Building robust models for Human Activity Recognition from raw accelerometers data using Gated Recurrent Units and Long Short Term Memory Neural Networks

Human Activity Recognition (HAR) is a growing field of research in biomedical engineering and it has many potential applications in the treatment and prevention of several diseases. Due to the recent advancement in technology, devices that collect position and orientation measurements (e.g. accelerometers and gyroscopes) are becoming ubiquitous. These measurements can then be used to train machine learning models for HAR. In this research, we propose one recurrent neural network architecture and a data augmentation approach for building robust and accurate models for HAR. We compared models with Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) layers. The proposed data augmentation approach was used to make the models robust to the cases where one or more sensors are missing. In this empirical study, we could also understand some relations between the ideal locations of the sensors in the participants and the types of activities performed. The proposed approaches were tested in the GOTOv dataset from a study which involved 35 participants performing 16 sedentary, ambulatory and lifestyle activities in a semi-structured environment. The results presented, clearly show that the models are able to detect these activities in a robust way.