DCentNet: Decentralized Multistage Biomedical Signal Classification using Early Exits
This work addresses energy efficiency for IoT-based biomedical monitoring, though it is incremental as it builds on existing early exit and compression techniques.
The paper tackles the problem of high energy consumption and latency in biomedical signal classification from IoT wearable sensors by proposing DCentNet, a decentralized multistage approach with early exits, which reduces wireless data transmission by up to 94.54% and power usage by 73.6% while maintaining accuracy and sensitivity.
DCentNet is a novel decentralized multistage signal classification approach designed for biomedical data from IoT wearable sensors, integrating early exit points (EEP) to enhance energy efficiency and processing speed. Unlike traditional centralized processing methods, which result in high energy consumption and latency, DCentNet partitions a single CNN model into multiple sub-networks using EEPs. By introducing encoder-decoder pairs at EEPs, the system compresses large feature maps before transmission, significantly reducing wireless data transfer and power usage. If an input is confidently classified at an EEP, processing stops early, optimizing efficiency. Initial sub-networks can be deployed on fog or edge devices to further minimize energy consumption. A genetic algorithm is used to optimize EEP placement, balancing performance and complexity. Experimental results on ECG classification show that with one EEP, DCentNet reduces wireless data transmission by 94.54% and complexity by 21%, while maintaining original accuracy and sensitivity. With two EEPs, sensitivity reaches 98.36%, accuracy 97.74%, wireless data transmission decreases by 91.86%, and complexity is reduced by 22%. Implemented on an ARM Cortex-M4 MCU, DCentNet achieves an average power saving of 73.6% compared to continuous wireless ECG transmission.