Indonesian Journal of Electrical Engineering and Computer Science Vol. 25, No. 2, February 2022, pp. 931~940 ISSN: 2502-4752, DOI: 10.11591/ijeecs.v25.i2.pp931-940  931 Journal homepage: http://ijeecs.iaescore.com Classify arrhythmia by using 2D spectral images and deep neural network Tran Anh Vu 1 , Hoang Quang Huy 1 , Pham Duy Khanh 1 , Nguyen Thi Minh Huyen 1 , Trinh Thi Thu Uyen 1 , Pham Thi Viet Huong 2 1 Biomedical Engineering Department, School of Electronics and Telecommunications, Hanoi University of Science and Technology, Hanoi, Vietnam 2 International School, Vietnam National University, Hanoi, Vietnam Article Info ABSTRACT Article history: Received Jul 21, 2021 Revised Dec 8, 2021 Accepted Dec 18, 2021 Electrocardiogram (ECG) is the most common method for monitoring the working of the heart. ECG signal is the basis to determine normal or abnormal rhythm, thereby helping to accurately diagnose cardiovascular diseases. Therefore, an automatic algorithm to detect and diagnose abnormal heart rhythms is essential. There are many methods of classifying arrhythmias using machine learning algorithms such as k-nearest neighbors (KNN), support vector machines (SVM), based on the features extracted from the record of ECG signal. Actually, deep learning algorithms are evolving and highly effective in image analysis and processing. In this research, a dense neural network model is proposed to classify normal and abnormal beats. Input ECG signal presenting a time series is converted into 2-D spectral image by applying wavelet transform. Our research is evaluated based on using the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia database. The accuracy of the classification algorithm we employ is 99.8%, demonstrating the model's validity when compared to other reports' findings. This is the foundation for our algorithm to prove it can be utilized as an efficient model for categorizing arrhythmia using ECG signals. Keywords: 2-D spectral image Continuous wavelet transform Deep neural network ECG signal This is an open access article under the CC BY-SA license. Corresponding Author: Pham Thi Viet Huong International School, Vietnam National University 144 Xuan Thuy, Cau Giay, Hanoi, Vietnam Email: huongptv@isvnu.vn 1. INTRODUCTION An arrhythmia [1] is an electrical irregularity of the heart, which can be a pacing or electrical conduction anomaly in the heart chambers, in which the heartbeat is irregular, too fast or too slow. An arrhythmia can be asymptomatic or cause symptoms such as palpitations, a sense that the heart is beating too quickly or irregularly, or a break between heartbeats [2]. Many cases of severe arrhythmias cause the patient to become dizzy, faint, have trouble breathing, and have chest pain. Complications can occur such as stroke, heart failure, or sudden death. According to WHO [3], cardiovascular diseases are the cause of the largest mortality in the world (more than 30%), higher than death from cancer. It is estimated that each year about 17.9 million people worldwide die from cardiovascular diseases of which 85% are from heart attack and stroke. Especially in the current situation of COVID-19 epidemic, the risk of death often focuses mainly on the elderly or patients with underlying medical conditions including cardiovascular disease. Electrocardiogram (ECG) is a chart that records the electrical impulses generated by cardiac muscle cell through electrodes placed in the body. The ECG signals are displayed in a 1-D time series that helps