Abstract
Recognizing human activities in indoor environments is a key component in smart home and surveillance systems. In this study, we introduce an innovative method for activity recognition using Channel State Information (CSI) of WiFi signals. Compared with traditional approaches that rely on wearable devices or cameras, our method utilizes existing WiFi infrastructure, ensuring privacy and minimal user intrusion. By analyzing the changes in CSI induced by human motions, we develop a robust model capable of accurately identifying a range of activities. Extensive experiments demonstrate the effectiveness of our approach in various indoor settings, highlighting its promise for broad implementation in practical scenarios.

This publication has 17 references indexed in Scilit: