Combining sparse coding and time-domain features for heart sound classification

Whitaker, Bradley M.; Suresha, Pradyumna Byappanahalli; Liu, Chengyu; Clifford, Gari D.; Anderson, David V.

doi:10.1088/1361-6579/aa7623

Cited by 88 publications

(53 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Notable features reported for this dataset includes, time, frequency and statistical features [8], Mel-frequency Cepstral Coefficients (MFCC) [9], and Continuous Wavelet Transform (CWT) [10]. Classifiers like SVM [11], k-Nearest Neighbor (k-NN) [9], Multilayer Perceptron (MLP) [10], [12] and Random Forest [8], deep learning approaches with 1D & 2D CNNs [13], [14], and Recurrent Neural Network (RNN) [15] based architectures were employed in the challenge submissions. The winning algorithm, similar to a good number of other submissions, proposed an ensemble; a static filter front-end 1D-CNN model combined with an Adaboost-Abstain classifier using a threshold-based voting algorithm.…”

Section: Introductionmentioning

confidence: 99%

Towards Domain Invariant Heart Sound Abnormality Detection Using Learnable Filterbanks

Humayun

Ghaffarzadegan

Ansari

et al. 2020

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Objective: Cardiac auscultation is the most practiced non-invasive and cost-effective procedure for the early diagnosis of heart diseases. While machine learning based systems can aid in automatically screening patients, the robustness of these systems is affected by numerous factors including the stethoscope/sensor, environment and data collection protocol. This paper studies the adverse effect of domain variability on heart sound classification and develops strategies to address this problem. Methods: We propose a novel Convolutional Neural Network (CNN) layer, consisting of time-convolutional (tConv) units, that emulate Finite Impulse Response (FIR) filters. The filter coefficients can be updated via backpropagation and be stacked in the front-end of the network as a learnable filterbank. These filters can incorporate properties such as linear/zero phase-response and symmetry while improving robustness due to domain variability. Results: Our methods are evaluated using multi-domain heart sound recordings obtained from publicly available phonocardiogram (PCG) datasets. On multi-domain evaluation tasks, the proposed method surpasses the top-scoring systems found in the literature for heart sound classification. Our systems achieved relative improvements of up to 11.84% in terms of a modified accuracy (Macc) metric, compared to state-of-theart methods. Conclusion: The results demonstrate the effectiveness of the proposed learnable filterbank CNN architecture in achieving robustness towards sensor/domain variability in PCG signals. Significance: The proposed methods pave the way for deploying automated cardiac screening systems in diversified and underserved communities.

show abstract

Section: Introductionmentioning

confidence: 99%

Towards Domain Invariant Heart Sound Abnormality Detection Using Learnable Filterbanks

Humayun

Ghaffarzadegan

Ansari

et al. 2020

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

show abstract

“…Tang et al [19] derived the multimodal features based on the HSMM segmentation method and predicted the abnormality of heart sounds using the SVM classifier. Bradley et al [11] extracted the features using sparse coding and time domain followed by classification based on the SVM classifier. Messner et al [16] segmented heart sounds based on a deep recurrent neural network with an average F 1 score of 96%.…”

Section: Introductionmentioning

confidence: 99%

Short unsegmented PCG classification based on ensemble classifier

Singh¹,

Majumder²

2020

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Diseases associated with the heart are one of the main reasons of death worldwide. Hence, early examination of the heart is important. For analysis of cardiac disorders, a study of heart sounds is a crucial and beneficial approach.Still, automated classification of heart sounds is a challenging task that mainly depends on segmentation of heart sounds and derivation of features using segmented samples. In the literature available for PCG classification provided by PhysioNet/CinC Challenge 2016, most of the research has focused on enhancing the accuracy of the classification model based on complicated segmentation processes and has failed to improve the sensitivity. In this paper, we present an automated heart sound classification by eliminating the segmentation steps using multidomain features, which results in enhanced sensitivity. The study is based on homomorphic envelogram, mel frequency cepstral coefficient (MFCC), power spectral density (PSD), and multidomain feature extraction. The extracted features are trained using the 5-fold cross-validation method based on an ensemble boosting algorithm over 100 independent iterations. Our proposed design is evaluated using public datasets published in PhysioNet/Computers in Cardiology Challenge 2016. Accuracy of 92.47% with improved sensitivity of 94.08% and specificity of 91.95% is achieved using our model. The output performance proves that our proposed model offers superior performance results.

show abstract

“…Plesinger et al [9] proposed a novel segmentation method, a histogram based feature selection method and parameterized sigmoid functions per feature, to discriminate between classes. Various machine learning algorithms including SVM [10], k-Nearest Neighbor (k-NN) [7], Multilayer Perceptron (MLP) [11], [12], Random Forest [6], 1D [13] and 2D CNNs [8], and Recurrent Neural Network (RNN) [14] were employed in the challenge. A good number of submissions used an ensemble of classifiers with a voting algorithm [6], [11], [12], [13].…”

Section: Introductionmentioning

confidence: 99%

Learning Front-end Filter-bank Parameters using Convolutional Neural Networks for Abnormal Heart Sound Detection

Humayun

Ghaffarzadegan

Feng

et al. 2018

2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

Automatic heart sound abnormality detection can play a vital role in the early diagnosis of heart diseases, particularly in low-resource settings. The state-of-the-art algorithms for this task utilize a set of Finite Impulse Response (FIR) band-pass filters as a front-end followed by a Convolutional Neural Network (CNN) model. In this work, we propound a novel CNN architecture that integrates the front-end bandpass filters within the network using time-convolution (tConv) layers, which enables the FIR filter-bank parameters to become learnable. Different initialization strategies for the learnable filters, including random parameters and a set of predefined FIR filter-bank coefficients, are examined. Using the proposed tConv layers, we add constraints to the learnable FIR filters to ensure linear and zero phase responses. Experimental evaluations are performed on a balanced 4-fold cross-validation task prepared using the PhysioNet/CinC 2016 dataset. Results demonstrate that the proposed models yield superior performance compared to the state-of-the-art system, while the linear phase FIR filterbank method provides an absolute improvement of 9.54% over the baseline in terms of an overall accuracy metric.

show abstract

Combining sparse coding and time-domain features for heart sound classification

Cited by 88 publications

References 23 publications

Towards Domain Invariant Heart Sound Abnormality Detection Using Learnable Filterbanks

Towards Domain Invariant Heart Sound Abnormality Detection Using Learnable Filterbanks

Short unsegmented PCG classification based on ensemble classifier

Learning Front-end Filter-bank Parameters using Convolutional Neural Networks for Abnormal Heart Sound Detection

Contact Info

Product

Resources

About