Wen Zhou

Wen Zhou

Ph.D., Associated Prof. in School of Computer & Information of Anhui Normal University, Wuhu City, Anhui Province, P.R.China

Novel learning framework for optimal multi-object video trajectory tracking

Published in Virtual Reality & Intelligent Hardware, 2023

With the rapid development of Web3D, virtual reality, and digital twins, virtual trajectories and decision data considerably rely on the analysis and understanding of real video data, particularly in emergency evacuation scenarios. Correctly and effectively evacuating crowds in virtual emergency scenarios are becoming increasingly urgent. One good solution is to extract pedestrian trajectories from videos of emergency situations using a multi-target tracking algorithm and use them to define evacuation procedures.

Recommended citation: Siyuan Chen, Xiaowu Hu, Wenying Jiang, Wen Zhou* , Xintao Ding, Novel learning framework for optimal multi-object video trajectory tracking. Virtual Reality & Intelligent Hardware, 2023,5(5):422-438.

Dual deep Q-learning network guiding a multiagent path planning approach for virtual fire emergency scenarios

Published in Applied Intelligence, 2023

With continuous deterioration of the natural environment and the corresponding significant increase in the occurrence of disasters, forest fire accidents have frequently occurred in recent decades. Therefore, it is important to perform extensive effective fire drills to increase evacuation experience and emergency reaction capacity. In comparison to traditional fire drills, which are subject to many latent uncertainties and incur high costs, fire exercises based on virtual scenarios offer many advantages, such as low cost and high safety. Accordingly, the planning and design of effective evacuation paths that sufficiently match real conditions have become an imperative focus of related research. In this paper, we propose a novel framework for path planning in virtual emergency scenarios, which consists of three parts. (a) Configuration of the virtual environment: for convenience in handling, the virtual emergency scenario is discretized into many individual grid cells. (b) Policy generation: a dual deep Q-learning network approach is employed to obtain an effective policy that can allow agents to intelligently find effective paths. (c) Grouping strategy: a strategy is proposed to support multiple agents in achieving collective evacuation based on a given policy. Finally, extensive experiments are presented to validate the superiority of the proposed framework. The results show that by comparison with the existing related state-of-the-art methods, our proposed framework is superior and feasible

Recommended citation: Wen Zhou , C. Zhang, S. Chen, Dual deep Q-learning network guiding a multiagent path planning approach for virtual fire emergency scenarios. Applied Intelligence, 2023,53:21858–21874.

An Improved Federated Learning Approach Enhanced Internet of Health Things Framework for Private Decentralized Distributed Data

Published in Information Science, 2022

With the privacy protection increasingly being concerned, Data centralization often heavily causes a big risk of privacy protection, gradually, there is a prevailing trend to enhance the security performance by means of data decentralization, above all, for health care internet of things(IoT) data.Meanwhile, Federated learning has obvious privacy advantages compared to data center training on protecting privacy data.For this reason, a novel framework based on federated learning is presented in this paper, which is suitable for private and decentralized data sets, such as big data in healthy Internet of Things. Specifically, the main work of the puts forward framework includes: (1)Multi-center data collection of healthy Internet of Things. (2)healthy data analysis of Internet of Things. (3)privacy protection method for data of healthy Internet of Things. Finally, related experiments show that the proposed method is feasible, and compared with the traditional methods, it has significantly improved the performace in Quality of Service (QoS) and IoUs indicator.

Recommended citation: Huang, C., Xu, G., Chen, S., Zhou, Wen*, NG, E. Y., & de Albuquerque, Victor Hugo C. de Albuquerque*. An Improved Federated Learning Approach Enhanced Internet of Health Things Framework for Private Decentralized Distributed Data. Information Sciences, 2022, 614:138-152

Multiagent Evacuation Framework for a Virtual Fire Emergency Scenario Based on Generative Adversary Imitation Learning

Published in Computer Animation and Virtual Worlds, 2022

MultiAgents GAIL methods for conducting the fire path planning on virutal fire emeregency scenario.

Recommended citation: Wen Zhou,W. Jiang, B. Jie, W. Bian. "Multiagent Evacuation Framework for a Virtual Fire Emergency Scenario Based on Generative Adversary Imitation Learning." Computer Animation and Virtual Worlds. 2022, 33(1): e2035.

A robust approach for privacy data protection: IoT security assurance using generative adversarial imitation learning

Published in IEEE Internet of Things Journal, 2021

With the increasing importance of data security, privacy protection has gradually risen to a strategic position, especially IoT data privacy protection. The concern for data security has become a national strategy. The discovery of potential risks of privacy data is of great significance, such as the risk of data privacy leakage, data security vulnerabilities, etc. In this article, starting from the privacy data protection mechanism in the Industrial Internet of Things (IIoT) scenario, we proposed a method based on generative adversarial imitation learning (GAIL) to discover the privacy data security risks in IIoT by training privacy protection agents using a large amount of expert data on privacy protection. Finally, our proposed method is validated by relevant simulation experiments, and the results show that our proposed method has wide generalizability and reliability to obtain the maximum payoff of the agents and thus, reduce the risk of data security leakage

Recommended citation: C. Huang, S. Chen, Y. Zhang, Wen Zhou*, etc. "A robust approach for privacy data protection: IoT security assurance using generative adversarial imitation learning." IEEE Internet of Things Journal. 2021,9(18):17089-17097.

Training Deep Convolutional Neural Networks to Acquire the Best View of a 3D Shape

Published in Multimedia Tools and Applications, 2020

Acquring the best view to achieve 3D shape transforming 2D images, which is the best respresentation for 3D shape.

Recommended citation: Wen Zhou, J. Jia "Training Deep Convolutional Neural Networks to Acquire the Best View of a 3D Shape"[J]. Multimedia Tools and Applications, 2020, 79(1):581-601.