The proposed ECG signal analysis method using artificial neural networks successfully extracted important cardiac features and detected abnormalities to assist early diagnosis but exact accuracy was not quantified.
A proposed automated system using signal processing and artificial neural networks can extract key ECG features to assist in the detection of cardiac abnormalities.
Electrocardiogram (ECG) signal analysis is an important technique used for monitoring the electrical activity of the human heart and detecting cardiac abnormalities. Cardiovascular diseases are one of the major causes of death worldwide, so early detection is very important for proper treatment. The ECG signal consists of different waveform components such as P wave, QRS complex, and T wave which represent the electrical functioning of the heart. By analyzing these components, it is possible to identify irregular heart conditions such as arrhythmia and other cardiac disorders. In this project, ECG signals are analyzed using signal processing techniques to detect abnormalities. The acquired ECG signal is first processed to remove noise and improve signal quality. Important features like heart rate, amplitude, and time intervals are extracted from the ECG waveform. These features help in identifying deviations from normal heart activity. The system helps in detecting abnormal patterns in heart signals. The proposed method provides an effective way to monitor cardiac health. It can assist medical professionals in early diagnosis of heart diseases. Therefore, ECG signal analysis plays a vital role in modern healthcare and cardiac monitoring systems.
International Journal for Research In Science & Advanced Technologies (Sun,) conducted a other in Individuals with cardiac abnormalities and normal ECG signals from available datasets. ECG signal analysis using signal processing and Artificial Neural Network classification vs. No classification or manual ECG analysis was evaluated on Accuracy of classification of ECG signals as normal or abnormal. The proposed ECG signal analysis method using artificial neural networks successfully extracted important cardiac features and detected abnormalities to assist early diagnosis but exact accuracy was not quantified.