A Hierarchical Approach to Activity Recognition and Fall Detection Using Wavelets and Adaptive Pooling
Human activity recognition has been a key study topic in the development of cyber physical systems and assisted living applications. In particular, inertial sensor based systems have become increasingly popular because they do not restrict users’ movement and are also relatively simple to implement...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/19/6653 |
| _version_ | 1797515685225562112 |
|---|---|
| author | Abbas Shah Syed Daniel Sierra-Sosa Anup Kumar Adel Elmaghraby |
| author_facet | Abbas Shah Syed Daniel Sierra-Sosa Anup Kumar Adel Elmaghraby |
| author_sort | Abbas Shah Syed |
| collection | DOAJ |
| description | Human activity recognition has been a key study topic in the development of cyber physical systems and assisted living applications. In particular, inertial sensor based systems have become increasingly popular because they do not restrict users’ movement and are also relatively simple to implement compared to other approaches. In this paper, we present a hierarchical classification framework based on wavelets and adaptive pooling for activity recognition and fall detection predicting fall direction and severity. To accomplish this, windowed segments were extracted from each recording of inertial measurements from the SisFall dataset. A combination of wavelet based feature extraction and adaptive pooling was used before a classification framework was applied to determine the output class. Furthermore, tests were performed to determine the best observation window size and the sensor modality to use. Based on the experiments the best window size was found to be 3 s and the best sensor modality was found to be a combination of accelerometer and gyroscope measurements. These were used to perform activity recognition and fall detection with a resulting weighted F1 score of 94.67%. This framework is novel in terms of the approach to the human activity recognition and fall detection problem as it provides a scheme that is computationally less intensive while providing promising results and therefore can contribute to edge deployment of such systems. |
| first_indexed | 2024-03-10T06:50:46Z |
| format | Article |
| id | doaj.art-0cb0e212ecee4f16add2004446785026 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T06:50:46Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-0cb0e212ecee4f16add20044467850262023-11-22T16:49:22ZengMDPI AGSensors1424-82202021-10-012119665310.3390/s21196653A Hierarchical Approach to Activity Recognition and Fall Detection Using Wavelets and Adaptive PoolingAbbas Shah Syed0Daniel Sierra-Sosa1Anup Kumar2Adel Elmaghraby3Department of Computer Science and Engineering, University of Louisville, Louisville, KY 40208, USADepartment of Computer Science and Information Technology, Hood College, Frederick, MD 21701, USADepartment of Computer Science and Engineering, University of Louisville, Louisville, KY 40208, USADepartment of Computer Science and Engineering, University of Louisville, Louisville, KY 40208, USAHuman activity recognition has been a key study topic in the development of cyber physical systems and assisted living applications. In particular, inertial sensor based systems have become increasingly popular because they do not restrict users’ movement and are also relatively simple to implement compared to other approaches. In this paper, we present a hierarchical classification framework based on wavelets and adaptive pooling for activity recognition and fall detection predicting fall direction and severity. To accomplish this, windowed segments were extracted from each recording of inertial measurements from the SisFall dataset. A combination of wavelet based feature extraction and adaptive pooling was used before a classification framework was applied to determine the output class. Furthermore, tests were performed to determine the best observation window size and the sensor modality to use. Based on the experiments the best window size was found to be 3 s and the best sensor modality was found to be a combination of accelerometer and gyroscope measurements. These were used to perform activity recognition and fall detection with a resulting weighted F1 score of 94.67%. This framework is novel in terms of the approach to the human activity recognition and fall detection problem as it provides a scheme that is computationally less intensive while providing promising results and therefore can contribute to edge deployment of such systems.https://www.mdpi.com/1424-8220/21/19/6653smart healthInternet of Things (IoT)artificial intelligenceactivity recognitioncyber physical systemsfall detection |
| spellingShingle | Abbas Shah Syed Daniel Sierra-Sosa Anup Kumar Adel Elmaghraby A Hierarchical Approach to Activity Recognition and Fall Detection Using Wavelets and Adaptive Pooling Sensors smart health Internet of Things (IoT) artificial intelligence activity recognition cyber physical systems fall detection |
| title | A Hierarchical Approach to Activity Recognition and Fall Detection Using Wavelets and Adaptive Pooling |
| title_full | A Hierarchical Approach to Activity Recognition and Fall Detection Using Wavelets and Adaptive Pooling |
| title_fullStr | A Hierarchical Approach to Activity Recognition and Fall Detection Using Wavelets and Adaptive Pooling |
| title_full_unstemmed | A Hierarchical Approach to Activity Recognition and Fall Detection Using Wavelets and Adaptive Pooling |
| title_short | A Hierarchical Approach to Activity Recognition and Fall Detection Using Wavelets and Adaptive Pooling |
| title_sort | hierarchical approach to activity recognition and fall detection using wavelets and adaptive pooling |
| topic | smart health Internet of Things (IoT) artificial intelligence activity recognition cyber physical systems fall detection |
| url | https://www.mdpi.com/1424-8220/21/19/6653 |
| work_keys_str_mv | AT abbasshahsyed ahierarchicalapproachtoactivityrecognitionandfalldetectionusingwaveletsandadaptivepooling AT danielsierrasosa ahierarchicalapproachtoactivityrecognitionandfalldetectionusingwaveletsandadaptivepooling AT anupkumar ahierarchicalapproachtoactivityrecognitionandfalldetectionusingwaveletsandadaptivepooling AT adelelmaghraby ahierarchicalapproachtoactivityrecognitionandfalldetectionusingwaveletsandadaptivepooling AT abbasshahsyed hierarchicalapproachtoactivityrecognitionandfalldetectionusingwaveletsandadaptivepooling AT danielsierrasosa hierarchicalapproachtoactivityrecognitionandfalldetectionusingwaveletsandadaptivepooling AT anupkumar hierarchicalapproachtoactivityrecognitionandfalldetectionusingwaveletsandadaptivepooling AT adelelmaghraby hierarchicalapproachtoactivityrecognitionandfalldetectionusingwaveletsandadaptivepooling |