Low PRF Low Frequency Radar Sensor for Fall Detection by Using Deep Learning

In this paper, we propose an approach that span a wide range of potential radar data for deep learning to detect fall motion. This approach generates a number of training data from a small set of measurements of the the multiple input multiple-output (MIMO) stepped-frequency continuous wave ultra-widehand (SFCW-UWB) radar, which can attain 99.38% accuracy in deep learning. Even if the radar is operating in the lower frequency band with low pulse repetition frequency (PRF), which results in the inconspicuous time-frequency (TF) signatures and Doppler ambiguity, greatly increasing the difficulty of fall detection, the proposed method still works well. This work learns and captures the intricate properties of the TF signatures without human intervention and feeds the underlying features to the classifier. Experimental data is used to demonstrate the effectiveness of the proposed fall detection deep learning approach.