On the Feasibility of On-body Roaming Models in Human Activity Recognition

Mubarak Abdu-Aguye, Walid Gomaa, Yasushi Makihara, Yasushi Yagi

Abstract

In the domain of human activity recognition, the primary goal is to determine the action a user was performing based on data collected through some sensor modalities. Common modalities adopted to this end include visual and Inertial Measurement Units (IMUs), with the latter taking precedence in recent times due to their unobtrusiveness, low cost and mobility. However, a secondary challenge arises in such sensor-based activity recognition. Difficulties in collecting and annotating training samples are significant and can hinder the performance of models trained on such limited data. As such, there is a need to explore techniques capable of tackling this problem in this domain. In this work, we explore the feasibility of reusing samples collected from different ”source” body locations in activity recognition at different ”target” body locations. This is achieved through the use of ”roaming” models based on recurrent neural networks. We investigate the predictive performance of the transferred samples relative to the performance from samples collected natively at the target body locations. Our results suggest that such roaming models can permit the reuse of cross-body samples without a significant loss in discriminative performance.

Download


Paper Citation


in Harvard Style

Abdu-Aguye M., Gomaa W., Makihara Y. and Yagi Y. (2019). On the Feasibility of On-body Roaming Models in Human Activity Recognition.In Proceedings of the 16th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO, ISBN 978-989-758-380-3, pages 680-690. DOI: 10.5220/0007921606800690


in Bibtex Style

@conference{icinco19,
author={Mubarak Abdu-Aguye and Walid Gomaa and Yasushi Makihara and Yasushi Yagi},
title={On the Feasibility of On-body Roaming Models in Human Activity Recognition},
booktitle={Proceedings of the 16th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,},
year={2019},
pages={680-690},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007921606800690},
isbn={978-989-758-380-3},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,
TI - On the Feasibility of On-body Roaming Models in Human Activity Recognition
SN - 978-989-758-380-3
AU - Abdu-Aguye M.
AU - Gomaa W.
AU - Makihara Y.
AU - Yagi Y.
PY - 2019
SP - 680
EP - 690
DO - 10.5220/0007921606800690