Device-Free Human Identification Using Behavior Signatures in WiFi Sensing
Wireless sensing can be used for human identification by mining and quantifying individual behavior effects on wireless signal propagation. This work proposes a novel device-free biometric (DFB) system, WirelessID, that explores the joint human fine-grained behavior and body physical signatures embe...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/17/5921 |
| _version_ | 1797520791523295232 |
|---|---|
| author | Ronghui Zhang Xiaojun Jing |
| author_facet | Ronghui Zhang Xiaojun Jing |
| author_sort | Ronghui Zhang |
| collection | DOAJ |
| description | Wireless sensing can be used for human identification by mining and quantifying individual behavior effects on wireless signal propagation. This work proposes a novel device-free biometric (DFB) system, WirelessID, that explores the joint human fine-grained behavior and body physical signatures embedded in channel state information (CSI) by extracting spatiotemporal features. In addition, the signal fluctuations corresponding to different parts of the body contribute differently to the identification performance. Inspired by the success of the attention mechanism in computer vision (CV), thus, to extract more robust features, we introduce the spatiotemporal attention function into our system. To evaluate the performance, commercial WiFi devices are used for prototyping WirelessID in a real laboratory environment with an average accuracy of 93.14% and a best accuracy of 97.72% for five individuals. |
| first_indexed | 2024-03-10T08:03:37Z |
| format | Article |
| id | doaj.art-0caef1192bd346a8b35f42af2d1e29f5 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T08:03:37Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-0caef1192bd346a8b35f42af2d1e29f52023-11-22T11:14:30ZengMDPI AGSensors1424-82202021-09-012117592110.3390/s21175921Device-Free Human Identification Using Behavior Signatures in WiFi SensingRonghui Zhang0Xiaojun Jing1School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaWireless sensing can be used for human identification by mining and quantifying individual behavior effects on wireless signal propagation. This work proposes a novel device-free biometric (DFB) system, WirelessID, that explores the joint human fine-grained behavior and body physical signatures embedded in channel state information (CSI) by extracting spatiotemporal features. In addition, the signal fluctuations corresponding to different parts of the body contribute differently to the identification performance. Inspired by the success of the attention mechanism in computer vision (CV), thus, to extract more robust features, we introduce the spatiotemporal attention function into our system. To evaluate the performance, commercial WiFi devices are used for prototyping WirelessID in a real laboratory environment with an average accuracy of 93.14% and a best accuracy of 97.72% for five individuals.https://www.mdpi.com/1424-8220/21/17/5921device-freedeep learninghuman identificationchannel state informationwireless sensing |
| spellingShingle | Ronghui Zhang Xiaojun Jing Device-Free Human Identification Using Behavior Signatures in WiFi Sensing Sensors device-free deep learning human identification channel state information wireless sensing |
| title | Device-Free Human Identification Using Behavior Signatures in WiFi Sensing |
| title_full | Device-Free Human Identification Using Behavior Signatures in WiFi Sensing |
| title_fullStr | Device-Free Human Identification Using Behavior Signatures in WiFi Sensing |
| title_full_unstemmed | Device-Free Human Identification Using Behavior Signatures in WiFi Sensing |
| title_short | Device-Free Human Identification Using Behavior Signatures in WiFi Sensing |
| title_sort | device free human identification using behavior signatures in wifi sensing |
| topic | device-free deep learning human identification channel state information wireless sensing |
| url | https://www.mdpi.com/1424-8220/21/17/5921 |
| work_keys_str_mv | AT ronghuizhang devicefreehumanidentificationusingbehaviorsignaturesinwifisensing AT xiaojunjing devicefreehumanidentificationusingbehaviorsignaturesinwifisensing |