A Deep Learning Network with Aggregation Residual Transformation for Human Activity Recognition Using Inertial and Stretch Sensors
With the rise of artificial intelligence, sensor-based human activity recognition (S-HAR) is increasingly being employed in healthcare monitoring for the elderly, fitness tracking, and patient rehabilitation using smart devices. Inertial sensors have been commonly used for S-HAR, but wearable device...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Computers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-431X/12/7/141 |
| _version_ | 1797589702955499520 |
|---|---|
| author | Sakorn Mekruksavanich Anuchit Jitpattanakul |
| author_facet | Sakorn Mekruksavanich Anuchit Jitpattanakul |
| author_sort | Sakorn Mekruksavanich |
| collection | DOAJ |
| description | With the rise of artificial intelligence, sensor-based human activity recognition (S-HAR) is increasingly being employed in healthcare monitoring for the elderly, fitness tracking, and patient rehabilitation using smart devices. Inertial sensors have been commonly used for S-HAR, but wearable devices have been demanding more comfort and flexibility in recent years. Consequently, there has been an effort to incorporate stretch sensors into S-HAR with the advancement of flexible electronics technology. This paper presents a deep learning network model, utilizing aggregation residual transformation, that can efficiently extract spatial–temporal features and perform activity classification. The efficacy of the suggested model was assessed using the w-HAR dataset, which included both inertial and stretch sensor data. This dataset was used to train and test five fundamental deep learning models (CNN, LSTM, BiLSTM, GRU, and BiGRU), along with the proposed model. The primary objective of the w-HAR investigations was to determine the feasibility of utilizing stretch sensors for recognizing human actions. Additionally, this study aimed to explore the effectiveness of combining data from both inertial and stretch sensors in S-HAR. The results clearly demonstrate the effectiveness of the proposed approach in enhancing HAR using inertial and stretch sensors. The deep learning model we presented achieved an impressive accuracy of 97.68%. Notably, our method outperformed existing approaches and demonstrated excellent generalization capabilities. |
| first_indexed | 2024-03-11T01:10:19Z |
| format | Article |
| id | doaj.art-03a5a9559f1649f98dce8c1bc7816539 |
| institution | Directory Open Access Journal |
| issn | 2073-431X |
| language | English |
| last_indexed | 2024-03-11T01:10:19Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computers |
| spelling | doaj.art-03a5a9559f1649f98dce8c1bc78165392023-11-18T18:52:33ZengMDPI AGComputers2073-431X2023-07-0112714110.3390/computers12070141A Deep Learning Network with Aggregation Residual Transformation for Human Activity Recognition Using Inertial and Stretch SensorsSakorn Mekruksavanich0Anuchit Jitpattanakul1Department of Computer Engineering, School of Information and Communication Technology, University of Phayao, Phayao 56000, ThailandDepartment of Mathematics, Faculty of Applied Science, King Mongkut’s University of Technology North Bangkok, Bangkok 10800, ThailandWith the rise of artificial intelligence, sensor-based human activity recognition (S-HAR) is increasingly being employed in healthcare monitoring for the elderly, fitness tracking, and patient rehabilitation using smart devices. Inertial sensors have been commonly used for S-HAR, but wearable devices have been demanding more comfort and flexibility in recent years. Consequently, there has been an effort to incorporate stretch sensors into S-HAR with the advancement of flexible electronics technology. This paper presents a deep learning network model, utilizing aggregation residual transformation, that can efficiently extract spatial–temporal features and perform activity classification. The efficacy of the suggested model was assessed using the w-HAR dataset, which included both inertial and stretch sensor data. This dataset was used to train and test five fundamental deep learning models (CNN, LSTM, BiLSTM, GRU, and BiGRU), along with the proposed model. The primary objective of the w-HAR investigations was to determine the feasibility of utilizing stretch sensors for recognizing human actions. Additionally, this study aimed to explore the effectiveness of combining data from both inertial and stretch sensors in S-HAR. The results clearly demonstrate the effectiveness of the proposed approach in enhancing HAR using inertial and stretch sensors. The deep learning model we presented achieved an impressive accuracy of 97.68%. Notably, our method outperformed existing approaches and demonstrated excellent generalization capabilities.https://www.mdpi.com/2073-431X/12/7/141human activity recognitioninertial sensorstretch sensorlow-power wearable devicedeep residual learning network |
| spellingShingle | Sakorn Mekruksavanich Anuchit Jitpattanakul A Deep Learning Network with Aggregation Residual Transformation for Human Activity Recognition Using Inertial and Stretch Sensors Computers human activity recognition inertial sensor stretch sensor low-power wearable device deep residual learning network |
| title | A Deep Learning Network with Aggregation Residual Transformation for Human Activity Recognition Using Inertial and Stretch Sensors |
| title_full | A Deep Learning Network with Aggregation Residual Transformation for Human Activity Recognition Using Inertial and Stretch Sensors |
| title_fullStr | A Deep Learning Network with Aggregation Residual Transformation for Human Activity Recognition Using Inertial and Stretch Sensors |
| title_full_unstemmed | A Deep Learning Network with Aggregation Residual Transformation for Human Activity Recognition Using Inertial and Stretch Sensors |
| title_short | A Deep Learning Network with Aggregation Residual Transformation for Human Activity Recognition Using Inertial and Stretch Sensors |
| title_sort | deep learning network with aggregation residual transformation for human activity recognition using inertial and stretch sensors |
| topic | human activity recognition inertial sensor stretch sensor low-power wearable device deep residual learning network |
| url | https://www.mdpi.com/2073-431X/12/7/141 |
| work_keys_str_mv | AT sakornmekruksavanich adeeplearningnetworkwithaggregationresidualtransformationforhumanactivityrecognitionusinginertialandstretchsensors AT anuchitjitpattanakul adeeplearningnetworkwithaggregationresidualtransformationforhumanactivityrecognitionusinginertialandstretchsensors AT sakornmekruksavanich deeplearningnetworkwithaggregationresidualtransformationforhumanactivityrecognitionusinginertialandstretchsensors AT anuchitjitpattanakul deeplearningnetworkwithaggregationresidualtransformationforhumanactivityrecognitionusinginertialandstretchsensors |