scholarly journals Pay More Attention with Fewer Parameters: A Novel 1-D Convolutional Neural Network for Heart Sounds Classification

2018 ◽  
Author(s):  
Yunqiu Xu ◽  
Bin Xiao ◽  
Xiuli Bi ◽  
Weisheng Li ◽  
Junhui Zhang ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Heart Sounds

scholarly journals A novel 1-D densely connected feature selection convolutional neural network for heart sounds classification

2021 ◽  
Vol 9 (24) ◽  
pp. 1752-1752
Author(s):  
Xin Zhou ◽  
Xuying Wang ◽  
Xianhong Li ◽  
Yao Zhang ◽  
Ying Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Feature Selection ◽  
Convolutional Neural Network ◽  
Heart Sounds

scholarly journals Heart Sound Segmentation Based on Personalized Gaussian Mixture Model and Convolutional Neural Network

2020 ◽  
Author(s):  
Chun Dong Xu ◽  
Jing Zhou ◽  
Dong Wen Ying ◽  
Lei Jing Hou ◽  
Qing Hua Long
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Heart Sound ◽  
Gaussian Mixture ◽  
Heart Sounds ◽  
Spectral Amplitude ◽  
Heart Sound Segmentation ◽  
F Measure

Abstract Background: Heart sound segmentation is a long-standing problem in heart analysis, and it is mainly caused by noise interference and diversification of heart sounds. Faced with the challenging of heart sound segmentation, a more applicable segmentation model was studied. Methods: In this process, the optimal modified Log-spectral amplitude and wavelet were used to suppress the noise in the heart sound, and used the duration-dependent hidden Markov model based on personalized Gaussian mixture model (PGMM-DHMM) to segment the fundamental heart sound (FHS) and the non-fundamental heart sound (non-FHS). Then used the optimized Mel frequency cepstral coefficient (MFCC) to realize the classification of S1 and S2 heart sound frames through the Convolutional neural network (CNN) classifier, which can avoid the errors caused by the ambiguity of the time domain features. Results: PGMM-DHMM can segment FHS more effectively, and the accuracy is 94.3%. The CNN classifier obtained the best results in the S1 and S2 classifications, the accuracy is 90.92%, the precision of S1 is 90.76%, the recall is 91.05%, the F-measure is 90.9%, and the precision of S2 is 91.07%, the recall is 90.79%, the F-measure is 90.93%. The final segmentation accuracy is 92.92%. In addition, the experimental results further indicate that CNN has more robust performance when classifying abnormal S1 and abnormal S2. Conclusions: The PGMM-DHMM model can better segment FHS and Non-FHS. The optimization of MFCC improves the classification effect of S1 and S2, and the improvement effect by the CNN classifier is significant, especially for abnormal heart sounds. The proposed algorithm is better than other algorithms at this stage.

scholarly journals Heart Sound Segmentation Based on Personalized Gaussian Mixture Model and Convolutional Neural Network

2020 ◽  
Author(s):  
Chun Dong Xu ◽  
Jing Zhou ◽  
Dong Wen Ying ◽  
Lei Jing Hou ◽  
Qing Hua Long
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Heart Sound ◽  
Gaussian Mixture ◽  
Heart Sounds ◽  
Spectral Amplitude ◽  
Heart Sound Segmentation ◽  
F Measure

Abstract Background: Heart sound segmentation is a long-standing problem in heart analysis, and it is mainly caused by noise interference and diversification of heart sounds. Faced with the challenging of heart sound segmentation, a more applicable segmentation model was studied. Methods: In this process, the optimal modified Log-spectral amplitude and wavelet were used to suppress the noise in the heart sound, and used the duration-dependent hidden Markov model based on personalized Gaussian mixture model (PGMM-DHMM) to segment the fundamental heart sound (FHS) and the non-fundamental heart sound (non-FHS). Then used the optimized Mel frequency cepstral coefficient (MFCC) to realize the classification of S1 and S2 heart sound frames through the Convolutional neural network (CNN) classifier, which can avoid the errors caused by the ambiguity of the time domain features. Results: PGMM-DHMM can segment FHS more effectively, and the accuracy is 94.3%. The CNN classifier obtained the best results in the S1 and S2 classifications, the accuracy is 90.92%, the precision of S1 is 90.76%, the recall is 91.05%, the F-measure is 90.9%, and the precision of S2 is 91.07%, the recall is 90.79%, the F-measure is 90.93%. The final segmentation accuracy is 92.92%. In addition, the experimental results further indicate that CNN has more robust performance when classifying abnormal S1 and abnormal S2. Conclusions: The PGMM-DHMM model can better segment FHS and Non-FHS. The optimization of MFCC improves the classification effect of S1 and S2, and the improvement effect by the CNN classifier is significant, especially for abnormal heart sounds. The proposed algorithm is better than other algorithms at this stage.

Heart sounds classification using a novel 1-D convolutional neural network with extremely low parameter consumption

2020 ◽  
Vol 392 ◽  
pp. 153-159 ◽  
Author(s):  
Bin Xiao ◽  
Yunqiu Xu ◽  
Xiuli Bi ◽  
Junhui Zhang ◽  
Xu Ma
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Heart Sounds

scholarly journals Classification of Heart Sounds Using Convolutional Neural Network

2020 ◽  
Vol 10 (11) ◽  
pp. 3956 ◽  
Author(s):  
Fan Li ◽  
Hong Tang ◽  
Shang Shang ◽  
Klaus Mathiak ◽  
Fengyu Cong
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Signal To Noise Ratio ◽  
Class Imbalance ◽  
Heart Sounds ◽  
Feature Maps ◽  
Objective Classification ◽  
Sensitivity Specificity ◽  
Fully Connected

Heart sounds play an important role in the diagnosis of cardiac conditions. Due to the low signal-to-noise ratio (SNR), it is problematic and time-consuming for experts to discriminate different kinds of heart sounds. Thus, objective classification of heart sounds is essential. In this study, we combined a conventional feature engineering method with deep learning algorithms to automatically classify normal and abnormal heart sounds. First, 497 features were extracted from eight domains. Then, we fed these features into the designed convolutional neural network (CNN), in which the fully connected layers that are usually used before the classification layer were replaced with a global average pooling layer to obtain global information about the feature maps and avoid overfitting. Considering the class imbalance, the class weights were set in the loss function during the training process to improve the classification algorithm’s performance. Stratified five-fold cross-validation was used to evaluate the performance of the proposed method. The mean accuracy, sensitivity, specificity and Matthews correlation coefficient observed on the PhysioNet/CinC Challenge 2016 dataset were 86.8%, 87%, 86.6% and 72.1% respectively. The proposed algorithm’s performance achieves an appropriate trade-off between sensitivity and specificity.

Sign in / Sign up

Export Citation Format

Share Document