10 April 2023 in IEEE Internet of Things Journal
Mobile Crowdsensing (MCS), which relies on a large number of ordinary participants to complete sensing tasks, has become a new data collection paradigm in the Internet of Things (IoT). In the MCS system, how to select reliable participants to participate in the sensing task and provide appropriate rewards for participants is one of the main problems faced by MCS. This paper proposes a reliable participant selection strategy driven by dynamic incentives. The whole participant selection process is divided into multiple stages. First, the platform calculates participants reliability by considering task completion rate and task pass rate. Then, when the platform releases tasks at each stage, it considers the task deadline and the task completion progress to quantify the task requirements, and then determines the maximum price of the tasks at that stage. Finally, the platform selects participants who meet the requirements for different tasks at each stage, and conducts bargaining games with participants to determine appropriate rewards. Considering the situation that participants quit midway and the task cannot be completed, the platform adopts a task delegation mechanism to ensure the effective completion of the task. The results show that the proposed strategy can guarantee the task completion rate and data quality, and optimize the reward of participants.
1 January 2021 in Wireless Communications and Mobile Computing
How to improve delay‐sensitive traffic throughput is an open issue in vehicular communication networks, where a great number of vehicle to infrastructure (V2I) and vehicle to vehicle (V2V) links coexist. To address this issue, this paper proposes to employ a hybrid deep transfer learning scheme to allocate radio resources. Specifically, the traffic throughput maximization problem is first formulated by considering interchannel interference and statistical delay guarantee. The effective capacity theory is then applied to develop a power allocation scheme on each channel reused by a V2I and a V2V link. Thereafter, a deep transfer learning scheme is proposed to obtain the optimal channel assignment for each V2I and V2V link. Simulation results validate that the proposed scheme provides a close performance guarantee compared to a globally optimal scheme. Besides, the proposed scheme can guarantee lower delay violation probability than the schemes aiming to maximize the channel capacity.
24 October 2020 in New Generation Computing
1 June 2021 in Computer Standards & Interfaces
24 May 2022 in Computers and Electrical Engineering
16 January 2026 in Signal, Image and Video Processing