A Novel Data Augmentation Strategy for Robust Deep Learning Classification of Biomedical Time-Series Data: Application to ECG and EEG Analysis

TL;DR

This paper introduces a unified deep learning framework with a novel data augmentation strategy for robust classification of biomedical time-series data, achieving state-of-the-art accuracy on ECG and EEG datasets.

Contribution

It proposes a ResNet-based CNN with attention and a new time-domain concatenation augmentation, effectively handling diverse signals and class imbalance for improved biomedical classification.

Findings

Achieved over 99.9% accuracy on benchmark datasets.

Demonstrated robustness across ECG and EEG signals.

Suitable for deployment on low-resource devices.

Abstract

The increasing need for accurate and unified analysis of diverse biological signals, such as ECG and EEG, is paramount for comprehensive patient assessment, especially in synchronous monitoring. Despite advances in multi-sensor fusion, a critical gap remains in developing unified architectures that effectively process and extract features from fundamentally different physiological signals. Another challenge is the inherent class imbalance in many biomedical datasets, often causing biased performance in traditional methods. This study addresses these issues by proposing a novel and unified deep learning framework that achieves state-of-the-art performance across different signal types. Our method integrates a ResNet-based CNN with an attention mechanism, enhanced by a novel data augmentation strategy: time-domain concatenation of multiple augmented variants of each signal to generate richer representations. Unlike prior work, we scientifically increase signal complexity to achieve future-reaching capabilities, which resulted in the best predictions compared to the state of the art. Preprocessing steps included wavelet denoising, baseline removal, and standardization. Class imbalance was effectively managed through the combined use of this advanced data augmentation and the Focal Loss function. Regularization techniques were applied during training to ensure generalization. We rigorously evaluated the proposed architecture on three benchmark datasets: UCI Seizure EEG, MIT-BIH Arrhythmia, and PTB Diagnostic ECG. It achieved accuracies of 99.96%, 99.78%, and 100%, respectively, demonstrating robustness across diverse signal types and clinical contexts. Finally, the architecture requires ~130 MB of memory and processes each sample in ~10 ms, suggesting suitability for deployment on low-end or wearable devices.