GAF-FusionNet: Multimodal ECG Analysis via Gramian Angular Fields and Split Attention

TL;DR

GAF-FusionNet is a new multimodal ECG classification framework that combines time-series and image-based features using Gramian Angular Fields and split attention, significantly improving accuracy across multiple datasets.

Contribution

The paper introduces GAF-FusionNet, a novel multimodal ECG analysis model that fuses temporal and spatial features with a split attention mechanism for enhanced classification.

Findings

Achieved 94.5%, 96.9%, and 99.6% accuracy on three ECG datasets.

Significant performance improvements over existing methods.

Effective integration of time-series and image representations.

Abstract

Electrocardiogram (ECG) analysis plays a crucial role in diagnosing cardiovascular diseases, but accurate interpretation of these complex signals remains challenging. This paper introduces a novel multimodal framework(GAF-FusionNet) for ECG classification that integrates time-series analysis with image-based representation using Gramian Angular Fields (GAF). Our approach employs a dual-layer cross-channel split attention module to adaptively fuse temporal and spatial features, enabling nuanced integration of complementary information. We evaluate GAF-FusionNet on three diverse ECG datasets: ECG200, ECG5000, and the MIT-BIH Arrhythmia Database. Results demonstrate significant improvements over state-of-the-art methods, with our model achieving 94.5\%, 96.9\%, and 99.6\% accuracy on the respective datasets. Our code will soon be available at https://github.com/Cross-Innovation-Lab/GAF-FusionNet.git.