Syori Usaka
Papers
1
Total Citations
3
H-Index
1
About
Syori Usaka is a researcher whose work bridges computer vision and infrastructure monitoring, with a particular focus on applying deep learning to power line inspection. Their most-cited paper, "Investigation of Texture Classification for Power Line Surface by Using CNN" (2019), introduces a convolutional neural network approach to classify surface textures on power lines—a critical task for detecting wear, corrosion, or damage in electrical grids. This work, with 3 citations, demonstrates Usaka’s contribution to automating visual inspection processes, reducing reliance on manual checks and enhancing safety in utility maintenance. While their citation count reflects a focused, emerging area of study, Usaka’s research holds practical significance for the energy sector, where early defect detection can prevent outages and hazards. By integrating texture analysis with deep learning, they have laid groundwork for more robust, real-time monitoring systems. Usaka’s work is notable for its applied nature, directly addressing real-world challenges in infrastructure reliability. Their research continues to inspire further exploration into computer vision for industrial applications, making them a promising voice in the intersection of AI and civil engineering.
Research Focus
Key Achievements
Top Papers
- 1