Kümeleme Analizi için Meta-sezgisel Algoritmaların K-Means ile Hibritlenmesi: Tıbbi Veri Kümeleri Üzerine Bir İnceleme

Abstract

K-Means kümeleme, veri kümeleme için yaygın olarak kullanılan bir yöntemdir. Ancak özellikle büyük tıbbi verilerle çalışırken yerel optimuma takılmak ve yavaş yakınsama gibi sorunlarla karşılaşılabilir. Literatürde bu tür sorunları ele almak için kümeleme çalışmalarında metasezgisel algoritmaların kullanılmasının önerildiği görülmektedir. Bu çalışma, dört farklı tıbbi veri kümesi üzerinde (Dermatoloji, Diyabet, Parkinson ve Tiroid) hastalıkların doğru teşhisini koymayı ve hastalıkların doğru teşhis oranını artırmayı amaçlamaktadır. Bu veri kümelerindeki hastalıkları belirleyen girdi parametrelerine ağırlık atamak için optimizasyon algoritmalarını kullandık ve sonuç olarak kümeleme performansını artırdık. Önerilen modelimiz, Karga Arama Algoritması, Ağaç Tohum Algoritması ve Harris Hawks Optimizasyon algoritmalarını K-Means ile hibrit bir yapıda birleştirmektedir. Performans metrikleri kullanarak istatistiksel değerlendirmeler yaptık. Sonuçlar, Harris Hawks Optimizasyon algoritmasının Dermatoloji veri kümesinde en yüksek doğruluk oranını (%97.19) elde ettiğini göstermektedir. Ayrıca Tiroid veri kümesinde Karga Arama Algoritması (%96.29) ve Dermatoloji veri kümesinde Ağaç Tohum Algoritması (%95.32) ile başarılı teşhisler elde edildi. Bu çalışma, tıbbi veri kümelerinde çeşitli hastalıkları tespit etmek için daha az personel iş yükü, daha düşük test maliyetleri, gelişmiş doğruluk oranları ve daha hızlı test sonuçları gibi önemli faydalar sunmaktadır.

Keywords

• K-means kümeleme
• metasezgisel algoritmalar
• hastalık teşhisi
• optimizasyon
• karar destek sistemleri

Hybridization of Meta-heuristic Algorithms with K-Means for Clustering Analysis: Case of Medical Datasets

Abstract

K-means clustering is commonly used for data clustering, but it suffers from limitations such as being prone to local optima and slow convergence, particularly when handling large medical files. The literature recommends employing metaheuristic algorithms in clustering studies to address these issues. This study aims to accurately diagnose diseases in four medical datasets (Dermatology, Diabetes, Parkinson's, and Thyroid) and increase the rate of correct diagnosis of diseases. We utilized optimization algorithms to assign weights to input parameters determining diseases in these datasets, thereby improving clustering performance. Our proposed model incorporates the Crow Search Algorithm, Tree Seed Algorithm, and Harris Hawks Optimization algorithms in a hybrid structure with K-means. We conducted statistical evaluations using performance metrics. The results indicate that the Harris Hawks Optimization algorithm achieved the highest accuracy (%97.19) in the Dermatology dataset, followed by the Crow Search Algorithm (%96.29) in the Thyroid dataset, and the Tree Seed Algorithm (%95.32) in the Dermatology dataset. This study offers significant benefits, including reduced staff workload, lower test costs, improved accuracy rates, and faster test results for detecting various diseases in medical datasets.

Keywords

• K-means clustering
• metaheuristic algorithms
• disease diagnosis
• optimization
• decision support systems

References

1. [1] I. Zheliznyak, Z. Rybchak, and I. Zavuschak, “Analysis of clustering algorithms.,” in Advances in Intelligent Systems and Computing: Selected Papers from the International Conference on Computer Science and Information Technologies, September 6-10 , 2017. Lviv, Ukraine. Springer, 2017, pp. 305–314.
2. [2] D. Karaboga and C. Ozturk, “A novel clustering approach: Artificial Bee Colony (ABC) algorithm.,” Applied soft computing, vol. 11, no. 1, pp. 652–657, 2011. doi.org/10.1016/j.asoc.2009.12.025
3. [3] M. Ren, J. Zhang, L. Khoukhi, H. Labiod, and V. Vèque, “A unified framework of clustering approach in vehicular ad hoc networks.,” IEEE Transactions on intelligent transportation systems, vol. 19, no. 5, pp. 1401–1414, 2017. doi.org/10.1109/TITS.2017.2727226
4. [4] M.M. Rahman and D.N. Davis, “Addressing the class imbalance problem in medical datasets.,” International Journal of Machine Learning and Computing, vol. 3, no. 2, p. 224, 2013. doi.org/10.7763/IJMLC.2013.V3.307
5. [5] S. Ding, H. Jia, M. Du, and Y. Xue, “A semi-supervised approximate spectral clustering algorithm based on HMRF model,” Information Sciences, vol. 429, pp. 215–228, 2018. doi.org/10.1016/j.ins.2017.11.016
6. [6] M.W. Berry, A. Mohamed, and B.W. Yap, “Supervised and unsupervised learning for data science,” Springer, 2019.
7. [7] C. Fraley and A.E. Raftery, “How many clusters? Which clustering method? Answers via model-based cluster analysis.,” The computer journal, vol. 41, no. 8, pp. 578–588, 1998. doi.org/10.1093/comjnl/41.8.578
8. [8] A. Saxena, M. Prasad, A. Gupta, et al., “A review of clustering techniques and developments,” Neurocomputing, vol. 267, pp. 664–681, 2017. doi.org/10.1016/j.neucom.2017.06.053

9. [9] T. Yi, M. Shi, and H. Zhu, “Medical data publishing based on average distribution and clustering,” CAAI Transactions on Intelligence Technology, vol. 7, no. 3, pp. 381–394, 2022. doi.org/10.1049/cit2.12094
10. [10] J. Si, Z. Tian, D. Li, et al., “A multi‐modal clustering method for traditonal Chinese medicine clinical data via media convergence.,” CAAI Transactions on Intelligence Technology, p. 2023. doi.org/10.1049/cit2.12230
11. [11] S. Dörterler, “KANSER HASTALIĞI TEŞHİSİNDE ÖLÜM OYUNU OPTİMİZASYON ALGORİTMASININ ETKİS,” Mühendislik Alanında Uluslararası Araştırmalar VIII, p. 15, 2023.
12. [12] S. Dörterler, H. Dumlu, D. Özdemir, and H. Temurtaş, “Hybridization of K-means and Meta-Heuristics Algorithms for Heart Disease Diagnosis,” In: NEW TRENDS IN ENGINEERING AND APPLIED NATURAL SCIENCES, pp. 55. Duvar Publishing (2022).
13. [13] S. Dörterler, H. Dumlu, D. Özdemir, and H. Temurtaş, “Melezlenmiş K-means ve Diferansiyel Gelişim Algoritmaları ile Kalp Hastalığının Teşhisi,” in International Conference on Engineering and Applied Natural Sciences, May 10-12, 2022. Konya, Turkey, ICEANS 2022. pp. 1840–1844.
14. [14] A. Tekerek and M. Dörterler, “The adaptation of gray wolf optimizer to data clustering,” Politeknik Dergisi, p. 1, 2020. doi.org/10.2339/politeknik.778630
15. [15] J. Cui, Z. Ding, P. Fan, and N. Al-Dhahir, “Unsupervised machine learning-based user clustering in millimeter-wave-NOMA systems,” IEEE Transactions on Wireless Communications, vol. 17, no. 11, pp. 7425–7440, 2018. doi.org/10.1109/TWC.2018.2867180
16. [16] F. Hu, H. Chen, and X. Wang, “An Intuitionistic Kernel-Based Fuzzy C-Means Clustering Algorithm With Local Information for Power Equipment Image Segmentation,” IEEE Access, vol. 8, pp. 4500–4514, 2020. doi.org/10.1109/ACCESS.2019.2963444
17. [17] J. Maia, C.A.S. Junior, F.G. Guimarães, et al., “Evolving clustering algorithm based on mixture of typicalities for stream data mining,” Future Generation Computer Systems, vol. 106, pp. 672–684, 2020. doi.org/10.1016/j.future.2020.01.017
18. [18] R.M. Alguliyev, R.M. Aliguliyev, and L. V Sukhostat, “Efficient algorithm for big data clustering on single machine,” CAAI Transactions on Intelligence Technology, vol. 5, no. 1, pp. 9–14, 2020. doi.org/10.1049/trit.2019.0048
19. [19] Y. Li, J. Qi, X. Chu, and W. Mu, “Customer Segmentation Using K-Means Clustering and the Hybrid Particle Swarm Optimization Algorithm,” The Computer Journal, p. 2022. doi.org/10.1093/comjnl/bxab206
20. [20] S.H. Shihab, S. Afroge, and S.Z. Mishu, “RFM based market segmentation approach using advanced k-means and agglomerative clustering: a comparative study,” in 2019 International Conference on Electrical, Computer and Communication Engineering (ECCE). February 7-9, 2019. IEEE , pp. 1–4.
21. [21] A. Fallah Tehrani and D. Ahrens, “Modified sequential k‐means clustering by utilizing response: A case study for fashion products,” Expert Systems, vol. 34, no. 6, p. e12226, 2017. doi.org/10.1111/exsy.12226
22. [22] O. Akman, T. Comar, D. Hrozencik, and J. Gonzales, “Data clustering and self-organizing maps in biology,” in Algebraic and Combinatorial Computational Biology, pp. 351–374. Elsevier (2019). doi.org/10.1016/B978-0-12-814066-6.00011-8
23. [23] J.P.L. Johnson, “Clustering statistics, roughness feedbacks, and randomness in experimental step‐pool morphodynamics,” Geophysical Research Letters, vol. 44, no. 8, pp. 3653–3662, 2017. doi.org/10.1002/2016GL072246
24. [24] L. Wen, K. Zhou, and S. Yang, “A shape-based clustering method for pattern recognition of residential electricity consumption,” Journal of cleaner production, vol. 212, pp. 475–488, 2019. doi.org/10.1016/j.jclepro.2018.12.067
25. [25] K.P. Sinaga and M.-S. Yang, “Unsupervised K-means clustering algorithm.,” IEEE Access, vol. 8, pp. 80716–80727, 2020. doi.org/10.1109/ACCESS.2020.2988796
26. [26] R.-Q. Liu, Y.-C. Lee, and H.-L. Mu, “Customer Classification and Market Basket Analysis Using K-Means Clustering and Association Rules: Evidence from Distribution Big Data of Korean Retailing Company,” Knowledge Management Research, vol. 19, no. 4, pp. 59–76, 2018. doi.org/10.15813/kmr.2018.19.4.004
27. [27] M. Mehrazma and B. Mahboobi, “Customer Clustering by Combining the Particle Swarm And K-Means Algorithms and Analyzing Their Behavior on Commercial Websites,” Signal Processing and Renewable Energy, vol. 5, no. 2, pp. 83–97, 2021. dorl.net/dor/20.1001.1.25887327.2021.5.2.6.7
28. [28] Y. Tang, Y. Guo, Q. Sun, et al., “Industrial polymers classification using laser-induced breakdown spectroscopy combined with self-organizing maps and K-means algorithm,” Optik, vol. 165, pp. 179–185, 2018. doi.org/10.1016/j.ijleo.2018.03.121
29. [29] J. Fonseca, G. Douzas, and F. Bacao, “Improving Imbalanced Land Cover Classification with K-Means SMOTE: Detecting and Oversampling Distinctive Minority Spectral Signatures,” Information, vol. 12, no. 7, p. 266, 2021. doi.org/10.3390/info12070266
30. [30] M.R. Kanthan and S.N. Sujatha, “Rain drop detection and removal using k-means clustering,” in 2015 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC). pp. 1–5. IEEE ,10-12 December 2015, Madurai, India. doi.org/10.1109/ICCIC.2015.7435707
31. [31] D. Yu, X. Zhou, Y. Pan, Z. Niu, and H. Sun, “Application of Statistical K-Means Algorithm for University Academic Evaluation,” Entropy, vol. 24, no. 7, p. 1004, 2022. doi.org/10.3390%2Fe24071004
32. [32] J. Heil, V. Häring, B. Marschner, and B. Stumpe, “Advantages of fuzzy k-means over k-means clustering in the classification of diffuse reflectance soil spectra: A case study with West African soils.” Geoderma, vol. 337, pp. 11–21, 2019. doi.org/10.1016/j.geoderma.2018.09.004
33. [33] N. Xiaoying, X. Liya, and Z. Xiaoyu, “Classification of Rice According to the Geographic Origin Based on K-Means Cluster and Hierarchinal Cluster [J],” Journal of Agricultural Mechanization Research, vol. 6, p. 2012.
34. [34] T.K. Anderson, “Kernel density estimation and K-means clustering to profile road accident hotspots,” Accident Analysis & Prevention, vol. 41, no. 3, pp. 359–364, 2009. doi.org/10.1016/j.aap.2008.12.014
35. [35] F. Bação, V. Lobo, and M. Painho, “Self-organizing maps as substitutes for k-means clustering,” in International Conference on Computational Science, 22-25 May 2005, pp. 476–483. Springer, Atlanta, USA. doi.org/10.1007/11428862_65
36. [36] S. Chakraborty, N.K. Nagwani, and L. Dey, “Weather forecasting using incremental K-means clustering,” arXiv preprint arXiv:1406.4756. p. 2014. doi.org/10.48550/arXiv.1406.4756
37. [37] D.E. Kurniawan and A. Fatulloh, “Clustering of Social Conditions in Batam, Indonesia Using K-Means Algorithm and Geographic Information System,” International Journal of Earth Sciences and Engineering (IJEE), vol. 10, no. 05, pp. 1076–1080, 2017. doi.org/10.31227/osf.io/qc342
38. [38] J. Zhou and L.C. Le Liang, “Geographic profiling based on multi-point centrography with K-means clustering,” p. 2012. doi.org/10.5281/zenodo.1058785
39. [39] R.S. Evans, J.F. Lloyd, G.J. Stoddard, J.R. Nebeker, and M.H. Samore, “Risk factors for adverse drug events: a 10-year analysis,” Annals of Pharmacotherapy, vol. 39, no. 7–8, pp. 1161–1168, 2005. doi.org/10.1345/aph.1e642
40. [40] E.R. Vickers, H. Boocock, R.D. Harris, et al., “Analysis of the acute postoperative pain experience following oral surgery: identification of ‘unaffected’,‘disabled’and ‘depressed, anxious and disabled’patient clusters,” Australian dental journal, vol. 51, no. 1, pp. 69–77, 2006. doi.org/10.1111/j.1834-7819.2006.tb00404.x
41. [41] D.M. Falkenbach, E.E. Reinhard, and M. Zappala, “Identifying psychopathy subtypes using a broader model of personality: An investigation of the five factor model using model-based cluster analysis,” Journal of interpersonal violence, vol. 36, no. 15–16, pp. 7161–7184, 2021. doi.org/10.1177/0886260519831388
42. [42] H. Kim, B. Kim, S.H. Kim, C.H.K. Park, E.Y. Kim, and Y.M. Ahn, “Classification of attempted suicide by cluster analysis: A study of 888 suicide attempters presenting to the emergency department,” Journal of affective disorders, vol. 235, pp. 184–190, 2018. doi.org/10.1016/j.jad.2018.04.001
43. [43] R. Shai, T. Shi, T.J. Kremen, et al., “Gene expression profiling identifies molecular subtypes of gliomas,” Oncogene, vol. 22, no. 31, pp. 4918–4923, 2003. doi.org/10.1038/sj.onc.1206753
44. [44] F. Bertucci, P. Finetti, J. Rougemont, et al., “Gene expression profiling identifies molecular subtypes of inflammatory breast cancer,” Cancer research, vol. 65, no. 6, pp. 2170–2178, 2005. doi.org/10.1158/0008-5472.can-04-4115
45. [45] K. Ushizawa, C.B. Herath, K. Kaneyama, et al., “cDNA microarray analysis of bovine embryo gene expression profiles during the pre-implantation period,” Reproductive Biology and Endocrinology, vol. 2, no. 1, pp. 1–16, 2004. doi.org/10.1186/1477-7827-2-77
46. [46] E. Şahin, D. Özdemir, and H. Temurtaş, “Multi-objective optimization of ViT architecture for efficient brain tumor classification,” Biomedical Signal Processing and Control, vol. 91, p. 105938, 2024. doi.org/10.1016/j.bspc.2023.105938
47. [47] N. Yagmur, İ. Dag, and H. Temurtas, “Classification of anemia using Harris hawks optimization method and multivariate adaptive regression spline,” Neural Computing and Applications, pp. 1–20, 2024. doi.org/10.1007/s00521-023-09379-y
48. [48] N.N. Arslan, D. Ozdemir, and H. Temurtas, “ECG heartbeats classification with dilated convolutional autoencoder,” Signal, Image and Video Processing, vol. 18, no. 1, pp. 417–426, 2024. doi.org/10.1007/s11760-023-02737-2
49. [49] N. Yagmur, I. Dag, and H. Temurtas, “A new computer‐aided diagnostic method for classifying anaemia disease: Hybrid use of Tree Bagger and metaheuristics,” Expert Systems, p. e13528, 2023. doi.org/10.1111/exsy.13528
50. [50] F. Aydemir and S. Arslan, “Covid-19 pandemi sürecinde çocukların el yıkama alışkanlığının nesnelerin interneti tabanlı sistem ile izlenmesi,” Mühendislik Bilimleri ve Araştırmaları Dergisi, vol. 3, no. 2, pp. 161–168, 2021. doi.org/10.46387/bjesr.949311
51. [51] N. Yağmur, H. Temurtaş, and İ. Dağ, “Anemi hastalığının yapay sinir ağları yöntemleri kullanılarak sınıflandırılması,” Journal of Scientific Reports-B, no. 008, pp. 20–34, 2023.
52. [52] A.M. Ikotun, M.S. Almutari, and A.E. Ezugwu, “K-Means-Based Nature-Inspired Metaheuristic Algorithms for Automatic Data Clustering Problems: Recent Advances and Future Directions,” Applied Sciences, vol. 11, no. 23, p. 11246, 2021. doi.org/10.3390/app112311246
53. [53] M. Delattre and P. Hansen, “Bicriterion cluster analysis.,” IEEE Transactions on Pattern Analysis and Machine Intelligence. no. 4, pp. 277–291, 1980. https://doi.org/10.1109/TPAMI.1980.4767027
54. [54] A.K. Jain, M.N. Murty, and P.J. Flynn, “Data clustering: a review,” ACM computing surveys (CSUR), vol. 31, no. 3, pp. 264–323, 1999. doi.org/10.1145/331499.331504
55. [55] A.G.D.Ç. TAŞKIN and G.G. Emel, “Veri Madenciliğinde Kümeleme Yaklaşimlari Ve Kohonen Ağlari İle Perakendecilik Sektöründe Bir Uygulama,” Süleyman Demirel Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, vol. 15, no. 3, pp. 395–409, 2010.
56. [56] L. Zhang, M. Jin, and S.-J. Yoo, “A clustering detector with graph theory for blind detection of spatial modulation systems,” Wireless Networks, vol. 27, no. 2, pp. 1193–1201, 2021. doi.org/10.1007/s11276-020-02508-8
57. [57] M. Sharma, G.N. Purohit, and S. Mukherjee, “Information retrieves from brain MRI images for tumor detection using hybrid technique K-means and artificial neural network (KMANN),” in Networking communication and data knowledge engineering, pp. 145–157, Springer (2018). doi.org/10.1007/978-981-10-4600-1_14
58. [58] J. Estupiñán Ricardo, J.J. Domínguez Menéndez, I.F. Barcos Arias, J.M. Macías Bermúdez, and N. Moreno Lemus, “Neutrosophic K-means for the analysis of earthquake data in Ecuador,” Neutrosophic Sets and Systems, vol. 44, no. 1, p. 29, 2021.
59. [59] M. Roberto e Souza, A. Carlos Sousa e Santos, and H. Pedrini, “A Hybrid Approach Using the k‐means and Genetic Algorithms for Image Color Quantization,” Recent Advances in Hybrid Metaheuristics for Data Clustering, pp. 151–171, 2020. doi.org/10.1002/9781119551621.ch9
60. [60] S. Kumar, V.K. Solanki, S.K. Choudhary, A. Selamat, and R. González Crespo, “Comparative Study on Ant Colony Optimization (ACO) and K-Means Clustering Approaches for Jobs Scheduling and Energy Optimization Model in Internet of Things (IoT),” International Journal of Interactive Multimedia & Artificial Intelligence, vol. 6, no. 1, p. 2020. doi.org/10.9781/ijimai.2020.01.003
61. [61] A.K. Abasi, A.T. Khader, M.A. Al-Betar, S. Naim, Z.A.A. Alyasseri, and S.N. Makhadmeh, “A novel hybrid multi-verse optimizer with K-means for text documents clustering,” Neural Computing and Applications, vol. 32, no. 23, pp. 17703–17729, 2020. doi.org/10.1007/s00521-020-04945-0
62. [62] A. Kaur, S.K. Pal, and A.P. Singh, “Hybridization of Chaos and Flower Pollination Algorithm over K-Means for data clustering,” Applied Soft Computing, vol. 97, p. 105523, 2020. doi.org/10.1016/j.asoc.2019.105523
63. [63] J. Chen, X. Qi, L. Chen, F. Chen, and G. Cheng, “Quantum-inspired ant lion optimized hybrid k-means for cluster analysis and intrusion detection,” Knowledge-Based Systems, vol. 203, p. 106167, 2020. doi.org/10.1016/j.knosys.2020.106167
64. [64] S. Aggarwal and P. Singh, “Cuckoo and krill herd‐based k‐means++ hybrid algorithms for clustering,” Expert Systems, vol. 36, no. 4, p. e12353, 2019. doi.org/10.1111/exsy.12353
65. [65] Markelle Kelly, Rachel Longjohn, and Kolby Nottingham, The UCI Machine Learning Repository. USA, 2022.
66. [66] H. Naz and S. Ahuja, “Deep learning approach for diabetes prediction using PIMA Indian dataset,” Journal of Diabetes & Metabolic Disorders, vol. 19, no. 1, pp. 391–403, 2020. doi.org/10.1007%2Fs40200-020-00520-5
67. [67] M. Little, P. McSharry, E. Hunter, J. Spielman, and L. Ramig, “Suitability of dysphonia measurements for telemonitoring of Parkinson’s disease,” Nature Precedings, p. 1, 2008. doi.org/10.1109%2FTBME.2008.2005954
68. [68] M. Hosseinzadeh, O.H. Ahmed, M.Y. Ghafour, et al., “A multiple multilayer perceptron neural network with an adaptive learning algorithm for thyroid disease diagnosis in the internet of medical things,” The Journal of Supercomputing, vol. 77, no. 4, pp. 3616–3637, 2021. doi.org/10.1007/s11227-020-03404-w
69. [69] H.A. Güvenir, G. Demiröz, and N. Ilter, “Learning differential diagnosis of erythemato-squamous diseases using voting feature intervals,” Artificial intelligence in medicine, vol. 13, no. 3, pp. 147–165, 1998. doi.org/10.1016/s0933-3657(98)00028-1
70. [70] M. Ahmed, R. Seraj, and S.M.S. Islam, “The k-means algorithm: A comprehensive survey and performance evaluation,” Electronics, vol. 9, no. 8, p. 1295, 2020. doi.org/10.3390/electronics9081295
71. [71] A.A. Heidari, S. Mirjalili, H. Faris, I. Aljarah, M. Mafarja, and H. Chen, “Harris hawks optimization: Algorithm and applications,” Future generation computer systems, vol. 97, pp. 849–872, 2019. doi.org/10.1016/j.future.2019.02.028
72. [72] M.S. Kiran, “TSA: Tree-seed algorithm for continuous optimization,” Expert Systems with Applications, vol. 42, no. 19, pp. 6686–6698, 2015. doi.org/10.1016/j.eswa.2015.04.055
73. [73] M. Aslan, M. Beskirli, H. Kodaz, and M.S. Kiran, “An improved tree seed algorithm for optimization problems,” Int J Mach Learn Comput, vol. 8, no. 1, pp. 20–25, 2018. doi.org/10.18178/ijmlc.2018.8.1.657
74. [74] A. Beşkirli, D. Özdemir, and H. Temurtaş, “A comparison of modified tree–seed algorithm for high-dimensional numerical functions,” Neural Computing and Applications, vol. 32, no. 11, pp. 6877–6911, 2020. doi.org/10.1007/s00521-019-04155-3
75. [75] A. Askarzadeh, “A novel metaheuristic method for solving constrained engineering optimization problems: crow search algorithm,” Computers & Structures, vol. 169, pp. 1–12, 2016. doi.org/10.1016/j.compstruc.2016.03.001
76. [76] Y. Li and H. Wu, “A clustering method based on K-means algorithm,” Physics Procedia, vol. 25, pp. 1104–1109, 2012. doi.org/10.1016/j.phpro.2012.03.206
77. [77] J.M. Pena, J.A. Lozano, and P. Larranaga, “An empirical comparison of four initialization methods for the k-means algorithm,” Pattern recognition letters, vol. 20, no. 10, pp. 1027–1040, 1999. doi.org/10.1016/S0167-8655(99)00069-0
78. [78] A. Ucan, M. Dörterler, and E. Akçapınar Sezer, “An emotion analysis scheme based on Gray Wolf optimization and deep learning,” Concurrency and Computation: Practice and Experience, vol. 33, no. 13, p. e6204, 2021. doi.org/10.1002/cpe.6204
79. [79] H. Karamollaoğlu, İ.A. Doğru, M. Dörterler, A. Utku, and O. Yıldız, “Sentiment analysis on Turkish social media shares through lexicon based approach,” in 2018 3rd International Conference on Computer Science and Engineering (UBMK). September 20-23, 2018. IEEE, pp. 45–49.
80. [80] F. Aydemir and S. Arslan, “A System Design With Deep Learning and IoT to Ensure Education Continuity for Post-COVID,” IEEE Transactions on Consumer Electronics, p. 2023. doi.org/10.1109/TCE.2023.3245129