DapFall: Dynamic Amplitude Probability Density Profile-Based Wi-Fi CSI Sensing for Fall Detection

The Wi-Fi channel state information (CSI)-based fall detection is highly sensitive to different environments. Existing work ignores the CSI subcarrier mutual information (SMI) which carries critical characteristic of each activity and is robust to environment. In this article, we propose a data-efficient DapFall system, which enables cross-environment fall detection without model retraining. The key insight of DapFall is to transform the CSI amplitude into dynamic amplitude probability density (DAPD), which is a 3-D visual representation, strongly emphasizing the dynamic features. Furthermore, DAPD retains SMI and meanwhile reduces static components. Then, we use specific data augmentations to change the amplitude variation feature and further increase the diversity of fall dataset. DAPD enables an efficient cross-domain knowledge utilization using deep learning model R $2+1$ -D pretrained in a totally unrelated task and then facilitate detection capability without the need for extensive data. Experimental results demonstrate that DapFall achieves a 94.3% recall true-positive rate (TPR) and 6.25% false-positive rate (FPR) in original environments with limited training samples and meanwhile exhibit robust performance in other environments without retraining the model.