Fengquan Dong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Fengquan Dong has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
Baoyi Li
College of Life Science and Oceanography, ShenZhen University, Shenzhen, China
2 shared publications- Haiying Li
Department of Cardiology, Shenzhen University General Hospital, Shenzhen, China
2 shared publications Xiaowan Jin
College of Life Science and Oceanography, ShenZhen University, Shenzhen, China
2 shared publicationsXiaozheng Li
College of Life Science and Oceanography, ShenZhen University, Shenzhen, China
2 shared publications- Alice Baird
EIHW Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Augsburg, Germany
1 shared publication - Bin Hu
Key Laboratory of Brain Health Intelligent Evaluation and Intervention, Ministry of Education, Beijing Institute of Technology, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 1 January 2024
- Published by American Association for the Advancement of Science (AAAS) in Cyborg and Bionic Systems
- Vol. 5, 0075
Learning Representations from Heart Sound: A Comparative Study on Shallow and Deep Models
Leveraging the power of artificial intelligence to facilitate an automatic analysis and monitoring of heart sounds has increasingly attracted tremendous efforts in the past decade. Nevertheless, lacking on standard open-access database made it difficult to maintain a sustainable and comparable research before the first release of the PhysioNet CinC Challenge Dataset. However, inconsistent standards on data collection, annotation, and partition are still restraining a fair and efficient comparison between different works. To this line, we introduced and benchmarked a first version of the Heart Sounds Shenzhen (HSS) corpus. Motivated and inspired by the previous works based on HSS, we redefined the tasks and make a comprehensive investigation on shallow and deep models in this study. First, we segmented the heart sound recording into shorter recordings (10 s), which makes it more similar to the human auscultation case. Second, we redefined the classification tasks. Besides using the 3 class categories (normal, moderate, and mild/severe) adopted in HSS, we added a binary classification task in this study, i.e., normal and abnormal. In this work, we provided detailed benchmarks based on both the classic machine learning and the state-of-the-art deep learning technologies, which are reproducible by using open-source toolkits. Last but not least, we analyzed the feature contributions of best performance achieved by the benchmark to make the results more convincing and interpretable.
- 1 January 2024
- Published by American Association for the Advancement of Science (AAAS) in Cyborg and Bionic Systems
- Vol. 5, 0075
Open AccessLearning Representations from Heart Sound: A Comparative Study on Shallow and Deep Models
Leveraging the power of artificial intelligence to facilitate an automatic analysis and monitoring of heart sounds has increasingly attracted tremendous efforts in the past decade. Nevertheless, lacking on standard open-access database made it difficult to maintain a sustainable and comparable research before the first release of the PhysioNet CinC Challenge Dataset. However, inconsistent standards on data collection, annotation, and partition are still restraining a fair and efficient comparison between different works. To this line, we introduced and benchmarked a first version of the Heart Sounds Shenzhen (HSS) corpus. Motivated and inspired by the previous works based on HSS, we redefined the tasks and make a comprehensive investigation on shallow and deep models in this study. First, we segmented the heart sound recording into shorter recordings (10 s), which makes it more similar to the human auscultation case. Second, we redefined the classification tasks. Besides using the 3 class categories (normal, moderate, and mild/severe) adopted in HSS, we added a binary classification task in this study, i.e., normal and abnormal. In this work, we provided detailed benchmarks based on both the classic machine learning and the state-of-the-art deep learning technologies, which are reproducible by using open-source toolkits. Last but not least, we analyzed the feature contributions of best performance achieved by the benchmark to make the results more convincing and interpretable.
- Retracted
- 17 January 2020
- Published by Taylor & Francis in Journal of Coordination Chemistry
- Vol. 73 (2) , 297-306
RETRACTED ARTICLE: A new Cu(II) coordination polymer with helical double chains: crystal structure, molecular docking, and protective activity on coronary heart disease by reducing oxidative stress
A new layered coordination polymer [Cu(ox)(bib)]n (1, ox = C2O42−; bib = 1,4-bis(imidazol)butane) with helical double chains has been prepared under hydrothermal conditions and characterized by elemental analysis as well as single crystal X-ray diffraction. A green grinding method was used to produce nanorods of 1 (denoted as nano 1 hereafter) with good water dispersibility. To evaluate the protective effect of nano 1 in vivo, the coronary heart disease (CHD) rat model was constructed and nano 1 was given for treatment. The promotion of the cardiac function was measured by the left ventricular ejection fraction (LVEF) and systolic internal diameter (LVID) values. The anti-oxidative effect of nano 1 was determined by reactive oxygen species (ROS) detection. The binding interaction of 1 with the probe protein has been further examined by molecular docking simulation.
- 17 January 2020
- Published by Taylor & Francis in Journal of Coordination Chemistry
- Vol. 73 (2) , 297-306
RetractedRETRACTED ARTICLE: A new Cu(II) coordination polymer with helical double chains: crystal structure, molecular docking, and protective activity on coronary heart disease by reducing oxidative stress
A new layered coordination polymer [Cu(ox)(bib)]n (1, ox = C2O42−; bib = 1,4-bis(imidazol)butane) with helical double chains has been prepared under hydrothermal conditions and characterized by elemental analysis as well as single crystal X-ray diffraction. A green grinding method was used to produce nanorods of 1 (denoted as nano 1 hereafter) with good water dispersibility. To evaluate the protective effect of nano 1 in vivo, the coronary heart disease (CHD) rat model was constructed and nano 1 was given for treatment. The promotion of the cardiac function was measured by the left ventricular ejection fraction (LVEF) and systolic internal diameter (LVID) values. The anti-oxidative effect of nano 1 was determined by reactive oxygen species (ROS) detection. The binding interaction of 1 with the probe protein has been further examined by molecular docking simulation.
- 22 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 24 (7) , 2082-2092
Machine Listening for Heart Status Monitoring: Introducing and Benchmarking HSS—The Heart Sounds Shenzhen Corpus
Auscultation of the heart is a widely studied technique, which requires precise hearing from practitioners as a means of distinguishing subtle differences in heart-beat rhythm. This technique is popular due to its non-invasive nature, and can be an early diagnosis aid for a range of cardiac conditions. Machine listening approaches can support this process, monitoring continuously and allowing for a representation of both mild and chronic heart conditions. Despite this potential, relevant databases and benchmark studies are scarce. In this paper, we introduce our publicly accessible database, the Heart Sounds Shenzhen Corpus (HSS), which was first released during the recent INTERSPEECH 2018 ComParE Heart Sound sub-challenge. Additionally, we provide a survey of machine learning work in the area of heart sound recognition, as well as a benchmark for HSS utilising standard acoustic features and machine learning models. At best our support vector machine with Log Mel features achieves 49.7% unweighted average recall on a three category task (normal, mild, moderate/severe).
- 22 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 24 (7) , 2082-2092
Machine Listening for Heart Status Monitoring: Introducing and Benchmarking HSS—The Heart Sounds Shenzhen Corpus
Auscultation of the heart is a widely studied technique, which requires precise hearing from practitioners as a means of distinguishing subtle differences in heart-beat rhythm. This technique is popular due to its non-invasive nature, and can be an early diagnosis aid for a range of cardiac conditions. Machine listening approaches can support this process, monitoring continuously and allowing for a representation of both mild and chronic heart conditions. Despite this potential, relevant databases and benchmark studies are scarce. In this paper, we introduce our publicly accessible database, the Heart Sounds Shenzhen Corpus (HSS), which was first released during the recent INTERSPEECH 2018 ComParE Heart Sound sub-challenge. Additionally, we provide a survey of machine learning work in the area of heart sound recognition, as well as a benchmark for HSS utilising standard acoustic features and machine learning models. At best our support vector machine with Log Mel features achieves 49.7% unweighted average recall on a three category task (normal, mild, moderate/severe).
- Retracted
- 21 October 2019
- Published by Wiley in ChemistrySelect
- Vol. 4 (39) , 11500-11505
Retracted: A New Mixed‐Ligand Coordination Polymer: Crystal Structure, Molecular Docking and Alleviating Effect on Myocarditis by Inhibiting the NLRP3‐Caspase‐1 Pathway in Cardiomyocytes
A new mixed‐ligand coordination polymer {[Co(Hbidc)(2,2′‐bpy)(H 2 O) 2 ] ⋅ 1.5H 2 O} n ( 1 ) has been successfully prepared by the reaction of Co(NO 3 ) 2 ⋅6H 2 O, 2, 2′‐bipyridine (2,2′‐bpy) as well as benzimidazole‐5, 6‐dicarboxylic acid (H 3 bidc) in the mixed solvent of water and DMA under solvothermal conditions. Furthermore, a mechanical grinding method was used to produce the nanostructure 1 with the average size of 263 nm. The integrity of H9 C2 cardiomyocytes cell membrane after nano 1 treatment was detected by LDH detection. After nano 1 incubation, the inflammatory level in the H9 C2 cardiomyocytes was evaluated by western blot and ELISA measurement. In addition, the ROS accumulation in H9 C2 cardiomyocytes after nano 1 treatment was determined by H2DCFDA detection assay. Finally, possible interactions between the studied complex 1 and protein has been probed using molecular docking simulation.
- 21 October 2019
- Published by Wiley in ChemistrySelect
- Vol. 4 (39) , 11500-11505
RetractedRetracted: A New Mixed‐Ligand Coordination Polymer: Crystal Structure, Molecular Docking and Alleviating Effect on Myocarditis by Inhibiting the NLRP3‐Caspase‐1 Pathway in Cardiomyocytes
A new mixed‐ligand coordination polymer {[Co(Hbidc)(2,2′‐bpy)(H 2 O) 2 ] ⋅ 1.5H 2 O} n ( 1 ) has been successfully prepared by the reaction of Co(NO 3 ) 2 ⋅6H 2 O, 2, 2′‐bipyridine (2,2′‐bpy) as well as benzimidazole‐5, 6‐dicarboxylic acid (H 3 bidc) in the mixed solvent of water and DMA under solvothermal conditions. Furthermore, a mechanical grinding method was used to produce the nanostructure 1 with the average size of 263 nm. The integrity of H9 C2 cardiomyocytes cell membrane after nano 1 treatment was detected by LDH detection. After nano 1 incubation, the inflammatory level in the H9 C2 cardiomyocytes was evaluated by western blot and ELISA measurement. In addition, the ROS accumulation in H9 C2 cardiomyocytes after nano 1 treatment was determined by H2DCFDA detection assay. Finally, possible interactions between the studied complex 1 and protein has been probed using molecular docking simulation.