Feature selection is one of the issues that have been raised in the discussion of machine learning and statistical identification model. We have provided definitions for feature selection and definitions needed to understand this issue, we check. Then, different methods for this problem were based on the type of product, as well as how to evaluate candidate subsets of features, we classify the following categories. As in previous studies may not have understood that different methods of assessment data into consideration, We propose a new approach for assessing similarity of data to understand the relationship between diversity and stability of the data is selected. After review and meta-heuristic algorithms to implement the algorithm found that the cluster has better performance compared with other algorithms for feature selection sustained.

Feature selection is one of the issues that have been raised in the discussion of machine learning and statistical identification model. We have provided definitions for feature selection and definitions needed to understand this issue, we check. Then, different methods for this problem were based on the type of product, as well as how to evaluate candidate subsets of features, we classify the following categories. As in previous studies may not have understood that different methods of assessment data into consideration, We propose a new approach for assessing similarity of data to understand the relationship between diversity and stability of the data is selected. After review and meta-heuristic algorithms to implement the algorithm found that the cluster algorithm has better performance compared with other algorithms for feature selection sustained.

Now a days, developing the science and technology and technology tools, the ability of reviewing and saving the important data has been provided. It is needed to have knowledge for searching the data to reach the necessary useful results. Data mining is searching for big data sources automatically to find patterns and dependencies which are not done by simple statistical analysis. The scope is to study the predictive role and usage domain of data mining in medical science and suggesting a frame for creating, assessing and exploiting the data mining patterns in this field. As it has been found out from previous researches that assessing methods can not be used to specify the data discrepancies, our suggestion is a new approach for assessing the data similarities to find out the relations between the variation in data and stability in selection. Therefore we have chosen meta heuristic methods to be able to choose the best and the stable algorithms among a set of algorithms.