oscar: WiFi人體特徵生物辨識

2019年12月20日星期五

1.WiFi新技術：探測人體生命特徵

2.WiFi辨識生物特徵有關的重要名詞

Channel State Information (CSI)
- 關鍵技術
- CSI包含WiFi訊號的反射、散佈、衰減等資訊
- 「WiFi辨識生物特徵」的突破來自CSI可以從消費性WiFi產品上取得
through-the-wall (TTW) human detection
- 隔牆人體偵測
- WiFi有可以穿透牆壁的優點
device-free human detection
- 不需穿載裝置的人體偵測
- 例如腦波儀

3.Human Detection

此研究隔牆偵測房間有沒有人(而且可以走動不需靜止)，平均準確度高達99%。
Zhu, H., Xiao, F., Sun, L., Wang, R., & Yang, P. (2017). R-TTWD: Robust device-free through-the-wall detection of moving human with WiFi. IEEE Journal on Selected Areas in Communications, 35(5), 1090-1103.

4.偵測睡眠

偵測睡眠姿勢變換
也可以進一步偵測打瞌睡的點頭行為、抖手、抖腳
Gu, Y., Zhang, Y., Li, J., Ji, Y., An, X., & Ren, F. (2018). Sleepy: Wireless Channel Data Driven Sleep Monitoring via Commodity WiFi Devices. IEEE Transactions on Big Data.

5. To detect human activity

CARM, CSI based human Activity Recognition and Monitoring system
youtu.be/FnK4QHj00nk
平均94.8% Accuracy
辨識動作: Running, walking, sitting down, Opening refrigerator, Falling, Boxing, Pushing one hand, Brushing teeth, No activity.
Wang, W., Liu, A. X., Shahzad, M., Ling, K., & Lu, S. (2015, September). Understanding and modeling of wifi signal based human activity recognition. In Proceedings of the 21st annual international conference on mobile computing and networking(pp. 65-76). ACM.

6. 搭配Deep Learning的室內定位應用

WiFi電波應用在室內定位
此研究加入Deep Learning來加強辨識正確性(但沒有具體寫出準確度)
Wang, X., Gao, L., Mao, S., & Pandey, S. (2017). CSI-based fingerprinting for indoor localization: A deep learning approach. IEEE Transactions on Vehicular Technology, 66(1), 763-776.

oscar