Analysis of Filters in ECG Signal for Emotion Prediction

Electrocardiograms (ECG) is a process of capturing the electronic signals of the heart and which is used widely for detection of heart diseases. In recent years the ECG signals were used to detect the Emotions of the human by which it takes the human computer interaction to the next level. To do this process the system have to be provided with error free ECG signals. ECG signals might have noise signals or distractions during signal capturing or transmission. Many researches are carried over to remove noise in signals. In this paper we implemented three filters namely Butterworth, Chebyshev and Kaiser window on ECG signals which are captured for the different human emotions and the performance of the filters are measured using the performance metrics namely Mean Square Error, Peak Signal to noise Ratio and signal to Interference Ratio. The entire process was carried down in Python environment. The results proved that Butter worth band pass filter order1 result least MSE value compared to Butter worth band pass filter order2,3,4,Chebyshev filter order 1,2 and kaiser window