Keynote 5: Environmental sensing using WiFi signals
Abstract/Description
This talk will provide an overview of our recent work that utilizes ubiquitously present radio signals (such as WiFi) for novel sensing applications. For instance, in our recent Globebcom paper, we use commodity WiFi radios to detect concealed metallic objects on a person walking in an indoor environment. In particular, we utilize the channel state information available from Intel 5300 cards coupled with a deep convolution neural network to achieve a classification accuracy of approximately 86%. Another recent project uses an in-house WiFi-like PHY with USRP radios from National Instruments to detect risky driver behavior in an in-vehicle environment. Similarly, in another project we utilize SDRs with WiFi-like PHY to perform non-intrusive load monitoring of electrical load appliances. Time permitting, the talk will also discuss our recent work on using radio signals for soil moisture sensing in precision farming applications.
Location
Lecture Hall A (Aman Tower, 12th floor)
Session Theme
Keynote Session IV
Session Type
Keynote Speech
Start Date
17-11-2019 9:30 AM
End Date
17-11-2019 10:10 AM
Recommended Citation
Uppal, D. A. (2019). Keynote 5: Environmental sensing using WiFi signals. International Conference on Information and Communication Technologies. Retrieved from https://ir.iba.edu.pk/icict/2019/2019/28
COinS
Keynote 5: Environmental sensing using WiFi signals
Lecture Hall A (Aman Tower, 12th floor)
This talk will provide an overview of our recent work that utilizes ubiquitously present radio signals (such as WiFi) for novel sensing applications. For instance, in our recent Globebcom paper, we use commodity WiFi radios to detect concealed metallic objects on a person walking in an indoor environment. In particular, we utilize the channel state information available from Intel 5300 cards coupled with a deep convolution neural network to achieve a classification accuracy of approximately 86%. Another recent project uses an in-house WiFi-like PHY with USRP radios from National Instruments to detect risky driver behavior in an in-vehicle environment. Similarly, in another project we utilize SDRs with WiFi-like PHY to perform non-intrusive load monitoring of electrical load appliances. Time permitting, the talk will also discuss our recent work on using radio signals for soil moisture sensing in precision farming applications.