Title

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

This document is currently not available here.

Share

COinS
 
Nov 17th, 9:30 AM Nov 17th, 10:10 AM

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.