Heart Sound Anomaly and Quality Detection using Ensemble of Neural Networks without Segmentation. Zabihi, M., Bahrami Rad, A., Kiranyaz, S., Gabbouj, M., & K. Katsaggelos, A. In Computing in Cardiology, volume 43, pages 613–616, sep, 2016. Paper doi abstract bibtex Phonocardiogram (PCG) signal is used as a diagnostic test in ambulatory monitoring in order to evaluate the heart hemodynamic status and to detect a cardiovascular disease. The objective of this study is to develop an automatic classification method for anomaly (normal vs. abnormal) and quality (good vs. bad) detection of PCG recordings without segmentation. For this purpose, a subset of 18 features is selected among 40 features based on a wrapper feature selection scheme. These features are extracted from time, frequency, and time-frequency domains without any segmentation. The selected features are fed into an ensemble of 20 feedforward neural networks for classification task. The proposed algorithm achieved the overall score of 91.50% (94.23% sensitivity and 88.76% specificity) and 85.90% (86.91% sensitivity and 84.90% specificity) on the train and unseen test datasets, respectively. The proposed method got the second best score in the PhysioNet/CinC Challenge 2016.
@inproceedings{Morteza2016,
abstract = {Phonocardiogram (PCG) signal is used as a diagnostic test in ambulatory monitoring in order to evaluate the heart hemodynamic status and to detect a cardiovascular disease. The objective of this study is to develop an automatic classification method for anomaly (normal vs. abnormal) and quality (good vs. bad) detection of PCG recordings without segmentation. For this purpose, a subset of 18 features is selected among 40 features based on a wrapper feature selection scheme. These features are extracted from time, frequency, and time-frequency domains without any segmentation. The selected features are fed into an ensemble of 20 feedforward neural networks for classification task. The proposed algorithm achieved the overall score of 91.50% (94.23% sensitivity and 88.76% specificity) and 85.90% (86.91% sensitivity and 84.90% specificity) on the train and unseen test datasets, respectively. The proposed method got the second best score in the PhysioNet/CinC Challenge 2016.},
author = {Zabihi, Morteza and {Bahrami Rad}, Ali and Kiranyaz, Serkan and Gabbouj, Moncef and {K. Katsaggelos}, Aggelos},
booktitle = {Computing in Cardiology},
doi = {10.22489/CinC.2016.180-213},
isbn = {9781509008964},
issn = {2325887X},
month = {sep},
pages = {613--616},
title = {{Heart Sound Anomaly and Quality Detection using Ensemble of Neural Networks without Segmentation}},
url = {http://www.cinc.org/archives/2016/pdf/180-213.pdf},
volume = {43},
year = {2016}
}
Downloads: 0
{"_id":"NJDq7sQaqCFWyJKXW","bibbaseid":"zabihi-bahramirad-kiranyaz-gabbouj-kkatsaggelos-heartsoundanomalyandqualitydetectionusingensembleofneuralnetworkswithoutsegmentation-2016","author_short":["Zabihi, M.","Bahrami Rad, A.","Kiranyaz, S.","Gabbouj, M.","K. Katsaggelos, A."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","abstract":"Phonocardiogram (PCG) signal is used as a diagnostic test in ambulatory monitoring in order to evaluate the heart hemodynamic status and to detect a cardiovascular disease. The objective of this study is to develop an automatic classification method for anomaly (normal vs. abnormal) and quality (good vs. bad) detection of PCG recordings without segmentation. For this purpose, a subset of 18 features is selected among 40 features based on a wrapper feature selection scheme. These features are extracted from time, frequency, and time-frequency domains without any segmentation. The selected features are fed into an ensemble of 20 feedforward neural networks for classification task. The proposed algorithm achieved the overall score of 91.50% (94.23% sensitivity and 88.76% specificity) and 85.90% (86.91% sensitivity and 84.90% specificity) on the train and unseen test datasets, respectively. The proposed method got the second best score in the PhysioNet/CinC Challenge 2016.","author":[{"propositions":[],"lastnames":["Zabihi"],"firstnames":["Morteza"],"suffixes":[]},{"propositions":[],"lastnames":["Bahrami Rad"],"firstnames":["Ali"],"suffixes":[]},{"propositions":[],"lastnames":["Kiranyaz"],"firstnames":["Serkan"],"suffixes":[]},{"propositions":[],"lastnames":["Gabbouj"],"firstnames":["Moncef"],"suffixes":[]},{"propositions":[],"lastnames":["K. Katsaggelos"],"firstnames":["Aggelos"],"suffixes":[]}],"booktitle":"Computing in Cardiology","doi":"10.22489/CinC.2016.180-213","isbn":"9781509008964","issn":"2325887X","month":"sep","pages":"613–616","title":"Heart Sound Anomaly and Quality Detection using Ensemble of Neural Networks without Segmentation","url":"http://www.cinc.org/archives/2016/pdf/180-213.pdf","volume":"43","year":"2016","bibtex":"@inproceedings{Morteza2016,\nabstract = {Phonocardiogram (PCG) signal is used as a diagnostic test in ambulatory monitoring in order to evaluate the heart hemodynamic status and to detect a cardiovascular disease. The objective of this study is to develop an automatic classification method for anomaly (normal vs. abnormal) and quality (good vs. bad) detection of PCG recordings without segmentation. For this purpose, a subset of 18 features is selected among 40 features based on a wrapper feature selection scheme. These features are extracted from time, frequency, and time-frequency domains without any segmentation. The selected features are fed into an ensemble of 20 feedforward neural networks for classification task. The proposed algorithm achieved the overall score of 91.50% (94.23% sensitivity and 88.76% specificity) and 85.90% (86.91% sensitivity and 84.90% specificity) on the train and unseen test datasets, respectively. The proposed method got the second best score in the PhysioNet/CinC Challenge 2016.},\nauthor = {Zabihi, Morteza and {Bahrami Rad}, Ali and Kiranyaz, Serkan and Gabbouj, Moncef and {K. Katsaggelos}, Aggelos},\nbooktitle = {Computing in Cardiology},\ndoi = {10.22489/CinC.2016.180-213},\nisbn = {9781509008964},\nissn = {2325887X},\nmonth = {sep},\npages = {613--616},\ntitle = {{Heart Sound Anomaly and Quality Detection using Ensemble of Neural Networks without Segmentation}},\nurl = {http://www.cinc.org/archives/2016/pdf/180-213.pdf},\nvolume = {43},\nyear = {2016}\n}\n","author_short":["Zabihi, M.","Bahrami Rad, A.","Kiranyaz, S.","Gabbouj, M.","K. Katsaggelos, A."],"key":"Morteza2016","id":"Morteza2016","bibbaseid":"zabihi-bahramirad-kiranyaz-gabbouj-kkatsaggelos-heartsoundanomalyandqualitydetectionusingensembleofneuralnetworkswithoutsegmentation-2016","role":"author","urls":{"Paper":"http://www.cinc.org/archives/2016/pdf/180-213.pdf"},"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://sites.northwestern.edu/ivpl/files/2023/06/IVPL_Updated_publications-1.bib","dataSources":["D8k2SxfC5dKNRFgro","7Dwzbxq93HWrJEhT6","qhF8zxmGcJfvtdeAg","fvDEHD49E2ZRwE3fb","H7crv8NWhZup4d4by","DHqokWsryttGh7pJE","vRJd4wNg9HpoZSMHD","sYxQ6pxFgA59JRhxi","w2WahSbYrbcCKBDsC","XasdXLL99y5rygCmq","3gkSihZQRfAD2KBo3","t5XMbyZbtPBo4wBGS","bEpHM2CtrwW2qE8FP","teJzFLHexaz5AQW5z"],"keywords":[],"search_terms":["heart","sound","anomaly","quality","detection","using","ensemble","neural","networks","without","segmentation","zabihi","bahrami rad","kiranyaz","gabbouj","k. katsaggelos"],"title":"Heart Sound Anomaly and Quality Detection using Ensemble of Neural Networks without Segmentation","year":2016}