Distributed Incremental Clustering Algorithms: A Bibliometric and Word-Cloud Review Analysis

ABSTRACT

“Incremental Learning (IL)” is the niche area of “Machine Learning.” It is of utmost essential to keep learning incremental for ever-increasing data from all domains for effectual decisions, predications and solving problems. This can be achieved effectually by applying “Incremental Clustering” methods on real-time data sources. IL can be achieved by “Incremental Clustering” easily as well as effectively. To achieve worldwide data analysis related to the data and to achieve broader perspectives, it is essential to deploy “Incremental Clustering” algorithms on distributed platforms, which will enable them to accept data from varied sources; analyze it and produce distributed worldwide solutions. This paper hence focuses on understanding the current status of “Distributed Incremental Clustering Algorithms (DICA),” its scope, limitations and other details so as to formulate better than the best algorithm in future. To enhance the analysis further Word-Clouds of impactful papers were explored and added in this paper, along with the details about platforms used to implement DICA by various upcoming researchers, readers and authors.

KEYWORDS:

• Bibliometric
• clustering
• DICA
• distributed
• incremental
• incremental clustering
• incremental learning
• word cloud

Acknowledgments

This research supported by Microsoft through the project “Data Science (CRM: 0795037)” and “AI for Earth,” 2018-19 and 2019-20, for two years from 2018 to 2020. The authors acknowledge the “Sakal India Foundation,” Pune, India, for their support.