Optimized ECG Segmentation Using Hilbert Transform for Accurate Signal Classification

The study introduces an improved Hilbert Transform (iSEGMENT) method to segment ECG signals which boosts the detection of cardiovascular diseases (CVD). The authors conducted a performance comparison of iSEGMENT against HT and DCT-DOST and KPCC and U-Net and SSA for ECG signal segmentation. Experimental trials using the MIT-BIH database within MATLAB environment demonstrate iSEGMENT provides better results than other methods. The classification results for iSEGMENT reach 99.87% achievement with RBFNN and 99% with PSO-PNN. Execution time analysis shows that iSEGMENT operates with high computational speed. The robust performance characteristics of iSEGMENT include precision (99.1), recall (99.2) and F1-score (99.1). Success factors of iSEGMENT stem from its effective algorithms together with its adaptive processing methods and parallel processing capabilities. Accurate feature extraction depends heavily on the advanced segmentation method that proves important for earliest disease detection capabilities. iSEGMENT proves to be a trustworthy ECG segmentation method which surpasses traditional approaches in terms of accuracy and efficiency thus making it suitable for real-time clinical applications.