A Hybrid Approach for the Fertility Rate Analysis In Human Beings Using Classification Algorithms

A decline in human sperm quality and quantity has been reported in numerous Western countries. This observation was also accompanied by an increase in urogenital malformations. The need for epidemiological studies dealing with unbiased populations in order to understand the causes of these observations is obvious. In this work three classification techniques of Data Mining are combine using Human disease datasets from University of California, Irvine (UCI) Machine Learning Repository. Accuracy and time complexity for execution by each classifier is observed. These algorithms were Naïve Bayes, SVM (Support Vector Machines) and hybrid classifiers are highly scalable, requiring a number of parameters linear in the number of variables (features/predictors) in a learning problem. Maximum-likelihood training can be done by evaluating a closed-form expression, which takes linear time, rather than by expensive iterative approximation as used for many other types of classifiers. This thesis discussed various techniques which are able to classify with future human semen analysis data will increase or decrease better than level of significance. Also, it investigated various global events and their issues classify on Human disease. It supports numerically and graphically. Classification is used to classify each item in a set of data into one of predefined set of classes or groups.