An efficient parallel clustering algorithm on big data using Spark

• Main Authors: Mallik, Moksud Alam, Zulkurnain, Nurul Fariza, Nizamuddin, Mohammed Khaja, Sarkar, Rashel, Ahmed, S K Jamil
• Format: Article
• Language: English
• Published: East China University of Science and Technology 2022
• Subjects: TK7885 Computer engineering
• Online Access: http://irep.iium.edu.my/99923/1/99923_An%20efficient%20parallel%20clustering%20algorithm.pdf; http://irep.iium.edu.my/99923/; http://hdlgdxxb.info/index.php/JE_CUST/article/view/106
• Institution: Universiti Islam Antarabangsa Malaysia

Clustering is a useful tool for dealing with large amounts of data. When dealing with larger datasets, typical algorithms become inefficient. The main reason for this is that most algorithms do not support large data sets or dimensionality. Furthermore, they are only capable of handling organized data. Every second, data from numerous streams such as log files, social media, and YouTube is poured in. Because of the increasing number and variety of data on the internet, we need to refine a parallel clustering algorithm that is both efficient and effective for Big Data. There are mainly two frameworks to process big data: MapReduce and Spark. Spark is the future of the big data platform. It is 100 times faster than Map Reduce. Here we are proposing a new parallel fuzzy clustering algorithm called "An efficient parallel clustering algorithm on big data using spark" which deals with real-time processing. Proposed algorithm gives the fast and iterative data processing and eliminates the effect of batch processing.