A novel benchmark on human activity recognition using WiFi signals

WiFi-based Human activity recognition has attracted attention in the human-computer interaction, smart homes, and security monitoring fields. We first construct a WiFi-based activity dataset, namely WiAR, to provide a benchmark for existing works. Then, we leverage the moving variance of CSI to detect the start and end of activity. Moreover, we present K-means-based subcarrier selection mechanism according to subcarrier's sensitivity on human activity to enhance the robustness of human activity recognition. Finally, we leverage several classification algorithms to evaluate the performance of WiAR. Our results show that WiAR satisfies primary demand and achieves an average accuracy of greater than 93% using SVM, 80% using kNN, Random forest, and Decision tree.

[1]  Wen Hu,et al.  Radio-based device-free activity recognition with radio frequency interference , 2015, IPSN.

[2]  Kaishun Wu,et al.  WiFall: Device-free fall detection by wireless networks , 2017, IEEE INFOCOM 2014 - IEEE Conference on Computer Communications.

[3]  Yusheng Ji,et al.  Teach Your WiFi-Device: Recognise Simultaneous Activities and Gestures from Time-Domain RF-Features , 2014, Int. J. Ambient Comput. Intell..

[4]  Yunhao Liu,et al.  On Multipath Link Characterization and Adaptation for Device-Free Human Detection , 2015, 2015 IEEE 35th International Conference on Distributed Computing Systems.

[5]  Moustafa Youssef,et al.  The Horus WLAN location determination system , 2005, MobiSys '05.

[6]  Kaishun Wu,et al.  We Can Hear You with Wi-Fi! , 2016, IEEE Trans. Mob. Comput..

[7]  Jie Yang,et al.  E-eyes: device-free location-oriented activity identification using fine-grained WiFi signatures , 2014, MobiCom.

[8]  Paramvir Bahl,et al.  RADAR: an in-building RF-based user location and tracking system , 2000, Proceedings IEEE INFOCOM 2000. Conference on Computer Communications. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies (Cat. No.00CH37064).

[9]  Yunhao Liu,et al.  Mobility Increases Localizability , 2015, ACM Comput. Surv..

[10]  Ning An,et al.  SCPL: indoor device-free multi-subject counting and localization using radio signal strength , 2013, IPSN.

[11]  Yunhao Liu,et al.  Inferring Motion Direction using Commodity Wi-Fi for Interactive Exergames , 2017, CHI.

[12]  Yunhao Liu,et al.  Non-Invasive Detection of Moving and Stationary Human With WiFi , 2015, IEEE Journal on Selected Areas in Communications.

[13]  Li Sun,et al.  WiDraw: Enabling Hands-free Drawing in the Air on Commodity WiFi Devices , 2015, MobiCom.

[14]  Qi Tian,et al.  Human Daily Action Analysis with Multi-view and Color-Depth Data , 2012, ECCV Workshops.

[15]  Shwetak N. Patel,et al.  Whole-home gesture recognition using wireless signals , 2013, MobiCom.

[16]  Khaled A. Harras,et al.  WiGest demo: A ubiquitous WiFi-based gesture recognition system , 2015, 2015 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS).

[17]  Mi Zhang,et al.  BodyScan: Enabling Radio-based Sensing on Wearable Devices for Contactless Activity and Vital Sign Monitoring , 2016, MobiSys.

[18]  Romit Roy Choudhury,et al.  Using mobile phones to write in air , 2011, MobiSys '11.

[19]  Parth H. Pathak,et al.  Analyzing Shopper's Behavior through WiFi Signals , 2015, WPA@MobiSys.

[20]  Lu Wang,et al.  FIMD: Fine-grained Device-free Motion Detection , 2012, 2012 IEEE 18th International Conference on Parallel and Distributed Systems.

[21]  Michael Harville,et al.  Fast, integrated person tracking and activity recognition with plan-view templates from a single stereo camera , 2004, CVPR 2004.

[22]  Wei Wang,et al.  Keystroke Recognition Using WiFi Signals , 2015, MobiCom.

[23]  Khaled A. Harras,et al.  Wigest: A Ubiquitous Wifi-based Gesture Recognition System , 2014 .

[24]  Wei Wang,et al.  Gait recognition using wifi signals , 2016, UbiComp.

[25]  Marco Morana,et al.  Human Activity Recognition Process Using 3-D Posture Data , 2015, IEEE Transactions on Human-Machine Systems.

[26]  Ling Shao,et al.  Enhanced Computer Vision With Microsoft Kinect Sensor: A Review , 2013, IEEE Transactions on Cybernetics.

[27]  Wei Wang,et al.  Understanding and Modeling of WiFi Signal Based Human Activity Recognition , 2015, MobiCom.

[28]  Richard P. Martin,et al.  Detecting intra-room mobility with signal strength descriptors , 2010, MobiHoc '10.

[29]  Paul J. M. Havinga,et al.  Activity Recognition Using Inertial Sensing for Healthcare, Wellbeing and Sports Applications: A Survey , 2010, ARCS Workshops.

[30]  Antonio Fernández-Caballero,et al.  A survey of video datasets for human action and activity recognition , 2013, Comput. Vis. Image Underst..