Kosuke Minami

National Institute for Materials Science

Papers

Total Citations

H-Index

About

Kosuke Minami is a pioneering researcher at the intersection of machine learning, sensor technology, and olfactory science. His work focuses on developing automated systems that can replicate and innovate the human sense of smell, with key contributions in odor sensing and blending. Minami's most-cited paper, "Automated odor-blending with one-pot Bayesian optimization" (2024), introduces a groundbreaking system that enables robots to create new odors by intelligently blending existing ones. By integrating membrane-type surface stress sensors with Bayesian optimization, he has solved a long-standing challenge in robotics: the automated, data-driven generation of complex scents. This work has already garnered 4 citations in its first year, signaling its impact on fields from food science to environmental monitoring. Minami's approach not only advances robotic olfaction but also provides a scalable framework for chemical sensing and optimization. His research promises to transform industries reliant on scent creation, from perfumery to quality control, by replacing manual trial-and-error with efficient, machine-led discovery.