Content Based Spark –ITFS ,Features Selections for Extraction useful Information in Big Data

Big data handling is the most important challenges faced by many of the researchers in the world due to its varying structure and high volume of contents. The most useful and relevant information plays the most important role in the real world application environment scenario, which decides the successful completion of the task execution. Finding the useful information from the big data which consist of more irrelevant data would be the most complex process which needs to be done with more care for designing the most flexible framework that can handle the large volume of data in an efficient manner. Filtering is one of the most popular approaches, which is frequently followed by most of the researchers for eliminating the irrelevant columns and retrieving only useful information. There are various filtering mechanisms such as low variance filter, highly correlated filter, PCA filter are introduced in the existing scenarios for filtering the irrelevant information.