Machine Learning in Predicting the Impact of Filter Parameters on the Accuracy of Biosignal Measurement

In this scientific article under consideration, a machine learning model has been developed that allows predicting the impact of filter parameters on the accuracy of measuring a biosignal - an ECG (electrocardiography) signal. For the first time, quantitative results have shown the degree of influence and the error introduced into the measured biosignal and described through dependence. The results of assessing the obtained relationship of indicators demonstrate an inverse correlation relationship that characterizes a decrease in the accuracy of measurement at the output of a high-order digital filtering system. The machine learning model is based on the linear regression method the dependence of which is approximated by the method based on least squares and visualized using a scattergram. The adequacy of the developed machine learning model was confirmed by calculating the coefficient of determination and checking its statistical significance. The developed model can be used to create new or improve existing biomedical data processing systems to increase the reliability of the results.