Saved in:
Bibliographic Details
Main Authors: Calatrava-Nicolás, Francisco M., Miyauchi, Shoko, Rey, Vitor Fortes, Lukowicz, Paul, Stoyanov, Todor, Mozos, Oscar Martinez
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.05371
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908868538269696
author Calatrava-Nicolás, Francisco M.
Miyauchi, Shoko
Rey, Vitor Fortes
Lukowicz, Paul
Stoyanov, Todor
Mozos, Oscar Martinez
author_facet Calatrava-Nicolás, Francisco M.
Miyauchi, Shoko
Rey, Vitor Fortes
Lukowicz, Paul
Stoyanov, Todor
Mozos, Oscar Martinez
contents This paper addresses the problem of Human Activity Recognition (HAR) using data from wearable inertial sensors. An important challenge in HAR is the model's generalization capabilities to new unseen individuals due to inter-subject variability, i.e., the same activity is performed differently by different individuals. To address this problem, we propose a novel deep adversarial framework that integrates the concept of inter-subject variability in the adversarial task, thereby encouraging subject-invariant feature representations and enhancing the classification performance in the HAR problem. Our approach outperforms previous methods in three well-established HAR datasets using a leave-one-subject-out (LOSO) cross-validation. Further results indicate that our proposed adversarial task effectively reduces inter-subject variability among different users in the feature space, and it outperforms adversarial tasks from previous works when integrated into our framework. Code: https://github.com/FranciscoCalatrava/EmbeddedSubjectVariability.git
format Preprint
id arxiv_https___arxiv_org_abs_2603_05371
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Embedded Inter-Subject Variability in Adversarial Learning for Inertial Sensor-Based Human Activity Recognition
Calatrava-Nicolás, Francisco M.
Miyauchi, Shoko
Rey, Vitor Fortes
Lukowicz, Paul
Stoyanov, Todor
Mozos, Oscar Martinez
Machine Learning
This paper addresses the problem of Human Activity Recognition (HAR) using data from wearable inertial sensors. An important challenge in HAR is the model's generalization capabilities to new unseen individuals due to inter-subject variability, i.e., the same activity is performed differently by different individuals. To address this problem, we propose a novel deep adversarial framework that integrates the concept of inter-subject variability in the adversarial task, thereby encouraging subject-invariant feature representations and enhancing the classification performance in the HAR problem. Our approach outperforms previous methods in three well-established HAR datasets using a leave-one-subject-out (LOSO) cross-validation. Further results indicate that our proposed adversarial task effectively reduces inter-subject variability among different users in the feature space, and it outperforms adversarial tasks from previous works when integrated into our framework. Code: https://github.com/FranciscoCalatrava/EmbeddedSubjectVariability.git
title Embedded Inter-Subject Variability in Adversarial Learning for Inertial Sensor-Based Human Activity Recognition
topic Machine Learning
url https://arxiv.org/abs/2603.05371