A cardiac arrhythmia is an abnormal heart rhythm caused by irregular heartbeats. Cardiac arrhythmias include atrial or ventricular fibrillation, right or left bundle branch block beats, and premature atrial or ventricular contractions. Different cardiac arrhythmias have distinct causes and clinical presentations. The type of cardiac arrhythmia must be identified to enable further intervention and treatment for addressing its underlying causes. In this study, we developed a convolutional neural network (CNN) model that extracts and classifies time-domain features to detect cardiac arrhythmias automatically in electrocardiogram (ECG) signals. This model employs endpoint detection to detect the activity of time-domain signals in accordance with a threshold for identifying the peak wave in ECG signals. These features are then transferred to two-dimensional (2D) color patterns that indicate abnormal heartbeats. Subsequently, a one-dimensional (1D) or 2D CNN classifier is employed to distinguish normal heartbeats from cardiac arrhythmias in raw ECG data. The proposed model was trained, tested, and validated on the Massachusetts Institute of Technology–Beth Israel Deaconess Medical Center Arrhythmia Database (commonly known as the MIT-BIH Arrhythmia Database), and it exhibited promising performance in cardiac arrhythmia recognition, as indicated by its precision, recall, F1 score, and accuracy.