Multistage Pruning of CNN Based ECG Classifiers for Edge Devices

TL;DR

This paper introduces a multistage pruning method for CNNs that significantly reduces model complexity for ECG classification on edge devices while maintaining high accuracy and F1 scores.

Contribution

The paper proposes a novel multistage pruning technique that outperforms traditional pruning methods in reducing CNN complexity with minimal performance loss.

Findings

Achieves 97.7% accuracy at 60% sparsity

F1 score of 93.59% at 60% sparsity

60.4% reduction in run-time complexity

Abstract

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.