Privacy-Aware Human Activity Classification using a Transformer-based Model

Fall detection in a bathroom requires privacy as an essential issue. Ultra-wideband sensors have the ability to protect human privacy because their output has only limited information. As a result, interpreting the output is a challenging task. This research implemented a transformer model that learned time-series signals from an ultra-wideband sensor in a bathroom. First, the signals were preprocessed into the two-dimensional range-time format. Second, the range-time data were passed into a convolutional neural network encoder before going into a transformer. Third, the basic movements of humans were used for training. Finally, the encoder and the Transformer were trained separately. The model achieved good accuracy on static postures but not good on transitions due to their overlapped similarity with the static postures.