Collision-free parking recommendation based on multi-agent reinforcement learning in vehicular crowdsensing

The recent proliferation of Fifth-Generation(5G)networks and Sixth-Generation(6G)networks has given rise to Vehicular Crowd Sensing(VCS)systems which solve parking collisions by effectively incentivizing vehicle participation.However,instead of being an isolated module,the incentive mechanism usually interacts with other modules.Based on this,we capture this synergy and propose a Collision-free Parking Recommendation(CPR),a novel VCS system framework that integrates an incentive mechanism,a non-cooperative VCS game,and a multi-agent reinforcement learning algorithm,to derive an optimal parking strategy in real time.Specifically,we utilize an LSTM method to predict parking areas roughly for recommendations accurately.Its incentive mechanism is designed to motivate vehicle participation by considering dynamically priced parking tasks and social network effects.In order to cope with stochastic parking collisions,its non-cooperative VCS game further analyzes the uncertain interactions between vehicles in parking decision-making.Then its multi-agent reinforcement learning algorithm models the VCS campaign as a multi-agent Markov decision process that not only derives the optimal collision-free parking strategy for each vehicle independently,but also proves that the optimal parking strategy for each vehicle is Pareto-optimal.Finally,numerical results demonstrate that CPR can accomplish parking tasks at a 99.7%accuracy compared with other baselines,efficiently recommending parking spaces.

Achieving dynamic privacy measurement and protection based on reinforcement learning for mobile edge crowdsensing of IoT

With the maturity and development of 5G field,Mobile Edge CrowdSensing(MECS),as an intelligent data collection paradigm,provides a broad prospect for various applications in IoT.However,sensing users as data uploaders lack a balance between data benefits and privacy threats,leading to conservative data uploads and low revenue or excessive uploads and privacy breaches.To solve this problem,a Dynamic Privacy Measurement and Protection(DPMP)framework is proposed based on differential privacy and reinforcement learning.Firstly,a DPM model is designed to quantify the amount of data privacy,and a calculation method for personalized privacy threshold of different users is also designed.Furthermore,a Dynamic Private sensing data Selection(DPS)algorithm is proposed to help sensing users maximize data benefits within their privacy thresholds.Finally,theoretical analysis and ample experiment results show that DPMP framework is effective and efficient to achieve a balance between data benefits and sensing user privacy protection,in particular,the proposed DPMP framework has 63%and 23%higher training efficiency and data benefits,respectively,compared to the Monte Carlo algorithm.

An Incentive Mechanism Model for Crowdsensing with Distributed Storage in Smart Cities

Crowdsensing,as a data collection method that uses the mobile sensing ability of many users to help the public collect and extract useful information,has received extensive attention in data collection.Since crowdsensing relies on user equipment to consume resources to obtain information,and the quality and distribution of user equipment are uneven,crowdsensing has problems such as low participation enthusiasm of participants and low quality of collected data,which affects the widespread use of crowdsensing.This paper proposes to apply the blockchain to crowdsensing and solve the above challenges by utilizing the characteristics of the blockchain,such as immutability and openness.An architecture for constructing a crowdsensing incentive mechanism under distributed incentives is proposed.A multi-attribute auction algorithm and a k-nearest neighbor-based sensing data quality determination algorithm are proposed to support the architecture.Participating users upload data,determine data quality according to the algorithm,update user reputation,and realize the selection of perceived data.The process of screening data and updating reputation value is realized by smart contracts,which ensures that the information cannot be tampered with,thereby encouraging more users to participate.Results of the simulation show that using two algorithms can well reflect data quality and screen out malicious data.With the help of blockchain performance,the architecture and algorithm can achieve decentralized storage and tamper-proof information,which helps to motivate more users to participate in perception tasks and improve data quality.

UAV Frequency-based Crowdsensing Using Grouping Multi-agent Deep Reinforcement Learning

Mobile CrowdSensing(MCS)is a promising sensing paradigm that recruits users to cooperatively perform sensing tasks.Recently,unmanned aerial vehicles(UAVs)as the powerful sensing devices are used to replace user participation and carry out some special tasks,such as epidemic monitoring and earthquakes rescue.In this paper,we focus on scheduling UAVs to sense the task Point-of-Interests(PoIs)with different frequency coverage requirements.To accomplish the sensing task,the scheduling strategy needs to consider the coverage requirement,geographic fairness and energy charging simultaneously.We consider the complex interaction among UAVs and propose a grouping multi-agent deep reinforcement learning approach(G-MADDPG)to schedule UAVs distributively.G-MADDPG groups all UAVs into some teams by a distance-based clustering algorithm(DCA),then it regards each team as an agent.In this way,G-MADDPG solves the problem that the training time of traditional MADDPG is too long to converge when the number of UAVs is large,and the trade-off between training time and result accuracy could be controlled flexibly by adjusting the number of teams.Extensive simulation results show that our scheduling strategy has better performance compared with three baselines and is flexible in balancing training time and result accuracy.

A Differentially Private Data Aggregation Method Based on Worker Partition and Location Obfuscation for Mobile Crowdsensing

With the popularity of sensor-rich mobile devices,mobile crowdsensing(MCS)has emerged as an effective method for data collection and processing.However,MCS platform usually need workers’precise locations for optimal task execution and collect sensing data from workers,which raises severe concerns of privacy leakage.Trying to preserve workers’location and sensing data from the untrusted MCS platform,a differentially private data aggregation method based on worker partition and location obfuscation(DP-DAWL method)is proposed in the paper.DP-DAWL method firstly use an improved K-means algorithm to divide workers into groups and assign different privacy budget to the group according to group size(the number of workers).Then each worker’s location is obfuscated and his/her sensing data is perturbed by adding Laplace noise before uploading to the platform.In the stage of data aggregation,DP-DAWL method adopts an improved Kalman filter algorithm to filter out the added noise(including both added noise of sensing data and the system noise in the sensing process).Through using optimal estimation of noisy aggregated sensing data,the platform can finally gain better utility of aggregated data while preserving workers’privacy.Extensive experiments on the synthetic datasets demonstrate the effectiveness of the proposed method.

A Blockchain Based Mobile Crowdsensing Market

Mobile crowdsensing(MCS)is an emerging pattern which means task initiators attract mobile users sensing with their own devices by some platforms.MCS could exploit idle resources in low cost,while it has lots of flaws,which impede its developments.First,isolations between different MCS systems leads to wastage of social resources.What’s more,current MCS always operate in a centralized way,which causes it vulnerable and unbelievable.Blockchain is a promising technology which could supply a credible and transparent environment.This paper construct a blockchain based MCS market and design smart contract for its operation.In our design,platform breaks isolation by blockchain,task initiators and mobile users manage their tasks by smart contract and bargain price with distributed algorithm.By this way,resource could be exploited better,and the market could be more fair.What’s more,the paper analyzes Walrasian Equilibrium(WE)in the market,and details how to deploy MCS in blockchain.Evalution results shows that Equilibrium could be found.

Enhancing Task Assignment in Crowdsensing Systems Based on Sensing Intervals and Location

The popularity of mobile devices with sensors is captivating the attention of researchers to modern techniques,such as the internet of things(IoT)and mobile crowdsensing(MCS).The core concept behind MCS is to use the power of mobile sensors to accomplish a difficult task collaboratively,with each mobile user completing much simpler micro-tasks.This paper discusses the task assignment problem in mobile crowdsensing,which is dependent on sensing time and path planning with the constraints of participant travel distance budgets and sensing time intervals.The goal is to minimize aggregate sensing time for mobile users,which reduces energy consumption to encourage more participants to engage in sensing activities and maximize total task quality.This paper introduces a two-phase task assignment framework called location time-based algorithm(LTBA).LTBA is a framework that enhances task assignment in MCS,whereas assigning tasks requires overlapping time intervals between tasks and mobile users’tasks and the location of tasks and mobile users’paths.The process of assigning the nearest task to the mobile user’s current path depends on the ant colony optimization algorithm(ACO)and Euclidean distance.LTBA combines two algorithms:(1)greedy online allocation algorithm and(2)bio-inspired traveldistance-balance-based algorithm(B-DBA).The greedy algorithm was sensing time interval-based and worked on reducing the overall sensing time of the mobile user.B-DBA was location-based and worked on maximizing total task quality.The results demonstrate that the average task quality is 0.8158,0.7093,and 0.7733 for LTBA,B-DBA,and greedy,respectively.The sensing time was reduced to 644,1782,and 685 time units for LTBA,B-DBA,and greedy,respectively.Combining the algorithms improves task assignment in MCS for both total task quality and sensing time.The results demonstrate that combining the two algorithms in LTBA is the best performance for total task quality and total sensing time,and the greedy algorithm follows it then B-DBA.

Secure Mobile Crowdsensing Based on Deep Learning

To improve the quality of multimedia services and stimulate secure sensing in Internet of Things applications, such as healthcare and traffic monitoring, mobile crowdsensing(MCS) systems must address security threats such as jamming, spoofing and faked sensing attacks during both sensing and information exchange processes in large-scale dynamic and heterogeneous networks. In this article, we investigate secure mobile crowdsensing and present ways to use deep learning(DL) methods, such as stacked autoencoder, deep neural networks, convolutional neural networks, and deep reinforcement learning, to improve approaches to MCS security, including authentication, privacy protection, faked sensing countermeasures, intrusion detection and anti-jamming transmissions in MCS. We discuss the performance gain of these DLbased approaches compared to traditional security schemes and identify the challenges that must be addressed to implement these approaches in practical MCS systems.

Dynamic data-sharing based user recruitment in mobile crowdsensing

Mobile crowdsensing(MCS) has become an emerging paradigm to solve urban sensing problems by leveraging the ubiquitous sensing capabilities of the crowd. One critical issue in MCS is how to recruit users to fulfill more sensing tasks with budget restriction, while sharing data among tasks can be a credible way to improve the efficiency. The data-sharing based user recruitment problem under budget constraint in a realistic scenario is studied, where multiple tasks require homogeneous data but have various spatio-temporal execution ranges, meanwhile users suffer from uncertain future positions. The problem is formulated in a manner of probability by predicting user mobility, then a dynamic user recruitment algorithm is proposed to solve it. In the algorithm a greedy-adding-and-substitution(GAS) heuristic is repeatedly implemented by updating user mobility prediction in each time slot to gradually achieve the final solution. Extensive simulations are conducted using a real-world taxi trace dataset, and the results demonstrate that the approach can fulfill more tasks than existing methods.

Maximum-Profit Advertising Strategy Using Crowdsensing Trajectory Data

Out-door billboard advertising plays an important role in attracting potential customers.However,whether a customer can be attracted is influenced by many factors,such as the probability that he/she sees the billboard,the degree of his/her interest,and the detour distance for buying the product.Taking the above factors into account,we propose advertising strategies for selecting an effective set of billboards under the advertising budget to maximize commercial profit.By using the data collected by Mobile Crowdsensing(MCS),we extract potential customers’implicit information,such as their trajectories and preferences.We then study the billboard selection problem under two situations,where the advertiser may have only one or multiple products.When only one kind of product needs advertising,the billboard selection problem is formulated as the probabilistic set coverage problem.We propose two heuristic advertising strategies to greedily select advertising billboards,which achieves the expected maximum commercial profit with the lowest cost.When the advertiser has multiple products,we formulate the problem as searching for an optimal solution and adopt the simulated annealing algorithm to search for global optimum instead of local optimum.Extensive experiments based on three real-world data sets verify that our proposed advertising strategies can achieve the superior commercial profit compared with the state-of-the-art strategies.

BPPF:Bilateral Privacy-Preserving Framework for Mobile Crowdsensing

With the emergence of mobile crowdsensing (MCS), merchants can use their mobiledevices to collect data that customers are interested in. Now there are many mobilecrowdsensing platforms in the market, such as Gigwalk, Uber and Checkpoint, which publishand select the right workers to complete the task of some specific locations (for example,taking photos to collect the price of goods in a shopping mall). In mobile crowdsensing, in orderto select the right workers, the platform needs the actual location information of workersand tasks, which poses a risk to the location privacy of workers and tasks. In this paper, westudy privacy protection in MCS. The main challenge is to assign the most suitable worker toa task without knowing the task and the actual location of the worker. We propose a bilateralprivacy protection framework based on matrix multiplication, which can protect the locationprivacy between the task and the worker, and keep their relative distance unchanged.

A blockchain-based framework for data quality in edge-computing-enabled crowdsensing

With the rapid development of mobile technology and smart devices,crowdsensing has shown its large potential to collect massive data.Considering the limitation of calculation power,edge computing is introduced to release unnecessary data transmission.In edge-computing-enabled crowdsensing,massive data is required to be preliminary processed by edge computing devices(ECDs).Compared with the traditional central platform,these ECDs are limited by their own capability so they may only obtain part of relative factors and they can’t process data synthetically.ECDs involved in one task are required to cooperate to process the task data.The privacy of participants is important in crowdsensing,so blockchain is used due to its decentralization and tamperresistance.In crowdsensing tasks,it is usually difficult to obtain the assessment criteria in advance so reinforcement learning is introduced.As mentioned before,ECDs can’t process task data comprehensively and they are required to cooperate quality assessment.Therefore,a blockchain-based framework for data quality in edge-computing-enabled crowdsensing(BFEC)is proposed in this paper.DPoR(Delegated Proof of Reputation),which is proposed in our previous work,is improved to be suitable in BFEC.Iteratively,the final result is calculated without revealing the privacy of participants.Experiments on the open datasets Adult,Blog,and Wine Quality show that our new framework outperforms existing methods in executing sensing tasks.

Blockchain-Based MCS Detection Framework of Abnormal Spectrum Usage for Satellite Spectrum Sharing Scenario

In this paper, the problem of abnormal spectrum usage between satellite spectrum sharing systems is investigated to support multi-satellite spectrum coexistence. Given the cost of monitoring, the mobility of low-orbit satellites, and the directional nature of their signals, traditional monitoring methods are no longer suitable, especially in the case of multiple power level. Mobile crowdsensing(MCS), as a new technology, can make full use of idle resources to complete a variety of perceptual tasks. However, traditional MCS heavily relies on a centralized server and is vulnerable to single point of failure attacks. Therefore, we replace the original centralized server with a blockchain-based distributed service provider to enable its security. Therefore, in this work, we propose a blockchain-based MCS framework, in which we explain in detail how this framework can achieve abnormal frequency behavior monitoring in an inter-satellite spectrum sharing system. Then, under certain false alarm probability, we propose an abnormal spectrum detection algorithm based on mixed hypothesis test to maximize detection probability in single power level and multiple power level scenarios, respectively. Finally, a Bad out of Good(BooG) detector is proposed to ease the computational pressure on the blockchain nodes. Simulation results show the effectiveness of the proposed framework.

Behaviour recognition based on the integration of multigranular motion features in the Internet of Things

With the adoption of cutting-edge communication technologies such as 5G/6G systems and the extensive development of devices,crowdsensing systems in the Internet of Things(IoT)are now conducting complicated video analysis tasks such as behaviour recognition.These applications have dramatically increased the diversity of IoT systems.Specifically,behaviour recognition in videos usually requires a combinatorial analysis of the spatial information about objects and information about their dynamic actions in the temporal dimension.Behaviour recognition may even rely more on the modeling of temporal information containing short-range and long-range motions,in contrast to computer vision tasks involving images that focus on understanding spatial information.However,current solutions fail to jointly and comprehensively analyse short-range motions between adjacent frames and long-range temporal aggregations at large scales in videos.In this paper,we propose a novel behaviour recognition method based on the integration of multigranular(IMG)motion features,which can provide support for deploying video analysis in multimedia IoT crowdsensing systems.In particular,we achieve reliable motion information modeling by integrating a channel attention-based short-term motion feature enhancement module(CSEM)and a cascaded long-term motion feature integration module(CLIM).We evaluate our model on several action recognition benchmarks,such as HMDB51,Something-Something and UCF101.The experimental results demonstrate that our approach outperforms the previous state-of-the-art methods,which confirms its effective-ness and efficiency.

Real-time and generic queue time estimation based on mobile crowdsensing

People often have to queue for a busy service in many places around a city, and knowing the queue time can be helpful for making better activity plans to avoid long queues. Traditional solutions to the queue time monitoring are based on pre-deployed infrastructures, such as cameras and infrared sensors, which are costly and fail to deliver the queue time information to scattered citizens. This paper presents CrowdQTE, a mobile crowdsensing system, which utilizes the sensor-enhanced mobile devices and crowd hu- man intelligence to monitor and provide real-time queue time information for various queuing scenarios. When people are waiting in a line, we utilize the accelerometer sensor data and ambient contexts to automatically detect the queueing behav- ior and calculate the queue time. When people are not waiting in a line, it estimates the queue time based on the information reported manually by participants. We evaluate the perfor- mance of the system with a two-week and 12-person deploy- ment using commercially-available smartphones. The results demonstrate that CrowdQTE is effective in estimating queu- ing status.

CBSC: A Crowdsensing System for Automatic Calibrating of Barometers

The mobile crowdsensing software systems can complete large-scale and complex sensing tasks with the help of the collective intelligence from large numbers of ordinary users. In this paper, we build a typical crowdsensing system, which can efficiently calibrate large numbers of smartphone barometer sensors. The barometer sensor now becomes a very common sensor on smartphones. It is very useful in many applications, such as positioning, environment sensing and activity detection. Unfortunately, most smartphone barometers today are not accurate enough, and it is rather challenging to efficiently calibrate a large number of smartphone barometers. Here, we try to achieve this goal by designing a crowdsensingbased smartphone calibration system, which is called CBSC. It makes use of low-power barometers on smartphones and needs few reference points and little human assistant. We propose a hidden Markov model for peer-to-peer calibration, and calibrate all the barometers by solving a minimum dominating set problem. The field studies show that CBSC can get an accuracy of within 0.1 hPa in 84% cases. Compared with the traditional solutions, CBSC is more practical and the accuracy is satisfying. The experience gained when building this system can also help the development of other crowdsensing-based systems.

FIMI： A Constant Frugal Incentive Mechanism for Time WindowCoverage in Mobile Crowdsensing

Mobile crowdsensing has become an efficient paradigm for performing large-scale sensing tasks. An incentive mechanism is important for a mobile crowdsensing system to stimulate participants and to achieve good service quality. In this paper, we explore truthful incentive mechanisms that focus on minimizing the total payment for a novel scenario, where the platform needs the complete sensing data in a requested time window (RTW). We model this scenario as a reverse auction and design FIMI, a constant frugal incentive mechanism for time window coverage. FIMI consists of two phases, the candidate selection phase and the winner selection phase. In the candidate selection phase, it selects two most competitive disjoint feasible user sets. Afterwards, in the winner selection phase, it finds all the interchangeable user sets through a graph-theoretic approach. For every pair of such user sets, FIMI chooses one of them by the weighted cost. Further, we extend FIMI to the scenario where the RTW needs to be covered more than once. Through both rigorous theoretical analysis and extensive simulations, we demonstrate that the proposed mechanisms achieve the properties of RTW feasibility (or RTW multi-coverage), computation efficiency, individual rationality, truthfulness, and constant frugality.

User selection based on user-union and relative entropy in mobile crowdsensing

A critical issue in mobile crowdsensing(MCS) involves selecting appropriate users from a number of participants to guarantee the completion of a sensing task. Users may upload unnecessary data to the sensing platform, leading to redundancy and low user selection efficiency. Furthermore, using exact values to evaluate the quality of the user-union will further reduce selection accuracy when users form a union. This paper proposes a user selection method based on user-union and relative entropy in MCS. More specifically, a user-union matching scheme based on similarity calculation is constructed to achieve user-union and reduce data redundancy effectively. Then, considering the interval-valued influence, a user-union selection strategy with the lowest relative entropy is proposed. Extensive testing was conducted to investigate the impact of various parameters on user selection. The results obtained are encouraging and provide essential insights into the different aspects impacting the data redundancy and interval-valued estimation of MCS user selection.

Lightweight privacy-preserving truth discovery for vehicular air quality monitoring

Air pollution has become a global concern for many years.Vehicular crowdsensing systems make it possible to monitor air quality at a fine granularity.To better utilize the sensory data with varying credibility,truth discovery frameworks are introduced.However,in urban cities,there is a significant difference in traffic volumes of streets or blocks,which leads to a data sparsity problem for truth discovery.Protecting the privacy of participant vehicles is also a crucial task.We first present a data masking-based privacy-preserving truth discovery framework,which incorporates spatial and temporal correlations to solve the sparsity problem.To further improve the truth discovery performance of the presented framework,an enhanced version is proposed with anonymous communication and data perturbation.Both frameworks are more lightweight than the existing cryptography-based methods.We also evaluate the work with simulations and fully discuss the performance and possible extensions.

Preserving the Efficiency and Quality of Contributed Data in MCS via User and Task Profiling

Mobile crowdsensing is a new paradigm with powerful performance for data collection through a large number of smart devices.It is essential to obtain high quality data in crowdsensing campaign.Most of the existing specs ignore users’diversity,focus on solving complicated optimization problem,and consider devices as instances of intelligent software agents which can make reasonable choices on behalf of users.Thus,the efficiency and quality of contributed data cannot be preserved simultaneously.In this paper,we propose a new scheme for improving the quality of contributed data,which recommends tasks to users based on calculated score that jointly take the matching degree and task’s rationality into account.We design QIM as Quality Investigation Mechanism for profiling tasks’rationality and matching degree,which draw on support vector machine(SVM)to learn it from historical data.Our mechanism is validated against the examination in experiment,and the evaluation demonstrates that the QIM mechanism achieves a better performance while improving efficiency E and quality Q at the same time compared with benchmarks.