Phonocardiogram Classification Using Deep Convolutional Neural Networks with Majority Vote Strategy

Most current automated phonocardiogram (PCG) classification methods are relied on PCG segmentation. It is universal to make use of the segmented PCG signals and then extract efficiency features for computer-aided auscultation or heart sound classification. However, the accurate segmentation of the fundamental heart sounds depends greatly on the quality of the heart sound signals. In addition these methods that heavily relied on segmentation algorithm considerably increase the computational burden. To solve above two issues, we have developed a novel approach to classify normal and abnormal cardiac diseases with un-segmented PCG signals. A deep Convolutional Neural Networks (DCNNs) method is proposed for recognizing normal and abnormal cardiac diseases. In the proposed method, one-dimensional heart sound signals are first converted into twodimensional feature maps which have three channels and each of them represents Mel-frequency spectral coefficients (MFSC) features including static, delta and delta–delta. These artificial images are then fed to the proposed DCNNs to train and evaluate normal and abnormal heart sound signals. We combined the method of majority vote strategy to finally obtain the category of PCG signals. Sensitivity (Se), Specificity (Sp) and Mean accuracy (MAcc) are used as the evaluation metrics. Results: Experiments demonstrated that our approach achieved a significant improvement, with the high Se, Sp, and MAcc of 92.73%, 96.90% and 94.81% respectively. The proposed method improves the MAcc by 5.63% compared with the best result in the CinC Challenge 2016. In addition, it has better robustness performance when applying for the long heart sounds. The proposed DCNNs-based method can achieve the best accuracy performance on recognizing normal and abnormal heart sounds without the preprocessing of segmental algorithm. It significantly improves the classification performance compared with the current state-of-art algorithm.

Research on Fault Diagnosis Method Using Improved Multi-Class Classification Algorithm and Relevance Vector Machine

In view of the problems in traditional fault diagnosis method, such as small samples and nonlinear relations, a fault diagnosis method based on improved multi-class classification algorithm and relevance vector machine (RVM) is proposed in the paper. Through improving the majority-vote strategy of traditional One-Against-One (OAO) algorithm and combining the features of OAO and One-Against-Rest (OAR) algorithms, the k-class classification problem is transformed into k(k-1)/2 three-class classification problems based on the proposed majority-vote strategy of double-layer and thereby an improved multi-class classification algorithm of One-Against-One-Against-Rest (OAOAR) is presented. And on each three-class classification issue, OAO and RVM as the binary classifier are adopted to achieve the multi-class classification of RVM. Numerical simulations of UCI datasets and fault diagnostic experiments results of power transformers both demonstrate that the proposed method performs significantly better than other traditional methods in terms of increasing the diagnostic accuracy, optimizing the voting results, strengthening the diagnostic confidence and identifying the hidden classes, and has more practical value in engineering.

ANALYSIS OF CLASSIFICATION WITH A REJECT OPTION

In many classification problems, objects should be rejected when the confidence in their classification is too low. In this paper, we consider a new classification algorithm with a reject option. Based on the majority vote strategy and plug-in rules, we provide error analysis for this algorithm in ideal and realistic settings, respectively. In addition, some discussions of semi-supervised classification are given to demonstrate our theoretical analysis.