Internal structure of GRU [35].
<div><p>Cardiac auscultation requires the mechanical vibrations occurring on the body’s surface, which carries a range of sound frequencies. These sounds are generated by the movement and pulsation of different cardiac structures as they facilitate blood circulation. Subsequently, these...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , , |
| Published: |
2025
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1852021333302444032 |
|---|---|
| author | Hiam Alquran (17636906) |
| author2 | Yazan Al-Issa (18934001) Mohammed Alsalatie (21087775) Shefa Tawalbeh (21087778) |
| author2_role | author author author |
| author_facet | Hiam Alquran (17636906) Yazan Al-Issa (18934001) Mohammed Alsalatie (21087775) Shefa Tawalbeh (21087778) |
| author_role | author |
| dc.creator.none.fl_str_mv | Hiam Alquran (17636906) Yazan Al-Issa (18934001) Mohammed Alsalatie (21087775) Shefa Tawalbeh (21087778) |
| dc.date.none.fl_str_mv | 2025-04-14T20:08:29Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0320297.g005 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/figure/Internal_structure_of_GRU_35_/28791403 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Cell Biology Biotechnology Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified proposed approach achieved mechanical vibrations occurring including digital filtering facilitate blood circulation empirical mode decomposition different cardiac structures deep learning algorithms cardiology challenge 2016 body &# 8217 lub sound ), dub sound ), segmenting phonocardiogram signals circor digiscope phonocardiogram circor digiscop dataset deep learning models pcg signal underwent gru ), bidirectional pcg signal mithsdb ), sound frequencies pcg ). mithsdb dataset three well term memory systolic region study compared software tool segmentation process processing steps paper represents namely s1 massachusetts institute known datasets highest level first investigation directional long diastolic region aforementioned datasets 5 %. |
| dc.title.none.fl_str_mv | Internal structure of GRU [35]. |
| dc.type.none.fl_str_mv | Image Figure info:eu-repo/semantics/publishedVersion image |
| description | <div><p>Cardiac auscultation requires the mechanical vibrations occurring on the body’s surface, which carries a range of sound frequencies. These sounds are generated by the movement and pulsation of different cardiac structures as they facilitate blood circulation. Subsequently, these sounds are identified as phonocardiogram (PCG). In this research, deep learning models, namely gated recurrent neural Network (GRU), Bidirectional-GRU, and Bi-directional long-term memory (BILSTM) are applied separately to segment four specific regions within the PCG signal, namely S1 (lub sound), the systolic region, S2 (dub sound), and the diastolic region. These models are applied to three well-known datasets: PhysioNet/Computing in Cardiology Challenge 2016, Massachusetts Institute of Technology (MITHSDB), and CirCor DigiScope Phonocardiogram.The PCG signal underwent a series of pre-processing steps, including digital filtering and empirical mode decomposition, after then deep learning algorithms were applied to achieve the highest level of segmentation accuracy. Remarkably, the proposed approach achieved an accuracy of 97.2% for the PhysioNet dataset and 96.98% for the MITHSDB dataset. Notably, this paper represents the first investigation into the segmentation process of the CirCor DigiScop dataset, achieving an accuracy of 92.5%. This study compared the performance of various deep learning models using the aforementioned datasets, demonstrating its efficiency, accuracy, and reliability as a software tool in healthcare settings.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_d1fc21b28635f9a425be6902384f1908 |
| identifier_str_mv | 10.1371/journal.pone.0320297.g005 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/28791403 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Internal structure of GRU [35].Hiam Alquran (17636906)Yazan Al-Issa (18934001)Mohammed Alsalatie (21087775)Shefa Tawalbeh (21087778)Cell BiologyBiotechnologySpace ScienceBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedproposed approach achievedmechanical vibrations occurringincluding digital filteringfacilitate blood circulationempirical mode decompositiondifferent cardiac structuresdeep learning algorithmscardiology challenge 2016body &# 8217lub sound ),dub sound ),segmenting phonocardiogram signalscircor digiscope phonocardiogramcircor digiscop datasetdeep learning modelspcg signal underwentgru ), bidirectionalpcg signalmithsdb ),sound frequenciespcg ).mithsdb datasetthree wellterm memorysystolic regionstudy comparedsoftware toolsegmentation processprocessing stepspaper representsnamely s1massachusetts instituteknown datasetshighest levelfirst investigationdirectional longdiastolic regionaforementioned datasets5 %.<div><p>Cardiac auscultation requires the mechanical vibrations occurring on the body’s surface, which carries a range of sound frequencies. These sounds are generated by the movement and pulsation of different cardiac structures as they facilitate blood circulation. Subsequently, these sounds are identified as phonocardiogram (PCG). In this research, deep learning models, namely gated recurrent neural Network (GRU), Bidirectional-GRU, and Bi-directional long-term memory (BILSTM) are applied separately to segment four specific regions within the PCG signal, namely S1 (lub sound), the systolic region, S2 (dub sound), and the diastolic region. These models are applied to three well-known datasets: PhysioNet/Computing in Cardiology Challenge 2016, Massachusetts Institute of Technology (MITHSDB), and CirCor DigiScope Phonocardiogram.The PCG signal underwent a series of pre-processing steps, including digital filtering and empirical mode decomposition, after then deep learning algorithms were applied to achieve the highest level of segmentation accuracy. Remarkably, the proposed approach achieved an accuracy of 97.2% for the PhysioNet dataset and 96.98% for the MITHSDB dataset. Notably, this paper represents the first investigation into the segmentation process of the CirCor DigiScop dataset, achieving an accuracy of 92.5%. This study compared the performance of various deep learning models using the aforementioned datasets, demonstrating its efficiency, accuracy, and reliability as a software tool in healthcare settings.</p></div>2025-04-14T20:08:29ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0320297.g005https://figshare.com/articles/figure/Internal_structure_of_GRU_35_/28791403CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/287914032025-04-14T20:08:29Z |
| spellingShingle | Internal structure of GRU [35]. Hiam Alquran (17636906) Cell Biology Biotechnology Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified proposed approach achieved mechanical vibrations occurring including digital filtering facilitate blood circulation empirical mode decomposition different cardiac structures deep learning algorithms cardiology challenge 2016 body &# 8217 lub sound ), dub sound ), segmenting phonocardiogram signals circor digiscope phonocardiogram circor digiscop dataset deep learning models pcg signal underwent gru ), bidirectional pcg signal mithsdb ), sound frequencies pcg ). mithsdb dataset three well term memory systolic region study compared software tool segmentation process processing steps paper represents namely s1 massachusetts institute known datasets highest level first investigation directional long diastolic region aforementioned datasets 5 %. |
| status_str | publishedVersion |
| title | Internal structure of GRU [35]. |
| title_full | Internal structure of GRU [35]. |
| title_fullStr | Internal structure of GRU [35]. |
| title_full_unstemmed | Internal structure of GRU [35]. |
| title_short | Internal structure of GRU [35]. |
| title_sort | Internal structure of GRU [35]. |
| topic | Cell Biology Biotechnology Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified proposed approach achieved mechanical vibrations occurring including digital filtering facilitate blood circulation empirical mode decomposition different cardiac structures deep learning algorithms cardiology challenge 2016 body &# 8217 lub sound ), dub sound ), segmenting phonocardiogram signals circor digiscope phonocardiogram circor digiscop dataset deep learning models pcg signal underwent gru ), bidirectional pcg signal mithsdb ), sound frequencies pcg ). mithsdb dataset three well term memory systolic region study compared software tool segmentation process processing steps paper represents namely s1 massachusetts institute known datasets highest level first investigation directional long diastolic region aforementioned datasets 5 %. |