Heart sound recognition using hybrid joint transform correlator

Abstract This work introduces an innovative method for heart sound recognition using a hybrid joint transform correlator (JTC). Traditional techniques such as convolutional neural networks and machine learning models, although promising, often suffer from computational complexity and latency issues, resulting in slower processing speeds. In contrast, the proposed method overcomes these challenges by utilizing an optical correlator that operates at significantly accelerated speeds. The heart sound signals are initially converted into spectrograms, which are subsequently correlated using the hybrid JTC for recognition and decision-making. Moreover, to handle variability within heart sound classes and enhance recognition accuracy, a composite filter synthesized from multiple spectrograms is integrated with the JTC. As a result, the proposed approach not only enhances the speed of heart sound analysis but also maintains high precision and reliability. The effectiveness of the method has been confirmed through both simulation and experimental results.