Papers
2
Total Citations
7
H-Index
2
About
Shih-Hung Yang is a researcher whose work bridges computer vision and brain-computer interfaces (BCIs), with a focus on neural network-based algorithms and EEG signal processing. In computer vision, Yang developed a neural network-based stereo matching algorithm that leverages vertical disparity to solve matching problems in stereo vision, employing a two-dimensional Hopfield neural network to enforce geometric constraints. This work, published in 2010, has garnered 4 citations and laid groundwork for disparity-based depth estimation. In the BCI domain, Yang co-authored a 2020 study on simultaneous spatiospectral pattern learning and contaminated trial pruning for EEG-based BCIs, addressing the challenge of automatically designing spectral and spatial filters for motor imagery tasks. This approach enables more robust translation of neural commands into external device control, such as robotic arms, and has accumulated 3 citations. While Yang’s citation counts are modest, the work demonstrates a commitment to advancing practical, real-time neural interfaces and vision systems. The research is notable for its integration of machine learning techniques—like Hopfield networks and adaptive filtering—into constrained, real-world applications, offering a foundation for future work in assistive technology and autonomous perception.
Research Focus
Key Achievements
Top Papers
- 1
- 2