WiFi Sensing for Human Activity Recognition

#WiFi #Sensing #human #activity #recognition #(HAR) #Channel #State #Information #(CSI) #Integrated #and #Communication #(ISAC) #lightweight #scalable #machine #learning.
Share

Abstract:

This talk presents recent advances in WiFi sensing for human activity recognition (HAR), demonstrating how existing wireless communication infrastructure can be leveraged as a powerful sensing modality. By exploiting Channel State Information (CSI) readily available in commodity WiFi devices, it is possible to infer both large-scale and fine-grained human activities without requiring wearable sensors or dedicated hardware. The presentation begins with an overview of the emerging paradigm of Integrated Sensing and Communication (ISAC), including developments such as IEEE 802.11bf and future 6G systems, where communication signals are repurposed for environmental sensing. It then introduces signal processing techniques for extracting meaningful features from CSI, including time-frequency analysis and Doppler-based representations that capture motion dynamics. A key contribution discussed in the talk is the use of lightweight and scalable machine learning approaches, such as random convolutional kernels and deep neural networks, for efficient end-to-end activity recognition.



  Date and Time

  Location

  Hosts

  Registration



  • Add_To_Calendar_icon Add Event to Calendar
  • Concordia University
  • 1515 Ste. Catherine West
  • MONTREAL, Quebec
  • Canada H3G 1M8
  • Building: Electrical & Computer Engineering Department EV
  • Room Number: EV003-309

  • Contact Event Hosts
  • Starts 15 April 2026 04:00 AM UTC
  • Ends 19 May 2026 08:00 PM UTC
  • No Admission Charge


  Speakers

Professor Shahrokh Valaee of University of Toronto

Topic:

WiFi Sensing for Human Activity Recognition

Abstract:

This talk presents recent advances in WiFi sensing for human activity recognition (HAR), demonstrating how existing wireless communication infrastructure can be leveraged as a powerful sensing modality. By exploiting Channel State Information (CSI) readily available in commodity WiFi devices, it is possible to infer both large-scale and fine-grained human activities without requiring wearable sensors or dedicated hardware. The presentation begins with an overview of the emerging paradigm of Integrated Sensing and Communication (ISAC), including developments such as IEEE 802.11bf and future 6G systems, where communication signals are repurposed for environmental sensing. It then introduces signal processing techniques for extracting meaningful features from CSI, including time-frequency analysis and Doppler-based representations that capture motion dynamics. A key contribution discussed in the talk is the use of lightweight and scalable machine learning approaches, such as random convolutional kernels and deep neural networks, for efficient end-to-end activity recognition.

Biography:

 Dr. Shahrokh Valaee is a Professor with the Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto, and the holder of Nortel Chair of Network Architectures and Services. He is the Founder and the Director of the Wireless Innovation Research Laboratory (WIRLab) at the University of Toronto. Professor Valaee was the TPC Co-Chair and the Local Organization Chair of the IEEE Personal Mobile Indoor Radio Communication (PIMRC) Symposium 2011. He was the TPC Co-Chair of ICT 2015, and PIMRC 2017, and the Track Co-Chair of WCNC 2014, PIMRC 2020, VTC Fall 2020. He was the co-chair of the organizing committee for PIMRC 2023. He is currently a member of the Steering Committee of IEEE PIMRC. From December 2010 to December 2012, he was the Associate Editor of the IEEE Signal Processing Letters. From 2010 to 2015, he served as an Editor of IEEE Transactions on Wireless Communications. Currently, he is an Editor of the Journal of Computer and System Science and also an Editor of IEEE Transactions on Wireless Communications. From 2021 to 2023, he was a Distinguished Lecturer of the IEEE Communications Society. Currently, he serves as a Distinguished Lecturer for the IEEE Vehicular Technology Society. He was the co-recipient of the best paper award in the IEEE Machine Learning for Signal Processing (MLSP) 2020 workshop. Professor Valaee is a Fellow of the Engineering Institute of Canada and a Fellow of IEEE.

Email:

Address:Toronto, Ontario, Canada