Wrapper-based deep feature optimization for activity recognition in the wearable sensor networks of healthcare systems
Abstract The Human Activity Recognition (HAR) problem leverages pattern recognition to classify physical human activities as they are captured by several sensor modalities. Remote monitoring of an individual’s activities has gained importance due to the reduction in travel and physical activities du...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-27192-w |
| _version_ | 1797945934509768704 |
|---|---|
| author | Karam Kumar Sahoo Raghunath Ghosh Saurav Mallik Arup Roy Pawan Kumar Singh Zhongming Zhao |
| author_facet | Karam Kumar Sahoo Raghunath Ghosh Saurav Mallik Arup Roy Pawan Kumar Singh Zhongming Zhao |
| author_sort | Karam Kumar Sahoo |
| collection | DOAJ |
| description | Abstract The Human Activity Recognition (HAR) problem leverages pattern recognition to classify physical human activities as they are captured by several sensor modalities. Remote monitoring of an individual’s activities has gained importance due to the reduction in travel and physical activities during the pandemic. Research on HAR enables one person to either remotely monitor or recognize another person’s activity via the ubiquitous mobile device or by using sensor-based Internet of Things (IoT). Our proposed work focuses on the accurate classification of daily human activities from both accelerometer and gyroscope sensor data after converting into spectrogram images. The feature extraction process follows by leveraging the pre-trained weights of two popular and efficient transfer learning convolutional neural network models. Finally, a wrapper-based feature selection method has been employed for selecting the optimal feature subset that both reduces the training time and improves the final classification performance. The proposed HAR model has been tested on the three benchmark datasets namely, HARTH, KU-HAR and HuGaDB and has achieved 88.89%, 97.97% and 93.82% respectively on these datasets. It is to be noted that the proposed HAR model achieves an improvement of about 21%, 20% and 6% in the overall classification accuracies while utilizing only 52%, 45% and 60% of the original feature set for HuGaDB, KU-HAR and HARTH datasets respectively. This proves the effectiveness of our proposed wrapper-based feature selection HAR methodology. |
| first_indexed | 2024-04-10T21:04:00Z |
| format | Article |
| id | doaj.art-2cb706398f49425aae39f0bc30314745 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-10T21:04:00Z |
| publishDate | 2023-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-2cb706398f49425aae39f0bc303147452023-01-22T12:08:57ZengNature PortfolioScientific Reports2045-23222023-01-0113111810.1038/s41598-022-27192-wWrapper-based deep feature optimization for activity recognition in the wearable sensor networks of healthcare systemsKaram Kumar Sahoo0Raghunath Ghosh1Saurav Mallik2Arup Roy3Pawan Kumar Singh4Zhongming Zhao5Department of Computer Science and Engineering, National Institute of TechnologyDepartment of Information Technology, Jadavpur University, Jadavpur University Second CampusCenter for Precision Health, School of Biomedical Informatics, The University of Texas Health Science Center at HoustonDepartment of Computer Science and Engineering, Dr. B. C. Roy Engineering CollegeDepartment of Information Technology, Jadavpur University, Jadavpur University Second CampusCenter for Precision Health, School of Biomedical Informatics, The University of Texas Health Science Center at HoustonAbstract The Human Activity Recognition (HAR) problem leverages pattern recognition to classify physical human activities as they are captured by several sensor modalities. Remote monitoring of an individual’s activities has gained importance due to the reduction in travel and physical activities during the pandemic. Research on HAR enables one person to either remotely monitor or recognize another person’s activity via the ubiquitous mobile device or by using sensor-based Internet of Things (IoT). Our proposed work focuses on the accurate classification of daily human activities from both accelerometer and gyroscope sensor data after converting into spectrogram images. The feature extraction process follows by leveraging the pre-trained weights of two popular and efficient transfer learning convolutional neural network models. Finally, a wrapper-based feature selection method has been employed for selecting the optimal feature subset that both reduces the training time and improves the final classification performance. The proposed HAR model has been tested on the three benchmark datasets namely, HARTH, KU-HAR and HuGaDB and has achieved 88.89%, 97.97% and 93.82% respectively on these datasets. It is to be noted that the proposed HAR model achieves an improvement of about 21%, 20% and 6% in the overall classification accuracies while utilizing only 52%, 45% and 60% of the original feature set for HuGaDB, KU-HAR and HARTH datasets respectively. This proves the effectiveness of our proposed wrapper-based feature selection HAR methodology.https://doi.org/10.1038/s41598-022-27192-w |
| spellingShingle | Karam Kumar Sahoo Raghunath Ghosh Saurav Mallik Arup Roy Pawan Kumar Singh Zhongming Zhao Wrapper-based deep feature optimization for activity recognition in the wearable sensor networks of healthcare systems Scientific Reports |
| title | Wrapper-based deep feature optimization for activity recognition in the wearable sensor networks of healthcare systems |
| title_full | Wrapper-based deep feature optimization for activity recognition in the wearable sensor networks of healthcare systems |
| title_fullStr | Wrapper-based deep feature optimization for activity recognition in the wearable sensor networks of healthcare systems |
| title_full_unstemmed | Wrapper-based deep feature optimization for activity recognition in the wearable sensor networks of healthcare systems |
| title_short | Wrapper-based deep feature optimization for activity recognition in the wearable sensor networks of healthcare systems |
| title_sort | wrapper based deep feature optimization for activity recognition in the wearable sensor networks of healthcare systems |
| url | https://doi.org/10.1038/s41598-022-27192-w |
| work_keys_str_mv | AT karamkumarsahoo wrapperbaseddeepfeatureoptimizationforactivityrecognitioninthewearablesensornetworksofhealthcaresystems AT raghunathghosh wrapperbaseddeepfeatureoptimizationforactivityrecognitioninthewearablesensornetworksofhealthcaresystems AT sauravmallik wrapperbaseddeepfeatureoptimizationforactivityrecognitioninthewearablesensornetworksofhealthcaresystems AT aruproy wrapperbaseddeepfeatureoptimizationforactivityrecognitioninthewearablesensornetworksofhealthcaresystems AT pawankumarsingh wrapperbaseddeepfeatureoptimizationforactivityrecognitioninthewearablesensornetworksofhealthcaresystems AT zhongmingzhao wrapperbaseddeepfeatureoptimizationforactivityrecognitioninthewearablesensornetworksofhealthcaresystems |