# MAK-Net: A Multi-Scale Attentive Kolmogorov–Arnold Network with BiGRU for Imbalanced ECG Arrhythmia Classification

## TL;DR

MAK-Net is a deep learning model that improves ECG arrhythmia classification by handling imbalanced data and achieving high accuracy and reliability.

## Contribution

MAK-Net introduces a novel hybrid framework combining multiscale convolution, attention mechanisms, BiGRU, and KAN layers for imbalanced ECG classification.

## Key findings

- MAK-Net achieved 0.9980 accuracy and 0.9888 F1-score on the MIT-BIH arrhythmia database.
- The model outperforms existing methods in handling class imbalance with focal loss and SMOTE.
- Multiscale feature fusion and KAN layers enhance nonlinear representation and interpretability.

## Abstract

Accurate classification of electrocardiogram (ECG) signals is vital for reliable arrhythmia diagnosis and informed clinical decision-making, yet real-world datasets often suffer severe class imbalance that degrades recall and F1-score. To address these limitations, we introduce MAK-Net, a hybrid deep learning framework that combines: (1) a four-branch multiscale convolutional module for comprehensive feature extraction across diverse waveform morphologies; (2) an efficient channel attention mechanism for adaptive weighting of clinically salient segments; (3) bidirectional gated recurrent units (BiGRU) to capture long-range temporal dependencies; and (4) Kolmogorov–Arnold Network (KAN) layers with learnable spline activations for enhanced nonlinear representation and interpretability. We further mitigate imbalance by synergistically applying focal loss and the Synthetic Minority Oversampling Technique (SMOTE). On the MIT-BIH arrhythmia database, MAK-Net attains state-of-the-art performance—0.9980 accuracy, 0.9888 F1-score, 0.9871 recall, 0.9905 precision, and 0.9991 specificity—demonstrating superior robustness to imbalanced classes compared with existing methods. These findings validate the efficacy of multiscale feature fusion, attention-guided learning, and KAN-based nonlinear mapping for automated, clinically reliable arrhythmia detection.