A CSI-Based Multi-Environment Human Activity Recognition Framework
Passive human activity recognition (HAR) systems, in which no sensors are attached to the subject, provide great potentials compared to conventional systems. One of the recently used techniques showing tremendous potential is channel state information (CSI)-based HAR systems. In this work, we presen...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/2/930 |
| _version_ | 1797495933571694592 |
|---|---|
| author | Baha A. Alsaify Mahmoud M. Almazari Rami Alazrai Sahel Alouneh Mohammad I. Daoud |
| author_facet | Baha A. Alsaify Mahmoud M. Almazari Rami Alazrai Sahel Alouneh Mohammad I. Daoud |
| author_sort | Baha A. Alsaify |
| collection | DOAJ |
| description | Passive human activity recognition (HAR) systems, in which no sensors are attached to the subject, provide great potentials compared to conventional systems. One of the recently used techniques showing tremendous potential is channel state information (CSI)-based HAR systems. In this work, we present a multi-environment human activity recognition system based on observing the changes in the CSI values of the exchanged wireless packets carried by OFDM subcarriers. In essence, we introduce a five-stage CSI-based human activity recognition approach. First, the acquired CSI values associated with each recorded activity instance are processed to remove the existing noise from the recorded data. A novel segmentation algorithm is then presented to identify and extract the portion of the signal that contains the activity. Next, the extracted activity segment is processed using the procedure proposed in the first stage. After that, the relevant features are extracted, and the important features are selected. Finally, the selected features are used to train a support vector machine (SVM) classifier to identify the different performed activities. To validate the performance of the proposed approach, we collected data in two different environments. In each of the environments, several activities were performed by multiple subjects. The performed experiments showed that our proposed approach achieved an average activity recognition accuracy of 91.27%. |
| first_indexed | 2024-03-10T01:56:36Z |
| format | Article |
| id | doaj.art-21dcf3b6a1264bef87f96e08d7fed91a |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T01:56:36Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-21dcf3b6a1264bef87f96e08d7fed91a2023-11-23T12:55:21ZengMDPI AGApplied Sciences2076-34172022-01-0112293010.3390/app12020930A CSI-Based Multi-Environment Human Activity Recognition FrameworkBaha A. Alsaify0Mahmoud M. Almazari1Rami Alazrai2Sahel Alouneh3Mohammad I. Daoud4Network Engineering and Security Department, Jordan University of Science and Technology, Irbid 22110, JordanNetwork Engineering and Security Department, Jordan University of Science and Technology, Irbid 22110, JordanComputer Engineering Department, German Jordanian University, Amman 11180, JordanComputer Engineering Department, German Jordanian University, Amman 11180, JordanComputer Engineering Department, German Jordanian University, Amman 11180, JordanPassive human activity recognition (HAR) systems, in which no sensors are attached to the subject, provide great potentials compared to conventional systems. One of the recently used techniques showing tremendous potential is channel state information (CSI)-based HAR systems. In this work, we present a multi-environment human activity recognition system based on observing the changes in the CSI values of the exchanged wireless packets carried by OFDM subcarriers. In essence, we introduce a five-stage CSI-based human activity recognition approach. First, the acquired CSI values associated with each recorded activity instance are processed to remove the existing noise from the recorded data. A novel segmentation algorithm is then presented to identify and extract the portion of the signal that contains the activity. Next, the extracted activity segment is processed using the procedure proposed in the first stage. After that, the relevant features are extracted, and the important features are selected. Finally, the selected features are used to train a support vector machine (SVM) classifier to identify the different performed activities. To validate the performance of the proposed approach, we collected data in two different environments. In each of the environments, several activities were performed by multiple subjects. The performed experiments showed that our proposed approach achieved an average activity recognition accuracy of 91.27%.https://www.mdpi.com/2076-3417/12/2/930channel state information (CSI)human activity recognition (HAR)multi-environmentsupport vector machine (SVM) |
| spellingShingle | Baha A. Alsaify Mahmoud M. Almazari Rami Alazrai Sahel Alouneh Mohammad I. Daoud A CSI-Based Multi-Environment Human Activity Recognition Framework Applied Sciences channel state information (CSI) human activity recognition (HAR) multi-environment support vector machine (SVM) |
| title | A CSI-Based Multi-Environment Human Activity Recognition Framework |
| title_full | A CSI-Based Multi-Environment Human Activity Recognition Framework |
| title_fullStr | A CSI-Based Multi-Environment Human Activity Recognition Framework |
| title_full_unstemmed | A CSI-Based Multi-Environment Human Activity Recognition Framework |
| title_short | A CSI-Based Multi-Environment Human Activity Recognition Framework |
| title_sort | csi based multi environment human activity recognition framework |
| topic | channel state information (CSI) human activity recognition (HAR) multi-environment support vector machine (SVM) |
| url | https://www.mdpi.com/2076-3417/12/2/930 |
| work_keys_str_mv | AT bahaaalsaify acsibasedmultienvironmenthumanactivityrecognitionframework AT mahmoudmalmazari acsibasedmultienvironmenthumanactivityrecognitionframework AT ramialazrai acsibasedmultienvironmenthumanactivityrecognitionframework AT sahelalouneh acsibasedmultienvironmenthumanactivityrecognitionframework AT mohammadidaoud acsibasedmultienvironmenthumanactivityrecognitionframework AT bahaaalsaify csibasedmultienvironmenthumanactivityrecognitionframework AT mahmoudmalmazari csibasedmultienvironmenthumanactivityrecognitionframework AT ramialazrai csibasedmultienvironmenthumanactivityrecognitionframework AT sahelalouneh csibasedmultienvironmenthumanactivityrecognitionframework AT mohammadidaoud csibasedmultienvironmenthumanactivityrecognitionframework |