Refining Fetal Electrocardiogram Classification: A Hybrid Approach with Multimodal Data Fusion and Advanced Deep Learning

This research introduces a novel framework for reliably identifying coupled fetal and maternal electrocardiogram (ECG) data, addressing issues such as input reduction and iteration optimization. The technique utilizes independent component analysis (ICA) and principal component analysis (PCA) on cardiological data from implanted electrodes, emphasizing regulated inputs to mitigate potential health risks. By employing the AlexNet Deep Neural Network Architecture, an intelligent machine evaluates signal quality through image classification over time, despite using few inputs for performance evaluation. The framework aims to enhance fetal ECG detection, thereby improving prenatal healthcare diagnosis and monitoring.