Tracking Human Motion Direction With Commodity Wireless Networks

Habibur Rahaman, Vladimir Dyo

Research output: Contribution to journalArticlepeer-review


Detecting when a person leaves a room, or a house is essential to create a safe living environment for people suffering from dementia or other mental disorders. The approaches based on wearable devices, e.g. GPS bracelets may detect such events require periodic maintenance to recharge or replace batteries, and therefore may not be suitable for certain types of users. On the other hand, camera-based systems require illumination and raise potential privacy concerns. In this paper, we propose a device-free walking direction detection approach based on RF-sensing, which does not require a person to wear any equipment. The proposed approach monitors the signal strength fluctuations caused by the human body on ambient wireless links and analyses its spatial patterns using a convolutional neural network to identify the walking direction. The approach has been evaluated experimentally to achieve up to 98% classification accuracy depending on the environment.
Original languageEnglish
Pages (from-to)23344-23351
Number of pages8
JournalIEEE Sensors Journal
Issue number20
Publication statusPublished - 7 Sept 2021


  • Wireless sensor networks
  • Wireless communication
  • Convolutional neural networks

Cite this