Investigation on male fertility and Heart disease prediction using Efficient machine classification Algorithms

Abstract

In this research work, heart disease prediction and male fertility prediction can be done using efficient machine learning algorithms. Thus, two works are done in the thesis. In the first work, heart disease prediction model is presented. Electrocardiogram (ECG) gives essential information regarding different heart attack criteria of the human heart this analysis is the main objective of the research to detect and prevent the threatening of cardiac circumstances. The proposed method using machine learning techniques for classifying and analyzing ECG signal processing and this research mainly developed for early detection of heart diseases and also the stages of prediction level. The dataset was utilized as a person ECG signal of Heart Database which was taken from the UCI repository of Machine learning dataset vault. The first work proposes a simple algorithm for automatic detection of the R-peaks from a single lead digital ECG data. The proposed method detecting the time interval of the ECG signal from the R-peaks level next level with the double squared difference signal is used to localize the region of QRS which is the time interval between the binary data. This method consists of different stages of sorting from the raw data for reducing nosier signal, threshold a difference signal of ECG by analyzing the time interval of QRS, and finally a comparison of relative magnitude to detect the region of interval processing to analyze accuracy result. The proposed research novel machine learning techniques of the multi-module neural network system (MMNNS) is used to analyze the imbalance problem form the ECG signal classification if the wave was abnormal then the user of dataset patients will be affected by heart diseases newline