Activity recognition using Wi-Fi CSI (Channel State Information) has become popular due to its low deployment cost, requiring only Wi-Fi devices for applications like elderly monitoring. However, the accuracy and coverage of CSI-based sensing depend on the number of Wi-Fi devices in the environment, which may not be cost-effective.
To address this, the paper proposes a Wi-Fi CSI-based sensing method using backscatter tags with microwatt-level energy consumption. These tags allow the collection of CSI data from various Wi-Fi channels, increasing the number of CSI observations without needing additional Wi-Fi devices.
Published Papers
- Erdélyi, V., Miyao, K., Uchiyama, A., & Murakami, T. (2023, March). Towards Activity Recognition Using Wi-Fi CSI from Backscatter Tags. In 2023 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops) (pp. 346-349). IEEE.
- Erdélyi, V., Miyao, K., Uchiyama, A., & Murakami, T. (2024, June). Poster: Activity Recognition Using CSI Backscatter with Commodity Wi-Fi. In Proceedings of the 22nd Annual International Conference on Mobile Systems, Applications and Services (pp. 636-637).