Towards Learning Discrete Representations via Self-Supervision for Wearables-Based Human Activity Recognition
Sensors · 15.02.2024 · 24 (4) · 1238
DOI: 10.3390/s24041238 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 15.02.2024. Verfasst von Harish Haresamudram und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA. Hauptthemen laut MEDLINE: Human Activities, Wearable Electronic Devices. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 101 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NSF.
Abstract (Originalsprache)
Human activity recognition (HAR) in wearable and ubiquitous computing typically involves translating sensor readings into feature representations, either derived through dedicated pre-processing procedures or integrated into end-to-end learning approaches. Independent of their origin, for the vast majority of contemporary HAR methods and applications, those feature representations are typically continuous in nature. That has not always been the case. In the early days of HAR, discretization approaches had been explored—primarily motivated by the desire to minimize computational requirements on HAR, but also with a view on applications beyond mere activity classification, such as, for example, activity discovery, fingerprinting, or large-scale search. Those traditional discretization approaches, however, suffer from substantial loss in precision and resolution in the resulting data representations with detrimental effects on downstream analysis tasks. Times have changed, and in this paper, we propose a return to discretized representations. We adopt and apply recent advancements in vector quantization (VQ) to wearables applications, which enables us to directly learn a mapping between short spans of sensor data and a codebook of vectors, where the index comprises the discrete representation, resulting in recognition performance that is at least on par with their contemporary, continuous counterparts—often surpassing them. Therefore, this work presents a proof of concept for demonstrating how effective discrete representations can be derived, enabling applications beyond mere activity classification but also opening up the field to advanced tools for the analysis of symbolic sequences, as they are known, for example, from domains such as natural language processing. Based on an extensive experimental evaluation of a suite of wearable-based benchmark HAR tasks, we demonstrate the potential of our learned discretization scheme and discuss how discretized sensor data analysis can lead to substantial changes in HAR.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA.
- School of Interactive Computing, Georgia Institute of Technology, Atlanta, GA 30332, USA.
ORCID-Profile: Thomas Plötz
Förderung
- NSF
Zitieren
APA
Haresamudram, H., Essa, I., & Plötz, T. (2024). Towards Learning Discrete Representations via Self-Supervision for Wearables-Based Human Activity Recognition. Sensors, 24(4), 1238. https://doi.org/10.3390/s24041238
Vancouver
Haresamudram H, Essa I, Plötz T. Towards Learning Discrete Representations via Self-Supervision for Wearables-Based Human Activity Recognition. Sensors. 2024;24(4):1238. doi:10.3390/s24041238
BibTeX
@article{Haresamudram2024,
author = {Haresamudram, Harish and Essa, Irfan and Plötz, Thomas},
title = {Towards Learning Discrete Representations via Self-Supervision for Wearables-Based Human Activity Recognition},
journal = {Sensors},
year = {2024},
volume = {24},
number = {4},
pages = {1238},
doi = {10.3390/s24041238}
}
EUVIMED