Name: Li Hengyi
Gender: Male
Professional Title: Lecturer
Degree: Ph.D.
Education and Work Experience:
1. June 2024–present, Lecturer, School of Automation and Electrical Engineering, Zhongyuan University of Technology
2. May 2023–April 2024, Senior Researcher, Research Organization of Science and Technology, Ritsumeikan University
3. April 2020–March 2023, Ph.D. in Electronic Systems, Ritsumeikan University
4. September 2011–March 2020, Laboratory Engineer, School of Electronic Information, Zhongyuan University of Technology
5. September 2007–July 2011, Bachelor's degree in Automation, Zhongyuan University of Technology
Research Directions:
1. Deep learning model compression and acceleration design
2. Optimization of high-performance computing and edge computing for artificial intelligence
3. Machine vision perception and applications
Academic Research Projects:
1. Henan Key R&D and Promotion Program (Science and Technology Research Project): Design of a High-Order Coupled Vector Computing Accelerator Based on RISC-V Architecture for Deep Convolutional Neural Networks, January 2025–December 2026, RMB 100,000, ongoing, Principal Investigator.
2. Henan International Science and Technology Cooperation Project (Key Project), No. 251111520400: Research on Key Technologies for Intelligent Wearable Abnormal Gait Recognition for Lower-Limb Rehabilitation Assistance, January 2025–December 2027, ongoing, participant (role as shown on official page).
3. Ritsumeikan University, Japan, Research Institute of Advanced Technology, Research Department Project, RARA2023M: Establishment of Technologies for Automatic AI Model Construction and Autonomous Updating and Their Industrial Applications, April 2023–April 2028, RMB 1.2 million, ongoing, participant.
4. Japan Science and Technology Agency, National Project (Africa–Japan Collaborative Research Project), FY2023M: IoT-Based Intelligent Hybrid Biogas and Photovoltaic System, April 2023–April 2026, RMB 600,000, ongoing, participant.
Representative Papers:
1. Hengyi Li, Zhichen Wang, Xuebin Yue, Wenwen Wang, Hiroyuki Tomiyama, and Lin Meng, An Architecture-level Analysis on Deep Learning Models for Low-Impact Computations, Artificial Intelligence Review, Vol. 56, No. 3, pp. 1971–2010, March 2023.
2. Hengyi Li and Lin Meng, Hardware-aware Approach to Deep Neural Network Optimization, Neurocomputing, Vol. 558, Article 126808, November 2023.
3. Hengyi Li, Xuebin Yue, Chengyan Zhao, and Lin Meng, Lightweight deep neural network from scratch, Applied Intelligence, Vol. 53, pp. 18868–18886, August 2023.
4. Hengyi Li, Xuebin Yue, and Lin Meng, Enhanced Mechanisms of Pooling and Channel Attention for Deep Learning Feature Maps, PeerJ Computer Science, Vol. 8, November 2022.
5. Hengyi Li, Aihui Wang, Shengda Gao, Yan Wang, Shiyong Geng and Yongping Dan, The Transformer Enhanced Feature Representation with CNNs, 2024 IIKI, Kusatsu, Japan, pp. 18–23, 2024.
6. Jiale Ren, Hengyi Li, Aihui Wang, Kenshi Saho, and Lin Meng, Radar-based gait analysis by Transformer-liked network for dementia diagnosis, Biomedical Signal Processing and Control, Vol. 91, 2024.
7. Bing Lyu, Hengyi Li, Ami Tanaka, and Lin Meng, The Early Japanese Books Reorganization by Combining Image Processing and Deep Learning, CAAI Transactions on Intelligence Technology, October 2022.
Contact:
Email: lihengyi@zut.edu.cn
