A paper authored by Jun Masaki (second-year master's student) as the first author has been accepted for publication in IEEE Transactions on Neural Systems and Rehabilitation Engineering.
Jun Masaki, Ariaki Higashi, Naoko Shinagawa, Kazuhiko Hirata, Yuichi Kurita, and Akira Furui
Skeleton-Based Multi-Action Fusion Framework for Binary Classification of FIM Score from Simplified Rehabilitation Actions
IEEE Transactions on Neural Systems and Rehabilitation Engineering (accepted).
This study proposes a multi-action fusion framework that classifies the functional independence measure (FIM) score from skeleton data of simplified rehabilitation exercises. The framework extracts action-specific features with skeleton-based deep learning models and fuses them, aiming to reduce the burden of FIM assessment on clinicians and patients. Experiments with 277 rehabilitation patients demonstrated higher classification performance than using a single action alone.
This is Masaki's first international journal paper. Congratulations!