Mobile Crowdsensing Platform Research Articles

Malicious Participants and Fake Task Detection Incorporating Gaussian Bias

Mobile crowdsensing (MCS) is a combination of crowdsourcing ideas and mobile sensing devices, designed to enable rational allocation of resources at scale. However, the MCS platform is highly vulnerable to injection attacks from malicious participants and fake tasks that interfere with platform service capabilities and sensing activities. To this end, the participant and task submission process is modeled as a multivariate time series, and a detection model for malicious participants and fake tasks (MP-FTD) with a Gaussian prior on the attentional mechanism and a two-stage adversarial training process is proposed. The attention mechanism was corrected using Gaussian bias, and then the corrected attention mechanism was used to obtain the correlation discrepancies between the data. Using the adversarial training method of Generative Adversarial Networks (GAN), the output of the correlation discrepancy reconstruction phase is transformed into a focus score, to amplify the reconstruction error in the output of the focus score reconstruction phase, and to improve the differentiation between the injected data and normal data of malicious attackers. The detection of these malicious attackers will effectively improve the robustness of the sensing platform. Experiments on six real-world datasets showed that the average F1-score reached 93.44%, outperforming the current baseline method, and resulting in an average 12.07% improvement in participant assignment accuracy and an average 12.25% improvement in task assignment accuracy in task assignment experiments.

A UAV deployment strategy based on a probabilistic data coverage model for mobile CrowdSensing applications

Mobile CrowdSensing (MCS) is a computational paradigm designed to gather sensing data by using personal devices of MCS platform users. However, being the mobility of devices tightly correlated with mobility of their owners, the locations from which data are collected might be limited to specific sub-regions. We extend the data coverage capability of a traditional MCS platform by exploiting unmanned aerial vehicles (UAV) as mobile sensors gathering data from low covered locations. We present a probabilistic model designed to measure the coverage of a location. The model analyses the user’s trajectories and the detouring capability of users towards locations of interest. Our model provides a coverage probability for each of the target locations, so that to identify low-covered locations. In turn, these locations are used as targets for the StationPositioning algorithms which optimizes the deployment of k UAV stations. We analyze the performance of StationPositioning by comparing the ratio of the covered locations against Random, DBSCAN and KMeans deployment algorithm. We explore the performance by varying the time period, the deployment regions and the existence of areas where it is not possible to deploy any station. Our experimental results show that StationPositioning is able to optimize the selected target location for a number of UAV stations with a maximum covered ratio up to 60%.

An evolutionary multi-task assignment method adapting to travel convenience in mobile crowdsensing

Mobile crowdsensing (MCS) is a powerful IoT sensing model that leverages the mobility of workers and the sensors embedded in smartphones to sense diverse phenomena in the city. The task assignment in MCS is primarily location-based, with workers traveling to the corresponding location to complete tasks. Assigning tasks that are far away from a worker’s destination may cause inconvenience. Thus, this paper shortens remaining distances to improve workers’ travel convenience, which may, however, negatively impact the MCS platform’s utility. To strike a balance between these two objectives, we assign different weights to them and transfer them into a single objective optimization problem. Then we propose an evolutionary algorithm, the Travel Convenience Adaptive algorithm based on Genetic Algorithm (TCA-GA), to solve the objective optimization problem. We determine the appropriate weights for each objective under different experiment settings and conduct an experimental analysis based on synthetic and real-world datasets. The results verify that the proposed algorithm can effectively improve workers’ travel convenience while the MCS platform’s utility is maintained at a high level.

Truth based three-tier Combinatorial Multi-Armed Bandit ecosystems for mobile crowdsensing

Many Multi-Armed Bandit (MAB) based workers selection schemes have been proposed to select high-quality workers to enhance the quality of tasks. However, in Mobile Crowd Sensing (MCS), a complex mutual effect exists among task requestors, the MCS platforms, and workers. Only considering the interaction of two sides doesn’t make MCS a balanced ecosystem. Therefore, it is urgent to establish a tripartite mutual incentive mechanism to make the MCS system a balanced ecosystem. In this paper, a truth based Three-tier Combinatorial Multi-Armed Bandit (TCMAB) incentive mechanism is proposed for selecting each other to maximize their revenues in MCS. In TCMAB, there exists a three-tier and two-way MAB-based incentive scheme. For the mutual interaction between the platform and the worker, a truth-based CMAB scheme is established for the platform to select high-quality workers, and also a CMAB scheme is proposed for workers to select a “good” platform to report data in order to maximize their revenue. Besides, for the mutual interaction between the task requestor and the platform, the platforms adopt the CMAB-based scheme to select a high-payment task requestor that gives high payment. And a platform selection scheme base on CMAB is also established for task requestors to select the platforms which have lower fees and higher quality. What’s more, we don’t adopt the assumption that platforms get the data quality as soon as they get data, but propose a data quality acquisition scheme based on the truth data discovery and cooperation frequency, which is the base to instruct the three-tier interaction, thus establish a kind of truth-based MCS interaction ecosystems. Simulation results show that the proposed TCMAB provides an effective solution for the problem of information elicitation without verification (IEWV) in MCS, and can improve the utilities, data quality, and applications quality for MCS, which is not achieved in the previous studies significantly.

Credit and quality intelligent learning based multi-armed bandit scheme for unknown worker selection in multimedia MCS

The field of intelligent multimedia systems, which rely heavily on multimodal models trained on large amounts of high-quality data, has been revolutionized by the use of deep learning. One promising approach to collect such multimodal data is Mobile Crowd Sensing (MCS). However, MCS platforms face a significant challenge in selecting both high-credit and high-quality workers at low cost due to the Post-Unknown Worker Recruitment (PUWR) problem. The PUWR problem makes it difficult to determine the credits and qualities of workers in advance, which can lead to the recruitment of dishonest or low-quality workers. This problem severely affects the quality and quantity of MCS data collection, posing a serious threat to the security and robustness of large-scale multimedia models. To address this issue, we propose a Credit and Quality Learning based Multi-Armed Bandit (CQL-MAB) scheme, which consists of a novel credit identification algorithm, a fine-grained worker quality calculation method, and a two-stage reward-based Multi-Armed Bandit (MAB) for worker selection in reverse auction. The theoretical proof shows that the CQL-MAB scheme achieves the truthfulness, individual rationality, and efficiency of the auction mechanism. A large number of simulation experiments on real data traces are conducted to demonstrate the outstanding performance of CQL-MAB.

Practical Byzantine Fault Tolerance Based Robustness for Mobile Crowdsensing

Mobile crowdsensing (MCS) has become a prominent paradigm to collect and share data based on sensing devices with built-in sensors in the Internet of Things era. Nevertheless, conventional MCS confronts various security and privacy vulnerabilities in terms of decentralized, openness, and non-dedicated properties. Currently, the submitted tasks are collected and managed conventionally by a centralized MCS platform. A centralized MCS platform is not safe enough to protect and prevent tampering sensing tasks since it confronts the single point of failure, which reduces the effectiveness and robustness of the MCS system. Meanwhile, fake task attack is a serious threat, as it would drain excessive resources from the participant devices and clog the MCS servers to disrupt the services offered by the MCS. To address the centralized issue and identify fake tasks, a blockchain-based decentralized MCS is designed. Integration of blockchain into MCS enables a decentralized framework. Moreover, the distributed nature of a blockchain chain prevents sensing tasks from being tampered. The blockchain uses a practical Byzantine fault tolerance consensus that can tolerate one-third faulty nodes, making the implemented MCS system robust and sturdy. In addition, an ensemble learning approach is deployed in the blockchain for eliminating fake tasks by malicious requesters. The evaluation test is conducted under two different datasets representing a big city and a small one to have an MCS campaign. Numerical results show that the ensemble approach eliminates most of the fake tasks with a detection accuracy of up to 0.99. Furthermore, the ensemble learning integrated system outperforms individual learner based centralized systems, and non-fault tolerant systems in terms of Ratio of Legitimate Tasks (RoLT) saved and Ratio of Fake Tasks (RoFT).RoFTis low to 0.01, andRoLTis high up to 0.913 via the proposed MCS blockchain-driven framework.

Dynamic Task Assignment Framework for Mobile Crowdsensing with Deep Reinforcement Learning

Task assignment is a key issue in mobile crowdsensing (MCS). Previous task assignment methods were mainly static offline assignment. However, the MCS platform needs to process dynamically changing workers and tasks online in the actual assignment process. Hence, a reliable dynamic assignment strategy is crucial to improving the platform’s efficiency. This paper proposes an MCS dynamic task assignment framework to solve the task maximization assignment problem with spatiotemporal properties. First, a single worker is modeled for the Markov decision process, and a deep reinforcement learning algorithm (DDQN) is used to perform offline learning on historical task data. Then, in the dynamic assignment process, we consider the impact of current decisions on future decisions. Use the maximum flow model to maximize the number of tasks completed in each period while maximizing the expected Q value of all workers to achieve the optimal global assignment. Experiments show that the strategy proposed in this paper has good performance compared with the baseline strategy under different conditions.

Incentive Mechanism with Task Bundling for Mobile Crowd Sensing

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.

Beach and Weather: A Mobile Crowdsensing platform to report beach conditions

Beach and Weather: A Mobile Crowdsensing platform to report beach conditions

PSARE: A RL-Based Online Participant Selection Scheme Incorporating Area Coverage Ratio and Degree in Mobile Crowdsensing

Mobile crowdsensing (MCS) is a cost-effective paradigm for gathering real-time and location-related urban sensing data. To complete MCS tasks, MCS platform needs to exploit the trajectory of participants (vehicles or individuals, etc.) for effectively choosing participants. On one hand, the existing works usually assume that platform has possessed the abundant historical movement trajectory for participant selection, or can accurately predict the movement of participant before selection, but this assumption is impractical for many MCS applications, for some candidates have just arrived without sufficient mobility profiles, so-called trajectory from-scratch, or cold-trajectory issue. On the other hand, most of works only considers the coverage ratio of the sensing area, while some hotspots should be sensed frequently, so-called coverage degree of hotspots. To solve the issue, this paper proposes a reinforcement learning (RL) based, i.e., an improved Q-learning based online participant selection scheme to incorporate both coverage ratio and degree, PSARE. First, to solve the explosion of state-value table in traditional tabular Q-learning, an improved two-level Q-learning method is proposed to select participants in online way so as to achieve high long-term return. Specifically, in each selection round, PSARE dynamically compresses all the real participants (RPs) into several virtual participants (VPs) using the available historical trajectories of RPs, and the VP-based state-value table is constructed and constantly updated (i.e., the first level). Then, after selecting the VP through looking up the table, PARSE chooses the RP with the largest expected reward in this VP using epsilon-greedy way to balance the effect of exploration and exploitation (i.e., the second level). Moreover, the reward function is designed to measure the MCS coverage quality, including both coverage degree of hotspots and coverage ratio of target area. Thorough experiments on real-world mobility data set demonstrate that PSARE outperforms than other RL based online participant selection schemes (including deep Q-learning network) and traditional offline selection methods.

An Adaptive Data Uploading Scheme for Mobile Crowdsensing via Deep Reinforcement Learning With Graph Neural Network

Mobile crowdsensing (MCS), as an alternative to traditional sensor networks, has attracted much research attention because of its flexibility and low deployment fee. Compared with the traditional sensor networks, MCS exploits existing network infrastructures (such as edge servers and user devices) to intelligently cooperate with smart device owners. In this way, MCS combines machine intelligence and human intelligence to perform various sensing tasks more efficiently with a significantly lower cost. A challenging problem in MCS is data uploading, where mobile phone users as workers need to upload collected data to an MCS platform. In Xu and Song (2022), we proposed a heuristic approach to make a data transmission plan between mobile phone users and edge servers, which can help an MCS system leverage network resources in edge servers to facilitate data uploading efficiently. In this article, we reinvestigate the data uploading problem in Xu and Song (2022), analyze the heuristic approach’s drawbacks, and propose a deep reinforcement learning (DRL)-based method to complement these drawbacks. Specifically, we show that the heuristic approach may not sufficiently address heterogeneous cases, although it can achieve high efficiency in the homogeneous scenarios. Furthermore, we find that the heuristic method is not a one-fit-for-all method and cannot adjust itself when facing new scenarios. Instead of making a new fixed heuristic to deal with these new scenarios, we design an adaptive method based on DRL and graph neural networks (GNNs) to learn heuristics, enabling the new method to handle all possible situations in theory. Specifically, we train a DRL agent with a group of data uploading instances and then generalize the agent to other instances. Extensive numerical results show that the DRL-based approach achieves a high approximation ratio and performs stably in all sorts of experiment settings.

Dynamic Delayed-Decision Task Assignment Under Spatial-Temporal Constraints in Mobile Crowdsensing

Task assignment is a research focus of Mobile Crowd Sensing(MCS). On the arrival of a sensing task, most researches use the way of immediate recruitment to assign the task, ignoring the impact of the task assignment time point. However, the arrival time and start time of a task are often different, hence an earlier assignment decision leads to rough predictions of users reaching the destination of task, which reduces task completion ratio and budget utilization ratio. In order to solve this problem, in this paper we propose a dynamic delayed-decision task assignment method. Firstly, we formalize a new task assignment problem considering the time point of task assignment, in which each selected user can complete as many tasks as possible within the given spatial-temporal constraints, rather than only one task, and propose a method of decision time point selection using a delayed-decision strategy to deal with the tasks of dynamically arriving at the MCS platform. Secondly, we propose two mobility prediction methods to efficiently compute the probabilities of users reaching the destinations before the end time of the sensing tasks, and then propose the related task assignment algorithms, namely with TDMar and TDMeta, which use the proposed semi-Markov prediction and meta-path prediction, respectively. Finally, by using large-scale real data sets, we evaluate the two algorithms and compare them with the baseline methods. The results show that using delayed-decision strategy could evidently improve the task completion ratio and budget utilization ratio, and also decrease the user singleness.

Efficient Data Uploading for Mobile Crowdsensing via Team Collaborating and Matching

With the proliferation of mobile devices and crowdsensing applications, mobile crowdsensing (MCS) has been an appealing sensing paradigm as an alternative to the traditional sensor networks. Instead of deploying static and expensive sensors in sensing areas, MCS leverages sensors embedded in mobile devices and intelligence of mobile users to sense their surroundings, which utilizes the existing communication infrastructure. In a typical sensing cycle in MCS, recruited mobile users as workers collect data according to specified requirements and upload them to an MCS platform. A challenging problem of MCS is data uploading, which requires workers to upload their collected data in a cost-effective manner. A promising solution is to integrate edge computing and exploit the redundant resources of various edge nodes to facilitate data uploading. In this paper, we investigate such a data uploading problem in MCS, which incorporates collaborations among multiple edge nodes and properly matches a team of edge nodes with a sensing worker according to various constraints. Notably, we ensure that the demand of a worker for data uploading is fully satisfied even if served by multiple edge nodes. As we prove that the problem is NP-hard, we propose an efficient solution based on Lagrangian relaxation. Extensive numerical results show that our approach achieves a high approximation ratio and performs stably in various experiment settings.

A Stackelberg Game Approach for Managing AI Sensing Tasks in Mobile Crowdsensing

Mobile Crowdsensing (MCS) is a new paradigm that leverages the collective sensing ability of a crowd so that a special task can be performed through the aggregation of information collected from personal mobile devices. While MCS brings several benefits, its application is prevented by challenges such as the efficient recruitment of users, effective mechanisms for rewarding users to encourage participation, and an effective and fast enough approach for managing the underlying resources that support large-scale MCS applications involving a large number of people in data collection. On the other hand, Artificial Intelligence (AI) applications, which are mostly based on Deep Neural Networks (DNN), are becoming pervasive today and are executed by the end users’ mobile devices, which are characterised by limited memory and computing power, and low battery level. This paper describes and evaluates an incentive mechanism for a mobile crowdsensing system with an AI sensing task based on a one-leader multi-follower Stackelberg game. The MCS platform, as a leader, provides an AI sensing task to be executed by a DNN, which can be deployed in two different ways: fully on the user device or partially on the device and partially on edge or cloud resources. The users, as followers, make their decisions regarding their participation to the MCS system and select their desired deployment given the energy and memory available on their device and the deployment reward proposed by the MCS platform. The goals of the MCS platform are: i) to motivate the users to participate in the system, ii) to maximize its profit, and iii) to identify the optimal resources supporting the sensing task that minimizes the cost and provide performance guarantees. This problem has been formulated as a mixed integer nonlinear program and propose an efficient algorithmic approach to solve it quickly. The proposed approach has been compared with some baseline methods and with BARON state-of-the-art solver. Results show that our approach converges to the optimal solution much faster than BARON (up to orders of magnitude) especially in large scale systems. Furthermore, the comparison to the baseline methods shows that our approach always beats the best baseline method under different scenarios providing up to 16% improvement for the MCS platform profit.

Self-Adaptive Learning and Cellular Automata based Mobile Crowdsensing

Mobile Crowdsensing (MCS) is frequently utilized for computation assignments, but it is particularly useful for sensing complicated environments. Previously, the MCS platform spent a lot of time and effort establishing incentive mechanisms and task assignment algorithms to encourage mobile users to participate. In actuality, because of their sensing environment and other participants' methodologies, MCS participants face numerous uncertainties, and it is unknown how they interact with one another and make sensing decisions. This study uses the perspectives of MCS participants to develop a web detection arrangement that will maximize their payoffs through MCS participation. Self-adaptive cellular automata-based Markov decision process exhibits interactions among mobile clients and detecting contexts. With the help of Self-Adaptive Support Learning (SASL) and Cellular Automata (CA), we developed a novel method that uses the ideal detecting technique for each client to improve the predicted payoff against random detecting scenarios in a stochastic multi-agent environment. With distinct dynamic sensing, the SASL and CA based smart Crowdsensing enhances user’s payoff, as shown in the simulation.

MP-Coopetition: Competitive and Cooperative Mechanism for Multiple Platforms in Mobile Crowd Sensing

Mobile Crowd Sensing (MCS) enables the platform to offer data-based service by incentivizing mobile users to perform sensing task and collecting sensing data from them. Most of the existing works on MCS only consider designing incentive mechanisms for a single MCS platform. In this paper, we study the incentive mechanism in MCS with multiple platforms under two scenarios: competitive platform and cooperative platform. We correspondingly propose new competitive and cooperative mechanisms for each scenario. In the competitive platform scenario, platforms decide their prices on rewards to attract more participants, while the users choose which platform to work for. We model such a competitive platform scenario as a two-stage Stackelberg game. In the cooperative platform scenario, platforms cooperate to share sensing data with each other. We model it as many-to-many bargaining. Moreover, we first prove the NP-hardness of exact bargaining and then propose heuristic bargaining. Finally, numerical results show that (1) platforms in the competitive platform scenario can guarantee their payoff by optimally pricing on rewards and participants can select the best platform to contribute; (2) platforms in the cooperative platform scenario can further improve their payoff by bargaining with other platforms for cooperatively sharing collected sensing data.

#Safe Mapping Platform: A GIS Mobile Crowd Sensing Platform for COVID-19 Self-Tracking and Self-Risk Managing

Increases in the social sector of open data and online mapping technologies are starting new chances for interactive mapping in many research applications. Mobile crowd sensing is an application that gathers data from a network of conscientious volunteers and implements it for a public benefit which is very helpful for collecting related information during the COVID-19 situation. The paper aims to demonstrate the concept of #Safe Mapping Platform which followed a framework of opensource technology and implementation aspects. The #Safe Mapping Platform was established for self-tracking and self-risk managing by integrating GIS opensource technologies, location-based services, and LINE application. The developed platform can be adapted to the public for self-tracking and self-risk managing in any health issues in the future.

Task coalition formation for Mobile CrowdSensing based on workers' routes preferences

In this paper, we address the problem of task allocation in Mobile Crowdsensing (MCS) by means of forming tasks publisher coalition taking into consideration workers' route preferences. In prior research works, only one of the MCS components (either task publishers, contributors or platform) dominates the task allocation process. Currently, other approaches have investigated tasks coalition based on their geographical locations. In this paper, we address the aforementioned problem by proposing a new scheme taking into accounts the interest of all the participating parties. To this end, our approach provides (1) strategies for selecting the best routes for workers with better long-term earnings and (2) task publishers' coalition formation based on worker's routes selection and preferences regardless of the order of individual execution of tasks. We proposed two models for the coalition formation: i) a centralized approach to solve the problem of the coalition formation together with the route selection, and ii) a simplified heuristic version that first determines disjoint tasks' coalitions based on the preferred routes selected by workers, then, MCS platform sorts the coalitions with best quality of information and selects the best routes for each ordered coalition. Simulation results with real data-set show that the coalition of task publishers together with the distributed route selection per worker does guarantee the quality of information satisfaction of the sensing tasks while enhancing the worker payment.

RL-Recruiter+: Mobility-Predictability-Aware Participant Selection Learning for From-Scratch Mobile Crowdsensing

Participant selection is a fundamental research issue in Mobile Crowdsensing (MCS). Previous approaches commonly assume that adequately long periods of candidate participants’ historical mobility trajectories are available to model their patterns before the selection process, which is not realistic for some new MCS applications or platforms. The sparsity or even absence of mobility traces will incur inaccurate location prediction, thus undermining the deployment of new MCS applications. To this end, this paper investigates a novel problem called “From-Scratch MCS” (FS-MCS for short), in which we study how to intelligently select participants to minimize such a “cold-start” effect. Specifically, we propose a novel framework based on reinforcement learning, named RL-Recruiter+. With the gradual accumulation of mobility trajectories over time, RL-Recruiter+ is able to make a good sequence of participant selection decisions for each sensing slot. Compared to its previous version, RL-Recruiter, Re-Recruiter+ jointly considers both the previous coverage and current mobility predictability when training the participant selection decision model. We evaluate our approach experimentally based on two real-world mobility datasets. The results demonstrate that RL-Recruiter+ outperforms the baseline approaches, including RL-Recruiter under various settings.

BioMCS 2.0: A distributed, energy-aware fog-based framework for data forwarding in mobile crowdsensing

Mobile crowdsensing (MCS) paradigm enables users equipped with energy-constrained smart devices to participate in sensing and reporting of assigned tasks. To achieve seamless communication as well as effective energy and resource management, we leveraged the fog computing platform to propose a centralized, energy-efficient and robust data collection framework, called bioMCS, based on the topological properties of a biological network called transcriptional regulatory network. However, since MCS platforms may potentially entail a high number of mobile users and massive volumes of data traffic, we extend the current work under the name bioMCS 2.0 to conceive a distributed energy-aware data forwarding mechanism where the fog devices function as task data relay nodes. bioMCS 2.0 combines energy-awareness, abundance of subgraphs (called motifs) in the fog network and proximity to the base station to perform efficient task sensing and forwarding in a dynamic scenario where fog devices are both energy constrained and mobile. It also ensures quality of information by accepting task data from reliable smart devices. Extensive simulation on the map of New York City and realistic mobility models suggests that bioMCS 2.0 exhibits comparable performance in terms of data delivery, latency and energy efficiency in comparison with both random next hop (fog node) selection as well as centralized forwarding technique that rely on global network knowledge.