Interpretable High-level Features for Human Activity Recognition

Yale Hartmann, Hui Liu, Steffen Lahrberg, Tanja Schultz

2022

Abstract

This paper introduces and evaluates a novel way of processing human activities based on unique combinations of interpretable categorical high-level features with applications to classification, few-shot learning, as well as cross-dataset and cross-sensor comparison, combination, and analysis. Feature extraction is considered as a classification problem and solved with Hidden Markov Models making the feature space easily extensible. The feature extraction is person-independently evaluated on the CSL-SHARE and UniMiB SHAR datasets and achieves balanced accuracies up from 96.1% on CSL-SHARE and up to 91.1% on UniMiB SHAR. Furthermore, classification experiments on the separate and combined datasets achieve 85% (CSL-SHARE), 65% (UniMiB SHAR), and 74% (combined) accuracy. The few-shot learning experiments show potential with low errors in feature extraction but require further work for good activity classification. Remarkable is the possibility to attribute errors and indicate optimization areas easily. These experiments demonstrate the potential and possibilities of the proposed method and the high-level, extensible, and interpretable feature space.

Paper Citation

in Harvard Style

Hartmann Y., Liu H., Lahrberg S. and Schultz T. (2022). Interpretable High-level Features for Human Activity Recognition. In Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2022) - Volume 4: BIOSIGNALS; ISBN 978-989-758-552-4, SciTePress, pages 40-49. DOI: 10.5220/0010840500003123

in Bibtex Style

@conference{biosignals22,
author={Yale Hartmann and Hui Liu and Steffen Lahrberg and Tanja Schultz},
title={Interpretable High-level Features for Human Activity Recognition},
booktitle={Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2022) - Volume 4: BIOSIGNALS},
year={2022},
pages={40-49},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010840500003123},
isbn={978-989-758-552-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2022) - Volume 4: BIOSIGNALS
TI - Interpretable High-level Features for Human Activity Recognition
SN - 978-989-758-552-4
AU - Hartmann Y.
AU - Liu H.
AU - Lahrberg S.
AU - Schultz T.
PY - 2022
SP - 40
EP - 49
DO - 10.5220/0010840500003123
PB - SciTePress