Using Incoherent Doppler Sensing with Machine Learning for Detecting Movement

The Doppler shift is a phenomenon experienced by radio signals influenced by movement of wireless stations and mobile scatterers. This phenomenon can be measured and analyzed for determining new information about the channel environment. In this tutorial paper, we present a method for extracting the Doppler shift from incoherent transmission and reception of continuous wave signals for classification of movement. The Doppler shift observed over multiple time intervals reveals a Doppler profile conveying important information about the physical dynamics of the stations and environmental scatterers. Whereas previous studies have investigated Doppler profiles from continuous waves using coherent systems, we explain how to process and analyze incoherent transmission of Doppler information for analysis with machine learning techniques. To demonstrate the workflow, we apply our understanding to identify key events leading up to a car collision in vehicle-to- vehicle networks.

[1]  Yusun Chang,et al.  Improved 5.9GHz V2V Short Range Path Loss Model , 2015, 2015 IEEE 12th International Conference on Mobile Ad Hoc and Sensor Systems.

[2]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[3]  Larry A. Rendell,et al.  A Practical Approach to Feature Selection , 1992, ML.

[4]  Yusun Chang,et al.  Automotive Doppler sensing: The Doppler profile with machine learning in vehicle-to-vehicle networks for road safety , 2017, 2017 IEEE 18th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

[5]  Hongwei Liu,et al.  Noise-Robust Classification of Ground Moving Targets Based on Time-Frequency Feature From Micro-Doppler Signature , 2014, IEEE Sensors Journal.

[6]  Jane Labadin,et al.  Feature selection based on mutual information , 2015, 2015 9th International Conference on IT in Asia (CITA).

[7]  M. Andric,et al.  Ground Surveillance Radar Target Classification Based On Fuzzy Logic Approach , 2005, EUROCON 2005 - The International Conference on "Computer as a Tool".

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

[9]  Ferat Sahin,et al.  A survey on feature selection methods , 2014, Comput. Electr. Eng..

[10]  Alenka Zajic,et al.  Mobile-to-Mobile Wireless Channels , 2012 .

[11]  Hao Ling,et al.  Design of multiple frequency continuous wave radar hardware and micro-doppler based detection and classification algorithms , 2008 .

[12]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Yusun Chang,et al.  Doppler domain localization for collision avoidance in VANETs by using omnidirectional antennas , 2014, 2014 International Conference on Connected Vehicles and Expo (ICCVE).

[14]  Xiang Li,et al.  Device-Free WiFi Human Sensing: From Pattern-Based to Model-Based Approaches , 2017, IEEE Communications Magazine.