Show simple item record

dc.contributor.authorNoman, Fuad
dc.contributor.authorTing, Chee-Ming
dc.contributor.authorSalleh, Sh-Hussain
dc.contributor.authorOmbao, Hernando
dc.date.accessioned2019-07-10T13:27:39Z
dc.date.available2019-07-10T13:27:39Z
dc.date.issued2019-04-17
dc.identifier.citationNoman, F., Ting, C.-M., Salleh, S.-H., & Ombao, H. (2019). Short-segment Heart Sound Classification Using an Ensemble of Deep Convolutional Neural Networks. ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). doi:10.1109/icassp.2019.8682668
dc.identifier.doi10.1109/ICASSP.2019.8682668
dc.identifier.urihttp://hdl.handle.net/10754/655968
dc.description.abstractThis paper proposes a framework based on deep convolutional neural networks (CNNs) for automatic heart sound classification using short-segments of individual heart beats. We design a 1D-CNN that directly learns features from raw heart-sound signals, and a 2D-CNN that takes inputs of two-dimensional time-frequency feature maps based on Mel-frequency cepstral coefficients. We further develop a time-frequency CNN ensemble (TF-ECNN) combining the 1D-CNN and 2D-CNN based on score-level fusion of the class probabilities. On the large PhysioNet CinC challenge 2016 database, the proposed CNN models outperformed traditional classifiers based on support vector machine and hidden Markov models with various hand-crafted time- and frequency-domain features. Best classification scores with 89.22% accuracy and 89.94% sensitivity were achieved by the ECNN, and 91.55% specificity and 88.82% modified accuracy by the 2D-CNN alone on the test set.
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.relation.urlhttps://ieeexplore.ieee.org/document/8682668/
dc.relation.urlhttps://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8682668
dc.relation.urlhttp://arxiv.org/pdf/1810.11573
dc.rightsArchived with thanks to IEEE
dc.subjectHeart sound classification
dc.subjectconvolutional neural network
dc.subjectensemble classifiers
dc.titleShort-segment Heart Sound Classification Using an Ensemble of Deep Convolutional Neural Networks
dc.typeConference Paper
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentStatistics
dc.contributor.departmentStatistics Program
dc.conference.date12-17 May 2019
dc.conference.nameICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
dc.conference.locationBrighton, United Kingdom
dc.eprint.versionPre-print
dc.contributor.institutionSchool of Biomedical Engineering & Health Sciences, Universiti Teknologi Malaysia, Malaysia
dc.identifier.arxivid1810.11573
kaust.personTing, Chee-Ming
kaust.personOmbao, Hernando
refterms.dateFOA2019-12-11T08:28:40Z


Files in this item

Thumbnail
Name:
Conference Paperfile1.pdf
Size:
261.1Kb
Format:
PDF
Description:
Pre-print

This item appears in the following Collection(s)

Show simple item record