10.57647/ijm2c.2027.1701.06

Hybrid Optimization of K-Means Clustering for BIG Data Using Deep Reinforcement Learning and Quantum Whale Optimization Algorithm

PDF
  • Zaid Hikmat Kareem Albayati1,
  • Mahdi Mosleh*1,
  • Yahya Mahdi Hadi Al-Mayali2,
  • Mohammad Mosleh3,
  1. Department of Computer Engineering, Isf.C., Islamic Azad University, Isfahan, Iran
  2. Department of Computer Techniques Engineering, College of Technical Engineering University of Alkafeel, Najaf, Iraq
  3. Department of Computer Engineering, Dez. C., Islamic Azad University, Dezful, Iran

Received: 30-01-2026

Revised: 19-05-2026

Accepted: 24-05-2026

Published Online: 26-05-2026

Copyright (c) 2025 Zaid Hikmat Kareem Albayati, Mahdi Mosleh, Yahya Mahdi Hadi Al-Mayali, Mohammad Mosleh (Author)

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Kareem Albayati, Z. H., Mosleh, M., Hadi Al-Mayali, Y. M., & Mohammad Mosleh. (2025). Hybrid Optimization of K-Means Clustering for BIG Data Using Deep Reinforcement Learning and Quantum Whale Optimization Algorithm. International Journal of Mathematical Modelling & Computations. https://doi.org/10.57647/ijm2c.2027.1701.06
Crossref
Scopus
Google Scholar
Europe PMC

Abstract

In this paper, a novel hybrid clustering framework, Deep Reinforcement Learning–Quantum Whale Optimization–KMeans (DRL–QWOA–KMeans), is proposed to overcome major limitations of conventional K‑Means, including initialization sensitivity, premature convergence, and reduced clustering accuracy on complex data distributions. In the proposed model, Deep Reinforcement Learning (DRL) is employed to dynamically balance the exploration–exploitation process within the Quantum Whale Optimization Algorithm (QWOA), which adaptively optimizes the initial centroids of K‑Means to achieve global convergence. Extensive experiments conducted on benchmark UCI datasets demonstrate the robustness and efficiency of the proposed method compared with classical meta‑heuristic‑based clustering algorithms such as GA, PSO, DE, WOA, and QWOA. Quantitative evaluation using multiple performance metrics—WCSS, AAcc, ASen, ASpe, and FscoreM—indicates a significant improvement in intra‑cluster compactness and inter‑cluster separability. Moreover, visual analysis confirms that DRL–QWOA–KMeans yields more stable and interpretable clusters compared to standard K‑Means. These findings highlight the competitive potential of DRL‑guided quantum optimization for complex clustering problems and provide a foundation for future investigations on larger-scale or streaming data environments

Keywords

  • Clustering,
  • Quantum inspired Whale Optimization Algorithm (QWOA),
  • Deep Reinforcement Learning (DRL),
  • K Means,
  • Metaheuristics,
  • Adaptive Optimization,
  • Within Cluster Sum of Squares (WCSS),
  • Data Mining
PDF

References

  1. Jain AK (2008) Data clustering: 50 years beyond k-means. In: Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD), pp 3–4.
  2. GeethaRamani R, Balasubramanian L (2018) Macula segmentation and fovea localization employing image processing and heuristic-based clustering for automated retinal screening. Comput Methods Programs Biomed 160:153–163.
  3. Abualigah LM, Khader AT, Al-Betar MA, Alomari OA (2017) Text feature selection with a robust weight scheme and dynamic dimension reduction to text document clustering. Expert Syst Appl 84:24–36.
  4. Triguero I, del Río S, López V, Bacardit J, Benítez JM, Herrera F (2015) ROSEFW-RF: the winner algorithm for the ECBDL’14 big data competition: an extremely imbalanced big data bioinformatics problem. Knowl-Based Syst 87:69–79.
  5. Zhu J, Lung C-H, Srivastava V (2015) A hybrid clustering technique using quantitative and qualitative data for wireless sensor networks. Ad Hoc Netw 25:38–53.
  6. Gan G, Ng MK-P (2017) K-means clustering with outlier removal. Pattern Recogn Lett 90:8–14.
  7. Raykov YP, Boukouvalas A, Baig F, Little MA (2016) What to do when k-means clustering fails: a simple yet principled alternative algorithm. PLoS ONE 11(9):e0162259.
  8. Jahwar AF, Abdulazeez AM (2020) Meta-heuristic algorithms for k-means clustering: a review. PalArch’s J Archaeol Egypt/Egyptol 17(7):12002–12020.
  9. Minh H-L, Sang-To T, Wahab MA, Cuong-Le T (2022) A new metaheuristic optimization based on k-means clustering algorithm and its application to structural damage identification. Knowl-Based Syst 251:109189.
  10. Braik, Malik, et al. "Enhanced whale optimization algorithm-based modeling and simulation analysis for industrial system parameter identification." Journal of Supercomputing 79.13 (2023).‏
  11. Bezdan T, Stoean C, Naamany AA, Bacanin N, Rashid TA, Zivkovic M, Venkatachalam K (2021) Hybrid fruit-fly optimization algorithm with k-means for text document clustering. Mathematics 9(16):1929.
  12. Abasi AK, Khader AT, Al-Betar MA, Naim S, Alyasseri ZAA, Makhadmeh SN (2020) A novel hybrid multi-verse optimizer with k-means for text document clustering. Neural Comput Appl 32:17703–17729.
  13. Purushothaman R, Rajagopalan S, Dhandapani G (2020) Hybridizing gray wolf optimization with grasshopper optimization algorithm for text feature selection and clustering. Appl Soft Comput 96:106651.
  14. Braik M, Sheta A, Al-Hiary H (2021) A novel meta-heuristic search algorithm for solving optimization problems: capuchin search algorithm. Neural Comput Appl 33:2515–2547.
  15. Braik M (2021) A hybrid multi-gene genetic programming with capuchin search algorithm for modeling a nonlinear challenge problem: industrial winding process case study. Neural Process Lett 53(4):2873–2916.
  16. Kanipriya M, Hemalatha C, Sridevi N, SriVidhya S, Shabu SJ (2022) An improved capuchin search algorithm optimized hybrid CNN–LSTM architecture for malignant lung nodule detection. Biomed Signal Process Control 78:103973.
  17. Abd Elaziz M, Al-qaness MA, Dahou A, Ibrahim RA, Abd El-Latif AA (2023) Intrusion detection approach for cloud and IoT environments using deep learning and capuchin search algorithm. Adv Eng Softw 176:103402.
  18. Al-qaness MA, Ewees AA, Fan H, Abualigah L, Elsheikh AH, Abd Elaziz M (2023) Wind power prediction using random vector functional link network with capuchin search algorithm. Ain Shams Eng J 14(9):102095.
  19. Braik M, Awadallah MA, Al-Betar MA, Hammouri AI, Alzubi OA (2023) Cognitively enhanced versions of capuchin search algorithm for feature selection in medical diagnosis: a COVID-19 case study. Cognit Comput, pp 1–38.
  20. Li S, Li Z, Li Q, Zhang M, Li L (2023) Hybrid improved capuchin search algorithm for plant image thresholding. Front Plant Sci 14:1122788.
  21. Rizk-Allah RM, Hassanien AE, Snášel V (2022) A hybrid chameleon swarm algorithm with superiority of feasible solutions for optimal combined heat and power economic dispatch problem. Energy 254:124340.
  22. Braik MS, Awadallah MA, Al-Betar MA, Hammouri AI, Zitar RA (2023) A non-convex economic load dispatch problem using chameleon swarm algorithm with roulette wheel and Lévy flight methods. Appl Intell, pp 1–40.
  23. Braik MS, Hammouri AI, Awadallah MA, Al-Betar MA, Khtatneh K (2023) An improved hybrid chameleon swarm algorithm for feature selection in medical diagnosis. Biomed Signal Process Control 85:105073.
  24. Kumar S, Fred AL, Varghese PS (2019) Suspicious lesion segmentation using optimized spatial feature-based superpixel fuzzy c-means clustering. J Digit Imaging 32(2):322–335.
  25. Zhao X, Wu Y, Song G, Li Z, Zhang Y, Fan Y (2018) A deep learning model integrating FCNNs and CRFs for brain tumor segmentation. Med Image Anal 43:98–111.
  26. Dolz J, Desrosiers C, Ayed IB (2018) 3D fully convolutional networks for subcortical segmentation in MRI: a large-scale study. NeuroImage 170:456–470.
  27. Ali HH, Kadhum LE (2017) K-means clustering algorithm applications in data mining and pattern recognition. Int J Sci Res 6(8):1577–1584.
  28. Septiarini A, Hamdani H, Sari SU, Hatta HR, Puspitasari N, Hadikurniawati W (2022) Tomato image segmentation using k-means clustering and edge detection. In: Proc IEEE ISMODE, pp 92–96.
  29. Bouadjenek MR, Sanner S, Du Y (2020) Relevance- and interface-driven clustering for visual information retrieval. Inf Syst 94:101592.
  30. Likas A, Vlassis N, Verbeek JJ (2003) The global k-means clustering algorithm. Pattern Recogn 36(2):451–461.
  31. Karaboga D, Ozturk C (2011) A novel clustering approach: artificial bee colony (ABC) algorithm. Appl Soft Comput 11(1):652–657.
  32. Shelokar P, Jayaraman VK, Kulkarni BD (2004) An ant colony approach for clustering. Anal Chim Acta 509(2):187–195.
  33. Chen C-Y, Ye F (2012) Particle swarm optimization and its application to clustering analysis. In: Proc IEEE Conf Electrical Power Distribution, pp 789–794.
  34. Senthilnath J, Omkar SN, Mani V (2011) Clustering using firefly algorithm: performance study. Swarm Evol Comput 1(3):164–171.
  35. Hatamlou A, Abdullah S, Nezamabadi-Pour H (2012) A combined approach for clustering based on k-means and gravitational search algorithms. Swarm Evol Comput 6:47–52.
  36. Hatamlou A (2013) Black hole: a new heuristic optimization approach for data clustering. Inf Sci 222:175–184.
  37. Hatamlou A, Abdullah S, Hatamlou M (2011) Data clustering using big bang–big crunch algorithm. In: Proc Int Conf Innovative Computing Technology, Springer, pp 383–388.
  38. Das P, Das DK, Dey S (2018) Modified bee colony optimization hybridized with k-means for data clustering. Appl Soft Comput 70:590–603.
  39. Niknam T, Amiri B (2010) An efficient hybrid approach based on PSO, ACO and k-means for cluster analysis. Appl Soft Comput 10(1):183–197.
  40. Boushaki SI, Kamel N, Bendjeghaba O (2018) A new quantum chaotic cuckoo search algorithm for data clustering. Expert Syst Appl 96:358–372.
  41. Zhou L, Li L (2018) Improvement of the firefly-based k-means clustering algorithm. In: Proc Int Conf Data Science.
  42. Hassanzadeh T, Meybodi MR (2012) A hybrid firefly and k-means clustering approach. In: Proc IEEE AISP, pp 7–11.
  43. Han X, Quan L, Xiong X, Almeter M, Xiang J, Lan Y (2017) A novel data clustering algorithm based on modified gravitational search algorithm. Eng Appl Artif Intell 61:1–7.
  44. Nanda SJ, Panda G (2014) A survey on nature-inspired metaheuristic algorithms for partitional clustering. Swarm Evol Comput 16:1–18.
  45. Gupta A, Datta S, Das S (2019) Evolutionary multiobjective fuzzy clustering at different fuzziness levels. IEEE Trans Cybern 51(5):2601–2611.
  46. Lai Z, Feng X, Yu H, Luo F (2018) Parallel social spider optimization algorithm based on emotional learning. IEEE Trans Syst Man Cybern Syst 51(2):797–808.
  47. Yan D, Cao H, Yu Y, Wang Y, Yu X (2020) Cat swarm optimization-based clustering for single- and multiobjective data partitioning. IEEE Trans Autom Sci Eng 17(3):1633–1646.
  48. Blake C, Merz C (2015) Uci repository of machine learning databases, department of information and computer science, university of california, irvine, ca, URL: http://www. archive. ics. uci. edu/ml

Most read articles by the same author(s)