International Research Journal of Education and Technology

Electrocardiogram (ECG) signal classification is crucial in diagnosing cardiac disorders, aiding in early detection and accurate medical intervention. Traditional methods for ECG classification often involve manual interpretation, which is time-consuming and prone to human error. This project aims to implement a machine learning-based approach for ECG signal classification by integrating the MIT-BIH Arrhythmia and PTB Diagnostic ECG datasets. The combined dataset ensures diverse sample representation, improving classification accuracy. To address class imbalance issues, the Synthetic Minority Over-sampling Technique (SMOTE) is applied, enhancing the model's ability to learn from underrepresented classes. Feature extraction focuses on the PQRST intervals of ECG waveforms, allowing the model to capture essential characteristics of normal and abnormal heartbeats. Various machine learning algorithms, including Support Vector Machines (SVM), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM) networks, are explored to classify ECG signals into normal or abnormal categories.

Key Words: ECG Classification, Machine Learning, MIT-BIH, PTB Diagnostic, SMOTE, PQRST Interval, CNN, LSTM.