Xiaoke Hou

Qingdao University of Science and Technology

Papers

1

Total Citations

55

H-Index

1

About

Xiaoke Hou is a researcher at the forefront of applying deep learning and embedded systems to marine science. His work centers on real-time marine animal image classification, leveraging lightweight neural networks like MobileNet and transfer learning to overcome the computational constraints of underwater environments. His most cited paper, "Real-time Marine Animal Images Classification by Embedded System Based on Mobilenet and Transfer Learning" (2019, 55 citations), demonstrates a practical, high-efficiency solution for monitoring marine growth, fishing activities, and water conditions—critical for sustainable aquaculture. By enabling accurate, low-power classification directly on embedded devices, Hou’s contributions bridge the gap between advanced AI and field-deployable marine technology. His research not only advances automated underwater monitoring but also offers a scalable framework for real-time ecological surveillance, making him a key figure in the intersection of computer vision, edge computing, and marine biology.

Research Focus

Key Achievements

1
H-Index
1
Papers
55
Total Citations
55
Avg Citations/Paper
🏆 Most Cited Paper
Real-time Marine Animal Images Classification by Embedded System Based on Mobilenet and Transfer Learning
55 citations · 2019
📈 Most Prolific Year: 2019 (1 Papers)
🤝 Key Collaborators: 5
🏛 Institutions: Qingdao University of Science and Technology

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 11 days ago