Search

Ubiquitous smartphones with various built-in sensors have boosted development of many crowdsensing applications in recent years. To achieve good performance with this class of applications, a large number of participating users with sensed data are needed. Two important considerations for improving user participation in crowdsensing are the incentive mechanism for motivating users to contribute their sensing capabilities, and the techniques for protecting user privacy. In this article, we survey the works that address these issues by integrating privacy techniques with incentive mechanisms. We also advocate two future research directions to enhance incentive mechanisms for mobile crowdsensing. [ABSTRACT FROM AUTHOR]

Spatial crowdsourcing and crowdsensing are two emerging crowdsourcing paradigms, which enable a variety of location-based query and sensing tasks. In spatial crowdsourcing, mobile workers are required to travel physically to target locations in order to complete query tasks. Most existing work, hence, has focused on designing efficient query task assignment schemes to maximize the task completion rate under traveling constraints of workers for spatial crowdsourcing systems. In crowdsensing, on the other hand, sensor recordings of workers’ smartphones are of interest and have been collected to build various applications. Therefore, work concerning crowdsensing has strived to maximize the coverage area of sensor trajectories by selecting a set of workers. In this paper, we investigate the integration of these two paradigms. We notice a key link between these paradigms: While a worker is traveling to the target location of a query task, his trajectory may provide valuable coverage for a sensing task. Therefore, we propose a task management framework, named SpatialRecruiter, to efficiently match workers to the merged query and sensing tasks. We propose two coverage estimation functions to compute the coverage potential of a worker. Then, we design a greedy heuristic to select and assign workers. The experimental results on a real-world dataset demonstrate that the proposed strategies are efficient and effective in meeting the requirements of both paradigms. [ABSTRACT FROM AUTHOR]

Mobile crowdsensing systems aim to provide various novel applications by employing pervasive smartphones. A key factor to enable such systems is substantial participation of normal smartphone users, which requires effective incentive mechanisms. In this paper, we investigate incentive mechanisms for online scenarios, where users arrive and interact with a task requester in a random order, and they have preferences (e.g., photographing) or limits (e.g., travel distance) over the sensing tasks. In existing online mechanisms, the task requester has limited power in assigning tasks to the selected users, i.e., it has to pay for all of the tasks specified by the selected users, although some of these tasks are of little value. To accommodate this, we investigate a more flexible setting, where the requester can actively assign most valuable tasks to the selected users. We design two online incentive mechanisms motivated by a sampling-accepting process and weighted maximum matching. We prove that the designed mechanisms achieve computational efficiency, individual rationality, budget feasibility, truthfulness, consumer sovereignty, and constant competitiveness. By carrying out extensive experiments on two real-world geographical datasets, we demonstrate the practical applicability of the proposed mechanisms. [ABSTRACT FROM PUBLISHER]

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

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