Evaluation of Meta-Heuristic Algorithms for Stable Feature Selection

Now a days, developing the science and\udtechnology and technology tools, the ability of reviewing\udand saving the important data has been provided. It is\udneeded to have knowledge for searching the data to reach\udthe necessary useful results. Data mining is searching for\udbig data sources automatically to find patterns and\uddependencies which are not done by simple statistical\udanalysis. The scope is to study the predictive role and\udusage domain of data mining in medical science and\udsuggesting a frame for creating, assessing and exploiting\udthe data mining patterns in this field. As it has been\udfound out from previous researches that assessing\udmethods can not be used to specify the data discrepancies,\udour suggestion is a new approach for assessing the data\udsimilarities to find out the relations between the variation\udin data and stability in selection. Therefore we have\udchosen meta heuristic methods to be able to choose the\udbest and the stable algorithms among a set of algorithm