Papers
5
Total Citations
78
H-Index
5
About
Min-Hsiung Hung’s research bridges robotics, artificial intelligence, and smart manufacturing, with a focus on automating labor-intensive processes in agriculture and industry. His most impactful work applies deep learning to coffee production, where he developed a GAN-based data augmentation method for defective bean inspection (46 citations). This innovation significantly reduces the human effort required for quality control by enabling automated, high-precision defect removal. Hung has also made foundational contributions to robotic force distribution, deriving efficient formulations for tree-structured mechanisms like walking machines and mobile-base robots (14 and 7 citations). His work on ZigBee indoor positioning (6 citations) advanced location fingerprinting through signal-index-pair preprocessing, enhancing neural network training accuracy. More recently, he proposed a quad-partitioning robotic arm guidance system using a single inexpensive camera for precise bean defect picking (5 citations), demonstrating cost-effective automation solutions. Hung’s research consistently integrates theoretical rigor with practical deployment, addressing real-world challenges from coffee sorting to robotic coordination. His citation record reflects sustained impact across robotics, sensor systems, and AI-driven manufacturing.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5