Big Data Classification using the Deep Learning Enabled Spark Architecture: A Survey
16 Pages Posted: 15 Jul 2019 Last revised: 30 Sep 2019
Date Written: May 18, 2019
Currently the Big Data applications such as social networking, medical healthcare, agriculture, banking, stock market, education, Facebook etc. are generating the data with very high speed. Volume and Velocity of the Big data plays an important role in the performance of Big data applications. Performance of the Big data application can be affected by various parameters. Speedily search, efficiency and accuracy are the some of the dominant parameters which affect the overall execution of any Big data applications. Due the direct and indirect involvement of the characteristics of 7Vs of Big data, every Big Data services expect the high performance. High performance is the biggest challenge in today's changing scenario. In this paper we made a survey to propose the Big Data classification approach to speed up the Big Data applications. This paper is the survey paper, we refer various Big data technologies and the related work in the field of Big Data Classification. After learning and understanding the literature we find out the gaps in existing work and methodologies. Our exhaustive search and the outcome of this survey help us to propose the novel approach of Big Data classification. In this survey our approach depends upon the Deep Learning and Apache Spark architecture. In the proposed work two phases are shown; first phase is feature selection and second phase is Big Data Classification. Apache Spark is the most suitable and dominant technology to implement this proposed work. Apache Spark is having two nodes; initial nodes and final nodes. The feature selection will be take place in initial nodes and Big Data Classification will take place in final nodes of Apache Spark.
Keywords: Big Data Classification, Deep Learning, Apache Spark
JEL Classification: Y60
Suggested Citation: Suggested Citation