Kyoto University · Engineering
Professor Tomoki Uchiyama's research lab specializes in advanced materials and computational methods for energy conversion and artificial intelligence. The lab focuses on optimizing catalysts for fuel cell reactions, particularly through the study of ionomer effects on platinum-based catalysts, and explores innovative applications of machine learning in 3D video analysis. A key direction involves developing explainable AI techniques, such as 3D occlusion sensitivity analysis, to interpret deep learning models in temporal-spatial data. The lab also investigates color image segmentation using competitive learning for computer vision applications.
Figures are computed from collected data and may differ slightly.
Presents a color image segmentation method which divides the color space into clusters. Competitive learning is used as a tool for clustering the color space based on the least sum-of-squares criterion. We show that competitive learning converges to approximate the optimum solution based on this criterion, theoretically and experimentally. We apply this method to various color scenes and show its efficiency as a color image segmentation method. We also show the effects of using different color c
The influence of specific adsorption of the sulfo group in the perfluorosulfonic acid ionomer, Nafion, on the oxygen reduction reaction (ORR) of a carbon-supported Pt/C catalyst using a thin-film rotating disk electrode was investigated. The relationship between the catalyst activity and coating of the Pt/C catalyst with Nafion was quantitatively evaluated through electrochemical measurements, operando X-ray absorption spectroscopy (XAS), and CO stripping voltammetry. Activity of the Pt/C cataly
This paper proposes a method for visually explaining the decision-making process of 3D convolutional neural networks (CNN) with a temporal extension of occlusion sensitivity analysis. The key idea here is to occlude a specific volume of data by a 3D mask in an input 3D temporalspatial data space and then measure the change degree in the output score. The occluded volume data that produces a larger change degree is regarded as a more critical element for classification. However, while the occlusi
Open papers in the app to read, cite, and organize with AI.
