CAE Adaptive Compression, Transmission Energy and Cost Optimization for m-Health Systems

Abstract

The rapid increase in the number of patients requiring constant monitoring inspires researchers to investigate the area of mobile health (m-Health) systems for intelligent and sustainable remote healthcare applications. Extensive real-time medical data transmission using battery-constrained devices is challenging due to the dynamic network and the medical system constraints. Such requirements include end-to-end delay, bandwidth, transmission energy consumption, and application-level Quality of Services (QoS) requirements. As a result, adaptive data compression based on network and application resources before data transmission would be beneficial. A minimal distortion can be assured by applying Convolutional Auto-encoder (CAE) compression approach. This paper proposes a cross-layer framework that considers the patients’ movement while compressing and transmitting EEG data over heterogeneous wireless environments. The main objective of the framework is to minimize the trade-off between the transmission energy consumption along with the distortion ratio and monetary costs. Simulation results show that an optimal trade-off between the optimization objectives is achieved considering networks and application QoS requirements for m-Health systems.