Comparison of shallow and deep learning methods of ECG signals clas-sification for arrhythmia detection

The research aimed to compare the classification performance of arrhythmia classification from the ECG signal dataset from the Massachusetts Institute of Technology–Beth Israel Hospital (MIT-BIH) database. Shallow learning methods that were used in this study are Support Vector Machine,  Naïve Baye...

Full description

Saved in:
Bibliographic Details
Main Authors: Dodon Turianto Nugrahadi, Rudy Herteno, Dwi Kartini, Muhammad Haekal, Mohammad Reza Faisal
Format: Article
Language:English
Published: Lublin University of Technology 2023-06-01
Series:Journal of Computer Sciences Institute
Subjects:
Online Access:https://ph.pollub.pl/index.php/jcsi/article/view/3273
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849387882152722432
author Dodon Turianto Nugrahadi
Rudy Herteno
Dwi Kartini
Muhammad Haekal
Mohammad Reza Faisal
author_facet Dodon Turianto Nugrahadi
Rudy Herteno
Dwi Kartini
Muhammad Haekal
Mohammad Reza Faisal
author_sort Dodon Turianto Nugrahadi
collection DOAJ
description The research aimed to compare the classification performance of arrhythmia classification from the ECG signal dataset from the Massachusetts Institute of Technology–Beth Israel Hospital (MIT-BIH) database. Shallow learning methods that were used in this study are Support Vector Machine,  Naïve Bayes, and Random Forest. 1D Convolutional Neural Network (1D CNN), Long Short Term Memory (LSTM), and Gated Recurrent Unit (GRU) were deep learning methods that were used for the study. The models were tested on a dataset with 140 samples that were grouped into four class labels, and each sample has 2160 features. Those models were tested for classification performance. This research shows Random Forest and 1D CNN have the best performance.
format Article
id doaj-art-f313b1d5cb7a4d0c8256b6e6ea4c1909
institution Kabale University
issn 2544-0764
language English
publishDate 2023-06-01
publisher Lublin University of Technology
record_format Article
series Journal of Computer Sciences Institute
spelling doaj-art-f313b1d5cb7a4d0c8256b6e6ea4c19092025-08-20T03:42:28ZengLublin University of TechnologyJournal of Computer Sciences Institute2544-07642023-06-012710.35784/jcsi.3273Comparison of shallow and deep learning methods of ECG signals clas-sification for arrhythmia detectionDodon Turianto Nugrahadi0https://orcid.org/0000-0001-7746-2658Rudy HertenoDwi Kartinihttps://orcid.org/0000-0002-7382-5084Muhammad HaekalMohammad Reza Faisalhttps://orcid.org/0000-0001-5748-7639Lambung Mangkurat University The research aimed to compare the classification performance of arrhythmia classification from the ECG signal dataset from the Massachusetts Institute of Technology–Beth Israel Hospital (MIT-BIH) database. Shallow learning methods that were used in this study are Support Vector Machine,  Naïve Bayes, and Random Forest. 1D Convolutional Neural Network (1D CNN), Long Short Term Memory (LSTM), and Gated Recurrent Unit (GRU) were deep learning methods that were used for the study. The models were tested on a dataset with 140 samples that were grouped into four class labels, and each sample has 2160 features. Those models were tested for classification performance. This research shows Random Forest and 1D CNN have the best performance. https://ph.pollub.pl/index.php/jcsi/article/view/3273ECG signalsarrhythmia classificationshallow learningdeep learning
spellingShingle Dodon Turianto Nugrahadi
Rudy Herteno
Dwi Kartini
Muhammad Haekal
Mohammad Reza Faisal
Comparison of shallow and deep learning methods of ECG signals clas-sification for arrhythmia detection
Journal of Computer Sciences Institute
ECG signals
arrhythmia classification
shallow learning
deep learning
title Comparison of shallow and deep learning methods of ECG signals clas-sification for arrhythmia detection
title_full Comparison of shallow and deep learning methods of ECG signals clas-sification for arrhythmia detection
title_fullStr Comparison of shallow and deep learning methods of ECG signals clas-sification for arrhythmia detection
title_full_unstemmed Comparison of shallow and deep learning methods of ECG signals clas-sification for arrhythmia detection
title_short Comparison of shallow and deep learning methods of ECG signals clas-sification for arrhythmia detection
title_sort comparison of shallow and deep learning methods of ecg signals clas sification for arrhythmia detection
topic ECG signals
arrhythmia classification
shallow learning
deep learning
url https://ph.pollub.pl/index.php/jcsi/article/view/3273
work_keys_str_mv AT dodonturiantonugrahadi comparisonofshallowanddeeplearningmethodsofecgsignalsclassificationforarrhythmiadetection
AT rudyherteno comparisonofshallowanddeeplearningmethodsofecgsignalsclassificationforarrhythmiadetection
AT dwikartini comparisonofshallowanddeeplearningmethodsofecgsignalsclassificationforarrhythmiadetection
AT muhammadhaekal comparisonofshallowanddeeplearningmethodsofecgsignalsclassificationforarrhythmiadetection
AT mohammadrezafaisal comparisonofshallowanddeeplearningmethodsofecgsignalsclassificationforarrhythmiadetection