Feature Extraction and Classification of Phonocardiograms using Convolutional Neural Networks

Chakraborty, Devjyoti; Bhattacharya, Snehangshu; Thakur, Ayush; Gosthipaty, Aritra Roy; Datta, Chira

doi:10.1109/icce50343.2020.9290565

Cited by 7 publications

(10 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Whereas for the deep learning model, the calculation of the Mel spectrogram and signal quality are already optimised by using inbuilt MATLAB functions, so minimal improvements would be expected for optimising the code. However, YAMNet did require the upsampling of the recordings to 16 For heart sound quality classification, the removal of slow features resulted in only minor changes in results (Table 3). As only a maximum of 15 features was used, only the autocorrelation sample entropy feature was removed, which had a comparable feature selection score to other features in the top 20, meaning the removal of that feature was minor.…”

Section: Discussionmentioning

confidence: 99%

“…Furthermore, due to less research in lung signal quality analysis, there are fewer hand-crafted features, resulting in inferior results, in comparison to heart signal quality analysis [6]. The development of deep learning models, which take the timefrequency representation of the audio chest sound signal, offers the potential for removing the need for hand-crafted features for the estimation of signal quality [16].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Real-Time Multi-Level Neonatal Heart and Lung Sound Quality Assessment for Telehealth Applications

et al. 2022

View full text Add to dashboard Cite

In this study, a new method is proposed to assess heart and lung signal quality objectively and automatically on a 5-level scale in real-time, and to assess the effect of signal quality on vital sign estimation. A total of 207 10 s long chest sounds were taken from 119 preterm and full-term babies. Thirty of the recordings from ten subjects were obtained with synchronous vital signs from the Neonatal Intensive Care Unit (NICU). As a reference, seven annotators independently assessed the signal quality. For automatic quality classification, 400 features were extracted from the chest sounds. After feature ranking and selection, class balancing, and hyperparameter optimization, a variety of multi-class and ordinal classification and regression algorithms were trained. Then, heart rate and breathing rate were automatically estimated from the chest sounds. For the deep learning model, YAMNet, a deep convolutional neural network pre-trained on the AudioSet-Youtube corpus for sound classification was used. After modification of the final output layers of the neural network and class balancing, transfer learning was applied to YAMNet for heart and lung signal quality classification. The results of subject-wise leave-one-out cross-validation show that the best-performing models had a balanced accuracy of 56.8% and 51.2% for heart and lung qualities, respectively. The best-performing models for real-time analysis (<200 ms) had a balanced accuracy of 56.7% and 46.3%, respectively. Our experimental results underscore that increasing the signal quality leads to a reduction in vital sign error.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Real-Time Multi-Level Neonatal Heart and Lung Sound Quality Assessment for Telehealth Applications

et al. 2022

View full text Add to dashboard Cite

show abstract

“…An obvious limitation of this approach is the need for expert operators to classify each single signal recording. Also in 2020, Chakraborty et al [37] published a work in which they used a convolutional neural network fed with the spectrogram of the PCG signal to evaluate the signal quality. In the same year, a paper by Grooby et al [38] proposed the extraction of as many as 187 features from neonatal PCG signals and classified their quality using an ensemble classifier combining a support vector machine, a decision tree, K-nearest neighbors, and a Gaussian Naïve Bayes classifier.…”

Section: Discussionmentioning

confidence: 99%

“…Finally, it should be highlighted that more than half of the cited works related to PCG quality assessment [11,12,14,19,[31][32][33][34][35][36][37][38]44] were published in the last 3 years, implying that this topic is gaining importance within the scientific community.…”

Section: Discussionmentioning

confidence: 99%

Automated Assessment of the Quality of Phonocardographic Recordings through Signal-to-Noise Ratio for Home Monitoring Applications

Giordano

Rosati

Knaflitz

2021

Sensors

View full text Add to dashboard Cite

The signal quality limits the applicability of phonocardiography at the patients’ domicile. This work proposes the signal-to-noise ratio of the recorded signal as its main quality metrics. Moreover, we define the minimum acceptable values of the signal-to-noise ratio that warrantee an accuracy of the derived parameters acceptable in clinics. We considered 25 original heart sounds recordings, which we corrupted by adding noise to decrease their signal-to-noise ratio. We found that a signal-to-noise ratio equal to or higher than 14 dB warrants an uncertainty of the estimate of the valve closure latencies below 1 ms. This accuracy is higher than that required by most clinical applications. We validated the proposed method against a public database, obtaining results comparable to those obtained on our sample population. In conclusion, we defined (a) the signal-to-noise ratio of the phonocardiographic signal as the preferred metric to evaluate its quality and (b) the minimum values of the signal-to-noise ratio required to obtain an uncertainty of the latency of heart sound components compatible with clinical applications. We believe these results are crucial for the development of home monitoring systems aimed at preventing acute episodes of heart failure and that can be safely operated by naïve users.

show abstract

“…The most-cited heart sound dataset is the PhysioNet Heart Sound Database released in 2016 which contains over 2400 heart sound recordings from nearly 1300 healthy volunteers and patients [19]. The dataset has stimulated studies on algorithms for automatic segmentation, feature extraction and classification of heart sounds [20][21][22]. All these three tasks can be achieved using machine learning, which is discussed in Section 3.…”

Section: Figure 1 Trends Of Heart Sound Measurement Devices and Resea...mentioning

confidence: 99%

Environment and participation of adolescents with autism spectrum disorder

Krieger

View full text Add to dashboard Cite

published version features the final layout of the paper including the volume, issue and page numbers. Link to publication General rightsCopyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights.• Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal.If the publication is distributed under the terms of Article 25fa of the Dutch Copyright Act, indicated by the "Taverne" license above, please follow below link for the End User

show abstract

Feature Extraction and Classification of Phonocardiograms using Convolutional Neural Networks

Cited by 7 publications

References 5 publications

Real-Time Multi-Level Neonatal Heart and Lung Sound Quality Assessment for Telehealth Applications

Real-Time Multi-Level Neonatal Heart and Lung Sound Quality Assessment for Telehealth Applications

Automated Assessment of the Quality of Phonocardographic Recordings through Signal-to-Noise Ratio for Home Monitoring Applications

Environment and participation of adolescents with autism spectrum disorder

Contact Info

Product

Resources

About