Intelligent Cardiovascular Monitoring Through Continuous Wavelet and Neural Pooling Mechanisms

Abstract

Cardiovascular diseases remain a leading cause of mortality worldwide, requiring continuous and accurate monitoring systems for early detection and preventive healthcare. Traditional ECG-based monitoring systems often suffer from noise sensitivity, limited feature extraction capability, and reduced performance in real-time environments. To address these challenges, this study proposes an Intelligent Cardiovascular Monitoring Framework based on Continuous Wavelet Transform (CWT) and Neural Pooling Mechanisms. The proposed model integrates multi-resolution signal analysis using wavelet transforms with deep neural pooling layers to enhance feature extraction, reduce redundancy, and improve classification accuracy. Continuous Wavelet Transform enables precise time-frequency representation of ECG signals, while neural pooling mechanisms improve robustness by selecting dominant features and suppressing irrelevant variations. The framework is evaluated using standard cardiovascular datasets and compared with traditional machine learning and deep learning approaches. Experimental results demonstrate that the proposed model significantly improves accuracy, sensitivity, specificity, and computational efficiency. The findings confirm that combining continuous wavelet analysis with neural pooling provides a powerful and reliable solution for intelligent cardiovascular monitoring systems.