No Cover Image

Journal article 59 views 6 downloads

Human Activity Recognition: A Comparative Study of Validation Methods and Impact of Feature Extraction in Wearable Sensors

Saeed Ur Rehman Orcid Logo, Anwar Ali Orcid Logo, Adil Mehmood Khan, Cynthia Okpala

Algorithms, Volume: 17, Issue: 12, Start page: 556

Swansea University Author: Anwar Ali Orcid Logo

  • 68579.VOR.pdf

    PDF | Version of Record

    © 2024 by the authors. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.

    Download (2MB)

Check full text

DOI (Published version): 10.3390/a17120556

Abstract

With the increasing availability of wearable devices for data collection, studies in human activity recognition have gained significant popularity. These studies report high accuracies on k-fold cross validation, which is not reflective of their generalization performance but is a result of the inap...

Full description

Published in: Algorithms
ISSN: 1999-4893
Published: MDPI AG 2024
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa68579
Abstract: With the increasing availability of wearable devices for data collection, studies in human activity recognition have gained significant popularity. These studies report high accuracies on k-fold cross validation, which is not reflective of their generalization performance but is a result of the inappropriate split of testing and training datasets, causing these models to evaluate the same subjects that they were trained on, making them subject-dependent. This study comparatively discusses this validation approach with a universal approach, Leave-One-Subject-Out (LOSO) cross-validation which is not subject-dependent and ensures that an entirely new subject is used for evaluation in each fold, validated on four different machine learning models trained on windowed data and select hand-crafted features. The random forest model, with the highest accuracy of 76% when evaluated on LOSO, achieved an accuracy of 89% on k-fold cross-validation, demonstrating data leakage. Additionally, this experiment underscores the significance of hand-crafted features by contrasting their accuracy with that of raw sensor models. The feature models demonstrate a remarkable 30% higher accuracy, underscoring the importance of feature engineering in enhancing the robustness and precision of HAR systems.
Keywords: Machine learning; LOSO; human activity recognition
College: Faculty of Science and Engineering
Funders: This research received no external funding.
Issue: 12
Start Page: 556