Heart sounds classification using adaptive wavelet threshold and 1D LDCNN

Heart sounds classification plays an important role in cardiovascular disease detection. Currently, deep learning methods for heart sound with heavy parameters consumption cannot be deployed environments limited memory and computational budgets. Besides, de-noising of signals (HSSs) can affect accuracy classification, because erroneous removal meaningful components may lead to distortion. In this paper, automated method using adaptive wavelet threshold 1D LDCNN (One-dimensional Lightweight Deep Convolutional Neural Net work) is proposed. method, we exploit WT (Wavelet Transform) de-noise (HSSs). Furthermore, utilize realize automatic feature extraction de-noised sounds. Experiments on PhysioNet/CinC 2016 show that our proposed achieves the superior results excels parameter comparing state-of-the-art methods.