Design and Implementation of Inertial Sensor Based Wearable Gestural Hand Motion Identification System

Qifan Zhou, Chunyang Yu, Zahra Lari, Hai Zhang and Naser El-Sheimy

Abstract:	This paper presents a new design and implementation of Micro Electro Mechanical System (MEMS) inertial sensor-based wearable gestural hand motion identification system. The introduced system can be applied in Human Computer Interaction (HCI), activity recognition, motion monitoring, and entertainment interaction. This system aims to monitor and identify the exact gestural hand motions in real time. To achieve this objective, a novel gestural hand motion detection approach is introduced to segment inertial data based on the hand movement discipline, and the random forest classifier is employed to recognize the exact hand actions. The system hardware platform by integrating a low-cost microcontroller and a 9-axis MEMS inertial sensor has also been developed. Currently the system is capable of recognizing eight gestural hand motions. Experimental results verify that the proposed system has achieved 99.15% accuracy, 95.50% precision, 99.39% recall and 97.39% F-measure. The functionality of the system for real-time application has also been proved through practical experiments.
Published in:	Proceedings of the 2016 International Technical Meeting of The Institute of Navigation January 25 - 28, 2016 Hyatt Regency Monterey Monterey, California
Pages:	333 - 342
Cite this article:	Zhou, Qifan, Yu, Chunyang, Lari, Zahra, Zhang, Hai, El-Sheimy, Naser, "Design and Implementation of Inertial Sensor Based Wearable Gestural Hand Motion Identification System," Proceedings of the 2016 International Technical Meeting of The Institute of Navigation, Monterey, California, January 2016, pp. 333-342. https://doi.org/10.33012/2016.13409
Full Paper:	ION Members/Non-Members: 1 Download Credit Sign In