Atrial Fibrillation Detection Using Weight-Pruned, Log-Quantised Convolutional Neural Networks
This work addresses energy efficiency for atrial fibrillation detection on portable devices, but it is incremental as it combines existing pruning and quantization techniques.
The paper tackled the challenge of implementing deep neural networks on battery-powered medical devices by developing a convolutional neural network for atrial fibrillation detection from ECG signals, achieving 91.1% model compression with only a 1% accuracy loss and 91.7% final accuracy.
Deep neural networks (DNN) are a promising tool in medical applications. However, the implementation of complex DNNs on battery-powered devices is challenging due to high energy costs for communication. In this work, a convolutional neural network model is developed for detecting atrial fibrillation from electrocardiogram (ECG) signals. The model demonstrates high performance despite being trained on limited, variable-length input data. Weight pruning and logarithmic quantisation are combined to introduce sparsity and reduce model size, which can be exploited for reduced data movement and lower computational complexity. The final model achieved a 91.1% model compression ratio while maintaining high model accuracy of 91.7% and less than 1% loss.