Cargando…
Wearable Sensor-Based Human Activity Recognition with Transformer Model
Computing devices that can recognize various human activities or movements can be used to assist people in healthcare, sports, or human–robot interaction. Readily available data for this purpose can be obtained from the accelerometer and the gyroscope built into everyday smartphones. Effective class...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8914677/ https://www.ncbi.nlm.nih.gov/pubmed/35271058 http://dx.doi.org/10.3390/s22051911 |
_version_ | 1784667780129226752 |
---|---|
author | Dirgová Luptáková, Iveta Kubovčík, Martin Pospíchal, Jiří |
author_facet | Dirgová Luptáková, Iveta Kubovčík, Martin Pospíchal, Jiří |
author_sort | Dirgová Luptáková, Iveta |
collection | PubMed |
description | Computing devices that can recognize various human activities or movements can be used to assist people in healthcare, sports, or human–robot interaction. Readily available data for this purpose can be obtained from the accelerometer and the gyroscope built into everyday smartphones. Effective classification of real-time activity data is, therefore, actively pursued using various machine learning methods. In this study, the transformer model, a deep learning neural network model developed primarily for the natural language processing and vision tasks, was adapted for a time-series analysis of motion signals. The self-attention mechanism inherent in the transformer, which expresses individual dependencies between signal values within a time series, can match the performance of state-of-the-art convolutional neural networks with long short-term memory. The performance of the proposed adapted transformer method was tested on the largest available public dataset of smartphone motion sensor data covering a wide range of activities, and obtained an average identification accuracy of 99.2% as compared with 89.67% achieved on the same data by a conventional machine learning method. The results suggest the expected future relevance of the transformer model for human activity recognition. |
format | Online Article Text |
id | pubmed-8914677 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-89146772022-03-12 Wearable Sensor-Based Human Activity Recognition with Transformer Model Dirgová Luptáková, Iveta Kubovčík, Martin Pospíchal, Jiří Sensors (Basel) Article Computing devices that can recognize various human activities or movements can be used to assist people in healthcare, sports, or human–robot interaction. Readily available data for this purpose can be obtained from the accelerometer and the gyroscope built into everyday smartphones. Effective classification of real-time activity data is, therefore, actively pursued using various machine learning methods. In this study, the transformer model, a deep learning neural network model developed primarily for the natural language processing and vision tasks, was adapted for a time-series analysis of motion signals. The self-attention mechanism inherent in the transformer, which expresses individual dependencies between signal values within a time series, can match the performance of state-of-the-art convolutional neural networks with long short-term memory. The performance of the proposed adapted transformer method was tested on the largest available public dataset of smartphone motion sensor data covering a wide range of activities, and obtained an average identification accuracy of 99.2% as compared with 89.67% achieved on the same data by a conventional machine learning method. The results suggest the expected future relevance of the transformer model for human activity recognition. MDPI 2022-03-01 /pmc/articles/PMC8914677/ /pubmed/35271058 http://dx.doi.org/10.3390/s22051911 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 Dirgová Luptáková, Iveta Kubovčík, Martin Pospíchal, Jiří Wearable Sensor-Based Human Activity Recognition with Transformer Model |
title | Wearable Sensor-Based Human Activity Recognition with Transformer Model |
title_full | Wearable Sensor-Based Human Activity Recognition with Transformer Model |
title_fullStr | Wearable Sensor-Based Human Activity Recognition with Transformer Model |
title_full_unstemmed | Wearable Sensor-Based Human Activity Recognition with Transformer Model |
title_short | Wearable Sensor-Based Human Activity Recognition with Transformer Model |
title_sort | wearable sensor-based human activity recognition with transformer model |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8914677/ https://www.ncbi.nlm.nih.gov/pubmed/35271058 http://dx.doi.org/10.3390/s22051911 |
work_keys_str_mv | AT dirgovaluptakovaiveta wearablesensorbasedhumanactivityrecognitionwithtransformermodel AT kubovcikmartin wearablesensorbasedhumanactivityrecognitionwithtransformermodel AT pospichaljiri wearablesensorbasedhumanactivityrecognitionwithtransformermodel |