| ITI əməkdaşlarının elmi işləri - məqalə |
| Biblioqrafik təsvir | |
| Aliguliyev , R.M. Performance compatrison of k-means, parallel k-means and k-means++ / R.M. Aliguliyev , S.F. Tahirzada // RT&A. - 2025. - N: 7 (83), Volume 20. - P. 169-176. | |
| Annotasiya | |
| K-means clustering is a fundamental unsupervised machine learning technique widely applied in various domains such as data analysis, pattern recognition, and clustering-based tasks. However, its efficiency and scalability can be challenged, particularly when dealing with large-scale datasets and complex data structures. This thesis explores strategies to improve the performance of the K-means clustering algorithm through parallelism and iterative techniques. Parallelism leverages modern parallel computing architectures, including multi-core processors and distributed frameworks like Apache Spark, to enhance computational efficiency and scalability. On the other hand, an iterative approach involves refining clustering results through multiple iterations, adjusting cluster centroids, and optimizing convergence criteria. It delves into the design frameworks of these approaches, highlighting their respective advantages and limitations. Comparative analyses are conducted to evaluate the effectiveness of parallelism and iterative techniques in terms of execution time, scalability, clustering accuracy, and convergence speed. The findings contribute to advancing the understanding of how parallelism and iterative strategies can significantly improve K-means clustering performance, especially in the context of big data and complex datasets. By comparatively analyzing parallelism and iterative approaches, this paper aims to contribute to the development of more efficient and scalable clustering algorithms in the Big Data context. | |
| Elektron variant | |
| Elektron variant |
________
© ict.az http://ict.az/az