Cargando…
Explaining One-Dimensional Convolutional Models in Human Activity Recognition and Biometric Identification Tasks
Due to wearables’ popularity, human activity recognition (HAR) plays a significant role in people’s routines. Many deep learning (DL) approaches have studied HAR to classify human activities. Previous studies employ two HAR validation approaches: subject-dependent (SD) and subject-independent (SI)....
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9371158/ https://www.ncbi.nlm.nih.gov/pubmed/35957201 http://dx.doi.org/10.3390/s22155644 |
_version_ | 1784767051056807936 |
---|---|
author | Aquino, Gustavo Costa, Marly G. F. Costa Filho, Cicero F. F. |
author_facet | Aquino, Gustavo Costa, Marly G. F. Costa Filho, Cicero F. F. |
author_sort | Aquino, Gustavo |
collection | PubMed |
description | Due to wearables’ popularity, human activity recognition (HAR) plays a significant role in people’s routines. Many deep learning (DL) approaches have studied HAR to classify human activities. Previous studies employ two HAR validation approaches: subject-dependent (SD) and subject-independent (SI). Using accelerometer data, this paper shows how to generate visual explanations about the trained models’ decision making on both HAR and biometric user identification (BUI) tasks and the correlation between them. We adapted gradient-weighted class activation mapping (grad-CAM) to one-dimensional convolutional neural networks (CNN) architectures to produce visual explanations of HAR and BUI models. Our proposed networks achieved 0.978 and 0.755 accuracy, employing both SD and SI. The proposed BUI network achieved 0.937 average accuracy. We demonstrate that HAR’s high performance with SD comes not only from physical activity learning but also from learning an individual’s signature, as in BUI models. Our experiments show that CNN focuses on larger signal sections in BUI, while HAR focuses on smaller signal segments. We also use the grad-CAM technique to identify database bias problems, such as signal discontinuities. Combining explainable techniques with deep learning can help models design, avoid results overestimation, find bias problems, and improve generalization capability. |
format | Online Article Text |
id | pubmed-9371158 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-93711582022-08-12 Explaining One-Dimensional Convolutional Models in Human Activity Recognition and Biometric Identification Tasks Aquino, Gustavo Costa, Marly G. F. Costa Filho, Cicero F. F. Sensors (Basel) Article Due to wearables’ popularity, human activity recognition (HAR) plays a significant role in people’s routines. Many deep learning (DL) approaches have studied HAR to classify human activities. Previous studies employ two HAR validation approaches: subject-dependent (SD) and subject-independent (SI). Using accelerometer data, this paper shows how to generate visual explanations about the trained models’ decision making on both HAR and biometric user identification (BUI) tasks and the correlation between them. We adapted gradient-weighted class activation mapping (grad-CAM) to one-dimensional convolutional neural networks (CNN) architectures to produce visual explanations of HAR and BUI models. Our proposed networks achieved 0.978 and 0.755 accuracy, employing both SD and SI. The proposed BUI network achieved 0.937 average accuracy. We demonstrate that HAR’s high performance with SD comes not only from physical activity learning but also from learning an individual’s signature, as in BUI models. Our experiments show that CNN focuses on larger signal sections in BUI, while HAR focuses on smaller signal segments. We also use the grad-CAM technique to identify database bias problems, such as signal discontinuities. Combining explainable techniques with deep learning can help models design, avoid results overestimation, find bias problems, and improve generalization capability. MDPI 2022-07-28 /pmc/articles/PMC9371158/ /pubmed/35957201 http://dx.doi.org/10.3390/s22155644 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Aquino, Gustavo Costa, Marly G. F. Costa Filho, Cicero F. F. Explaining One-Dimensional Convolutional Models in Human Activity Recognition and Biometric Identification Tasks |
title | Explaining One-Dimensional Convolutional Models in Human Activity Recognition and Biometric Identification Tasks |
title_full | Explaining One-Dimensional Convolutional Models in Human Activity Recognition and Biometric Identification Tasks |
title_fullStr | Explaining One-Dimensional Convolutional Models in Human Activity Recognition and Biometric Identification Tasks |
title_full_unstemmed | Explaining One-Dimensional Convolutional Models in Human Activity Recognition and Biometric Identification Tasks |
title_short | Explaining One-Dimensional Convolutional Models in Human Activity Recognition and Biometric Identification Tasks |
title_sort | explaining one-dimensional convolutional models in human activity recognition and biometric identification tasks |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9371158/ https://www.ncbi.nlm.nih.gov/pubmed/35957201 http://dx.doi.org/10.3390/s22155644 |
work_keys_str_mv | AT aquinogustavo explainingonedimensionalconvolutionalmodelsinhumanactivityrecognitionandbiometricidentificationtasks AT costamarlygf explainingonedimensionalconvolutionalmodelsinhumanactivityrecognitionandbiometricidentificationtasks AT costafilhociceroff explainingonedimensionalconvolutionalmodelsinhumanactivityrecognitionandbiometricidentificationtasks |