Multistage Pruning of CNN Based ECG Classifiers for Edge Devices
This work addresses the computational limitations of edge devices for real-time ECG monitoring in healthcare, representing an incremental improvement over existing pruning methods.
The paper tackles the problem of deploying CNN-based ECG classifiers on low-powered edge devices by introducing a multistage pruning technique that reduces model complexity with minimal performance loss, achieving 97.7% accuracy, a 3.3% improvement in accuracy, and a 60.4% decrease in run-time complexity compared to baseline.
Using smart wearable devices to monitor patients electrocardiogram (ECG) for real-time detection of arrhythmias can significantly improve healthcare outcomes. Convolutional neural network (CNN) based deep learning has been used successfully to detect anomalous beats in ECG. However, the computational complexity of existing CNN models prohibits them from being implemented in low-powered edge devices. Usually, such models are complex with lots of model parameters which results in large number of computations, memory, and power usage in edge devices. Network pruning techniques can reduce model complexity at the expense of performance in CNN models. This paper presents a novel multistage pruning technique that reduces CNN model complexity with negligible loss in performance compared to existing pruning techniques. An existing CNN model for ECG classification is used as a baseline reference. At 60% sparsity, the proposed technique achieves 97.7% accuracy and an F1 score of 93.59% for ECG classification tasks. This is an improvement of 3.3% and 9% for accuracy and F1 Score respectively, compared to traditional pruning with fine-tuning approach. Compared to the baseline model, we also achieve a 60.4% decrease in run-time complexity.