FMCW Radar-Based Human Sitting Posture Detection
Sitting posture is closely related to our health. Poor sitting posture can cause various diseases and harm our physical health. Current methods to detect sitting posture include machine vision, wearable sensors, and pressure sensors. However, these methods have problems with respect to privacy, inco...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10239400/ |
| _version_ | 1797672257295745024 |
|---|---|
| author | Guoxiang Liu Xingguang Li Chunsheng Xu Lei Ma Hongye Li |
| author_facet | Guoxiang Liu Xingguang Li Chunsheng Xu Lei Ma Hongye Li |
| author_sort | Guoxiang Liu |
| collection | DOAJ |
| description | Sitting posture is closely related to our health. Poor sitting posture can cause various diseases and harm our physical health. Current methods to detect sitting posture include machine vision, wearable sensors, and pressure sensors. However, these methods have problems with respect to privacy, inconvenience, and cost. In this work, we proposed the use of frequency-modulated continuous wave radar (FMCW) for detecting human sitting posture, which employs wireless signal transmission to enable non-contact detection, protect privacy, and reduce costs. First, the range fast Fourier transform (FFT) and Doppler FFT of the radar’s intermediate frequency (IF) signals are performed to obtain range and Doppler feature information for different sitting postures. Second, to overcome the problem of range FFT bin offset, a single target angle measurement method is proposed to obtain angle features. Subsequently, we constructed various combinations of features to explore the influence of different combinations of features on the detection of posture while sitting. And we used five machine learning algorithms to perform sitting posture detection experiments. Finally, we conducted sedentary experiments in an office setting and provided sitting history records. The experimental results demonstrate that the method we proposed can identify five distinct sitting postures with an average accuracy of 98.07%. |
| first_indexed | 2024-03-11T21:27:25Z |
| format | Article |
| id | doaj.art-fb93c342f33545739afdcabdb6b4dff5 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-11T21:27:25Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-fb93c342f33545739afdcabdb6b4dff52023-09-27T23:00:21ZengIEEEIEEE Access2169-35362023-01-011110274610275610.1109/ACCESS.2023.331232810239400FMCW Radar-Based Human Sitting Posture DetectionGuoxiang Liu0Xingguang Li1https://orcid.org/0000-0002-5964-8843Chunsheng Xu2Lei Ma3https://orcid.org/0009-0000-5729-1484Hongye Li4Changchun University of Science and Technology, Jilin, Changchun, ChinaChangchun University of Science and Technology, Jilin, Changchun, ChinaChangchun University of Science and Technology, Jilin, Changchun, ChinaChangchun University of Science and Technology, Jilin, Changchun, ChinaChangchun University of Science and Technology, Jilin, Changchun, ChinaSitting posture is closely related to our health. Poor sitting posture can cause various diseases and harm our physical health. Current methods to detect sitting posture include machine vision, wearable sensors, and pressure sensors. However, these methods have problems with respect to privacy, inconvenience, and cost. In this work, we proposed the use of frequency-modulated continuous wave radar (FMCW) for detecting human sitting posture, which employs wireless signal transmission to enable non-contact detection, protect privacy, and reduce costs. First, the range fast Fourier transform (FFT) and Doppler FFT of the radar’s intermediate frequency (IF) signals are performed to obtain range and Doppler feature information for different sitting postures. Second, to overcome the problem of range FFT bin offset, a single target angle measurement method is proposed to obtain angle features. Subsequently, we constructed various combinations of features to explore the influence of different combinations of features on the detection of posture while sitting. And we used five machine learning algorithms to perform sitting posture detection experiments. Finally, we conducted sedentary experiments in an office setting and provided sitting history records. The experimental results demonstrate that the method we proposed can identify five distinct sitting postures with an average accuracy of 98.07%.https://ieeexplore.ieee.org/document/10239400/Frequency modulated continuous wave radarsitting posture detectionmachine learning |
| spellingShingle | Guoxiang Liu Xingguang Li Chunsheng Xu Lei Ma Hongye Li FMCW Radar-Based Human Sitting Posture Detection IEEE Access Frequency modulated continuous wave radar sitting posture detection machine learning |
| title | FMCW Radar-Based Human Sitting Posture Detection |
| title_full | FMCW Radar-Based Human Sitting Posture Detection |
| title_fullStr | FMCW Radar-Based Human Sitting Posture Detection |
| title_full_unstemmed | FMCW Radar-Based Human Sitting Posture Detection |
| title_short | FMCW Radar-Based Human Sitting Posture Detection |
| title_sort | fmcw radar based human sitting posture detection |
| topic | Frequency modulated continuous wave radar sitting posture detection machine learning |
| url | https://ieeexplore.ieee.org/document/10239400/ |
| work_keys_str_mv | AT guoxiangliu fmcwradarbasedhumansittingposturedetection AT xingguangli fmcwradarbasedhumansittingposturedetection AT chunshengxu fmcwradarbasedhumansittingposturedetection AT leima fmcwradarbasedhumansittingposturedetection AT hongyeli fmcwradarbasedhumansittingposturedetection |