On the Metrics and Adaptation Methods for Domain Divergences of sEMG-based Gesture Recognition

István Ketykó, Ferenc Kovács

Abstract

We propose a new metric to measure domain divergence and a new domain adaptation method for time-series classification. The metric belongs to the class of probability distributions-based metrics, is transductive, and does not assume the presence of source data samples. The 2-stage method utilizes an improved autoregressive, RNN-based architecture with deep/non-linear transformation. We assess our metric and the performance of our model in the context of sEMG/EMG-based gesture recognition under inter-session and inter-subject domain shifts.

Download


Paper Citation


in Harvard Style

Ketykó I. and Kovács F. (2020). On the Metrics and Adaptation Methods for Domain Divergences of sEMG-based Gesture Recognition.In Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 4: BIOSIGNALS, ISBN 978-989-758-398-8, pages 121-132. DOI: 10.5220/0009369501210132


in Bibtex Style

@conference{biosignals20,
author={István Ketykó and Ferenc Kovács},
title={On the Metrics and Adaptation Methods for Domain Divergences of sEMG-based Gesture Recognition},
booktitle={Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 4: BIOSIGNALS,},
year={2020},
pages={121-132},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009369501210132},
isbn={978-989-758-398-8},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 4: BIOSIGNALS,
TI - On the Metrics and Adaptation Methods for Domain Divergences of sEMG-based Gesture Recognition
SN - 978-989-758-398-8
AU - Ketykó I.
AU - Kovács F.
PY - 2020
SP - 121
EP - 132
DO - 10.5220/0009369501210132