Skip to Main Content
The paper discusses the recognition of heart sound for evaluating the cardiac contractility change trend, which includes heart sound samples recorded at different exercise condition. Especially, the recognition of heart sound recorded after great exercise workload is also discussed. The algorithm proposed consisted of two correlative methods. The first was used to recognize heart sound recorded at rest and after light exercise workloads by probabilistic neural network and the second was used to recognize heart sound recorded after great exercise workloads based on the knowledge of heart sound. Finally, the performance of the algorithm was evaluated using 45 digital heart sound recordings including normal and abnormal heart sound, which were recorded at rest and after light exercise workloads, and 28 digital heart sound recordings recorded after great exercise workloads. The result showed that over 94% of heart sound samples were classified and recognized correctly. This provides a basis for further heart sound analysis.