Wireless Sensing for Human Activity Recognition Using USRP

Artificial Intelligence (AI) in tandem wireless technologies is providing state-of-the-art techniques human motion detection for various applications including intrusion detection, healthcare and so on. Radio Frequency (RF) signal when propagating through the medium encounters reflection this information stored signals reach receiver side as Channel State (CSI). This paper develops an intelligent sensing prototype that can provide quasi-real time classification of CSI carrying activities obtained using USRP devices. The dataset collected from devices a volunteer sits down or stands up test case. A model created making predictions on unknown data. Random forest was able to best results with accuracy result 96.70% used model. wearable device benchmark comparison performance dataset.