Wenjie Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Wenjie Zhang has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Chang Qi
School of Computer Science and Engineering, Southeast University, Nanjing, China
1 shared publication - Ding Ding
Southeast University, Nanjing, China
1 shared publication - Hao Chen
School of Computer Science and Engineering, Southeast University, Nanjing, China
1 shared publication - Zheyu Cao
School of Computer Science and Engineering, Southeast University, Nanjing, China
1 shared publication
Latest Publications
- Open Access
- 5 February 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Sensor Networks
- Vol. 22 (5) , 1-15
CPNet: Real-Time Cybersickness Prediction without Physiological Sensors for Cybersickness Mitigation
Although virtual reality (VR) has developed rapidly, offering unique user experience and broad application prospects, a significant challenge remains: its usage often induces cybersickness in users. Therefore, real-time and accurate prediction of cybersickness is essential to meet the requirements of alleviating cybersickness. Considering the limitations of using physiological signal sensors to predict cybersickness and the insufficient performance of previous methods, we introduce a novel deep learning model, CPNet, designed to effectively predict the severity of cybersickness by comprehensively considering features including head-tracking, eye-tracking, visual complexity, and experience duration. Moreover, we conducted an empirical study with 30 participants to collect a dataset aimed at validating the performance of our cybersickness prediction model. The results demonstrate that our approach achieves higher prediction accuracy than advanced models such as Informer, TimesNet, and Islam’s cybersickness prediction model.
- 5 February 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Sensor Networks
- Vol. 22 (5) , 1-15
Open AccessCPNet: Real-Time Cybersickness Prediction without Physiological Sensors for Cybersickness Mitigation
Although virtual reality (VR) has developed rapidly, offering unique user experience and broad application prospects, a significant challenge remains: its usage often induces cybersickness in users. Therefore, real-time and accurate prediction of cybersickness is essential to meet the requirements of alleviating cybersickness. Considering the limitations of using physiological signal sensors to predict cybersickness and the insufficient performance of previous methods, we introduce a novel deep learning model, CPNet, designed to effectively predict the severity of cybersickness by comprehensively considering features including head-tracking, eye-tracking, visual complexity, and experience duration. Moreover, we conducted an empirical study with 30 participants to collect a dataset aimed at validating the performance of our cybersickness prediction model. The results demonstrate that our approach achieves higher prediction accuracy than advanced models such as Informer, TimesNet, and Islam’s cybersickness prediction model.