Multiclass Classification of Cardiac Arrhythmia Using Improved Feature Selection and SVM Invariants
Arrhythmia is considered a life-threatening disease causing serious health issues in patients, when left untreated. An early diagnosis of arrhythmias would be helpful in saving lives. This study is conducted to classify patients into one of the sixteen subclasses, among which one class represents ab...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2018-01-01
|
Series: | Computational and Mathematical Methods in Medicine |
Online Access: | http://dx.doi.org/10.1155/2018/7310496 |
id |
doaj-afcca39b90cd45f1bad8c4243db7aad6 |
---|---|
record_format |
Article |
spelling |
doaj-afcca39b90cd45f1bad8c4243db7aad62020-11-25T00:30:58ZengHindawi LimitedComputational and Mathematical Methods in Medicine1748-670X1748-67182018-01-01201810.1155/2018/73104967310496Multiclass Classification of Cardiac Arrhythmia Using Improved Feature Selection and SVM InvariantsAnam Mustaqeem0Syed Muhammad Anwar1Muahammad Majid2Software Engineering Department, University of Engineering and Technology, Taxila, PakistanSoftware Engineering Department, University of Engineering and Technology, Taxila, PakistanComputer Engineering Department, University of Engineering and Technology, Taxila, PakistanArrhythmia is considered a life-threatening disease causing serious health issues in patients, when left untreated. An early diagnosis of arrhythmias would be helpful in saving lives. This study is conducted to classify patients into one of the sixteen subclasses, among which one class represents absence of disease and the other fifteen classes represent electrocardiogram records of various subtypes of arrhythmias. The research is carried out on the dataset taken from the University of California at Irvine Machine Learning Data Repository. The dataset contains a large volume of feature dimensions which are reduced using wrapper based feature selection technique. For multiclass classification, support vector machine (SVM) based approaches including one-against-one (OAO), one-against-all (OAA), and error-correction code (ECC) are employed to detect the presence and absence of arrhythmias. The SVM method results are compared with other standard machine learning classifiers using varying parameters and the performance of the classifiers is evaluated using accuracy, kappa statistics, and root mean square error. The results show that OAO method of SVM outperforms all other classifiers by achieving an accuracy rate of 81.11% when used with 80/20 data split and 92.07% using 90/10 data split option.http://dx.doi.org/10.1155/2018/7310496 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Anam Mustaqeem Syed Muhammad Anwar Muahammad Majid |
spellingShingle |
Anam Mustaqeem Syed Muhammad Anwar Muahammad Majid Multiclass Classification of Cardiac Arrhythmia Using Improved Feature Selection and SVM Invariants Computational and Mathematical Methods in Medicine |
author_facet |
Anam Mustaqeem Syed Muhammad Anwar Muahammad Majid |
author_sort |
Anam Mustaqeem |
title |
Multiclass Classification of Cardiac Arrhythmia Using Improved Feature Selection and SVM Invariants |
title_short |
Multiclass Classification of Cardiac Arrhythmia Using Improved Feature Selection and SVM Invariants |
title_full |
Multiclass Classification of Cardiac Arrhythmia Using Improved Feature Selection and SVM Invariants |
title_fullStr |
Multiclass Classification of Cardiac Arrhythmia Using Improved Feature Selection and SVM Invariants |
title_full_unstemmed |
Multiclass Classification of Cardiac Arrhythmia Using Improved Feature Selection and SVM Invariants |
title_sort |
multiclass classification of cardiac arrhythmia using improved feature selection and svm invariants |
publisher |
Hindawi Limited |
series |
Computational and Mathematical Methods in Medicine |
issn |
1748-670X 1748-6718 |
publishDate |
2018-01-01 |
description |
Arrhythmia is considered a life-threatening disease causing serious health issues in patients, when left untreated. An early diagnosis of arrhythmias would be helpful in saving lives. This study is conducted to classify patients into one of the sixteen subclasses, among which one class represents absence of disease and the other fifteen classes represent electrocardiogram records of various subtypes of arrhythmias. The research is carried out on the dataset taken from the University of California at Irvine Machine Learning Data Repository. The dataset contains a large volume of feature dimensions which are reduced using wrapper based feature selection technique. For multiclass classification, support vector machine (SVM) based approaches including one-against-one (OAO), one-against-all (OAA), and error-correction code (ECC) are employed to detect the presence and absence of arrhythmias. The SVM method results are compared with other standard machine learning classifiers using varying parameters and the performance of the classifiers is evaluated using accuracy, kappa statistics, and root mean square error. The results show that OAO method of SVM outperforms all other classifiers by achieving an accuracy rate of 81.11% when used with 80/20 data split and 92.07% using 90/10 data split option. |
url |
http://dx.doi.org/10.1155/2018/7310496 |
work_keys_str_mv |
AT anammustaqeem multiclassclassificationofcardiacarrhythmiausingimprovedfeatureselectionandsvminvariants AT syedmuhammadanwar multiclassclassificationofcardiacarrhythmiausingimprovedfeatureselectionandsvminvariants AT muahammadmajid multiclassclassificationofcardiacarrhythmiausingimprovedfeatureselectionandsvminvariants |
_version_ |
1725324580015308800 |