FinD: Detection of Finger Movement using Smart Watch

Abstract

There were several trials to detect the movement of fingers, they necessitated special sensors, either rings or gloves, attached to the fingers. Based on the background, we have developed a system to identify the moved finger called FinD using the acceleration signals obtained with Commercial Off-The-Shelf (COTS) smart watches. We have investigated two methods: Non Matrix Factorization (NMF)-based (FinD-NMF) and time-series-based (FinD-TS) analyses. We have compared the two methods for three fingers with three subjects and found that FinD-TS exceeds FinD-NMF in the accuracy up to 40%-80%.