Enregistré dans:
Détails bibliographiques
Auteurs principaux: Leite, Clayton Souza, Mauranen, Henry, Zhanabatyrova, Aziza, Xiao, Yu
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2410.13605
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909353508864000
author Leite, Clayton Souza
Mauranen, Henry
Zhanabatyrova, Aziza
Xiao, Yu
author_facet Leite, Clayton Souza
Mauranen, Henry
Zhanabatyrova, Aziza
Xiao, Yu
contents Transformers have excelled in natural language processing and computer vision, paving their way to sensor-based Human Activity Recognition (HAR). Previous studies show that transformers outperform their counterparts exclusively when they harness abundant data or employ compute-intensive optimization algorithms. However, neither of these scenarios is viable in sensor-based HAR due to the scarcity of data in this field and the frequent need to perform training and inference on resource-constrained devices. Our extensive investigation into various implementations of transformer-based versus non-transformer-based HAR using wearable sensors, encompassing more than 500 experiments, corroborates these concerns. We observe that transformer-based solutions pose higher computational demands, consistently yield inferior performance, and experience significant performance degradation when quantized to accommodate resource-constrained devices. Additionally, transformers demonstrate lower robustness to adversarial attacks, posing a potential threat to user trust in HAR.
format Preprint
id arxiv_https___arxiv_org_abs_2410_13605
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Transformer-Based Approaches for Sensor-Based Human Activity Recognition: Opportunities and Challenges
Leite, Clayton Souza
Mauranen, Henry
Zhanabatyrova, Aziza
Xiao, Yu
Machine Learning
Transformers have excelled in natural language processing and computer vision, paving their way to sensor-based Human Activity Recognition (HAR). Previous studies show that transformers outperform their counterparts exclusively when they harness abundant data or employ compute-intensive optimization algorithms. However, neither of these scenarios is viable in sensor-based HAR due to the scarcity of data in this field and the frequent need to perform training and inference on resource-constrained devices. Our extensive investigation into various implementations of transformer-based versus non-transformer-based HAR using wearable sensors, encompassing more than 500 experiments, corroborates these concerns. We observe that transformer-based solutions pose higher computational demands, consistently yield inferior performance, and experience significant performance degradation when quantized to accommodate resource-constrained devices. Additionally, transformers demonstrate lower robustness to adversarial attacks, posing a potential threat to user trust in HAR.
title Transformer-Based Approaches for Sensor-Based Human Activity Recognition: Opportunities and Challenges
topic Machine Learning
url https://arxiv.org/abs/2410.13605