A Deep Learning Method of Human Identification from Radar Signal for Daily Sleep Health Monitoring
Radar signal has been shown as a promising source for human identification. In daily home sleep-monitoring scenarios, large-scale motion features may not always be practical, and the heart motion or respiration data may not be as ideal as they are in a controlled laboratory setting. Human identifica...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/11/1/2 |
| _version_ | 1827372764071198720 |
|---|---|
| author | Ken Chen Yulong Duan Yi Huang Wei Hu Yaoqin Xie |
| author_facet | Ken Chen Yulong Duan Yi Huang Wei Hu Yaoqin Xie |
| author_sort | Ken Chen |
| collection | DOAJ |
| description | Radar signal has been shown as a promising source for human identification. In daily home sleep-monitoring scenarios, large-scale motion features may not always be practical, and the heart motion or respiration data may not be as ideal as they are in a controlled laboratory setting. Human identification from radar sequences is still a challenging task. Furthermore, there is a need to address the open-set recognition problem for radar sequences, which has not been sufficiently studied. In this paper, we propose a deep learning-based approach for human identification using radar sequences captured during sleep in a daily home-monitoring setup. To enhance robustness, we preprocess the sequences to mitigate environmental interference before employing a deep convolution neural network for human identification. We introduce a Principal Component Space feature representation to detect unknown sequences. Our method is rigorously evaluated using both a public data set and a set of experimentally acquired radar sequences. We report a labeling accuracy of 98.2% and 96.8% on average for the two data sets, respectively, which outperforms the state-of-the-art techniques. Our method excels at accurately distinguishing unknown sequences from labeled ones, with nearly 100% detection of unknown samples and minimal misclassification of labeled samples as unknown. |
| first_indexed | 2024-03-08T11:05:48Z |
| format | Article |
| id | doaj.art-dd521a4ad961449fb15afdbf68ad4a2c |
| institution | Directory Open Access Journal |
| issn | 2306-5354 |
| language | English |
| last_indexed | 2024-03-08T11:05:48Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj.art-dd521a4ad961449fb15afdbf68ad4a2c2024-01-26T15:06:03ZengMDPI AGBioengineering2306-53542023-12-01111210.3390/bioengineering11010002A Deep Learning Method of Human Identification from Radar Signal for Daily Sleep Health MonitoringKen Chen0Yulong Duan1Yi Huang2Wei Hu3Yaoqin Xie4Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, ChinaShenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, ChinaShenzhen HUAYI Medical Technologies Co., Ltd., Shenzhen 518055, ChinaShenzhen HUAYI Medical Technologies Co., Ltd., Shenzhen 518055, ChinaShenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, ChinaRadar signal has been shown as a promising source for human identification. In daily home sleep-monitoring scenarios, large-scale motion features may not always be practical, and the heart motion or respiration data may not be as ideal as they are in a controlled laboratory setting. Human identification from radar sequences is still a challenging task. Furthermore, there is a need to address the open-set recognition problem for radar sequences, which has not been sufficiently studied. In this paper, we propose a deep learning-based approach for human identification using radar sequences captured during sleep in a daily home-monitoring setup. To enhance robustness, we preprocess the sequences to mitigate environmental interference before employing a deep convolution neural network for human identification. We introduce a Principal Component Space feature representation to detect unknown sequences. Our method is rigorously evaluated using both a public data set and a set of experimentally acquired radar sequences. We report a labeling accuracy of 98.2% and 96.8% on average for the two data sets, respectively, which outperforms the state-of-the-art techniques. Our method excels at accurately distinguishing unknown sequences from labeled ones, with nearly 100% detection of unknown samples and minimal misclassification of labeled samples as unknown.https://www.mdpi.com/2306-5354/11/1/2human identificationmillimeter wave radardeep learning |
| spellingShingle | Ken Chen Yulong Duan Yi Huang Wei Hu Yaoqin Xie A Deep Learning Method of Human Identification from Radar Signal for Daily Sleep Health Monitoring Bioengineering human identification millimeter wave radar deep learning |
| title | A Deep Learning Method of Human Identification from Radar Signal for Daily Sleep Health Monitoring |
| title_full | A Deep Learning Method of Human Identification from Radar Signal for Daily Sleep Health Monitoring |
| title_fullStr | A Deep Learning Method of Human Identification from Radar Signal for Daily Sleep Health Monitoring |
| title_full_unstemmed | A Deep Learning Method of Human Identification from Radar Signal for Daily Sleep Health Monitoring |
| title_short | A Deep Learning Method of Human Identification from Radar Signal for Daily Sleep Health Monitoring |
| title_sort | deep learning method of human identification from radar signal for daily sleep health monitoring |
| topic | human identification millimeter wave radar deep learning |
| url | https://www.mdpi.com/2306-5354/11/1/2 |
| work_keys_str_mv | AT kenchen adeeplearningmethodofhumanidentificationfromradarsignalfordailysleephealthmonitoring AT yulongduan adeeplearningmethodofhumanidentificationfromradarsignalfordailysleephealthmonitoring AT yihuang adeeplearningmethodofhumanidentificationfromradarsignalfordailysleephealthmonitoring AT weihu adeeplearningmethodofhumanidentificationfromradarsignalfordailysleephealthmonitoring AT yaoqinxie adeeplearningmethodofhumanidentificationfromradarsignalfordailysleephealthmonitoring AT kenchen deeplearningmethodofhumanidentificationfromradarsignalfordailysleephealthmonitoring AT yulongduan deeplearningmethodofhumanidentificationfromradarsignalfordailysleephealthmonitoring AT yihuang deeplearningmethodofhumanidentificationfromradarsignalfordailysleephealthmonitoring AT weihu deeplearningmethodofhumanidentificationfromradarsignalfordailysleephealthmonitoring AT yaoqinxie deeplearningmethodofhumanidentificationfromradarsignalfordailysleephealthmonitoring |