آی اس آی پیپر

دانلود رایکان مقاله انگلیسی ISI با موضوع یک الگوریتم تکاملی هیبریدی برای انتخاب ویژگی در داده کاوی

عنوان فارسی مقاله:

یک الگوریتم تکاملی هیبریدی برای انتخاب ویژگی در داده کاوی

عنوان انگلیسی مقاله:

A hybrid evolutionary algorithm for attribute selection in data mining

دانلود رایگان مقاله ISI با فرمت PDF:

مشاهده توضیحات کامل و خرید ترجمه فارسی با فرمت ورد تایپ شده:

بخشی از مقاله انگلیسی :

2. Attribute selection in data mining

2.1. Attribute selection

In the KDD process, interesting patterns and useful relationships are attained from the analysis of the input data. To ensure that the patterns derived are as accurate as possible, it is essential to improve the quality of the datasets in a pre-processing stage. Most real life data sets contain a certain amount of redundant data, which does not contribute significantly to the formation of important relationships. This redundancy not only increases the dimensionality of the data set and slows down the data mining process but also affects the subsequent classification performance. With this in mind, data reduction aims to trim down the quantity of data that is to be analyzed and yet produce almost similar, if not better, results as compared to the original data. More meaningful relationships can also be derived as the superfluous portions are removed.