Smart Agro-Forestry & Forest Sensor Networks
UAV and near-ground visual recognition for forest pests and wildfires, paired with low-power under-canopy wireless sensor networks.
Nanjing Forestry University · College of Information Science and Technology / College of Artificial Intelligence
Shenlin Yinxiang:From Forest Monitoring and Wireless Networks to Visual and Industrial Analytics
Focusing on smart agro-forestry, 5G/6G and satellite links, ISAC, visual/medical imaging, aging assessment, and power-grid analytics across 6 directions and 13 projects.
01 RESEARCH DIRECTIONS
Six Research Directions
Spanning forestry sensing, wireless communications, visual learning, and healthcare/power analytics.
Ultra-Dense Wireless Networks & Satellite-Terrestrial Multiple Access
Low-overhead channel acquisition, RIS interference management, and reliable multiple access for 5G/6G and LEO satellite IoT.
Integrated Sensing and Communications
Simultaneous RF data transmission and sensing, focusing on lightweight WiFi action recognition, full-duplex security, and RIS energy efficiency.
Visual Representation Learning & Medical Image Analysis
Wavelet and multi-channel deep network construction theory applied to medical image segmentation and thyroid-cancer metastasis prediction.
Aging Assessment & Smart Health Management
Algorithmic and applied research on physiological assessment, multi-organ aging quantification, and frailty risk warning.
Power Equipment Visual Inspection & Acoustic-Parameter Joint Analysis
Field image equipment localization and defect review workflows alongside synchronous transformer audio–parameter joint analysis.
Lead, research focus, related projects and publications for every direction.
All 6 Research Directions →02 SELECTED PROJECTS
Research & Industry Projects
Six representative topics from our 13 national, provincial, and industry research projects.
Categories, periods, roles and summaries for all 13 topics.
View All 13 Projects →03 REPRESENTATIVE PAPERS
Selected Publications
Selected work on pine wilt detection, wavelet dual-task networks, and multi-scale visual networks.
PWDViTNet: A lightweight early pine wilt disease detection model based on the fusion of ViT and CNN
A lightweight early pine wilt disease detection model fusing ViT and CNN.
A Pine Wilt Disease Detection Model Integrated with Mamba Model and Attention Mechanisms Using UAV Imagery
Pine wilt disease detection in UAV imagery with Mamba and attention mechanisms.
Wavelet-Based Dual-Task Network
A dual-task network built with wavelet structure.
Multiscale Low-Frequency Memory Network for Improved Feature Extraction in Convolutional Neural Networks
A multiscale low-frequency memory network for improved CNN feature extraction.
04 TEAM MEMBERS
Faculty & Researchers
Members are based in the Department of Internet of Things Engineering at the College of Information Science and Technology and College of Artificial Intelligence, Nanjing Forestry University.
Haifeng Lin 林海峰
Professor · Doctoral supervisor
Department of Internet of Things Engineering
Faculty Profile (ZH) ↗ (opens in a new window)Jie Liu 刘杰
Lecturer · Master's supervisor
Department of Internet of Things Engineering
Faculty Directory (ZH) ↗ (opens in a new window)Long Suo 索龙
Associate Professor · Master's supervisor
Department of Internet of Things Engineering
Faculty Directory (ZH) ↗ (opens in a new window)Fuzhi Wu 吴福志
Lecturer · Graduate Supervisor
Department of Internet of Things Engineering
Faculty Profile (ZH) ↗ (opens in a new window)05 TEACHING & PRACTICE
Coursework & Research Training
We organize literature reading, algorithm reproduction, and scientific figure design into daily study guides for undergraduate and graduate students.
06 CONNECT
Academic Exchange & Collaboration
We welcome academic discussions, coursework practice, and research collaboration across the six directions above. Feel free to email us with specific questions or collaboration topics.
Information Building, Nanjing Forestry University, 159 Longpan Road, Nanjing 210037, China · Graduate admissions policies and schedules follow official university and college announcements.