Shen-Shyang Ho

Papers

Total Citations

H-Index

About

Shen-Shyang Ho is a researcher whose work bridges the critical gap between real-world constraints and technological solutions, primarily in indoor localization and precision agriculture. His key research areas include GPS-denied navigation, deep learning for computer vision, and applied machine learning. Ho’s major contribution, "ParkLoc" (2018, 15 citations), tackles the pervasive challenge of locating vehicles indoors—such as in underground parking garages—where GPS and Wi-Fi signals are unavailable. By developing a smartphone-only solution that bypasses infrastructure like BLE beacons, Ho provides a scalable, cost-effective approach to indoor localization. In a significant pivot to agricultural technology, his 2021 study on weed detection in mulched onions (8 citations) compares state-of-the-art object detection models, including Scaled-YOLOv4-CSP, YOLOv5s, and SSD Mobilenet V2. This work demonstrates that YOLOv5s is the most suitable model for real-time, accurate weed control, enabling farming robots to operate efficiently. Ho’s impact lies in his ability to adapt advanced AI to practical, resource-limited environments, from urban parking to crop fields. His research not only advances autonomous systems but also offers tangible benefits for everyday users and sustainable farming, marking him as a versatile innovator in applied computer science.