No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
CrowdTracker: Optimized Urban Moving Object Tracking Using Mobile Crowd Sensing
Abstract
This paper proposes CrowdTracker, a novel object tracking system based on mobile crowd sensing (MCS). Different from traditional video-based object tracking approaches, CrowdTracker recruits people to collaboratively take photos of the object to achieve object movement prediction and tracking. The optimization objective of CrowdTracker is to effectively track the moving object in real time and minimize the cost on user incentives. Specifically, the incentive is determined by the number of workers assigned and the total distance that workers move to complete the task. In order to achieve the objective, we propose the MPRE model for object movement prediction and two other algorithms for task allocation, namely, T-centric and P-centric. T-centric selects workers in a task-centric way, while P-centric allocates tasks in a people-centric manner. By analyzing a large number of historical vehicle trajectories, MPRE builds a model to predict the object's next position. In the predicted regions, CrowdTracker selects workers by utilizing T-centric or P-centric. We evaluate the algorithms over a large-scale real-world dataset. Experimental results indicate that CrowdTracker can effectively track the object with a low incentive cost.
... However, the ML applications raise a privacy concern in the data collection for training purposes. In many ML applications (e.g., Crowdtracker [2], Waze Carpool [3], etc.), users are required to share their sensitive personal information (i.e., user location, user identity, user photos, etc.) to the server. Furthermore, uploading a massive amount of data throughout radio access links or the Internet to the cloud data centers is costly. ...
... Similar to our prior works [10], [20], we consider that the channel gain between the base station and the UE follows the exponential distribution with the mean g 0 (d 0 /d) 4 where g 0 = −40 dB, the reference distance d 0 = 1 m between BS and UEs. Here, the actual distance d between the UEs and the base station is uniformly generated between [2,50] m. Furthermore, the uplink system bandwidth B = 20 M Hz is shared amongst UEs, the Noise power spectral is 10 −10 W , and the transmit power of UEs and BS are 10 W and 40 W , respectively. ...
... For the local training model at UEs, we first set the training data size of UEs in each learning service following a uniform distribution in 10 − 20 M B. The maximum computation capacity (i.e., CPU frequency) at each UE is uniformly distributed between [1,2] GHz. The required CPU cycles c s to train one bit of data at the UE for each learning service is {50, 70, 90} cycles. ...
Federated Learning is a new learning scheme for collaborative training a shared prediction model while keeping data locally on participating devices. In this paper, we study a new model of multiple federated learning services at the multi-access edge computing server. Accordingly, the sharing of CPU resources among learning services at each mobile device for the local training process and allocating communication resources among mobile devices for exchanging learning information must be considered. Furthermore, the convergence performance of different learning services depends on the hyper-learning rate parameter that needs to be precisely decided. Towards this end, we propose a joint resource optimization and hyper-learning rate control problem, namely MS-FEDL, regarding the energy consumption of mobile devices and overall learning time. We design a centralized algorithm based on the block coordinate descent method and a decentralized JP-miADMM algorithm for solving the MS-FEDL problem. Different from the centralized approach, the decentralized approach requires many iterations to obtain but it allows each learning service to independently manage the local resource and learning process without revealing the learning service information. Our simulation results demonstrate the convergence performance of our proposed algorithms and the superior performance of our proposed algorithms compared to the heuristic strategy.
... In contrast, the network-based system involves hardware changes while designing the network with new equipment [13] [14]. Both the systems require a huge amount of investment, as the mobile travels to the particular destination [23] [24]. Normally, its future position is highly correlated with its personal mobility profile, the cells viewed currently, as well as the time spending in each position [15]. ...
... Whenever a sea lion identifies its target prey, it calls the other members to attack the prey. The arithmetical model of this behavior is determined in Eq. (22), (23), and (24). ...
In the modern world, it is necessary to monitor a user's mobility in everyday life to provide advanced mobile services. Mostly, the location-based services (LBS) depend on both the present and future location of the user, which shows the increasing demand on predicting the user's future location. The prediction of trajectories among two different locations is very important as it aids to optimize travel paths among the locations. Moreover, existing techniques rely on high-quality data to deliver optimal results. In this research, we proposed a new optimized deep learning architecture for mobility tracing. The prediction model is based on Optimized DCNN (Deep Conventional Neural Network) that is already trained with the traced location of the user and from the user’s trained movement the model can predict its next location. For precise prediction, the weight and activation function of DCNN is optimally selected with the aid of HS-EH (Hybrid SeaLion -Elephant Herding) algorithm, which is a hybridization of Sea lion Optimization (SLnO) and Elephant Herding Optimization (EHO). Eventually, the proposed method performance is executed in MATLAB 2019a and compared with state-of-art methods with certain performance metrics. Especially, the accuracy of the proposed DCNN + HS-EH algorithm at training rate 10 is 82.96%, 48.88%, 79.27%, and 61.67% better than existing methods.
... In traditional machine learning approaches, neural network models are trained at a server or a data center. Thus, the centralized learning approaches typically require the raw data, e.g., photos and location information, collected by mobile devices to be centralized at the server [1]. The centralized learning approaches thus face big issues including privacy, long propagation delay, and backbone network burden [2]. ...
... Recently, federated learning as a decentralized machine learning approach has been proposed to address the above issues [3], [4]. In the federated learning, mobile devices, i.e., workers, are required to collaboratively train the neural network model of the model owner 1 . In particular, the model owner first transmits its global model to the workers. ...
... In traditional machine learning approaches, neural network models are trained at a server or a data center. Thus, the centralized learning approaches typically require the raw data, e.g., photos and location information, collected by mobile devices to be centralized at the server [1]. The centralized learning approaches thus face big issues including privacy, long propagation delay, and backbone network burden [2]. ...
... Recently, federated learning as a decentralized machine learning approach has been proposed to address the above issues [3], [4]. In the federated learning, mobile devices, i.e., workers, are required to collaboratively train the neural network model of the model owner 1 . In particular, the model owner first transmits its global model to the workers. ...
Federated learning allows mobile devices, i.e., workers, to use their local data to collaboratively train a global model required by the model owner. Federated learning thus addresses the privacy issues of traditional machine learning. However, federated learning faces the energy constraints of the workers and the high network resource cost due to the fact that a number of global model transmissions may be required to achieve the target accuracy. To address the energy constraint, a power beacon can be used that recharges energy to the workers. However, the model owner may need to pay an energy cost to the power beacon for the energy recharge. To address the high network resource cost, the model owner can use a WiFi channel, called default channel, for the global model transmissions. However, communication interruptions may occur due to the instability of the default channel quality. For this, special channels such as LTE channels can be used, but this incurs channel cost. As such, the problem of the model owner is to decide amounts of energy recharged to the workers and to choose channels used to transmit its global model to the workers to maximize the number of global model transmissions while minimizing the energy and channel costs. This is challenging for the model owner under the uncertainty of the channel, energy and mobility states of the workers. In this paper, we thus propose to employ the Deep Q-Network (DQN) that enables the model owner to find the optimal decisions on the energy and the channels without any a priori network knowledge. Simulation results show that the proposed DQN always achieves better performance compared to the conventional algorithms.
... Based on the historical access data, we propose a deep reinforcement learning method called PA-DDQN to maximize the POI coverage and matching degree for instant sensing and then instant actuation. For sensing locations in urban area, some studies adopt the method of equal-grid division [30] to divide them into small areas, and then allocate the tasks within each grid. This method surely can obtain the locally optimal result, but it also has some disadvantages. ...
Task allocation is a key issue in Mobile Crowd Sensing (MCS), which affects the sensing efficiency and quality. Previous studies focus on the allocation of tasks that have already been published to the platform, but there are some very urgent tasks that need to be executed once they were detected. Existing studies for either delay-tolerant or time-sensitive tasks have a certain time delay from task publishing to execution, so it is impossible to achieve task detection then execution seamlessly. Thus, we first define the Instant Sensing and then Instant Actuation (ISIA) problem in MCS and propose a new model to solve it. We aim to allocate POIs where ISIA tasks are most likely to be detected to workers with similar sensing types so that these tasks can be executed once they are detected. This paper presents a two-phase task allocation framework called ISIATasker. In the sensing locations clustering and sensor selection phase, we cluster independent sensing locations into several POIs and then select the optimal cooperative sensor set for each POI to assist workers in completing sensing. In the POIs allocation phase, we propose a method called PA-DDQN based on deep reinforcement learning to plan an optimal path for each worker, thus maximize the overall sensing type matching degree and POI coverage to enable instant sensing and then instant actuation. Finally, extensive experiments are conducted based on real-world datasets to demonstrate that the matching degree and POI coverage of ISIATasker outperforms other baselines.
... Jing et al. proposed a semisupervised elastic net (SSEN) regression method to improve the "time-space intensive" assumption that a high enough video frame rate is required to capture the smoothness of the crowd on the time axis, by constructing a regular term based on the order information between an unlabeled sample and its neighbors in the time domain. ese are all penalized by unreasonable predicted changes [12]. Coşar argues that the real world is difficult to meet the requirements when considering issues such as data bandwidth, storage space, and actual hardware devices; it proposes an alternative semisupervised regression framework that uses information about the underlying population distribution geometry to perform transfer learning, while relaxing the requirements based on the "time-space intensive." ...
In this paper, we analyze and calculate the crowd density in a tourist area utilizing video surveillance dynamic information analysis and divide the crowd counting and density estimation task into three stages. In this paper, novel scale perception module and inverse scale perception module are designed to further facilitate the mining of multiscale information by the counting model; the main function of the third stage is to generate the population distribution density map, which mainly consists of three columns of void convolution with different void rates and generates the final population distribution density map using the feature maps of different branch regressions. Also, the algorithm uses jump connections between the top convolution and the bottom void convolution layers to reduce the risk of network gradient disappearance and gradient explosion and optimizes the network parameters using an intermediate supervision strategy. The hierarchical density estimator uses a hierarchical strategy to mine semantic features and multiscale information in a coarse-to-fine manner, and this is used to solve the problem of scale variation and perspective distortion. Also, considering that the background noise affects the quality of the generated density map, the soft attention mechanism is integrated into the model to stretch the distance between the foreground and background to further improve the quality of the density map. Also, inspired by multitask learning, this paper embeds an auxiliary count classifier in the count model to perform the count classification auxiliary task and to increase the model’s ability to express semantic information. Numerous experimental results demonstrate the effectiveness and feasibility of the proposed algorithm in solving the problems of scale variation and perspective distortion.
... On the other hand, some other popular methods utilized direct human participation instead of drones. CrowdTracker is one such method that recruits people to collaboratively take photographs of the surroundings to determine object movement prediction and tracking [10]. Depending on the location, budget, urgency the agency might have to select a specific approach from the list of available options. ...
Crowdsourcing is an efficient and scalable way for the service providers (SP) to provide a broad range of services with a low initial service setup cost. With its growing popularity, people are continuously introducing new crowdsourcing-based applications and searching for suitable crowd platforms for the deployment of those applications as a service. Consequently, a contributor participates in multiple platforms from different SPs and concurrently executes various tasks in a time interval. As the number of SP increases, managing and monitoring each contributor separately becomes a primary challenge for each SP. Moreover, upgrading a service, ensuring service scalability, and migration is tough for any crowd-based service provider. Frequently , a service provider has difficulty finding the appropriate contributors that will satisfy their service specifications. Besides, as a contributor, it is also hard to decide whether or not they should participate in a task offered by an SP. Therefore, in this paper, we introduced CrowdPick, a middleware that provides a crowdsourced platform for the people who want to provide a crowdsourcing-based service. Each SP contacts CrowdPick for initiating any service chooses an appropriate application package from its repository and specifies its service requirements. Instead of joining individually to each SP, the contributor needs to register into CrowdPick. All the tasks associated with services are scheduled and monitored by CrowdPick, and the CrowdPick decides the corresponding monetary incentives. Along with providing a detailed cost-benefit analysis of an SP and a contributor, we describe the service level agreement (SLA) policies. We simulate our model to show that implementing CrowdPick in real life is viable, and beneficial for both an SP and a contributor.
... Note that cameras are multifarious, not only include those for traffic and public surveillance, but also those of citizens' smart mobile phones, thus it is reasonable to assume that these cameras are distributed densely enough and with long-term recording capability (e.g., videos or images stored with time and location stamp). If that's not a reality, it will be in the near future, because the concept of collaborative sensing [16][17][18][19] is emerging, which can greatly enhance the urban sensing ability by the combination of both stationary infrastructures and mobile phones. Since the quantity of cameras can be up to several millions, and their records are last from the witness moment to current moment, the challenge is "how can we find the car with minimal number of spatiotemporal searches?" ...
Tracking a car or a person in a city is crucial for urban safety management. How can we complete the task with minimal number of spatiotemporal searches from massive camera records? This paper proposes a strategy named IHMs (Intermediate Searching at Heuristic Moments): each step we figure out which moment is the best to search according to a heuristic indicator, then at that moment search locations one by one in descending order of predicted appearing probabilities, until a search hits; iterate this step until we get the object's current location. Five searching strategies are compared in experiments, and IHMs is validated to be most efficient, which can save up to 1/3 total costs. This result provides an evidence that "searching at intermediate moments can save cost".
... We take image classification as a typical AI application in VEC. DNN-based image classification has been widely used in autopilot and interactive navigation for ICV, as well as object tracking and event detection in ITS [17], [18]. To obtain high accuracy and efficiency of model aggregation, the central server should evaluate the image quality and computation capability of vehicular clients, and select the ''fine'' models from vehicular clients. ...
Federated learning is a newly emerged distributed machine learning paradigm, where the clients are allowed to individually train local deep neural network (DNN) models with local data and then jointly aggregate a global DNN model at the central server. Vehicular edge computing (VEC) aims at exploiting the computation and communication resources at the edge of vehicular networks. Federated learning in VEC is promising to meet the ever-increasing demands of artificial intelligence (AI) applications in intelligent connected vehicles (ICV). Considering image classification as a typical AI application in VEC, the diversity of image quality and computation capability in vehicular clients potentially affects the accuracy and efficiency of federated learning. Accordingly, we propose a selective model aggregation approach, where “fine” local DNN models are selected and sent to the central server by evaluating the local image quality and computation capability. Regarding the implementation of model selection, the central server is not aware of the image quality and computation capability in the vehicular clients, whose privacy is protected under such a federated learning framework. To overcome this information asymmetry, we employ two-dimension contract theory as a distributed framework to facilitate the interactions between the central server and vehicular clients. The formulated problem is then transformed into a tractable problem through successively relaxing and simplifying the constraints, and eventually solved by a greedy algorithm. Using two datasets, i.e., MNIST and BelgiumTSC, our selective model aggregation approach is demonstrated to outperform the original federated averaging (FedAvg) approach in terms of accuracy and efficiency. Meanwhile, our approach also achieves higher utility at the central server compared with the baseline approaches.
... Wang et al. propose a hybrid predictive model by combining both the regularity and conformity of human mobility to boost the predictive performance based on heterogeneous mobility datasets [12]. Jing et al. propose a movement prediction model to predict the object's next position by analyzing historical vehicle trajectories [13]. Besides, Markov chain based prediction approach has been used to trajectory domains and proved to be effective. ...
Excavating human’s temporal and spatial regularities hidden in trajectory data and predicting users’ mobility patterns are conducive to providing proactive smart services for people. Combining Markov transition and tensor theories to improve the prediction performance has proved to be effective. However, existing state-of-the-art multivariate multi-order Markov model neglects the mutual influence among different users. In practical trajectory system, people’s mobility patterns are influenced by their social relationships. Therefore, this paper focuses on proposing a novel multi-user multivariate multi-order Markov model and a multi-modal user mobility pattern prediction approach. First, we construct two concrete Markov trajectory transition models based on the single-user multivariate multi-order Markov model. Then, we propose a multi-user multivariate multi-order Markov model including the influence model of multiple users and the multi-user Markov trajectory transition model. Afterwards, two unified product based power methods are developed to calculate the stationary joint eigentensor (SJE) for single-user and multi-user multivariate multi-order Markov models. Furthermore, an SJE based multi-modal prediction approach is proposed to realize precise mobility pattern prediction. Finally, we conduct a series of experiments based on real-world GPS trajectory dataset to verify the performance of the proposed approaches. Experimental results demonstrate that the proposed multi-user multivariate multi-order Markov based multi-modal prediction approach can improve the trajectory prediction accuracy by highest up to 31.10 percentage points compared with the Z-eigen based approach.
... In the traditional cloud-centric approach, data collected by mobile devices is uploaded and processed centrally in a cloudbased server or data center. In particular, data collected by IoT devices and smartphones such as measurements [5], photos [6], videos [7], and location information [8] are aggregated at the data center [9]. Thereafter, the data is used to provide insights or produce effective inference models. ...
In recent years, mobile devices are equipped with increasingly advanced sensing and computing capabilities. Coupled with advancements in Deep Learning (DL), this opens up countless possibilities for meaningful applications. Traditional Machine Learning (ML) approaches require the data to be centralized in a cloud server. However, this results in critical issues related to unacceptable latency and communication inefficiency. To this end, Mobile Edge Computing (MEC) has been proposed to bring intelligence closer to the edge, where data is produced. However, conventional enabling technologies for ML at mobile edge networks still require personal data to be shared with external parties, e.g., edge servers. Recently, in light of increasingly stringent data privacy legislation and growing privacy concerns, the concept of Federated Learning (FL) has been introduced. In FL, end devices use their local data to train an ML model required by the server. The end devices then send the model updates rather than raw data to the server for aggregation. FL can serve as an enabling technology in mobile edge networks since it enables the collaborative training of an ML model and also enables DL for mobile edge network optimization. However, in a large-scale and complex mobile edge network, heterogeneous devices with varying constraints are involved. This raises challenges of communication costs, resource allocation, and privacy and security in the implementation of FL at scale. In this survey, we begin with an introduction to the background and fundamentals of FL. Then, we highlight the aforementioned challenges of FL implementation and review existing solutions. Furthermore, we present the applications of FL for mobile edge network optimization. Finally, we discuss the important challenges, open issues and future research directions in FL.
... This way increases the cost of system and affects the availability negatively. In [13], the authors develop a crowdsensing-based object tracking system (CrowdTracker) for the purpose of tracking vehicles on road. Visual Crowd Sensing (VCS) is applied to the tracking system which utilizes participants' contributed photos with a lower incentive cost. ...
As the widespread of mobile devices in recent years, mobile crowdsensing (MCS) has become a powerful mechanism to produce knowledge by collecting the individual contributed sensor data. In this paper, we aim to solve the target tracking problem through mobile crowdsensing. The traditional tracking method tends to rely on photos or videos provided by pre-deployed monitors, which may consume much power resources. Different from the traditional tracking method, the Tracking Approach through Mobile Crowdsensing (TAMC) proposed in this paper utilizes the wireless communication of mobile users to collect and contribute the valuable information about the target’s whereabouts. Specifically, whenever the mobile users witness the target person, they will take photos of the target person and report the location and time of witnessing the target to the platform. Due to the fact that mobile users communicate with the platform only when they witness the target, the crowdsensing network composed of mobile users can be seen as a green network. In this way, the visited location history and corresponding time sequence of the target are available through the reports of mobile users. Once a new report is uploaded to the platform, the location history is updated. Then, according to the latest report, we apply a tree-based location prediction model named XGBoost, which is a scalable machine learning system, to predict the next place to be visited by the target. Finally, we conduct extensive experiments on a large-scale real-world dataset, namely, Gowalla check-in dataset. The experimental results show that compared with the baseline methods, the tracking approach can predict the next places accurately.
... CrowdTracker recruits people to collaboratively take photos to achieve object tracking. By analyzing a large number of historical vehicles' trajectories, CrowdTracker builds a model to predict the objects next position [19]. In contrast, we exploit the geometrical relationships among the location of the participant, the picture shooting direction, and the road network to locate the vehicle. ...
Traditionally, vehicle tracking is accomplished using pre-deployed video camera networks, which relies on stationary cameras and searches for the target vehicle from videos. In this work, we develop CrowdTracking, i.e., a crowd tracking system that people can collaboratively keep track of the moving vehicle by taking photos, especially in areas where video cameras are deficient. In other words, the underlying support of CrowdTracking is mobile crowdsensing. Several novel ideas underpin CrowdTracking. First, the vehicle can be rapidly localized by using both photographing contexts (including the location and the shooting direction) of the photographer and the road network. Second, the moving speed of the vehicle can be estimated according to two localization results and the trajectory will be predicted. As a result, through continuously collecting photos of the moving vehicle on different roads, the vehicle can be tracked and localized almost in real time. Through precisely localizing the specified vehicle, two optimization objectives are met: 1) maximizing the tracking coverage to the vehicle’s actual trajectory; 2) minimizing the number of participants who are assigned vehicle-tracking tasks. We evaluate the localization method with a real dataset and report about 6 meters error. We also evaluate the vehicle-tracking method of CrowdTracking using a synthetic data set, and experimental results validate its effectiveness and efficiency.
... The use of IoT for public transport has largely been limited to routing, navigation, safety and tracking [9][10][11]. On the other hand, wireless sensor networks to determine seat occupancy have been used in auditoriums, cinema halls and concerts [12]. ...
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.
In recent years, mobile devices are equipped with increasingly advanced sensing and computing capabilities. Coupled with advancements in Deep Learning, this opens up countless possibilities for meaningful applications to be developed. Traditional cloud-based Machine Learning approaches require the data to be aggregated in a cloud server or data center. However, this results in critical issues related to data privacy. In light of increasingly stringent data privacy legislations and growing privacy concerns, the concept of Federated Learning (FL) has been introduced. However, in a large-scale and complex mobile edge network, heterogeneous devices with varying constraints are involved. This raises the challenges of communication costs, resource allocation, and privacy and security in the implementation of FL at scale. In this chapter, we begin with an introduction to the background and fundamentals of FL. Then, we highlight the aforementioned challenges of FL implementation and review cutting-edge solutions. Furthermore, we present the applications of FL for mobile edge network optimization. Finally, we discuss the important challenges and future research directions in FL.
Federated learning (FL) has received significant attention as a practical alternative to traditional cloud-centric machine learning (ML). The performance (e.g., accuracy and convergence time) of FL is hampered by the selection of clients having non-independent and identically distributed (non-IID) data. In addition, a long convergence time is inevitable if clients with poor computation or communication capabilities participate in the FL procedure (i.e., the straggler problem). To minimize convergence time while guaranteeing high learning accuracy, we first formulate an optimization problem on client selection. As a practical solution, we devise a data distribution-aware online client selection (DOCS) algorithm. In DOCS, the FL server finds several clusters having near IID data and then uses a multi-armed bandit (MAB) technique to select the cluster with the lowest convergence time. The evaluation results demonstrate that DOCS can reduce the convergence time by up to
$10\% \sim 41\%$
and improve the learning accuracy by up to
$4\% \sim 13\%$
compared to the traditional client selection schemes.
By utilizing the mobile terminals’ sensing and computing capabilities, mobile crowdsourcing network is considered to be a promising technology to support the various large-scale sensing applications. However, considering the limited resources and security issue, mobile users may be unwilling to participate in crowdsourcing without any incentive. In this work, by combining reputation and contract theory, a dynamic long-term incentive mechanism is proposed to attract the mobile users to participate in mobile crowdsourcing networks. A two-period dynamic contract is first investigated to deal with the asymmetric information problem in the crowdsourcing tasks. Reputation strategy is then introduced to further attract the mobile users to complete the long-term crowdsourcing tasks. The optimal contracts are designed to obtain the maximum expected utility of service provider with reputation strategy and without reputation strategy, respectively. Simulation results demonstrate that the long-term crowdsourcing tasks can be guaranteed by combining the contract’s explicit incentive with the reputation’s implicit incentive. The incentive mechanism can gain a higher expected utility, the more implicit reputation effect factor.
Mobile crowdsensing (MCS) can be widely adopted for undertaking a variety of tasks for the smart city by recruiting distributed participants. With the rapid proliferation of MCS applications, tasks can be devised with different sensing scales. Hence, allocating the tasks to participants with variable spatiotemporal granularity would be urgent and challenging. To this end, we propose a behavior sequentializing and task mapping (BETA) framework, where MCS tasks can be flexibly mapped based on the moving behavior of a participant’s daily activities. A sequential behavior model is first proposed to describe the moving behavior of a participant’s daily activities. Specifically, the behavior of a daily activity is represented by the spatiotemporal trajectory distribution, and a sequential behavior graph is adopted to model the relationships among multiple activities. To extract the sequential behavior from historical trajectories, a projection-clustering (PC) algorithm and a behavior sequentializing approach are developed. Then, based on the extracted sequential behavior, a behavior-to-task mapping network is proposed to evaluate the fitness between tasks and a participant. Finally, extensive simulations are conducted to demonstrate the functionality and performance of BETA. The results show that our proposed method outperforms the state-of-the-art solutions in the mapping efficiency of tasks with different sensing scales.
Exploiting mobile cameras embedded on the widely-used smartphones to serve object tracking offers a new dimension to reduce the deployment cost of the stationary cameras and shorten the tracking latency, but brings the challenges in efficient task assignment and cooperations among workers due to the requirement of Mobile Crowdsensing (MCS) system. Most existing effort in the literature focuses on object tracking with MCS where the workers capture the moving object photos at pre-calculated sites. However, the contradiction between the tracking coverage and the system cost in these MCS-based tracking solutions is sharpened when tracking scenarios and worker number vary. In this paper, we investigate the tracking region to conduct the task assignment among top-k most probable sensing locations, which can achieve maximal tracking utility. Specifically, we construct a N-Gram prediction model to determine the k tracking locations and formulate the task assignment problem solved by the Kuhn-Munkras algorithm, respectively, laying a theoretical foundation. The prediction model soundness is verified statistically and the task assignment effectiveness is evaluated via large scale real-world data simulations.KeywordsMobile CrowdsensingObject trackingTrajectory predictionTask assignment
Position tracking has become a critical key component for a huge variety of devices, ranging from mobile telephone location tracking to biodiversity monitoring. The majority of location-based services rely mostly on the user’s ongoing and prospective position, indicating a growing need of forecasting the user’s future location. Together with position prediction, forecasting the trajectories between two terminals is beneficial, because it enables to optimize the travel direction between them. This study tackles the problem of increasing prediction accuracy to its maximum level. The proposed work undergoes two major phases: feature extraction and prediction. Initially, antecedent and consequent features, spatio-temporal matching based features, and matching users based features can all be generated from the raw input data. For more precise prediction the most relevant features are extracted. The features will then be fed into the prediction algorithm, which will forecast user mobility. The prediction phase is constructed with an optimized convolutional neural network (CNN). Moreover, the weight of CNN is fine-tuned via a new improved butterfly optimization algorithm (IBOA), which is a conceptual improvement of standard BOA. At last, the supremacy of the presented approach is proved over other models with respect to varied measures. The accuracy of the proposed work is 18.33%, 26.67%, 33.33%, 55.2%, and 61.67% better than the existing models like HS–EH, GAF-WO, CNN, and GSTF.
In this chapter, we discuss the role of federated learning for vehicular networks. Due to the high mobility of autonomous cars, there might not be seamless connectivity of the end-devices within cars with the roadside units, and thus traditional federated learning might not work well. To overcome this challenge, we introduced a dispersed federated learning framework for autonomous driving cars. We formulate a dispersed federated learning cost optimization problem and proposed an iterative scheme. Finally, we present extensive simulation results to validate the proposal.
Owing to dynamically changing resources and channel conditions of mobile devices (MDs), when a static deadline-based MD selection scheme is used for federated learning, resource utilization of MDs can be degraded. To mitigate this problem, we propose an adaptive deadline determination (ADD) algorithm for MD selection, where a deadline for each round is adaptively determined with the consideration of the performance disparity of MDs. Evaluation results demonstrate that ADD can achieve the fastest average convergence time among the comparison schemes.
Federated learning (FL) is an emerging privacy-preserving technology for machine learning, which enables end devices to cooperatively train a global model without uploading their local sensitive data. Because of limited network bandwidth and considerable communication overhead, communication efficiency has become an essential bottleneck for FL. Existing solutions attempt to improve this situation by reducing communication rounds while usually come with more computation resource consumption or model accuracy deterioration. In this paper, we propose a parameter Prediction-Based DL (PBFL). In which an extended Kalman filter-based prediction algorithm, a practical prediction error threshold setting mechanism and an effective global model updating strategy are included. Instead of collecting all updates from participants, PBFL takes advantage of predicting values to aggregate the model, which substantially reduces required communication rounds while guaranteeing model accuracy. Inspired by the idea of prediction, each participant checks whether its prediction value is out of the tolerance threshold limits and only uploads local updates that have an inaccurate prediction value. In this way, no additional local computational resources are required. Experimental results on both multilayer perceptrons and convolutional neural networks show that PBFL outperforms the state-of-the-art methods and improves the communication efficiency by >66% with 1% higher model accuracy.
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.
Tracking a suspicious car or a person in a city efficiently is crucial in urban safety management. But how can we complete the task with the minimal number of spatiotemporal searches when massive camera records are involved? To this end, this study proposes a strategy named intermediate searching at heuristic moments (IHMs). At each step, we determine which moment is the best one for the search based on a heuristic indicator. Then, at that moment, locations are searched one by one in descending order of predicted appearing probabilities until a search hit is obtained. We iterate this step until we derive the object’s current location. Five searching strategies are compared via experiments. Among these strategies, the IHMs strategy is validated as the most efficient. IHMs can save up to 1/3 of the total cost. This result provides evidence that “searching at intermediate moments can save cost.”
With the unprecedented proliferation of mobile devices, Mobile Crowd Sensing (MCS) emerges as a promising computing paradigm which utilizes sensor-embedded smart devices to collect sensory data. Recently, a number of privacy-preserving auction-based incentive mechanisms have been proposed. However, none of them guarantees the quality of sensing data in double-side auction scenarios. In this paper, we propose a Differentially Private Double Auction With Reliability-Aware in Mobile Crowd Sensing (DPDR). Specifically, we design the incentive mechanism by employing the exponential mechanism in double-side auction to select the clearing price tuple. Moreover, to collect precise sensory data, we heuristically choose more reliable workers as candidates for each clearing price tuple. We further improve the social welfare of the mechanism by designing the utility function with less sensitivity, or adopting a more practical pricing strategy. Through theoretical analysis, we demonstrate that our mechanisms can guarantee both differential privacy and economic properties, including individual rationality, budget balance, approximate truthfulness and approximate maximal social welfare. Extensive experimental results show that the improved mechanisms can achieve better performance than DPDR in term of social welfare, and all proposed mechanisms can produce high-quality data.
We propose a task distribution algorithm based on agent correlation to enhance the comprehensive research on the distribution sensing tasks in mobile sensor networks. First, in the proposed algorithm, the score and feature factors of the mobile agents are considered comprehensively in a direct correlation model, which is constructed by combining the direct and indirect correlation samples. Second, we introduce a mobility model based on the exponential distribution, and obtain a calculation method of probability parameter
$\lambda $
according to the analysis presented in this article. Finally, we integrate the constructed correlation model and mobility model; which are then applied to the distribution algorithm. By experimental research, the task distribution algorithm based on relationships of agents we proposed, has a precision improvement of 57.23% over MTPS, which is a fine-grained multitask allocation framework algorithm, and 12.31% of that to sequential MF, which is a recommendation algorithm based on collaborative filtering by exploiting sequential behaviors. These results indicate that the proposed algorithm improves the task distribution performance significantly, and offers a more accurate and reliable service.
Several cities around the world face security problems, such as vehicle theft. Locate and recover these vehicles are challengers for authorities. In smart cities, citizens can collaborate with authorities by sensing urban and environmental data, so-called crowdsensing. This work introduces Crowd-Auto, a crowdsensing approach that utilizes a crowded camera network from houses and commerce to identify vehicle plates, query on official databases and inform the authorities when stolen vehicles are identified. We've developed a prototype and demonstrated that Crowd-Auto is viable for allowing citizens to cooperate and improve security in cities.
To minimize the sensing cost in MCS while preserving the participants’ privacy, in this paper we propose a Data Sensing mechanism with User Privacy Preserved (DS-UPP). We introduce edge computing into MCS to support task allocation and user privacy protection. In DS-UPP, based on compressive sensing theory we minimize the amount of data needed to be submitted. We also design an algorithm based on local differential privacy theory. Selected participants only need to submit their real data along with the reconstructed data generated by the algorithm. It is proved that DS-UPP satisfies ε-differential privacy. We give the mathematical lower bound and upper bound of the number of participants needed for task accomplishment with the constraints that privacy budget is ε and recovery error of task data is 0, as well as the average amount of data that should be submitted by a participant. We also evaluate the performance of DS-UPP through simulations. Compared with the existing method PrivKV, DS-UPP can reduce the needed data amount by about 90% on the average while guarantee users’ privacy preserved.
For task allocation of mobile crowd sensing, aiming at the problem that the task can not be completed normally due to the change of sensing state and the data quality is reduced because the sensor willingness is not satisfied, a task allocation method with active learning ability based on the normal cloud model is proposed. Firstly, the data quality, sensing environment and network state of sensors are evaluated, and the threshold is set according to the power of sensor and the total amount of data sent, and on the basis, the sensor sensing ability is monitored in real time. Then, the multi-granularity standard distribution cloud and sensor state cloud are established through normal cloud model when the sensing state changes. Furthermore, the willingness score of the sensor to the task is obtained by cosine method. Finally, according to the willingness list, tasks are allocated by the maximum sensor willingness and the minimum number of sensors. Simulation experiment verifies that the task can be allocated when the sensing state is changed, and the quality of sensing data is better. Besides, in the incentive effect, the actual proportion of sensing sensors and the average numbers of tasks completed by sensors are better, and the incentive budget is smaller when the same data quality is obtained.
With the rapid development of wireless networks and mobile devices, mobile crowd sensing (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 bi-objective incentive mechanisms in this work. 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.
Crowdsensing high quality data relies on the efficient participation of users. However, the existing incentive mechanism is unable to take into account the dual requirements of both quantity and quality of users’ participation. In this paper, we propose Crowdsensing Task Selection algorithm and rewards allocation incentive mechanism based on Reputation Evaluation model(CTSRE), which deploys the reputation weighted rewards allocation method to effectively encourage users to actively participate in the execution of tasks. In CTSRE, we adopt a game-theoretic approach and apply best response dynamics based algorithm to achieve the goal of maximizing users’ utilities. We show that the task selection algorithm can converge in finite time and meet the fairness requirement. We also design a reputation conversion method and updating rule to improve incentive and fairness of the mechanism. Through numerical experiments and comparative analysis, we verify that the task selection algorithm meets the convergence requirements. The application of sigmoid function for reputation conversion improves the fairness of rewards allocation and motivate users to improve their reputation to obtain high rewards. Experimental results indicate that CTSRE can effectively ensure the quantity and the quality of users’ participation.
In recent years, mobile devices are equipped with increasingly advanced sensing and computing capabilities. Coupled with advancements in Deep Learning (DL), this opens up countless possibilities for meaningful applications, e.g., for medical purposes and in vehicular networks. Traditional cloud-based Machine Learning (ML) approaches require the data to be centralized in a cloud server or data center. However, this results in critical issues related to unacceptable latency and communication inefficiency. To this end, Mobile Edge Computing (MEC) has been proposed to bring intelligence closer to the edge, where data is produced. However, conventional enabling technologies for ML at mobile edge networks still require personal data to be shared with external parties, e.g., edge servers. Recently, in light of increasingly stringent data privacy legislations and growing privacy concerns, the concept of Federated Learning (FL) has been introduced. In FL, end devices use their local data to train an ML model required by the server. The end devices then send the model updates rather than raw data to the server for aggregation. FL can serve as an enabling technology in mobile edge networks since it enables the collaborative training of an ML model and also enables DL for mobile edge network optimization. However, in a large-scale and complex mobile edge network, heterogeneous devices with varying constraints are involved. This raises challenges of communication costs, resource allocation, and privacy and security in the implementation of FL at scale. In this survey, we begin with an introduction to the background and fundamentals of FL. Then, we highlight the aforementioned challenges of FL implementation and review existing solutions. Furthermore, we present the applications of FL for mobile edge network optimization. Finally, we discuss the important challenges and future research directions in FL.
While sensor networks have been pervasively deployed in the real world, more and more mobile crowdsensing (MCS) applications have come into realization to collaboratively detect events and collect data. This paper aims to design a novel incentive mechanism to achieve good services for mobile crowdsensing applications. Responding to insufficient participants, we propose a novel Experience-Based incentive mechanism using Reverse Auction (EBRA). Additionally, it can also guarantee fair competition while maximizing the total profit of the service platform. Through strictly proving, our proposed EBRA incentive mechanism satisfies four properties: computational efficiency, individual rationality, profitability, and truthfulness. The extensive simulations show that the proposed EBRA method has a better performance over 20% than other benchmark mechanisms.
Mobile crowd sensing (MCS) has been recognized as a promising method to acquire massive volume of data. Stimulating the enthusiasm of participants could be challenging at the same time. In this paper, we first propose a three-layer mobile crowd sensing architecture and introduce edge servers into it. The edge servers are used to process raw data and improve response time. Our goal is to maximize social welfare. Specifically, we model the social welfare maximization problem by Markov decision process and study a convex optimization pricing problem in the proposed three-layer architecture. The size of the tasks the edge servers assign is adjustable in this system. Then Lagrange multiplier method is leveraged to solve the problem. We derive the experimental data from real-world dataset and extensive simulations demonstrate the performance of our proposed method.
Mobile crowdsensing (MCS) represents a new sensing paradigm that utilizes the smart mobile devices to collect and share data. With the popularity of unmanned vehicles like UAVs and driverless cars, they can provide much more reliable, accurate and cost-efficient sensing services. In this paper, we propose a distributed control framework for energy-efficient and DIstributed VEhicle navigation with chaRging sTations, called Re-Divert". It is a distributed multi-agent deep reinforcement learning (DRL) solution, which uses a CNN to extract useful spatial features as the input to the actor-critic network to produce a real-time action. Also, e-Divert incorporates a distributed prioritized experience replay for better exploration and exploitation, and an LSTM enabled N-step temporal sequence modeling. The solution maximizes the energy efficiency, data collection ratio, geographic fairness, and minimize the energy consumption simultaneously. We find an appropriate set of hyperparameters that achieve the best performance, i.e., 5 actors in Ape-X architecture, priority exponent 0.5, and LSTM sequence length 3. Finally, we compare with three baselines including one state-of-the-art approach MADDPG and results show that our proposed e-Divert significantly improves the energy efficiency, as compared to MADDPG, by 3.62 and 2.36 times on average when varying different numbers of vehicles and charging stations, respectively.
Geospatial big data analytics are changing the way that businesses operate, and have enabled various intelligent services in smart cities. User mobility plays an important role in many context-aware applications such as location-based advertisement, traffic planning, and urban resource management. This study proposes CityTracker, a hidden markov model (HMM)-based framework to predict the temporal-spatial individual trajectory and analyze the representative citywide crowd mobility. After the locations are segmented into points of interests and modeled as states, HMM can find the most likely state sequence in a maximum-likelihood sense, and thus perform trajectory prediction with different orders. In addition, CityTracker can integrate the individual trajectories, achieving representative crowd mobility visualization in the target area. The proposed mechanism is evaluated on a database provided by HyXen, which contains temporal-geospatial records from thousands of smartphones in Taipei city. Experimental results confirm the effectiveness of CityTracker, which achieves prediction distance errors of approximately 1.28 km and outperforms traditional probabilistic and regression-based methods. The results also show the most representative crowd mobility behaviors in the map, which is essential for citywide applications.
Spatial crowdsourcing (SC) is an emerging paradigm of crowdsourcing, which commits workers to move to some particular locations to perform spatio-temporal-relevant tasks (e.g., sensing, activity organization). Task allocation or worker selection is a significant problem that may impact the quality of completion of SC tasks. Based on a conceptual model and generic framework of SC task allocation, this paper firstly gives a review of the current state of research in this field, including single task allocation, multiple task allocation, low-cost task allocation, and quality-enhanced task allocation. We further investigate the future trends and open issues of SC task allocation, including skill-based task allocation, group recommendation and collaboration, task composition and decomposition, and privacy-preserving task allocation. Finally, we discuss the practical issues on real-world deployment as well as the challenges for large-scale user study in SC task allocation.
Moving destination prediction offers an important category of location-based applications and provides essential intelligence to business and governments. In existing studies, a common approach to destination prediction is to match the given query trajectory with massive recorded trajectories by similarity calculation. Unfortunately, due to privacy concerns, budget constraints, and many other factors, in most circumstances, we can only obtain a sparse trajectory dataset. In sparse dataset, the available moving trajectories are far from enough to cover all possible query trajectories; thus the predictability of the matching-based approach will decrease remarkably. Toward destination prediction with sparse dataset, instead of searching similar trajectories over the sparse records, we alternatively examine the changes of distances from sampling locations to final destination on query trajectory. The underlying idea is intuitive: It is directly motivated by travel purpose, people always get closer to the final destination during the movement. By borrowing the conception of gradient descent in optimization theory, we propose a novel moving destination prediction approach, namely MGDPre. Building upon the mobility gradient descent, MGDPre only investigates the behavior characteristics of query trajectory itself without matching historical trajectories, and thus is applicable for sparse dataset. We evaluate our approach based on extensive experiments, using GPS trajectories generated by a sample of taxis over a 10-day period in Shenzhen city, China. The results demonstrate that the effectiveness, efficiency, and scalability of our approach outperform state-of-the-art baseline methods.. 2017. Moving destination prediction using sparse dataset: A mobility gradient descent approach.
Mobile Crowd Photographing (MCP) is an emerging area of interest for researchers as the built-in cameras of mobile devices are becoming one of the commonly used visual logging approaches in our daily lives. In order to meet diverse MCP application requirements and constraints of sensing targets, a multi-facet task model should be defined for a generic MCP data collection framework. Furthermore, MCP collects pictures in a distributed way in which a large number of contributors upload pictures whenever and wherever it is suitable. This inevitably leads to evolving picture streams. This paper investigates the multi-constraint-driven data selection problem in MCP picture aggregation and proposes a pyramid-tree (PTree) model which can efficiently select an optimal subset from the evolving picture streams based on varied coverage needs of MCP tasks. By utilizing the PTree model in a generic MCP data collection framework, which is called CrowdPic, we test and evaluate the effectiveness, efficiency and flexibility of the proposed framework through crowdsourcing-based and simulation-based experiments. Both the theoretical analysis and simulation results indicate that the PTree-based framework can effectively select a subset with high utility coverage and low redundancy ratio from the streaming data. The overall framework is also proved flexible and applicable to a wide range of MCP task scenarios.
Task allocation or participant selection is a key issue in Mobile Crowd Sensing (MCS). While previous participant selection approaches mainly focus on selecting a proper subset of users for a single MCS task, multi-task-oriented participant selection is essential and useful for the efficiency of large-scale MCS platforms. This paper proposes TaskMe, a participant selection framework for multi-task MCS environments. In particular, two typical multi-task allocation situations with bi-objective optimization goals are studied: (1) For FPMT (few participants, more tasks), each participant is required to complete multiple tasks and the optimization goal is to maximize the total number of accomplished tasks while minimizing the total movement distance. (2) For MPFT (more participants, few tasks), each participant is selected to perform one task based on pre-registered working areas in view of privacy, and the optimization objective is to minimize total incentive payments while minimizing the total traveling distance. Two optimal algorithms based on the Minimum Cost Maximum Flow theory are proposed for FPMT, and two algorithms based on the multi-objective optimization theory are proposed for MPFT. Experiments verify that the proposed algorithms outperform baselines based on a large-scale real-word dataset under different experiment settings (the number of tasks, various task distributions, etc.).
Sensing cost and data quality are two primary concerns in mobile crowdsensing. In this article, we propose a new crowdsensing paradigm, sparse mobile crowdsensing, which leverages the spatial and temporal correlation among the data sensed in different sub-areas to significantly reduce the required number of sensing tasks allocated, thus lowering overall sensing cost (e.g., smartphone energy consumption and incentives) while ensuring data quality. Sparse mobile crowdsensing applications intelligently select only a small portion of the target area for sensing while inferring the data of the remaining unsensed area with high accuracy. We discuss the fundamental research challenges in sparse mobile crowdsensing, and design a general framework with potential solutions to the challenges. To verify the effectiveness of the proposed framework, a sparse mobile crowdsensing prototype for temperature and traffic monitoring is implemented and evaluated. With several future research directions identified in sparse mobile crowdsensing, we expect that more research interests will be stimulated in this novel crowdsensing paradigm.
This paper first defines a novel spatial-temporal coverage metric, k-depth coverage, for mobile crowdsensing (MCS) problems. This metric considers both the fraction of subareas covered by sensor readings and the number of sensor readings collected in each covered subarea. Then iCrowd, a generic MCS task allocation framework operating with the energy-efficient Piggyback Crowdsensing task model, is proposed to optimize the MCS task allocation with different incentives and k-depth coverage objectives/constraints. iCrowd first predicts the call and mobility of mobile users based on their historical records, then it selects a set of users in each sensing cycle for sensing task participation, so that the resulting solution achieves two dual optimal MCS data collection goals — i.e., Goal. 1 nearmaximal k-depth coverage without exceeding a given incentive budget or Goal. 2 near-minimal incentive payment while meeting a predefined k-depth coverage goal. We evaluated iCrowd extensively using a large-scale real-world dataset for these two data collection goals. The results show that: for Goal.1, iCrowd significantly outperformed three baseline approaches by achieving 3% 60% higher k-depth coverage; for Goal.2, iCrowd required 10.0% - 73.5% less incentives compared to three baselines under the same k-depth coverage constraint.
With the surging of smartphone sensing, wireless networking, and mobile social networking techniques, Mobile Crowd Sensing and Computing (MCSC) has become a promising paradigm for cross-space and largescale sensing. MCSC extends the vision of participatory sensing by leveraging both participatory sensory data from mobile devices (offline) and user-contributed data from mobile social networking services (online). Further, it explores the complementary roles and presents the fusion/collaboration of machine and human intelligence in the crowd sensing and computing processes. This article characterizes the unique features and novel application areas of MCSC and proposes a reference framework for building human-in-the-loop MCSC systems. We further clarify the complementary nature of human and machine intelligence and envision the potential of deep-fused human-machine systems. We conclude by discussing the limitations, open issues, and research opportunities of MCSC.
Community bulletin boards serve an important function for public information sharing in modern society. Posted fliers advertise services, events, and other announcements. However, fliers posted offline suffer from problems such as limited spatial-temporal coverage and inefficient search support. In recent years, with the development of sensor-enhanced mobile devices, mobile crowd sensing (MCS) has been used in a variety of application areas. This paper presents FlierMeet, a crowd- powered sensing system for cross-space public information reposting, tagging, and sharing. The tags learned are useful for flier sharing and preferred information retrieval and suggestion. Specifically, we utilize various contexts (e.g., spatio-temporal info, flier publishing/reposting behaviors, etc.) and textual features to group similar reposts and classify them into categories. We further identify a novel set of crowd-object interaction hints to predict the semantic tags of reposts. To evaluate our system, 38 participants were recruited and 2,035 reposts were captured during an eight-week period. Experiments on this dataset showed that our approach to flier grouping is effective and the proposed features are useful for flier category/semantic tagging.
Data quality and budget are two primary concerns in urban-scale mobile crowdsensing applications. In this paper, we leverage the spatial and temporal correlation among the data sensed in different sub-areas to significantly reduce the required number of sensing tasks allocated (corresponding to budget), yet ensuring the data quality. Specifically, we propose a novel framework called CCS-TA, combining the state-of-the-art compressive sensing, Bayesian inference, and active learning techniques, to dynamically select a minimum number of sub-areas for sensing task allocation in each sensing cycle, while deducing the missing data of unallocated sub-areas under a probabilistic data accuracy guarantee. Evaluations on real-life temperature and air quality monitoring datasets show the effectiveness of CCS-TA. In the case of temperature monitoring, CCS-TA allocates 18.0-26.5% fewer tasks than baseline approaches, allocating tasks to only 15.5% of the sub-areas on average while keeping overall sensing error below 0.25 degree in 95% of the cycles.
This paper proposes a novel participant selection framework, named CrowdRecruiter, for mobile crowdsensing. CrowdRecruiter operates on top of energy-efficient Piggyback Crowdsensing (PCS) task model and minimizes incentive payments by selecting a small number of participants while still satisfying probabilistic coverage constraint. In order to achieve the objective when piggybacking crowdsensing tasks with phone calls, CrowdRecruiter first predicts the call and coverage probability of each mobile user based on historical records. It then efficiently computes the joint coverage probability of multiple users as a combined set and selects the near-minimal set of participants, which meets coverage ratio requirement in each sensing cycle of the PCS task. We evaluated CrowdRecruiter extensively using a large-scale real-world dataset and the results show that the proposed solution significantly outperforms three baseline algorithms by selecting 10.0\% - 73.5\% fewer participants on average under the same probabilistic coverage constraint.
Intense interest in disturbing child abductions by the mass media, public safety organizations, and the public has helped sustain a socially constructed mythology and sporadic “moral panic” about the presumed pervasiveness of this threat to children. The result has often been reactionary “memorial” legislation enacted in response to sensational cases. A recent example is the America's Missing Broadcast Emergency Response (AMBER) Alert system, which is designed to interrupt serious child kidnappings in progress by soliciting citizen tips to help officials quickly rescue victims. Drawing on available empirical evidence and theoretical considerations, the authors contend that AMBER Alert has not achieved and probably cannot achieve the ambitious goals that inspired its creation. In fact, AMBER Alert is arguably an example of what could be called crime control theater. It is a socially constructed “solution” to a socially constructed problem, enabling public officials to symbolically address an essentially intractable threat. Despite laudable intentions, AMBER Alert exemplifies how crime control theater can create unintended problems, such as public backlash when the theatrical policy fails and a distorted public discourse about the nature of crime. Considerations for the future of AMBER Alert in particular, and the concept of crime control theater in general, are discussed.
In this paper, we address the issue of predicting the next location of an individual based on the observations of his mobility behavior over some period of time and the recent locations that he has visited. This work has several potential applications such as the evaluation of geo-privacy mechanisms, the development of location-based services anticipating the next movement of a user and the design of location-aware proactive resource migration. In a nutshell, we extend a mobility model called Mobility Markov Chain (MMC) in order to incorporate the n previous visited locations and we develop a novel algorithm for next location prediction based on this mobility model that we coined as n-MMC. The evaluation of the efficiency of our algorithm on three different datasets demonstrates an accuracy for the prediction of the next location in the range of 70% to 95% as soon as n = 2.
In this paper we propose an approach for multi-camera multi-person seamless tracking that allows camera assignment and hand-off based on a set of user-supplied criteria. The approach is based on the application of game theory to camera assignment problem. Bargaining mechanisms are considered for collaborations as well as for resolving conflicts among the available cameras. Camera utilities and person utilities are computed based on a set of criteria. They are used in the process of developing the bargaining mechanisms. Experiments for multi-camera multi-person tracking are provided. Several different criteria and their combination of them are carried out and compared with each other to corroborate the proposed approach.
An image-based method for vehicle speed detection is presented. Conventional speed measurement techniques use radar- or laser-based devices, which are usually more expensive compared to a passive camera system. In this work, a single image captured with vehicle motion is used for speed measurement. Due to the relative motion between the camera and a moving object during the camera exposure time, motion blur occurs in the dynamic region of the image. It provides a visual cue for the speed measurement of a moving object. An approximate target region is first segmented and blur parameters are estimated from the motion blurred subimage. The image is then deblurred and used to derive other parameters. Finally, the vehicle speed is calculated according to the imaging geometry, camera pose, and blur extent in the image. Experiments have shown the estimated speeds within 5% of actual speeds for both local and highway traffic.
We describe a method called Predestination that uses a history of a driver's destinations, along with data about driving behaviors, to predict where a driver is going as a trip progresses. Driving behaviors include types of desti- nations, driving efficiency, and trip times. Beyond considering previously vis- ited destinations, Predestination leverages an open-world modeling methodol- ogy that considers the likelihood of users visiting previously unobserved loca- tions based on trends in the data and on the background properties of locations. This allows our algorithm to smoothly transition between "out of the box" with no training data to more fully trained with increasing numbers of observations. Multiple components of the analysis are fused via Bayesian inference to pro- duce a probabilistic map of destinations. Our algorithm was trained and tested on hold-out data drawn from a database of GPS driving data gathered from 169 different subjects who drove 7,335 different trips.
Large-scale, ground-level urban imagery has recently developed as an important element of online mapping tools such as Google's Street View. Such imagery is extremely valuable in a number of potential applications, ranging from augmented reality to 3D modeling, and from urban planning to monitoring city infrastructure. While such imagery is already available from many sources, including Street View and tourist photos on photo-sharing sites, these collections have drawbacks related to high cost, incompleteness, and accuracy. A potential solution is to leverage the community of photographers around the world to collaboratively acquire large-scale image collections. This work explores this approach through PhotoCity, an online game that trains its players to become "experts" at taking photos at targeted locations and in great density, for the purposes of creating 3D building models. To evaluate our approach, we ran a competition between two universities that resulted in the submission of over 100,000 photos, many of which were highly relevant for the 3D modeling task at hand. Although the number of players was small, we found that this was compensated for by incentives that drove players to become experts at photo collection, often capturing thousands of useful photos each.
Citizen science projects can collect a wealth of scientific data, but that data is only helpful if it is actually used. While previous citizen science research has mostly focused on designing effective capture interfaces and incentive mechanisms, in this paper we explore the application of HCI methods to ensure that the data itself is useful. To provide a focus for this exploration we designed and implemented Creek Watch, an iPhone application and website that allow volunteers to report information about waterways in order to aid water management programs. Working with state and local officials and private groups involved in water monitoring, we conducted a series of contextual inquiries to uncover what data they wanted, what data they could immediately use, and how to most effectively deliver that data to them. We iteratively developed the Creek Watch application and website based on our findings and conducted evaluations of it with both contributors and consumers of water data, including scientists at the city water resources department. Our study reveals that the data collected is indeed useful for their existing practices and is already in use in water and trash management programs. Our results suggest the application of HCI methods to design the data for the end users is just as important as their use in designing the user interface.
Mobile phones have evolved from devices that are just used for voice and text communication to platforms that are able to
capture and transmit a range of data types (image, audio, and location). The adoption of these increasingly capable devices
by society has enabled a potentially pervasive sensing paradigm - participatory sensing. A coordinated participatory sensing
system engages individuals carrying mobile phones to explore phenomena of interest using in situ data collection. For participatory
sensing to succeed, several technical challenges need to be solved. In this paper, we discuss one particular issue: developing
a recruitment framework to enable organizers to identify well-suited participants for data collections based on geographic
and temporal availability as well as participation habits. This recruitment system is evaluated through a series of pilot
data collections where volunteers explored sustainable processes on a university campus.
In this paper, a system based on the generation of a Hidden Markov Model from the past GPS log and current location is presented to predict a user’s destination when beginning a new trip. This approach drastically reduces the number of points supplied by the GPS device and it permits a “support-map” to be generated in which the main characteristics of the trips for each user are taken into account. Hence, in contrast with other similar approaches, total independence from a street-map database is achieved.
We present a generic tracker which can handle a variety of different objects. For this purpose, groups of low-level features like interest points, edges, homogeneous and textured regions, are combined on a flexible and opportunistic basis. They sufficiently characterize an object and allow robust tracking as they are complementary sources of information which describe both the shape and the appearance of an object. These low-level features are integrated into a particle filter framework as this has proven very successful for non-linear and non-Gaussian estimation problems. We concentrate on rigid objects under affine transformations. Results on real-world scenes demonstrate the performance of the proposed tracker.
Wearable computers have the potential to act as intelligent agents in everyday life and assist the user in a variety of tasks, using context to determine how to act. Location is the most common form of context used by these agents to determine the user's task. However, another potential use of location context is the creation of a predictive model of the user's future movements. We present a system that automatically clusters GPS data taken over an extended period of time into meaningful locations at multiple scales. These locations are then incorporated into a Markov model that can be consulted for use with a variety of applications in both single-user and collaborative scenarios.
Visual Crowdsensing (VCS), which leverages built-in cameras of smart devices to attain informative and comprehensive sensing of interesting targets, has become a predominant sensing paradigm of mobile crowdsensing (MCS). Compared to MCS tasks using other sensing modalities, VCS faces numerous unique issues, such as multi-dimensional coverage needs, data redundancy identification and elimination, low-cost transmission, as well as high data processing cost. This paper characterizes the concepts, unique features, and novel application areas of VCS, and investigates its challenges and key techniques. A generic framework for VCS systems is then presented, followed by discussions about the future directions of crowdsourced picture transmission and the experimental setup in VCS system evaluation.
Task allocation or participant selection is a key issue in Mobile Crowd Sensing (MCS). While previous participant selection approaches mainly focus on selecting a proper subset of users for a single MCS task, multi-task-oriented participant selection is essential and useful for the efficiency of large-scale MCS platforms. This paper proposes TaskMe, a participant selection framework for multi-task MCS environments. In particular, two typical multi-task allocation situations with bi-objective optimization goals are studied: (1) For FPMT (few participants, more tasks), each participant is required to complete multiple tasks and the optimization goal is to maximize the total number of accomplished tasks while minimizing the total movement distance. (2) For MPFT (more participants, few tasks), each participant is selected to perform one task based on pre-registered working areas in view of privacy, and the optimization objective is to minimize total incentive payments while minimizing the total traveling distance. Two optimal algorithms based on the Minimum Cost Maximum Flow theory are proposed for FPMT, and two algorithms based on the multi-objective optimization theory are proposed for MPFT. Experiments verify that the proposed algorithms outperform baselines based on a large-scale real-word dataset under different experiment settings (the number of tasks, various task distributions, etc.).
Visual crowdsensing is successfully applied in numerous application areas, yet little work has been done on measuring and improving the quality of worker contributed visual data. Rather than evaluating the visual quality based on traditional metrics such as resolution, we focus on data diversity, which is crucial for a broad stream of visual crowdsensing tasks. Two representative diversity-oriented task types are studied, namely static object imagery and evolving event photography. The former aims to collect multi-facet/aspect yet low redundant data about a stationary object, while the latter wants to detect and collect details of key scenes throughout an event. We link these quality needs with data utility and propose a unified visual crowdsensing framework called UtiPay. Data utility is characterized by the macro and micro diversity needs: at the macro level, the pyramid-tree approach is proposed for multi-attribute-based data grouping; at the micro level, we use several strategies for intra-group data selection and worker contribution measurement. To study the impact of our proposed utility measurement approaches, we propose two utility-enhanced payment schemes as incentive mechanisms: Uti and Uti-Bid. Experiments over several user studies with a total of 43 subjects validate the performance of UtiPay for measuring and enhancing the data quality of visual crowdsensing tasks.
With the wide use of mobile devices, predicting the destination of moving vehicles has become an increasingly important problem for location based recommendation systems and destination-based advertising. Most existing approaches are based on various Markov chain models, in which the historical trajectories are used to train the model and the top-k most probable destinations are returned. We identify certain limitations of the previous approaches. Instead, we propose a new data-driven framework, called DestPre, which is not based on a probabilistic model, but directly operates on the trajectories and makes the prediction. We make use of only historic trajectories, without individual identity information. Our design of DestPre, although simple, is a result of several useful observations from the real trajectory data. DestPre involves an index based on Bucket PR Quadtree and Minwise hashing, for efficiently retrieving similar trajectories, and a clustering on destinations for predictions. By incorporating some additional ideas, we show that the prediction accuracy can be further improved. We have conducted extensive experiments on real Beijing Taxi dataset. The experimental results demonstrate the effectiveness of DestPre.
Worker selection is a key issue in mobile crowd sensing (MCS). While the previous worker selection approaches mainly focus on selecting a proper subset of workers for a single MCS task, a multitask-oriented worker selection is essential and useful for the efficiency of large-scale MCS platforms. This paper proposes ActiveCrowd, a worker selection framework for multitask MCS environments. We study the problem of multitask worker selection under two situations: worker selection based on workers? intentional movement for time-sensitive tasks and unintentional movement for delay-tolerant tasks. For time-sensitive tasks, workers are required to move to the task venue intentionally and the goal is to minimize the total distance moved. For delay-tolerant tasks, we select workers whose route is predicted to pass by the task venues and the goal is to minimize the total number of workers. Two greedy-enhanced genetic algorithms are proposed to solve them. Experiments verify that the proposed algorithms outperform baseline methods under different experiment settings (scale of task sets, available workers, varied task distributions, etc.).
Mobile social media enables people to record ongoing physical events they witness and share them instantaneously online. However, since these event pictures are often individually provided, they are typically fragmented and possess high redundancy. Though there have been studies about visual event summarization, they pay little attention to collaborative sensing, subevent detection, and event summary. In this paper, we present several building blocks for a cooperative visual sensing and sharing system. We create a virtual opportunistic community associated with an event, where members collaborate to cover different aspects of the event. More specifically, a crowd-powered approach is first used to localize the event. We then propose three subevent segmentation methods based on crowd-event interaction patterns. Based on the segmentation results, we summarize the event at two levels: multi-facet subevent summary and crowd-behavior-based highlights. Experiments over 21 online datasets and two real world datasets demonstrate the effectiveness of our approaches.
Vehicle trajectory or route prediction is useful in online, data-driven transportation simulation to predict future traffic patterns and congestion, among other uses. The various approaches to route prediction have varying degrees of data required to predict future vehicle trajectories. Three approaches to vehicle trajectory prediction, along with extensions, are examined to assess their accuracy on an urban road network. These include an approach based on the intuition that drivers attempt to reduce their travel time, an approach based on neural networks, and an approach based on Markov models. The T-Drive trajectory data set consisting of GPS trajectories of over ten thousand taxicabs and including 15 million data points in Beijing, China is used for this evaluation. These comparisons illustrate that using trajectory data from other vehicles can substantially improve the accuracy of forward trajectory prediction in the T-Drive data set. These results highlight the benefit of exploiting dynamic data to improve the accuracy of transportation simulation predictions.
Finding a missing child is an important problem concerning not only parents but also our society. It is essential and natural to use serendipitous clues from neighbors for finding a missing child. In this paper, we explore a new architecture of crowd collaboration to expedite this mission-critical process and propose a crowd-sourced cooperative mobile application, CoSMiC. It helps parents find their missing child quickly on the spot before he or she completely disappears. A key idea lies in constructing the location history of a child via crowd participation, thereby leading parents to their child easily and quickly. We implement a prototype application and conduct extensive user studies to assess the design of the application and investigate its potential for practical use.
Consumer-centric mobile devices, such as smartphones, are an emerging category of devices at the edge of the Internet. Leveraging volunteers and their mobiles as a (sensing) data collection outlet is known as Mobile Crowd Sensing (MCS) and poses interesting challenges, with particular regard to the management of sensing resource contributors, dealing with their subscription, random and unpredictable join and leave, and node churn.
To facilitate and expedite the (commercial) exploitation of this trend, in this paper we propose to adopt a service-oriented approach to cope with MCS application deployment into a sensing Cloud infrastructure, decoupling the MCS application domain from the infrastructure one. To this purpose we provide the building blocks for implementing such a novel take on MCS, which from a Cloud layering perspective can be identified as a platform service, i.e., an MCS as a service (MCSaaS). A prototype implementation that serves as a blueprint and a proof-of-concept of the proposed framework is presented, while an evaluation of the effectiveness of the MCSaaS paradigm has been provided using suitable mobility-related use cases for a validation of the concept, as well as a modeling approach through the adoption of generalized stochastic Petri nets.
Location-based social networks (LBSNs) provide people with an interface to share their locations and write reviews about interesting places of attraction. The shared locations form the crowdsourced digital footprints, in which each user has many connections to many locations, indicating user preference to locations. In this paper, we propose an approach for personalized travel package recommendation to help users make travel plans. The approach utilizes data collected from LBSNs to model users and locations, and it determines users’ preferred destinations using collaborative filtering approaches. Recommendations are generated by jointly considering user preference and spatiotemporal constraints. A heuristic search-based travel route planning algorithm was designed to generate travel packages. We developed a prototype system, which obtains users’ travel demands from mobile client and generates travel packages containing multiple points of interest and their visiting sequence. Experimental results suggest that the proposed approach shows promise with respect to improving recommendation accuracy and diversity.
By using increasingly popular smartphones, participatory sensing systems can collect comprehensive sensory data to retrieve context-aware information for different applications (or sensing tasks). However, new challenges arise when selecting the most appropriate participants when considering their different incentive requirements, associated sensing capabilities, and uncontrollable mobility, to best satisfy the quality-of-information (QoI) requirements of multiple concurrent tasks with different budget constraints. This paper proposes a multitask-oriented participant selection strategy called “DPS,” which is used to tackle the aforementioned challenges, where three key design elements are proposed. First is the QoI satisfaction metric, where the required QoI metrics of the collected data are quantified in terms of data granularity and quantity. Second is the multitask-orientated QoI optimization problem for participant selection, where task budgets are treated as the constraint, and the goal is to select a minimum subset of participants to best provide the QoI satisfaction metrics for all tasks. The optimization problem is then converted to a nonlinear knapsack problem and is solved by our proposed dynamic participant selection (DPS) strategy. Third is how to compute the expected amount of collected data by all (candidate) participants, where a probability-based movement model is proposed to facilitate such computation. Real and extensive trace-based simulations show that, given the same budget, the proposed participant selection strategy can achieve far better QoI satisfactions for all tasks than selecting participants randomly or through the reversed-auction-based approaches.
Mobile crowdsourced sensing (MCS) is a new paradigm which takes advantage of pervasive smartphones to efficiently collect data, enabling numerous novel applications. To achieve good service quality for a MCS application, incentive mechanisms are necessary to attract more user participation. Most of existing mechanisms apply only for the offline scenario where all users' information are known a priori. On the contrary, we focus on a more realistic scenario where users arrive one by one online in a random order. Based on the online auction model, we investigate the problem that users submit their private types to the crowdsourcer when arrive, and the crowdsourcer aims at selecting a subset of users before a specified deadline for maximizing the value of services (assumed to be a non-negative monotone submodular function) provided by selected users under a budget constraint. We design two online mechanisms, OMZ and OMG, satisfying the computational efficiency, individual rationality, budget feasibility, truthfulness, consumer sovereignty and constant competitiveness under the zero arrival-departure interval case and a more general case, respectively. Through extensive simulations, we evaluate the performance and validate the theoretical properties of our online mechanisms.
This paper presents iSee, a crowdsourced approach to detecting and localizing events in outdoor environments. Upon spotting an event, an iSee user only needs to swipe on her smartphone's touchscreen in the direction of the event. These swiping directions are often inaccurate and so are the compass measurements. Moreover, the swipes do not encode any notion of how far the event is located from the user, neither is the GPS location of the user accurate. Furthermore, multiple events may occur simultaneously and users do not explicitly indicate which events they are swiping towards. Nonetheless, as more users start contributing data, we show that our proposed system is able to quickly detect and estimate the locations of the events. We have implemented iSee on Android phones and have experimented in real-world settings by planting virtual "events" in our campus and asking volunteers to swipe on seeing one. Results show that iSee performs appreciably better than established triangulation and clustering-based approaches, in terms of localization accuracy, detection coverage, and robustness to sensor noise.
Mobile crowd sensing is a new paradigm that takes advantage of pervasive mobile devices to efficiently collect data, enabling numerous largescale applications. Human involvement is one of the most important features, and human mobility offers unprecedented opportunities for both sensing coverage and data transmission. In this article, we investigate the opportunistic characteristics of human mobility from the perspectives of both sensing and transmission, and discuss how to exploit these opportunities to collect data efficiently and effectively. We also outline various open issues brought by human involvement in this emerging research area.
Information about urban air quality, e.g., the concentration of PM2.5, is of great importance to protect human health and control air pollution. While there are limited air-quality-monitor-stations in a city, air quality varies in urban spaces non-linearly and depends on multiple factors, such as meteorology, traffic volume, and land uses. In this paper, we infer the real-time and fine-grained air quality information throughout a city, based on the (historical and real-time) air quality data reported by existing monitor stations and a variety of data sources we observed in the city, such as meteorology, traffic flow, human mobility, structure of road networks, and point of interests (POIs). We propose a semi-supervised learning approach based on a co-training framework that consists of two separated classifiers. One is a spatial classifier based on an artificial neural network (ANN), which takes spatially-related features (e.g., the density of POIs and length of highways) as input to model the spatial correlation between air qualities of different locations. The other is a temporal classifier based on a linear-chain conditional random field (CRF), involving temporally-related features (e.g., traffic and meteorology) to model the temporal dependency of air quality in a location. We evaluated our approach with extensive experiments based on five real data sources obtained in Beijing and Shanghai. The results show the advantages of our method over four categories of baselines, including linear/Gaussian interpolations, classical dispersion models, well-known classification models like decision tree and CRF, and ANN.
We investigate opportunistic routing, centering on the recommendation of ideal diversions on trips to a primary destination when an unplanned waypoint, such as a rest stop or a refueling station, is desired. In the general case, an automated routing assistant may not know the driver's final destination and may need to consider probabilities over destinations in identifying the ideal waypoint along with the revised route that includes the waypoint. We consider general principles of opportunistic routing and present the results of several studies with a corpus of real-world trips. Then, we describe how we can compute the expected value of asking a user about the primary destination so as to remove uncertainly about the goal and show how this measure can guide an automated system's engagements with users when making recommendations for navigation and analogous settings in ubiquitous computing.
Mobile Crowd Sensing (MCS) is a new paradigm which takes advantage of
pervasive smartphones to efficiently collect data, enabling numerous novel
applications. To achieve good service quality for a MCS application, incentive
mechanisms are necessary to attract more user participation. Most of existing
mechanisms apply only for the offline scenario where all users' information are
known a priori. On the contrary, we focus on a more realistic scenario where
users arrive one by one online in a random order. Based on the online auction
model, we investigate the problem that users submit their private profiles to
the crowdsourcer when they arrive, and the crowdsourcer aims at selecting a
subset of users before a specified deadline for minimizing the total payment
while a specific number of tasks can be completed.We design three online
mechanisms, Homo-OMZ, Hetero-OMZ and Hetero-OMG, all of which can satisfy the
computational efficiency, individual rationality, cost-truthfulness, and
consumer sovereignty. The Homo-OMZ mechanism is applicable to the homogeneous
user model and can satisfy the social efficiency but not constant frugality.
The Hetero-OMZ and Hetero-OMG mechanisms are applicable to both the homogeneous
and heterogeneous user models, and can satisfy the constant frugality. Besides,
the Hetero-OMG mechanism can also satisfy the time-truthfulness. Through
extensive simulations, we evaluate the performance and validate the theoretical
properties of our online mechanisms.
It has been estimated that traffic congestion costs the world economy hundreds of billions of dollars each year, increases pollution, and has a negative impact on the overall quality of life in metropolitan areas. A significant part of congestion in urban areas is due to vehicles searching for on-street parking. Detailed and accurate on-street parking maps can help drivers easily locate areas with large numbers of legal parking spaces and thus relieve congestion. In this paper, we address the problem of mapping street parking spaces using vehicles' preinstalled parking sensors. In particular, we focus on identifying legal parking spaces from crowdsourced data, whereas earlier work has largely assumed that such maps of legal spaces are given. We demonstrate that crowdsensing data from vehicle parking sensors can be used to classify on-street areas into legal/illegal parking spaces. Based on more than 2 million data points collected in Highland Park, NJ and downtown Brooklyn, NY areas, we show that on-street parking maps can be estimated with an accuracy of ~90% using proposed weighted occupancy rate thresholding algorithm.
Compared to the other types of sensor networks, the wireless camera sensor networks can offer much more comprehensive and accurate information in mobile target tracking applications. We propose a dynamic node collaboration scheme for mobile target tracking in wireless camera sensor networks. Unlike the traditional sensing models, we develop a nonlinear localization-oriented sensing model for camera sensors by taking the perspective projection and the observation noises into account. Based on our sensing model, we apply the sequential Monte Carlo (SMC) technique to estimate the belief state of the target location. In order to implement the SMC based tracking mechanism efficiently, we propose a dynamic node collaboration scheme, which can balance the tradeoff between the quality of tracking and the network cost. Our scheme deploys the dynamic cluster architecture which mainly includes the following two components. First, we design a scheme to elect the cluster heads during the tracking process. Second, we develop an optimization-based algorithm to select an optimal subset of camera sensors as the cluster members for estimating the target location cooperatively. Also conducted is a set of extensive simulations to validate and evaluate our proposed schemes.
The detection and extraction of target blobs is implemented by an adaptive Gaussian mixture background modeling. Its computational complexity can be greatly reduced because of frame reconstruction and the flexibility of Gaussian mixture components. The unscented Kalman filter is used to dynamically predict the target position and estimate the tracking uncertainty. The target association combining homography transformation with hue histogram matching implements the identity of the same target in different views. For the same target, the confidence measure based on the target size and the tracking uncertainty is defined to achieve optimal node selection. And then the new camera node continues the target tracking and the next node selection process.
Destination prediction is an essential task for many emerging location based applications such as recommending sightseeing places and targeted advertising based on destination. A common approach to destination prediction is to derive the probability of a location being the destination based on historical trajectories. However, existing techniques using this approach suffer from the “data sparsity problem”, i.e., the available historical trajectories is far from being able to cover all possible trajectories. This problem considerably limits the number of query trajectories that can obtain predicted destinations. We propose a novel method named Sub-Trajectory Synthesis (SubSyn) algorithm to address the data sparsity problem. SubSyn algorithm first decomposes historical trajectories into sub-trajectories comprising two neighbouring locations, and then connects the sub-trajectories into “synthesised” trajectories. The number of query trajectories that can have predicted destinations is exponentially increased by this means. Experiments based on real datasets show that SubSyn algorithm can predict destinations for up to ten times more query trajectories than a baseline algorithm while the SubSyn prediction algorithm runs over two orders of magnitude faster than the baseline algorithm. In this paper, we also consider the privacy protection issue in case an adversary uses SubSyn algorithm to derive sensitive location information of users. We propose an efficient algorithm to select a minimum number of locations a user has to hide on her trajectory in order to avoid privacy leak. Experiments also validate the high efficiency of the privacy protection algorithm.
This article investigates how and to what extent the power of collective although imprecise intelligence can be employed in smart cities. The main visionary goal is to automate the organization of spontaneous and impromptu collaborations of large groups of people participating in collective actions (i.e., participAct), such as in the notable case of urban crowdsensing. In a crowdsensing environment, people or their mobile devices act as both sensors that collect urban data and actuators that take actions in the city, possibly upon request. Managing the crowdsensing process is a challenging task spanning several socio-technical issues: from the characterization of the regions under control to the quantification of the sensing density needed to obtain a certain accuracy; from the evaluation of a good balance between sensing accuracy and resource usage (number of people involved, network bandwidth, battery usage, etc.) to the selection of good incentives for people to participAct (monetary, social, etc.). To tackle these problems, this article proposes a crowdsensing platform with three main original technical aspects: an innovative geo-social model to profile users along different variables, such as time, location, social interaction, service usage, and human activities; a matching algorithm to autonomously choose people to involve in participActions and to quantify the performance of their sensing; and a new Android-based platform to collect sensing data from smart phones, automatically or with user help, and to deliver sensing/actuation tasks to users.
Barrier coverage is an important issue in wireless sensor network. In wireless camera sensor networks, the cameras take the images or videos of target objects, the position and angle of camera sensor impact on the sense range. Therefore, the barrier coverage problem in camera sensor network is different from scalar sensor network. In this paper, based on the definition of full-view coverage, we focus on the Minimum Camera Barrier Coverage Problem (MCBCP) in wireless camera sensor networks in which the camera sensors are deployed randomly in a target field. Firstly, we partition the target field into disjoint subregions which are full-view-covered regions or not-full-view-covered regions. Then we model the full-view-covered regions and their relationship as a weighted directed graph. Based on the graph, we propose an algorithm to find a feasible solution for the MCBCP problem. We also proved the correctness of the solution for the MCBCP problem. Furthermore, we propose an optimal algorithm for the MCBCP problem. Finally, simulation results demonstrate that our algorithm outperforms the existing algorithm.
This paper introduces a hierarchical Markov model that can learn and infer a user's daily movements through an urban community. The model uses multiple levels of abstraction in order to bridge the gap between raw GPS sensor measurements and high level information such as a user's destination and mode of transportation. To achieve efficient inference, we apply Rao–Blackwellized particle filters at multiple levels of the model hierarchy. Locations such as bus stops and parking lots, where the user frequently changes mode of transportation, are learned from GPS data logs without manual labeling of training data. We experimentally demonstrate how to accurately detect novel behavior or user errors (e.g. taking a wrong bus) by explicitly modeling activities in the context of the user's historical data. Finally, we discuss an application called “Opportunity Knocks” that employs our techniques to help cognitively-impaired people use public transportation safely.
The use of centralized, real-time position tracking is proliferating in the areas of logistics and public transportation. Real-time positions can be used to provide up-to-date information to a variety of users, and they can also be accumulated for uses in subsequent data analyses. In particular, historical data in combination with real-time data may be used to predict the future travel times of vehicles more accurately, thus improving the experience of the users who rely on such information. We propose a Nearest-Neighbor Trajectory (NNT) technique that identifies the historical trajectory that is the most similar to the current, partial trajectory of a vehicle. The historical trajectory is then used for predicting the future movement of the vehicle. The paper's specific contributions are two-fold. First, we define distance measures and a notion of nearest neighbor that are specific to trajectories of vehicles that travel along known routes. In empirical studies with real data from buses, we evaluate how well the proposed distance functions are capable of predicting future vehicle movements. Second, we propose a main-memory index structure that enables incremental similarity search and that is capable of supporting varying-length nearest neighbor queries.