Classification of Heart Sounds Based on Topological Data Analysis Method

Topological data analysis (TDA) method could catch the rich geometric and topologic information of big find subtle differences between different signals. TDA opens up a new way for biomedical analysis. In this study, we applied heart sound signals (PCG) classification. First, sliding window was used to build point cloud. Then, persistent barcode is extracted from cloud by using topology technology Vietoris-Rips (VR) filtration. At last, GoogLeNet transfer learning model classifing. The proposed did work well on 2016 PhysioNet/CinC challenge dataset, Se=99.30%, +P=99.57%, F1=99.44%, mAcc=99.47%. results showed that can be physiological in large quantities. study has opened space application methods signal