Analysis on the effect of ECG signals while listening to different genres of music

Electrocardiogram (ECG) is a non-invasive, simple and effective technique which is widely used for the diagnosis of cardiovascular diseases. In this work, a non-invasive type of ECG measurement system was used for recording of ECG signals. Further, the normal individuals were subjected to two different music genres namely rock and melody and the influence of music on the recorded ECG signals were analyzed. The descriptive statistical features, stress index, entropy, power and mobility features were extracted and the machine learning classifiers such as K-means, Naïve Bayes and Artificial Neural Network (ANN) classifiers were used to classify the ECG signals (before and after listening to music) for two different music genres. Results demonstrate that there are significant variations in the features extracted from the ECG signals at two different conditions. Further, the performance of ANN classifier is better when compared to other two adopted classifiers.