Masayoshi Ohta

Papers

Total Citations

H-Index

About

Masayoshi Ohta’s research centers on pattern recognition, neural networks, and self-organizing maps (SOMs), with a particular focus on improving vector classification systems. His most-cited work, “Effect of grouping in vector recognition system based on SOM” (2016, 4 citations), explores how grouping strategies enhance the performance of SOM-based classifiers. By leveraging the topology-preserving nature of unsupervised learning, Ohta demonstrates how structured clustering can refine pattern recognition in image processing and related applications. This contribution addresses a fundamental challenge in machine learning: balancing unsupervised feature extraction with classification accuracy. Though his citation count is modest, Ohta’s work offers practical insights for researchers developing more robust, scalable recognition systems. His findings are especially relevant for fields requiring efficient, data-driven grouping, such as computer vision and signal analysis. Ohta’s careful examination of SOM dynamics provides a foundation for future advances in adaptive neural network architectures, making his research a valuable reference for students and engineers seeking to optimize pattern recognition pipelines.