Efficient Clustering Techniques for Data Stream Mining

Year : 2025 | Volume : 12 | Issue : 02 | Page : 26 32
    By

    Abhishek Kumar Saxena,

  • Rashi Umar,

  1. Head, Department of Information Technology, Bansal Institute of Engineering and Technology, Lucknow, Uttar Pradesh, India
  2. Student, Department of Information Technology, Bansal Institute of Engineering and Technology, Lucknow, Uttar Pradesh, India

Abstract

Data mining mainly works on a massive database for storing heavy amount of data. It is generally essential for extracting the meaning insights from the massive, continuously growing database. The traditional method often struggles with sheer volume and the dynamic nature of the modern data. Data stream mining allows for the real-time analysis, means insights are generated as the data arrives, and not after the long batch process. This continuous flow processing is essential for the staying ahead of dynamic changes and then making the timely decision. A major difficultly is, data is not static, the pattern within the data changes overtime and this is called “concept drift”. Basically, the data keep changing, so we have to change our method for getting accurate and the relevant result. Data streams often lack labels or due to absence of pre-labeled data in many streams unsupervised methods are crucial for pattern identification. Clustering algorithms are very useful for the data stream mining, because these group similar types of data points together for revealing the hidden structure and trends that might get unnoticed. This helps in understanding the behavior of the underlaying of the data stream. The aim of this research is to provide a clear understanding of diverse challenges and the problem definition in the data stream mining. It will deeply study how to deal with the data which changes overtime, as it is a big problem for maintaining clustering accuracy. This research also analyzes how to make an algorithm that uses less memory and time as data stream has these limits. This study will compare the different clustering methods, mainly focusing on basic idea and rules they use. The main goal of this study is to create and test the better clustering method that will be best for the data stream, and making them more accurate and faster. Data mining has various challenges but one of its major challenges is the phenomenon of concept drift, where properties of data changes overtime. Data stream mining algorithms should be operated under the resource constraints, like processing capabilities and limited memory. Clustering algorithm is mostly same as stream mining, because both of them group similar data together so that relationship and the trends are shown clearly. This study compares several categories of the clustering techniques, and this comparison is done based on their ability to handle the noise, adaption towards concept drift, scalability towards large dataset and many more. This study allows us to analyze ever-evolving data stream in the more accurate and timely manner.

Keywords: Data mining, data stream mining, clustering, unsupervised learning, real time analysis

[This article belongs to Recent Trends in Parallel Computing ]

How to cite this article:
Abhishek Kumar Saxena, Rashi Umar. Efficient Clustering Techniques for Data Stream Mining. Recent Trends in Parallel Computing. 2025; 12(02):26-32.
How to cite this URL:
Abhishek Kumar Saxena, Rashi Umar. Efficient Clustering Techniques for Data Stream Mining. Recent Trends in Parallel Computing. 2025; 12(02):26-32. Available from: https://journals.stmjournals.com/rtpc/article=2025/view=222242


References

  1. Tsymbal A. The problem of concept drift: definitions and related work. Computer Science Department, Trinity College Dublin. 2004 Apr 29; 106(2): 58.
  2. Wang H, Fan W, Yu PS, Han J. Mining concept-drifting data streams using ensemble classifiers. In Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining. 2003 Aug 24; 226–235.
  3. Barbará D. Requirements for clustering data streams. ACM sIGKDD Explorations Newsletter. 2002 Jan 1; 3(2): 23–7.
  4. 35Khalilian M, Mustapha N. Data stream clustering: Challenges and issues. arXiv preprint arXiv:1006.5261. 2010 Jun 28.
  5. Zhang T, Ramakrishnan R, Livny M. BIRCH: an efficient data clustering method for very large databases. ACM Sigmod Rec. 1996 Jun 1; 25(2): 103–14.
  6. O’callaghan L, Mishra N, Meyerson A, Guha S, Motwani R. Streaming-data algorithms for high-quality clustering. In Proceedings IEEE 18th international conference on data engineering. 2002 Feb 26; 685–694.
  7. Asbagh MJ, Abolhassani H. Feature-based data stream clustering. In 2009 Eighth IEEE/ACIS International Conference on Computer and Information Science. 2009 Jun 1; 363–368.
  8. Aggarwal CC, Philip SY, Han J, Wang J. A framework for clustering evolving data streams. In Proceedings 2003 VLDB conference. Morgan Kaufmann. 2003 Jan 1; 81–92.
  9. Aggarwal CC, Philip SY. A framework for clustering uncertain data streams. In 2008 IEEE 24th International Conference on Data Engineering. 2008 Apr 7; 150–159.
  10. Pelleg D, Moore A. Accelerating exact k-means algorithms with geometric reasoning. In Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining. 1999 Aug 1; 277–281.
  11. Stoffel K, Belkoniene A. Parallel k/h-means clustering for large data sets. InEuro-Par’99 Parallel Processing: 5th International Euro-Par Conference Toulouse, France, August 31–September 3, 1999 Proceedings 5. Berlin Heidelberg: Springer; 1999; 1451–1454.
  12. Dhillon IS, Modha DS. Concept decompositions for large sparse text data using clustering. Machine Learning. 2001 Jan; 42: 143–75.
  13. Banerjee A, Ghosh J. Frequency-sensitive competitive learning for scalable balanced clustering on high-dimensional hyperspheres. IEEE Trans Neural Netw. 2004 May 10; 15(3): 702–19.
  14.  Mahdavi M, Abolhassani H. Harmony K-means algorithm for document clustering. Data Min Knowl Disc. 2009 Jun; 18(3): 370–91.
  15. Bagirov AM, Mardaneh K. Modified global k-means algorithm for clustering in gene expression data sets. In ACM International Conference Proceeding Series. 2006 Dec 1; 246: 23–28.
  16. Barbará D, Chen P. Using the fractal dimension to cluster datasets. In Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining. 2000 Aug 1; 260–264.
  17. Kailing K, Kriegel HP, Kröger P. Density-connected subspace clustering for high-dimensional data. In Proceedings of the 2004 SIAM international conference on data mining. Society for Industrial and Applied Mathematics. 2004 Apr 22; 246–256.
  18. Niu D, Dy JG, Jordan MI. Iterative discovery of multiple alternative clustering views. IEEE Trans Pattern Anal Mach Intell. 2013 Sep 23; 36(7): 1340–53.
  19. Chehreghani MH, Abolhassani H, Chehreghani MH. Improving density-based methods for hierarchical clustering of web pages. Data Knowl Eng. 2008 Oct 1; 67(1): 30–50.
  20. Aggarwal CC, Yu PS. A framework for clustering massive text and categorical data streams. In Proceedings of the 2006 SIAM International Conference on Data Mining. Society for Industrial and Applied Mathematics. 2006 Apr 20; 479–483.
  21. Chen Y, Tu L. Density-based clustering for real-time stream data. In Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining. 2007 Aug 12; 133–142.
  22. Li X, Yang J, Wang Q, Fan J, Liu P. Research and application of improved k-means algorithm based on fuzzy feature selection. In 2008 IEEE Fifth International Conference on Fuzzy Systems and Knowledge Discovery. 2008 Oct 18; 1: 401–405.
  23. Guha S, Meyerson A, Mishra N, Motwani R, O’Callaghan L. Clustering data streams: Theory and practice. IEEE Trans Knowl Data Eng. 2003 May 13; 15(3): 515–28.
  24. Wishart D. Number of clusters. Wiley StatsRef: Statistics Reference Online. John Wiley & Sons; 2014 Apr 14.
  25. Duda RO, Hart PE. Pattern classification. New Jersey, United States: John Wiley & Sons; 2006.
  26. Khalilian M, Boroujeni FZ, Mustapha N, Sulaiman MN. K-means divide and conquer clustering. In 2009 IEEE International Conference on Computer and Automation Engineering. 2009 Mar 8; 306–309.
  27. Lühr S, Lazarescu M. Incremental clustering of dynamic data streams using connectivity based representative points. Data Knowl Eng. 2009 Jan 1; 68(1): 1–27.
  28. Wan R, Yan X, Su X. A weighted fuzzy clustering algorithm for data stream. In 2008 IEEE ISECS International Colloquium on Computing, Communication, Control, and Management. 2008 Aug 3; 1: 360–364.
  29. Elahi M, Li K, Nisar W, Lv X, Wang H. Efficient clustering-based outlier detection algorithm for dynamic data stream. In 2008 IEEE Fifth International Conference on Fuzzy Systems and Knowledge Discovery. 2008 Oct 18; 5: 298–304.
  30. Fraley C, Raftery AE. Model-based clustering, discriminant analysis, and density estimation. J Am Stat Assoc. 2002 Jun 1; 97(458): 611–31.
  31. Alijamaat A, Khalilian M, Mustapha N. A novel approach for high dimensional data clustering. In 2010 IEEE Third International Conference on Knowledge Discovery and Data Mining. 2010 Jan 9; 264–267.
  32. Thangavel K, Pethalakshmi A. Dimensionality reduction based on rough set theory: A review. Appl Soft Comput. 2009 Jan 1; 9(1): 1–2.
  33. Peng J, Tang CJ, Yang DQ, Zhang J, Hu JJ. Similarity computing model of high dimension data for symptom classification of Chinese traditional medicine. Appl Soft Comput. 2009 Jan 1; 9(1): 209–18.
  34. Xu R, Wunsch D. Clustering. New Jersey, United States: John Wiley & Sons; 2008 Nov 3.
  35. Aggarwal CC, Han J, Wang J, Yu PS. A framework for projected clustering of high dimensional data streams. In Proceedings of the Thirtieth international conference on Very large data bases. 2004 Aug 31; 30: 852–863.
Regular Issue Subscription Original Research
Volume 12
Issue 02
Received 09/05/2025
Accepted 19/05/2025
Published 04/06/2025
Publication Time 26 Days
65


My IP

PlumX Metrics