Takafumi Sameshima

Papers

Total Citations

H-Index

About

Takafumi Sameshima’s research centers on the design and optimization of brain-machine interfaces (BMIs), with a particular focus on using near-infrared spectroscopy (NIRS) to interpret human cerebral activity. His major contributions include developing LVQ-based classifiers that can distinguish patterns of cerebral blood flow corresponding to different mental states, and investigating how learning conditions affect classification performance. Sameshima’s work addresses a critical challenge in BMI design: improving the accuracy and reliability of non-invasive neural signal decoding. His most-cited paper, “Design of Brain-Machine Interface Using Near-Infrared Spectroscopy” (2013), has garnered 3 citations, while his earlier conference paper on learning conditions for improved classification (2011) has 2 citations. Though his citation counts are modest, his research is foundational in the niche area of NIRS-based BMI, bridging robotics and medical science. Sameshima’s studies contribute to the long-term goal of creating practical, non-invasive interfaces that could one day assist individuals with motor disabilities, making his work notable for its potential real-world impact in assistive technology and neurorehabilitation.