rTsfNet: a DNN model with Multi-head 3D Rotation and Time Series Feature Extraction for IMU-based Human Activity Recognition

Although many deep learning (DL) algorithms have been proposed for the IMU-based HAR domain, traditional machine learning that utilizes handcrafted time series features (TSFs) still often performs well. It is not rare that combinations among DL and TSFs show better accuracy than DL-only approaches. However, there is a problem with time series features in IMU-based HAR. The amount of derived features can vary greatly depending on the method used to select the 3D basis. Fortunately, DL's strengths include capturing the …

accuracy algorithms cs.hc cs.lg deep learning dnn domain extraction feature feature extraction features head human machine machine learning multi-head recognition rotation series show time series traditional machine learning