Convolutional Autoencoder Approach for EEG Compression and Reconstruction in m-Health Systems

In the last few years, the number of patients with chronic diseases requiring constant monitoring increased rapidly, which motivates researchers to develop scalable remote health applications. Nevertheless, the amount of transmitted real-time data through current dynamic networks with limited and restricted bandwidth, end-to-end delay, and transmission power; limits having an efficient transmission of the data. Motivated by the high energy consumed for transmission, applying data reduction techniques to the vital signs at the transmitter side present an efficient edge-based approach that significantly reduces the transmission energy. However, a new problem arises, which is the ability of receiving the data at the server side with an acceptable distortion rate (i.e., deformation of vital signs because of inefficient data reduction). In this paper, we introduce a Deep Learning (DL) approach based on Convolutional Auto-Encoder (CAE), to compress and reconstruct the vital signs in general and Electroencephalogram Signal (EEG) specifically with minimum distortion. The results show that using CAE provides efficient distortion rate while maximizing compression ratio. However, learning makes CAE application-specific, where each CAE model is designed specifically for a certain application.