Perfecting a Video Game with Game Metrics
Vol 19, No 3: June 2021

Unidirectional-bidirectional recurrent networks for cardiac disorders classification

Annisa Darmawahyuni (Universitas Sriwijaya)
Siti Nurmaini (Universitas Sriwijaya)
Muhammad Naufal Rachmatullah (Universitas Sriwijaya)
Firdaus Firdaus (Universitas Sriwijaya)
Bambang Tutuko (Universitas Sriwijaya)



Article Info

Publish Date
01 Jun 2021

Abstract

The deep learning approach of supervised recurrent network classifiers model, i.e., recurrent neural networks (RNNs), long short-term memory (LSTM), and gated recurrent units (GRUs) are used in this study. The unidirectional and bidirectional for each cardiac disorder (CDs) class is also compared. Comparing both phases is needed to figure out the optimum phase and the best model performance for ECG using the Physionet dataset to classify five classes of CDs with 15 leads ECG signals. The result shows that the bidirectional RNNs method produces better results than the unidirectional method. In contrast to RNNs, the unidirectional LSTM and GRU outperformed the bidirectional phase. The best recurrent network classifier performance is unidirectional GRU with average accuracy, sensitivity, specificity, precision, and F1-score of 98.50%, 95.54%, 98.42%, 89.93% 92.31%, respectively. Overall, deep learning is a promising improved method for ECG classification.

Copyrights © 2021






Journal Info

Abbrev

TELKOMNIKA

Publisher

Subject

Computer Science & IT

Description

Submitted papers are evaluated by anonymous referees by single blind peer review for contribution, originality, relevance, and presentation. The Editor shall inform you of the results of the review as soon as possible, hopefully in 10 weeks. Please notice that because of the great number of ...