfigX, after large-scale pre-training, achieves robust zero-shot generalization to unseen tasks and outperforms state-of-the-art baselines. Moreover, ConfigX exhibits strong lifelong learning capabilities, allowing efficient adaptation to new tasks through fine-tuning. Our proposed ConfigX represents a significant step toward an automatic, all-purpose configuration agent for EAs.

Recently, Meta-Black-Box-Optimization (MetaBBO) methods significantly enhance the performance of traditional black-box optimizers through meta-learning flexible and generalizable meta-level policies that excel in dynamic algorithm configuration (DAC) tasks within the low-level optimization, reducing the expertise required to adapt optimizers for novel optimization tasks. Though promising, existing MetaBBO methods heavily rely on human-crafted feature extraction approach to secure learning effectiveness. To address this issue, this paper introduces a novel MetaBBO method that supports automated feature learning during the meta-learning process, termed as RLDE-AFL, which integrates a learnable feature extraction module into a reinforcement learning-based DE method to learn both the feature encoding and meta-level policy. Specifically, we design an attention-based neural network with mantissa-exponent based embedding to transform the solution populations and corresponding objective values during the low-level optimization into expressive landscape features. We further incorporate a comprehensive algorithm configuration space including diverse DE operators into a reinforcement learning-aided DAC paradigm to unleash the behavior diversity and performance of the proposed RLDE-AFL. Extensive benchmark results show that co-training the proposed feature learning module and DAC policy contributes to the superior optimization performance of RLDE-AFL to several advanced DE methods and recent MetaBBO baselines over both synthetic and realistic BBO scenarios.

Clustered federated learning (FL), which groups clients with similar data distributions for collaborative training, represents a pivotal technique within federated learning for effectively addressing the challenges posed by non-IID data on clients. Existing clustered FL algorithms typically endeavor to learn distribution similarities of clients iteratively or indirectly through representations like gradients and loss. This necessitates resource-intensive pre-training or multiple iterations to attain stable clusters, thereby incurring additional communication cost and computational overhead. To address the above issues, we propose lightweight Clustered Federated Learning via Feature Extraction (FECFL). FECFL adopts a simple but effective client representation, i.e., the features extracted from the clients’ data using identically initialized models without any pre-training, to perform efficient one-shot clustering. Moreover, client data distribution is often dynamic in practice. To tackle distribution shift, we embed a distribution monitoring mechanism in FECFL, enabling adaptive re-grouping for new distributions. Finally, we demonstrate the benefits of FECFL over the baselines by conducting experiments on various datasets and distributions.

Designing effective black‑box optimizers is hampered by limited problem-specific knowledge and manual control that spans months for almost every detail. In this paper, we present DesignX, the first automated algorithm design framework that generates an effective optimizer specific to a given black-box optimization problem within seconds. Rooted in the first principles, we identify two key sub-tasks: 1) algorithm structure generation and 2) hyperparameter control. To enable systematic construction, a comprehensive modular algorithmic space is first built, embracing hundreds of algorithm components collected from decades of research. We then introduce a dual-agent reinforcement learning system that collaborates on structural and parametric design through a novel cooperative training objective, enabling large-scale meta-training across 10k diverse instances. Remarkably, through days of autonomous learning, the DesignX-generated optimizers continuously surpass human-crafted optimizers by orders of magnitude, either on synthetic testbed or on realistic optimization scenarios such as Protein-docking, AutoML and UAV path planning. Further in-depth analysis reveals DesignX's capability to discover non-trivial algorithm patterns beyond expert intuition, which, conversely, provides valuable design insights for the optimization community. We provide DesignX's Python project at~\url{https://github.com/MetaEvo/DesignX}.

Sparse mobile crowdsensing (SMCS) is a cost-effective paradigm aimed at recruiting workers to complete sensing tasks and inferring the remaining unobserved data, with broad applications in large-scale, fine-grained monitoring services. In SMCS, spatial coverage of the sensing area or global completion accuracy is typically used as the performance metric. However, in many real-world service scenarios (e.g., temperature, humidity, air quality monitoring), users are generally only interested in data from their specific regions and expect the highest possible data accuracy. In such cases, relying solely on coverage or global completion error fails to adequately assess the quality of the platform’s service. To address this and satisfy users’ sensing demands as much as possible while maintaining low sensing costs, we propose the Demand-Driven Framework with Neighborhood-Aware Data Reconstruction (D2-SMCS), which integrates regional population demand calculation, dynamic clustering, and data reconstruction. Unlike existing approaches, we introduce quality of service (QoS) as a performance metric based on regional population demand. First, we quantify the interest level of sensing tasks in different regions by considering factors such as population demand and data fluctuation. Based on this quantification, the dynamic clustering module selects the regions most beneficial for accurate data completion. Finally, to overcome the limitation of traditional matrix completion methods in capturing short-term variations, we propose an innovative Neighborhood-Aware Latent Matrix Completion (NALMC) approach to infer and complete the unobserved regions. Extensive experiments on real-world datasets demonstrate the effectiveness of our framework.

As a collaborative and open network, billions of devices can be free to join the IoT-based data collection network for data perception and transmission. Along with this trend, more and more malicious attackers enter the network, they steal or tamper with data, and hinder data exchange and communication. To address these issues, we propose a Proactive Trust Evaluation System (PTES) for secure data collection by evaluating the trust of mobile data collectors. Specifically, PTES guarantees evaluation accuracy from trust evidence acquisition, trust evidence storage, and trust value calculation. First, PTES obtains trust evidence based on active detection of drones, feedbacks from interacted objects, and recommendations from trusted third parties. Then, these trust evidences are stored according to interaction time by adopting a sliding window mechanism. After that, credible, untrustworthy, and uncertain evidence sequences are extracted from the storage space, and assigned with positive, negative, and tendentious trust values, respectively. Consequently, the final normalized trust is obtained by combining the three trust values. Finally, extensive experiments conducted on a real-world dataset demonstrate PTES is superior to benchmark methods in terms of detection accuracy and profit.

The heterogeneity of local data and client performance, along with real-world system risks, is driving the evolution of federated learning (FL) towards personalized, model-heterogeneous, and decentralized approaches. However, due to the differing structures of heterogeneous models, it is hard to use them to identify clients with similar data distributions and further enhance the personalization of local models. Therefore, how to deal with data heterogeneity to obtain superior personalized local models for clients, while simultaneously addressing model heterogeneity and system risks is a challenging problem. In this paper, we propose a novel personalized FL framework with fine-gRained layEr aggregAtion andDecentralized cluStering (${\sf Reads}$), which integrates four key components: (1) deep mutual learning with privacy guarantee for model training and privacy preservation, (2) fine-grained layer similarity computation among heterogeneous model layers, (3) fully decentralized clustering for soft clustering of clients based on layer similarities, and (4) personalized layer aggregation for capturing common knowledge from other clients. Through${\sf Reads}$, clients obtain personalized models that accommodate model heterogeneity, while the system ensures robustness against a single point of failure. Extensive experiments demonstrate the efficacy of${\sf Reads}$in achieving these goals.

The pervasive distribution of data across clients with privacy concerns and heterogeneous performance in edge networks presents a significant opportunity to enhance AI model performance. Federated learning (FL) enables a model owner (MO) to recruit these clients, offering compensation for their contributions, and to improve model quality by aggregating knowledge from their locally trained models. However, several challenges arise in this process. Clients may decline participation if they do not achieve positive utility. Moreover, due to constraints in memory, computing, and communication resources, some clients can only train lightweight models that represent partial versions of the global model. Importantly, the MO's pricing for client contributions and the proportions of local model training are interdependent, collectively influencing client utilities and participation decisions. To address these challenges, we first model the utility functions of both the MO and the clients, accommodating the support for lightweight local models. We then formulate their interactions as a Stackelberg game and theoretically prove the existence of a Nash equilibrium. Based on this equilibrium, we derive optimal collaboration strategies for both the MO and the clients. Additionally, we design an efficient approximation algorithm to enable the MO to maximize its utility by selecting suitable clients to participate in FL. Finally, extensive experiments validate our theoretical findings, demonstrating the superior performance and effectiveness of the proposed algorithms

Many mobile crowdsensing applications require efficient recruitment of workers whose qualities are often unknown a priori. While prior research has explored multi-armed bandit-based mechanisms with short-term incentives to address this unknown worker recruitment challenge, these mechanisms mostly neglect the enduring participation issues stemming from privacy concern and selection starvation in the long-term task. Therefore, in this paper, we focus on incentivizing long-term participation of unknown workers, thereby providing crucial assurance for crowdsensing applications. We first establish an auction framework based on shuffle differential privacy (SDP), where we leverage SDP’s privacy amplification effect to mitigate privacy-related utility loss when dealing with the privacy-sensitive worker and the utility-sensitive platform. Following this, we model the selection requirements of workers as fairness constraints and propose two novel fairness-aware incentive mechanisms, GFA and IFA, to ensure group and individual fairness for unknown workers, respectively. Theoretical analyses highlight the desirable properties of GFA and IFA, complemented by an in-depth exploration of fairness violation and regret. Finally, numerical simulations are conducted on two real-world datasets, validating the superior performance of the proposed mechanisms.

Mobile edge computing (MEC) brings abundant computing resources to the edge networks, which supports users in offloading their tasks to the edge instead of the cloud, thereby reducing service delay and improving users' quality of experience. In this paper, we consider a three-tier multi-user multi-task offloading model, which contains multiple users with each user possessing multiple tasks, multiple base stations (BSs) with edge servers and a remote cloud. Taking into account the selfishness of individuals in the MEC system, we respectively formulate optimization problems for users, BSs and the cloud. Users aim to make their offloading strategies to minimize their respective costs, while BSs and the cloud aim to make their computation resource allocation decisions to minimize their respective task completion delays. We model the interaction among these selfish individuals based on Stackelberg game, where users act as leaders and BSs and the cloud act as followers. By using backward induction, we prove the existence of Stackelberg Equilibrium (SE). We further propose a distributed algorithm that enables the system to reach the SE, which includes three user selection strategies for the BSs. The numerical results demonstrate the superiority of the proposed scheme compared with several approaches.

Semisupervised node classification is a prevalent task on graphs, which involves predicting the labels of unlabeled nodes based on limited labeled data available. At present, centralized approaches to training models for this task are unsustainable due to the increasing demand for computational power, storage capacity, and privacy. An approach of potential is federated graph learning (FGL), which allows multiple clients to collaborate on learning a model while maintaining data privacy. However, current methods suffer from the inability to consider the topology of the graph data and inadequate use of unlabeled data. To address these issues, we propose federated graph augmentation (FedGA) by combining graph neural network (GNN) models to utilize similar topologies existing in different client graphs and augment the client data. Furthermore, we develop FedGA-L based on FedGA, which integrates pseudolabeling and label-injection to improve the utilization of unlabeled data. FedGA-L allows pseudolabels to be used as additional information to enhance data augmentation and further improve the accuracy of node classification. We evaluate the effectiveness of FedGA and FedGA-L through experiments on multiple datasets. The results demonstrate improved accuracy in solving typical classification tasks and their compatibility with a variety of federated learning (FL) frameworks. On widely recognized datasets for graph learning, we achieve an accuracy improvement of 5%–7% compared to vanilla federated learning algorithms.

Bidirectional service function chain (BSFC) consists of multiple virtual network functions (VNFs). Through VNF deployment and link mapping, BSFCs can be embedded into resource-constrained mobile edge networks to provide low-latency network function services to users participating in interactive applications such as multi-player online games. Data from these users are routed through BSFCs to the edge node where the application is located for interaction and then returned to the users through the BSFCs, thus enabling synchronization among multiple users. However, the edge nodes or links have limited computing or bandwidth resources to serve only a fraction of users simultaneously. Therefore, the embedding decisions among different users can affect each other. In this paper, we propose a novel BSFC embedding strategy for interactive applications with the goal of minimizing computing and bandwidth resources while satisfying users' latency requirements. We first model the BSFC embedding problem as an integer nonlinear programming problem. Then, by closely examining the complexity of the problem, we propose a distributed algorithm based on game theory. We theoretically analyze the properties of the proposed algorithm and show that it can obtain a solution with a worst-case performance bound. Finally, extensive experiments show that the proposed algorithm outperforms several existing algorithms.

Federated learning (FL) is a distributed machine learning paradigm that can be organized in two layers. In the outer layer of users, there is a model interaction process between the task publisher and users, through which all parties obtain their respective utilities. However, these parties’ utilities are coupled, both depending on the training sample size and local iterations. In the inner layer of users, a user's multiple devices (e.g., computers and smart phones) can be used to jointly train local models efficiently. Yet, due to device heterogeneity, it is challenging for users to determine which devices to participate in local training and allocate how many computing and communication resources to minimize training costs. In this paper, we tackle this novel two-layer optimization problem by designing utility game and resource control strategies. In the outer layer, we model the relationship between the task publisher and users as a Stackelberg game and obtain the optimal solution for both parties by solving a unique Stackelberg equilibrium point; while in the inner layer, we formulate the optimization problem as a mixed integer nonlinear programming problem, which is decomposed into sub-problems and solved by devising resource control algorithm based on successive convex approximation. Finally, extensive experiments show that the proposed algorithms outperform baseline algorithms.

With the popularity of Mobility-on-Demand (MOD) vehicles, a new market called MOD-Vehicular-Crowdsensing (MOVE-CS) was introduced for drivers to earn more by collecting road data. Unfortunately, MOVE-CS failed after two years of operation. To identify the root cause, we survey 581 drivers and reveal its simple incentive model based on blindly competitive rewards. This model brings most drivers few yields, resulting in their withdrawals. In contrast, a similar market termed MOD-Human-Crowdsensing (MOMAN-CS) remains successful thanks to a complex model based on exclusively customized rewards. Hence, we wonder whether MOVE-CS can be resurrected by learning from MOMAN-CS. Despite considerable similarity, we can hardly apply the incentive model of MOMAN-CS to MOVE-CS, since MOD drivers are also concerned with passenger missions that dominate their earnings. To this end, we analyze a large-scale dataset of 12,493 MOD vehicles, finding that drivers have explicit preference for short-term, immediate gains as well as implicit rationality in pursuit of long-term, stable profits. Therefore, we design a novel driver-oriented incentive mechanism for MOVE-CS, calledLSTAloc, at the heart of which lies a spatial-temporal differentiation-aware task allocation scheme empowered by submodular optimization. Applied to the dataset, our design would essentially benefit both the drivers and platform to incentivize MOD vehicular crowdsensing efficiently, thus possessing the potential to resurrect MOVE-CS.

Distributed learning has been increasingly studied in edge computing, enabling edge devices to learn a model collaboratively without exchanging their private data. However, existing approaches assume the private data owned by edge devices are all labeled while the reality is that massive private data are unlabeled and remain to be utilized, which leads to suboptimal performance. To overcome this limitation, we study a new practical problem, Distributed Semi-Supervised Learning (DSSL), to learn models collaboratively with mixed private labeled and unlabeled data on each device. We also propose a novel methodDistMatchthat exploits private unlabeled data by self-training on each device with the help of models from neighboring devices. DistMatch generates pseudo-labels for unlabeled data by properly averaging the predictions of these received models. Furthermore, to avoid self-training with wrong pseudo-labels, DistMatch proposes aconsensus consistencyloss to filter pseudo-labels with high consensus and force the output of the trained model to be consistent with these pseudo-labels. Extensive evaluation results via our self-developed testbed indicate the proposed method outperforms all baselines on commonly used image classification benchmark datasets.

Evolutionary algorithms, such as differential evolution, excel in solving real-parameter optimization challenges. However, the effectiveness of a single algorithm varies across different problem instances, necessitating considerable efforts in algorithm selection or configuration. This article aims to address the limitation by leveraging the complementary strengths of a group of algorithms and dynamically scheduling them throughout the optimization progress for specific problems. We propose a deep reinforcement learning-based dynamic algorithm selection framework to accomplish this task. Our approach models the dynamic algorithm selection a Markov decision process, training an agent in a policy gradient manner to select the most suitable algorithm according to the features observed during the optimization process. To empower the agent with the necessary information, our framework incorporates a thoughtful design of landscape and algorithmic features. Meanwhile, we employ a sophisticated deep neural network model to infer the optimal action, ensuring informed algorithm selections. Additionally, an algorithm context restoration mechanism is embedded to facilitate smooth switching among different algorithms. These mechanisms together enable our framework to seamlessly select and switch algorithms in a dynamic online fashion. Notably, the proposed framework is simple and generic, offering potential improvements across a broad spectrum of evolutionary algorithms. As a proof-of-principle study, we apply this framework to a group of differential evolution algorithms. The experimental results showcase the remarkable effectiveness of the proposed framework, not only enhancingthe overall optimization performance but also demonstrating favorable generalization ability across different problem classes.

Wearable devices have been important components for ubiquitous computing. However, text input remains challenging on wearables due to the lack of a physical keyboard. In this paper, we propose a novel ring-shaped virtual keyboard system named RingVKB for convenient text input using low-cost IMUs available on any wearables. At the core of RingVKB are two novel designs: 1) A circular keyboard layout with 12 equal sectors, which assembles all common keys on classical keyboards while allowing users to type with only one finger effectively, and 2) an error control algorithm that calculates the relative displacement of keystrokes from the noisy IMU sensor data. The two components, coupled together, enable high-accuracy and efficient text input for ubiquitous scenarios.We implement RingVKB using a small device consisting of a microcontroller and a MEMS sensor, which can be attached to the user's index finger.Experimental results show that RingVKB can effectively improve the relative displacement estimation accuracy, and achieves an overall keystroke recognition accuracy of 93% for 25 key positions. A user study also shows that RingVKB is easy to learn and use. Using only low-cost IMU sensors, RingVKB provides a virtual keyboard solution that can be widely adopted on wearables.

As a new computing paradigm, mobile edge computing (MEC) pushes the centralized cloud resources close to the edge network, which significantly reduces the pressure of the backbone network and meets the requirements of emerging mobile applications. To achieve high performance of the MEC system, it is essential to design efficient task offloading and service placement schemes, which are responsible for offloading tasks to the edge servers while considering the heterogeneity and diversity of computation services. Our MEC system aims to maximize the long-term average network utility while maintaining the stability of the edge network. Considering that synchronous manner overlooks the scenarios endowed with asymmetric update frequencies for service placement and task offloading, we propose an online algorithm based on the two-timescale Lyapunov optimization in a stochastic network environment without requiring the future information. By making asynchronous decisions on service placement and task offloading with different control parameters$V$, we can achieve a time-average sub-optimal solution that is close to the offline optimum. In addition, we introduce the varying control parameter$V(t)$and$\Omega$-additive approximation to enhance the robustness of the proposed algorithm within an error$\Omega$. Finally, rigorous theoretical analysis and extensive trace-driven experimental results show that the proposed algorithm achieves the$[O(1/V), O(V)]$performance-backlog tradeoff and is more competitive than benchmarks.

Task offloading offloads latency-sensitive and computation-intensive applications from resource-constrained terminal devices to relatively resource-rich edge servers to meet users’ demands for latency and energy consumption, which has attracted extensive attention from academia and industry. However, most of the existing researches only considers offloading dependent tasks within a single application or multiple independent applications, while ignoring the dependencies between applications. To this end, this paper proposes an offloading strategy for distributed dependent applications under the condition of limited computing and cache resources. The goal of the proposed strategy is to minimize the weighted sum of latency and energy to complete all applications while solving the offloading and resource allocation problems of dependent applications. However, the dual dependencies between applications and tasks within the application complicate offloading tasks. To accommodate this issue, we represent the dual dependencies as a directed acyclic graph. Then, we design the offloading strategy as follows: First, we transform the formulated non-convex problem into convex optimization subproblems. Second, we iteratively calculate the task priority and obtain the optimal offloading decision of the task according to the priority. Finally, we perform validation on real datasets. Compared with several state-of-the-art methods, our proposed strategy can significantly reduce the weighted sum of latency and energy.

Mobile crowd sensing (MCS) is a popular sensing paradigm that leverages the power of massive mobile workers to perform various location-based sensing tasks. To assign workers with suitable tasks, recent research works investigated mobility prediction methods based on probabilistic and statistical models to estimate the worker’s moving behavior, based on which the allocation algorithm is designed to match workers with tasks such that workers do not need to deviate from their daily routes and tasks can be completed as many as possible. In this paper, we propose a new multi-task allocation method based on mobility prediction, which differs from the existing works by (1) making use of workers’ historical trajectories more comprehensively by using the fuzzy logic system to obtain more accurate mobility prediction and (2) designing a global heuristic searching algorithm to optimize the overall task completion rate based on the mobility prediction result, which jointly considers workers’ and tasks’ spatiotemporal features. We evaluate the proposed prediction method and task allocation algorithm using two real-world datasets. The experimental results validate the effectiveness of the proposed methods compared against baselines.

With the easy access to mobile networks and the proliferation of video applications, video traffic is occupying a great portion of the network traffic, which poses a new challenge of how to alleviate the heavy backhaul traffic and ensure the high quality of experience for video services. As a promising solution towards addressing this challenge, video caching in edge networks has recently received significant attention, which mostly considers the video popularity and the user preference for the video. However, few studies consider the user behavior and the user preference for different parts of the video that indeed have an essential impact on caching efficiency. Hence, this article proposes a new caching and resource scheduling scheme for adaptive bitrate videos by incorporating these fine-grained factors. We first model the video service problem as a nonlinear integer programming problem, which can be divided into a cache placement problem and an online resource scheduling problem. Then, we design efficient algorithms based on several techniques, including greedy strategy, relaxation, and rounding, to solve the two problems. Extensive experimental results based on two real-world datasets show that the proposed solution achieves superior performance compared with several state-of-the-art caching approaches.

Mobile crowd sensing (MCS) has become a powerful sensing paradigm that allows requesters to outsource sensing tasks to a crowd of mobile users. Aware of the paramount importance of incentivizing participation for MCS, researchers have proposed various incentive mechanisms. Most mechanisms assume that the MCS platform can collect sufficient budget to recruit users, and hence only focus on incentivizing users. In this work, we consider MCS systems where the budget of a single task is insufficient for user recruitment. Commonly, a task requester with a simple task (e.g., inquiring a photo of a restaurant) only provides a small budget, while a user wants to earn a larger reward for his effort (e.g., traveling a long distance to take a photo). To address this disparity issue, we propose novel task-bundling-based two-stage incentive mechanisms to incentivize both requesters and users. Specifically, tasks are first clustered as bundles, where the budgets in one bundle are collected through a random partition method. Then, a double auction is conducted, which sorts budgets and bids to maximize matching. Through theoretical analysis and extensive evaluations on synthetic and real-world datasets, we demonstrate that the proposed mechanisms satisfy computational efficiency, individual rationality, budget balance, truthfulness, and constant competitiveness.

Mobile edge computing (MEC)deploys computing and storage resources close to mobile devices, enabling resource demanding applications to run on mobile devices with short network latency. In the past few years, large numbers of research works focused on the research hotspots in MEC, such as computation offloading and energy efficiency. However, few researchers have investigated the deployment of edge servers. On the one hand, blindly deploying numerous edge servers will result in a large amount of capital expenditure. On the other hand, the deployment of edge servers is a multimodal problem that should provide decision makers with multiple deployment options to deal with the impact of unmeasured real-world factors. Considering these factors, we study themultimodal optimization problem of edge server placement (MESP)with the goal of minimizing the average system response time in this work. Regarding the difficulty of the MESP problem, we propose a heuristic algorithm that combines particle swarm optimization and niching technology to obtain a set of competitive placement solutions. Extensive experiments over a real-world dataset show that the proposed algorithm can significantly reduce the system response time.

Multi-tier computing (MC) is a promising architecture that integrates cloud computing, fog computing, and edge computing to provide users with a consistent experience of computing services by fusing computing devices within the network through virtualization technology. Although MC combines powerful computation and communication resources, the massive demand from Service Function Chain (SFC) deployments continues to make it challenging regarding resource constraints, latency satisfaction, and revenue-cost tradeoffs. To this end, in this article, we study an SFC deployment problem in MC and formulate a problem for maximizing the revenue of online SFC deployment under latency, computation resources, and communication resources constraints. To solve this online problem better, we construct a computation and communication resource cost model and transform the original online problem into a deployment cost minimization problem and a request admission problem by an alternating optimization approach. To solve the two subproblems, we propose an online approximation algorithm with a provable competitive ratio for the particular scenario with no latency requirements. Then, based on the cost model, we propose an online heuristic algorithm that adopts a binary search method for the original problem with latency requirements. Simulation experiments show that our two proposed online algorithms have advantages in total revenue, running time, and load balancing compared with other comparison algorithms.

Mobile crowdsensing (MCS) has recently received considerable attention due to its capability of providing a promising paradigm to complete complex sensing tasks. Existing works on MCS mainly focus on designing incentive mechanisms to attract mobile users to participate in crowdsensing, while ignoring the freshness of information, i.e.,Age of Information(AoI). Although multiple source nodes with common observation can indeed improve the data quality of MCS, it complicates the calculation of the AoI. To address this issue, this article proposes a freshness-aware incentive mechanism in MCS, which not only captures the conflict interests/competitions among users, but also considers the age of information (AoI). Specifically, we define two data sampling models, namedsampling-at-willmodel andsampling-predeterminedmodel. For both models, we design efficient auction mechanisms, which recruit appropriate mobile users, determine the payments, and schedule the data sampling, so as to optimize the average AoI and data quality under budget constraint. It is proved that the proposed auction achieves several desirable properties, including individual rationality, budget balance, truthfulness and computational efficiency. We also theoretically derive the upper bound of the average AoI obtained by the proposed scheme. Finally, we conduct simulations to evaluate the efficiency of the proposed mechanism in optimizing the data quality and AoI.

Mobile-edge computing (MEC) is a burgeoning paradigm that performs computation close to the network edge. In MEC, computation offloading is an essential mechanism to alleviate the limitations of user equipment (UEs) by offloading computation-intensive and latency-sensitive tasks to edge servers deployed in base stations (BSs). For the partitionable task model, multi-BS offloading makes the parallel execution of tasks possible, which can further reduce the execution delay. In this article, we consider a MEC architecture in a dense network with multiple BSs and multiple UEs and formulate a computation offloading problem for partitionable tasks with the goal of minimizing the task completion time. We jointly optimize the computation and radio resources considering the heterogeneity of UEs’ geographic locations and task types. Specifically, we construct a task offloading game using the evolutionary game theory (EGT). We apply replicator dynamics to model the offloading decision process and obtain the evolutionary equilibrium, which is proved to be an evolutionary stable strategy. Based on the theoretical analysis, we propose an EGT-based offloading mechanism to achieve a suboptimal solution in the case of limited numbers of subtasks. The extensive evaluation results demonstrate the effectiveness of our proposed mechanism compared with the centralized optimal solution.

Data aggregation is a fundamental problem in mobile crowdsensing (MCS). However, the existing approaches are still unsatisfactory considering the privacy protection of sensing data and aggregation results. In addition, most existing privacy-preserving data aggregation schemes can only support a single type of aggregation, which limits their application scenarios. To address these issues, we propose a novel privacy-preserving and customization-supported data aggregation scheme that can achieve multiple types of aggregation. Specifically, we utilize additive secret sharing ($\mathcal {ASS}$) to protect the privacy of both sensing data and aggregation results and then propose a simplified secure triplet generation protocol based on$\mathcal {ASS}$to construct secure aggregation operations. Moreover, we design a secure comparison (SC) algorithm and a secure top-$K$algorithm to realize customized aggregation (i.e., statistical aggregation over top-$K$largest or smallest values of sensing data). The formal theoretical analysis demonstrates that the proposed scheme is effective, and the extensive experiments conducted on a real-world data set show that the proposed approach is privacy preserving and efficient.

There have been many studies focusing on edge server deployment and service placement in mobile-edge computing (MEC), respectively, but rare works took both of them into consideration. However, edge server deployment and service placement are coupling issues in practice, where the former affects the latter. Besides, the economic benefit of the MEC platform is also a consideration. Due to different service request rates and prices, appropriate service placement solutions are needed to increase the overall profit. In this article, we propose a complete process combining edge server and service placement, where service placement explicitly takes into account the structure of current edge server placement and different service request rates and prices. We design a joint edge server deployment and service placement model with the goal of maximizing the overall profit of all edge servers under the constraints of the number of edge servers, the relationship among edge servers and base stations, the storage capacity, and the computing capacity of each edge server. We propose a two-step method including the clustering algorithm and nonlinear programming to solve the formulated problem. Extensive evaluations based on the real-world data set demonstrate that the proposed algorithm outperforms the baseline methods.

Currently, mobile-edge computing (MEC) becomes a burgeoning paradigm to tackle the contradiction between delay-sensitive tasks and resource-limited mobile/IoT devices. However, a single MEC server is usually not able to satisfy the heavy computation tasks considering its limited storage and computation capability. Thus, the cooperation of MEC servers provides an effective way to accommodate this issue. In this article, we study the joint task offloading and resource allocation problem in the scenario with cooperative MEC servers. We first define resource fairness among IoT devices from the user experience perspective. Then, we formulate a joint optimization problem by taking into account the system efficiency and fairness, which is shown to be NP-hard and thus, intractable. To solve this problem, we propose a two-level algorithm: the upper level algorithm, inspired by evolutionary strategies, is able to search superior offloading schemes globally; while the lower level algorithm, taking into account fairness among all tasks, is able to generate resource allocation schemes that make full use of server resources. Comprehensive evaluation results demonstrate the efficiency and fairness of the proposed algorithm compared to baselines.

Among numerous indoor localization systems, WiFi fingerprint-based localization has been one of the most attractive solutions, which is known to be free of extra infrastructure and specialized hardware. To push forward this approach for wide deployment, three crucial goals on delightful deployment ubiquity, high localization accuracy, and low maintenance cost are desirable. However, due to severe challenges about signal variation, device heterogeneity, and database degradation root in environmental dynamics, pioneer works usually make a trade-off among them. In this paper, we propose iToLoc, a deep learning based localization system that achieves all three goals simultaneously. Once trained, iToLoc will provide accurate localization service for everyone using different devices and under diverse network conditions, and automatically update itself to maintain reliable performance anytime. iToLoc is purely based on WiFi fingerprints without relying on specific infrastructures. The core components of iToLoc are a domain adversarial neural network and a co-training based semi-supervised learning framework. Extensive experiments across 7 months with 8 different devices demonstrate that iToLoc achieves remarkable performance with an accuracy of 1.92m and > 95% localization success rate. Even 7 months after the original fingerprint database was established, the rate still maintains > 90%, which significantly outperforms previous works.

Mobile edge computing (MEC) pushes the centralized cloud resources close to the edge network, which significantly reduces the pressure of the backbone network and meets the requirements of emerging mobile applications. To achieve high performance of the MEC system, it is essential to design efficient task offloading schemes. Many existing works focus on offloading tasks to the edge servers while ignoring the heterogeneity and diversity of computation services, which is also important in MEC. In this paper, we investigate the joint problem of online task offloading and service placement-downloading and deploying the service-related resources at edge servers-in the dense MEC network. Our MEC system aims to maximize the long-term average network utility while maintaining the stability of the edge network. Due to the uncertainty of task demands, it is impossible to make an online long-term optimal decision. Therefore, we propose an online algorithm based on the two-timescale Lyapunov optimization without requiring the future information. By making asynchronous decisions on service placement and task offloading, we can achieve a time-average sub-optimal solution that is close to the offline optimum. In addition, rigorous theoretical analysis and extensive trace-driven experimental results show that the proposed algorithm is more competitive than benchmarks.

Crowdsensing is regarded as a critical component of the Internet of Things (IoT) and has been widely applied in smart city services. Incentive mechanism design, data reliability evaluation, and privacy preservation are the research focuses of crowdsensing. However, most existing incentive mechanisms fail to protect data privacy and evaluate data credibility, simultaneously. Moreover, traditional privacy and reliability-aware incentive schemes are usually challenging to realize real-time reward distribution. To this end, we first point out a single-time slice of failure problem in real-time incentive mechanisms and propose a two-layer truth discovery model (TLTD) to resolve this problem. Then, a reliability-aware real-time incentive mechanism (RRIM) is designed based on the proposed TLTD. In order to evaluate data reliability in a privacy-preserving manner, we build a privacy-preserving truth discovery solution (PriTD) based on secure computation protocols. Finally, our proposed system [privacy and reliability-aware real-time incentive system for crowdsensing (PRICE)] integrating the aforementioned protocols realizes real-time reward distribution, data reliability evaluation, and privacy protection, simultaneously. Theoretical analysis and experimental evaluations on a synthetic and real-world data set demonstrate the feasibility and efficiency of the proposed PRICE.

Mobile crowdsensing (MCS) is a popular paradigm to collect sensed data for numerous sensing applications. With the increment of tasks and workers in MCS, it has become indispensable to design efficient task allocation schemes to achieve high performance for MCS applications. Many existing works on task allocation focus on single-task allocation, which is inefficient in many MCS scenarios where workers are able to undertake multiple tasks. On the other hand, many tasks are time-limited, while the available time of workers is also limited. Therefore, time validity is essential for both tasks and workers. To accommodate these challenges, this paper proposes a multi-task allocation problem with time constraints, which investigates the impact of time constraints to multi-task allocation and aims to maximize the utility of the MCS platform. We first prove that this problem is NP-complete. Then two evolutionary algorithms are designed to solve this problem. Finally, we conduct the experiments based on synthetic and real-world datasets under different experiment settings. The results verify that the proposed algorithms achieve more competitive and stable performance compared with baseline algorithms.

Providing appropriate monetary rewards is an efficient way for mobile crowdsensing to motivate the participation of task participants. However, a monetary incentive mechanism is generally challenging to prevent malicious task participants and a dishonest task requester. Moreover, prior quality-aware incentive schemes are usually failed to preserve the privacy of task participants. Meanwhile, most existing privacy-preserving incentive schemes ignore the data quality of task participants. To tackle these issues, we propose a privacy-preserving and data quality-aware incentive scheme, called PACE. In particular, data quality consists of the reliability and deviation of data. Specifically, we first propose a zero-knowledge model of data reliability estimation that can protect data privacy while assessing data reliability. Then, we quantify the data quality based on the deviation between reliable data and the ground truth. Finally, we distribute monetary rewards to task participants according to their data quality. To demonstrate the effectiveness and efficiency of PACE, we evaluate it in a real-world dataset. The evaluation and analysis results show that PACE can prevent malicious behaviors of task participants and a task requester, and achieves both privacy-preserving and data quality measurement of task participants.

The minimum travel distance of task participants is one of the significant optimization objectives of privacy-preserving task assignment in mobile crowdsensing (MCS). However, when the travel distance is minimized, most of the previous schemes only focus on the task participant privacy and disregard the task requester privacy. Moreover, existing solutions usually only support the constraint of a single type, such as equality constraints or range constraints. In this paper, we propose a bilateral privacy-preserving Task Assignment mechanism for MCS (iTAM), which protects not only the task participants privacy but also the task requesters privacy and can minimize the travel distance. Furthermore, iTAM provides both equality and range constraints of task assignment by utilizing the Paillier cryptosystem. To accommodate the multiple relations between the task participants and the task, we propose the single/multiple task participants selection problems for a task requiring task participants to compete and cooperate. Experimental evaluations over synthetic and real-world data illustrate that iTAM is feasible and effective. Compared with the state-of-the-art, iTAM positively solves the optimal problem of travel distance. The complexities of iTAM are$\mathcal {O}(n)$and$\mathcal {O}(n\log n)$for a single and multiple task participants selection problems, respectively.

Smartphone localization is essential to a wide spectrum of applications in the era of mobile computing. The ubiquity of smartphone mobile cameras and surveillance ambient cameras holds promise for offering sub-meter accuracy localization services thanks to the maturity of computer vision techniques. In general, ambient-camera-based solutions are able to localize pedestrians in video frames at fine-grained, but the tracking performance under dynamic environments remains unreliable. On the contrary, mobile-camera-based solutions are capable of continuously tracking pedestrians; however, they usually involve constructing a large volume of image database, a labor-intensive overhead for practical deployment. We observe an opportunity of integrating these two most promising approaches to overcome above limitations and revisit the problem of smartphone localization with a fresh perspective. However, fusing mobile-camera-based and ambient-camera-based systems is non-trivial due to disparity of camera in terms of perspectives, parameters and incorrespondence of localization results. In this article, we propose iMAC, an integrated mobile cameras and ambient cameras based localization system that achieves sub-meter accuracy and enhanced robustness with zero-human start-up effort. The key innovation of iMAC is a well-designed fusing frame to eliminate disparity of cameras including a construction of projection map function to automatically calibrate ambient cameras, an instant crowd fingerprints model to describe user motion patterns, and a confidence-aware matching algorithm to associate results from two sub-systems. We fully implement iMAC on commodity smartphones and validate its performance in five different scenarios. The results show that iMAC achieves a remarkable localization accuracy of 0.68 m, outperforming the state-of-the-art systems by >75%.

Spatial crowdsourcing (SC) is a popular distributed problem-solving paradigm that harnesses the power of mobile workers (e.g., smartphone users) to perform location-based tasks (e.g., checking product placement or taking landmark photos). Typically, a worker needs to travel physically to the target location to finish the assigned task. Hence, the worker’s familiarity level on the target location directly influences the completion quality of the task. In addition, from the perspective of the SC server, it is desirable to finish all tasks with a low recruitment cost. Combining these issues, we propose a Bi-Objective Task Planning (BOTP) problem in SC, where the server makes a task assignment and schedule for the workers to jointly optimize the workers’ familiarity levels on the locations of assigned tasks and the total cost of worker recruitment. The BOTP problem is proved to be NP-hard and thus intractable. To solve this challenging problem, we propose two algorithms: a divide-and-conquer algorithm based on the constraint method and a heuristic algorithm based on the multi-objective simulated annealing algorithm. The extensive evaluations on a real-world dataset demonstrate the effectiveness of the proposed algorithms.

Mobile crowd sensing (MCS) is an emerging sensing paradigm that can be applied to build various smart city and IoT applications. In an MCS application, the participation level of mobile users plays an essential role. Thus a great many incentive mechanisms have been proposed to motivate users. However, most of these works focus on the bidding behavior of users and overlook the feature of task requesters. Specifically, there exists a disparity between the low payment a requester would like to make and the high reward a user would like to receive. In this work, we address this issue by designing a group-buying-based online incentive mechanism, which contains two stages: In Stage I, a price learning algorithm is designed to select winning tasks for each group of sensing tasks and obtain a competitive total budget for recruiting users. In Stage II, an online auction is conducted between group agents and online users before a given recruitment deadline. Through theoretical analysis and extensive evaluations, we show that the proposed mechanisms possess computational efficiency, individual rationality, budget balance, truthfulness, and good performance.

Smartphone localization is essential to a wide spectrum of applications in the era of mobile computing. The ubiquity of smartphone mobile cameras and surveillance ambient cameras holds promise for offering sub-meter accuracy localization services thanks to the maturity of computer vision techniques. In general, ambient-camera-based solutions are able to localize pedestrians in video frames at fine-grained, but the tracking performance under dynamic environments remains unreliable. On the contrary, mobile-camera-based solutions are capable of continuously tracking pedestrians, however, they usually involve constructing a large volume of image database, a labor-intensive overhead for practical deployment. We observe an opportunity of integrating these two most promising approaches to overcome above limitations and revisit the problem of smartphone localization with a fresh perspective. However, fusing mobile-camera-based and ambient-camera-based systems is non-trivial due to disparity of camera in terms of perspectives, parameters and incorrespondence of localization results. In this paper, we propose iMAC, an integrated mobile cameras and ambient cameras based localization system that achieves sub-meter accuracy and enhanced robustness with zero-human start-up effort. The key innovation of iMAC is a well-designed fusing frame to eliminate disparity of cameras including a construction of projection map function to automatically calibrate ambient cameras, an instant crowd fingerprints model to describe user motion patterns, and a confidence-aware matching algorithm to associate results from two sub-systems. We fully implement iMAC on commodity smart-phones and validate its performance in five different scenarios. The results show that iMAC achieves a remarkable localization accuracy of 0.68m, outperforming the state-of-the-art systems by > 75%.

Mobile crowd sensing (MCS) has become a powerful sensing paradigm that allows requesters to outsource location-based sensing tasks to a crowd of participating users carrying smart mobile devices. Aware of the paramount importance of incentivizing participation for MCS systems, researchers have proposed a wide variety of incentive mechanisms. Most of these mechanisms assume that the MCS platform can collect sufficient budget to recruit users, and hence only focus on incentivizing users efficiently. In this work, we consider MCS systems where the budget of a single task is insufficient for recruiting a user. Commonly, a task requester with a simple task (e.g., inquiring a photo of a restaurant) is willing to provide a low budget, while a user would like to earn a higher reward for his effort in completing a task (e.g., traveling a long distance to take a photo). To address this disparity issue between requesters and users, we propose a novel task-bundling-based two-stage incentive mechanism to incentivize both requesters and users. Through rigorous theoretical analysis and extensive simulations, we demonstrate that the proposed incentive mechanism satisfies the properties of computational efficiency, individual rationality, budget balance, truthfulness, and constant competitiveness.

With the rapid development of wireless networks and mobile devices, mobile crowdsensing (MCS) has enabled many smart city applications, which are key components in the Internet of Things. In an MCS system, the sufficient participation of mobile workers plays a significant role in the quality of sensing services. Therefore, researchers have studied various incentive mechanisms to motivate mobile workers in the literature. The existing works mostly focus on optimizing one objective function when selecting workers. However, some sensing tasks are associated with more than one objective inherently. This motivates us to investigate biobjective incentive mechanisms in this article. Specifically, we consider the scenario where the MCS system selects workers by optimizing the completion reliability and spatial diversity of sensing tasks. We first formulate the incentive model with two optimization goals and then design two online incentive mechanisms based on the reverse auction. We prove that the proposed mechanisms possess desirable properties, including computational efficiency, individual rationality, budget feasibility, truthfulness, and constant competitiveness. The experimental results indicate that the proposed incentive mechanisms can effectively optimize the two objectives simultaneously.

A reliable mobile crowdsensing (MCS) application usually relies on sufficient participants and trustworthy data. However, privacy concerns reduce participants' willingness to participate in sensing tasks. The uncertainty of participant behavior and heterogeneity of sensing devices result in the unreliability of sensing data and further bring unreliable MCS services. Hence, it is crucial to estimate the reliability of sensing data and protect privacy. Unfortunately, most existing privacy-preserving data estimation solutions are designed for single-type data. In practice, however, heterogeneous sensing data are ubiquitous in data integration tasks. To this end, we propose a privacy-preserving reliability estimation solution of heterogeneous data for MCS, called IronM, which is effective for text, number, and multimedia data (e.g., image, audio, and video). Specifically, IronM first formulates the reliability assessment of text, number, and multimedia data as equality and range constraints, and then estimates the reliability of heterogeneous data through our proposed privacy-preserving hybrid constraints assessment mechanism. Privacy analysis demonstrates that IronM can not only evaluate the reliability of heterogeneous data but also protect data confidentiality. The experimental results in real-world datasets show the effectiveness and efficiency of IronM.

Accurate forecast of citywide crowd flows on flexible region partition benefits urban planning, traffic management, and public safety. Previous research either fails to capture the complex spatiotemporal dependencies of crowd flows or is restricted on grid region partition that loses semantic context. In this paper, we propose DeepFlowFlex, a graph-based model to jointly predict inflows and outflows for each region of arbitrary shape and size in a city. Analysis on cellular datasets covering 2.4 million users in China reveals dependencies and distinctive patterns of crowd flows in not only the conventional space and time domains, but also the speed domain, due to the diverse transportation modes in the mobility data. DeepFlowFlex explicitly groups crowd flows with respect to speed and time, and combines graph convolutional long short-term memory networks and graph convolutional neural networks to extract complex spatiotemporal dependencies, especially long-term and long-distance inter-region dependencies. Evaluations on two big cellular datasets and public GPS trace datasets show that DeepFlowFlex outperforms the state-of-the-art deep learning and big-data-based methods on both grid and non-grid city map partition.

Spatial crowdsourcing (SC) is a promising framework for requesting workers (e.g., smartphone users) to perform location-based tasks (e.g., taking scenic photos or checking product placement). Specifically, to perform the assigned task, the worker needs to move physically to the target location, hence his familiarity with the target location has an impact on the efficiency and quality of the task completion. On the other hand, the SC server usually intends to finish all tasks with a low cost. Considering these factors, in this paper, we study a Bi-Objective Task Planning (BOTP) problem in SC, where the workers are assigned and scheduled to perform the appropriate tasks, such that the workers' familiarity with the locations of the spatial tasks and the SC server's cost for recruiting workers are jointly optimized. We prove that the BOTP problem is NP-hard and thus intractable. To tackle the BOTP problem, we propose a heuristic algorithm based on the multi-objective simulated annealing algorithm. The extensive experiments demonstrate the effectiveness of our proposed algorithm over a real-world dataset.

Online social networks (OSNs) are becoming more and more prevalent in people's life, but they face the problem of privacy leakage due to the centralized data management mechanism. The emergence of distributed OSNs (DOSNs) can solve this privacy issue, yet they bring inefficiencies in providing the main functionalities, such as access control and data availability. In this article, in view of the above-mentioned challenges encountered in OSNs and DOSNs, we exploit the emerging blockchain technique to design a new DOSN framework that integrates the advantages of both traditional centralized OSNs and DOSNs. By combining smart contracts, we use the blockchain as a trusted server to provide central control services. Meanwhile, we separate the storage services so that users have complete control over their data. In the experiment, we use real-world data sets to verify the effectiveness of the proposed framework.

Facial appearance transfer (FAT) is a critical component of various facial editing tasks. It aims to transfer the facial appearance of a reference into a target with good visual consistency. When there are considerable visual differences between a reference and a target, however, it may introduce visual artifacts into the results. To tackle this problem, we propose a facial appearance map with illumination-aware and region-aware properties that allows seamless FAT. We formulate the appearance-map generation as label propagation (LP) on a similarity graph, and propose a new regularization structure to facilitate the adaptive appearance-map diffusion. Solving the original LP model of appearance map in general requires on the order$O(kn^2)$time for an$n$-nodes graph where each node has$k$neighbors. It may be computationally prohibitive for an image with a large spatial resolution. To tackle this problem, we mathematically analyze the graph-based LP model and propose a fast algorithm with smart subset sampling. It selects a subset with$m$nodes of the graph with$n$nodes ($m\ll n$) to approximate the solution to the original system, which significantly reduces its computational requirements from$O(kn^2)$to$O(m^2n)$. Based on the adaptive LP-based appearance map, we construct a framework to achieve various editing effects with FAT, including face replacement, face dubbing, face swapping, and transfiguring. Comparisons with related methods show the effectiveness of the adaptive LP model for FAT. Qualitative and quantitative evaluations verify the computational improvements of the approximation algorithm.

Many trajectory-based applications require an essential step of mapping raw GPS trajectories onto the digital road network accurately. This task, commonly referred to as map matching, is challenging due to the measurement error of GPS devices in critical environment and the sampling error caused by long sampling intervals. Traditional algorithms focus on either a local or a global perspective to deal with the problem. To further improve the performance, this paper develops a novel map matching model that considers local geometric/topological information and a global similarity measure simultaneously. To accomplish the optimization goal in this complex model, we adopt an ant colony optimization algorithm that mimics the path finding process of ants transporting food in nature. The algorithm utilizes both local heuristic and global fitness to search the global optimum of the model. Experimental results verify that the proposed algorithm is able to provide accurate map matching results within a relatively short execution time.

Mobile crowdsourcing is an emerging complex problem solving paradigm that makes use of pervasive mobile devices equipped with multi-functional sensors. Recently, vehicles have also been increasingly adopted for mobile crowdsourcing, as the vehicles, as well as drivers, can provide diverse sensing capability and predictable mobility. Existing mobile crowdsourcing algorithms mostly recruit workers to complete one kind of sensing tasks, i.e., location-based query tasks or automatic sensing tasks. In this paper, we investigate the possibility of recruiting a set of vehicles to simultaneously complete these two categories of tasks, so as to maximize the sensing utility of each participant. We first model the worker recruitment for vehicle-based crowdsourcing as a bi-objective optimization problem with respect to the sensing capability and predictable mobility of vehicles. The recruitment problem is proven to be NP-hard, and we design two heuristic algorithms based on the bi-objective greedy strategy and the multi-objective genetic algorithm to find the solutions. The experimental results with a real-world traffic trace data set show that the proposed algorithms outperform some existing algorithms in finding solutions that maximize both objectives.

While location is one of the most important context information in mobile and pervasive computing, large-scale deployment of indoor localization system remains elusive. In this work, we propose MPiLoc, a multi-floor indoor localization system that utilizes data contributed by smartphone users through participatory sensing for automatic floor plan and radio map construction. Our system does not require manual calibration, prior knowledge, or infrastructure support. The key novelty of MPiLoc is that it clusters and merges walking trajectories annotated with sensor and signal strengths to derive a map of walking paths annotated with radio signal strengths in multi-floor indoor environments. We evaluate MPiLoc over five different indoor areas. Evaluation shows that our system can derive indoor maps for various indoor environments in multi-floor settings and achieve an average localization error of 1.82 m.

Cognitive diagnostic models (CDMs) are a new class of test models developed for educational assessment. They have gained growing attention in recent years for their distinctive ability to provide detailed feedback about examinees' ability. Automatic test assembly (ATA), as in other test models, has been one of the most critical issues in the development and applications of CDMs. However, developing ATA methods for CDMs is especially challenging because no close-form expressions can measure the quality of a test form based on the items used. Although some heuristic methods have been proposed for building a single test form of CDMs, few ATA methods can construct uniform test forms of CDMs, in which each test form contains a different set of items but meets equivalent demand of test quality. In order to fill the gap, this paper proposes a novel genetic algorithm (GA) for constructing uniform test forms of CDMs. The effectiveness and efficiency of the proposed method is validated on a synthetic item pool under different conditions.

This paper deals with the superpixel segmentation problem using a powerful global optimization technique: Differential Evolution. The algorithm mimics the process of nature evolution to realize efficient optimization, and it poses no restrictions on the form of objective functions. This way, we develop a novel and comprehensive objective function considering both local and global costs in the segmentation, including within-superpixel error, boundary gradient, a regularization term. The proposed method can produce superpixels in a computational time linear to the image size. Experimental results validate the competitive performance of our algorithm in terms of boundary adherence and segmentation capability.

Destination prediction is very important in location-based services such as recommendation of targeted advertising location. Most current approaches always predict destination according to existing trip based on history trajectories. However, no existing work has considered the difference between the effects of passing-by locations and the destination in history trajectories, which seriously impacts the accuracy of predicted results as the destination can indicate the purpose of traveling. Meanwhile, the temporal information of history trajectories in destination prediction plays an important role. On one hand, the history trajectories in different periods also differ in the influence, e.g., the history trajectories from last week can reflect the status quo more accurately than the history trajectories two years ago. On the other hand, the history trajectories in different time slots reflect different facts of traffic and moving habits of people, e.g., visiting a restaurant in the daytime and visiting a bar at night. Although a huge amount of history trajectories can be achieved in the era of big data, it is still far from covering all the query trajectories since a road network is widely distributed and trajectory data is sparse. The temporal sensitivity of history trajectories highlights the sparsity problem even more. Therefore, we propose a novel model T-DesP to solve the aforementioned problems. The model is comprised of two modules: trajectory learning and destination prediction. In the module of trajectory learning, a novel method called the mirror absorbing Markov chain model is proposed for modeling the trajectories for isolating the destination. We build a transition tensor to deduce the transition probability between each location pair in a particular time slot. To address the data sparsity problem, we fill the missing values in transition tensor through a context-aware tensor decomposition approach. In the module of destination prediction, an absorbing tensor is derived from the filled transition tensor, and the theoretical model is established for destination prediction. The experiments prove the effectiveness and efficiency of T-DesP.

Mobile sensing apps have proliferated rapidly over the recent years. Most of them rely on inference components heavily for detecting interesting activities or contexts. Existing work implements inference components using traditional models designed for balanced data sets, where the sizes of interesting (positive) and non-interesting (negative) data are comparable. Practically, however, the positive and negative sensing data are highly imbalanced. For example, a single daily activity such as bicycling or driving usually occupies a small portion of time, resulting in rare positive instances. Under this circumstance, the trained models based on imbalanced data tend to mislabel positive ones as negative. In this paper, we propose a new inference framework SLIM based on several machine learning techniques in order to accommodate the imbalanced nature of sensing data. Especially, guided under-sampling is employed to obtain balanced labelled subsets, followed by a similarity-based sampling that draws massive unlabelled data to enhance training. To the best of our knowledge, SLIM is the first model that considers data imbalance in mobile sensing. We prototype two sensing apps and the experimental results show that SLIM achieves higher recall (activity recognition rate) while maintaining the precision compared with five classical models. In terms of the overall recall and precision, SLIM is around 12 percent better than the compared solutions on average.

Crowdsourcing-based mobile applications are becoming more and more prevalent in recent years, as smartphones equipped with various built-in sensors are proliferating rapidly. The large quantity of crowdsourced sensing data stimulates researchers to accomplish some tasks that used to be costly or impossible, yet the quality of the crowdsourced data, which is of great importance, has not received sufficient attention. In reality, the low-quality crowdsourced data are prone to containing outliers that may severely impair the crowdsourcing applications. Thus in this work, we conduct pioneer investigation considering crowdsourced data quality. Specifically, we focus on estimating user motion trajectory information, which plays an essential role in multiple crowdsourcing applications, such as indoor localization, context recognition, indoor navigation, etc. We resort to the family of robust statistics and design a robust trajectory estimation scheme, name TrMCD, which is capable of alleviating the negative influence of abnormal crowdsourced user trajectories, differentiating normal users from abnormal users, and overcoming the challenge brought by spatial unbalance of crowdsourced trajectories. Two real field experiments are conducted and the results show that TrMCD is robust and effective in estimating user motion trajectories and mapping fingerprints to physical locations.

Off-the-shelf smartphones have boosted large scale participatory sensing applications as they are equipped with various functional sensors, possess powerful computation and communication capabilities, and proliferate at a breathtaking pace. Yet the low participation level of smartphone users due to various resource consumptions, such as time and power, remains a hurdle that prevents the enjoyment brought by sensing applications. Recently, some researchers have done pioneer works in motivating users to contribute their resources by designing incentive mechanisms, which are able to provide certain rewards for participation. However, none of these works considered smartphone users' nature of opportunistically occurring in the area of interest. Specifically, for a general smartphone sensing application, the platform would distribute tasks to each user on her arrival and has to make an immediate decision according to the user's reply. To accommodate this general setting, we design three online incentive mechanisms, named TBA, TOIM and TOIMAD, based on online reverse auction. TBA is designed to pursue platform utility maximization, while TOIM and TOIM-AD achieve the crucial property of truthfulness. All mechanisms possess the desired properties of computational efficiency, individual rationality, and profitability. Besides, they are highly competitive compared to the optimal offline solution. The extensive simulation results reveal the impact of the key parameters and show good approximation to the state-of-the-art offline mechanism.

Indoor localization has enabled a great number of mobile and pervasive applications, attracting attentions from researchers worldwide. Most of current solutions rely on Received Signal Strength (RSS) of wireless signals as location fingerprint, to discriminate locations of interest. Fingerprint uniqueness with respect to locations is a basic requirement in these fingerprinting-based solutions. However, due to insufficient number of signal sources, temporal variations of wireless signals, and rich multipath effects, such requirement is not always met in complex indoor environments, which we refer to as fingerprint ambiguity. In this work, we explore the potential of leveraging user motion against fingerprint ambiguity. Our basic idea is that user motion patterns collected by built-in sensors of mobile phones add to the diversity built by RSS fingerprints. On this basis, we propose MoLoc, a motion-assisted localization scheme implemented on mobile phones. MoLoc can easily be integrated in existing localization systems by simply adding a motion database that is constructed automatically by crowdsourcing. We conducted experiments in a large office hall. The experiment results show that MoLoc doubles the localization accuracy achieved by the fingerprinting method, and limits the mean localization error to less than 1m.