Parallel processing on Big Data in the context of Machine Learning and Hadoop Ecosystem: A Survey

Abstract

Emergent Big Data applications have become gradually more essential. In reality, a lot of institutes, businesses and in general entire society from diverse segments depend more and more on information take out from enormous quantity of raw information, statistics and numbers. On the other hand, in Big Data perspective, customary information methods and policies are not as much of capable. They prove a time-consuming receptiveness and are short of quantifiability, measurability, presentation and accurateness. To solve the      composite Big Data constraints and difficulties, a large amount effort has been carried out. As an effect, different categories of packages, distributions and technologies have been developed. In this paper an evaluation is done, this studies recent technologies developed for Big Data. It aims to assist to choose and adopt the exact combination of diverse Big Data technologies according to their technological, scientific needs and particular applications requirements. It provides not only a worldwide sight of most important Big Data technologies but also relationship according to special organizational, classifications levels such as Information Storage Level, Information Processing Level, Information Querying Level, Information Access Level and Management Level. It classifies and talks about main tools and its features, advantages, restrictions and treatments.