K-means
2 articles · search the full text for this term
-
Advancements in K-Means Clustering: Boosting Algorithm Performance through Innovations
Abstract: K-Means clustering is a widely used unsupervised learning algorithm for partitioning a dataset into distinct clusters. Despite its popularity and simplicity, K-Means has several limitations, such as sensitivity to initial centroids, convergence to local minima, and inefficiency with large datasets. This paper reviews recent advancements aimed at addressing these challenges and enhancing the performance of the K-Means algorithm. Innovations include improved initialization methods, such as K-Means++, which significantly reduce the …
Published in International Journal of Solid State Innovations & Research · Vol. 3, Issue 1, 2025 · pp. 30–37 Read article
-
Country Cluster Visualization Based on Agricultural Imports: Unsupervised Learning Approach
Abstract: The clustering algorithm used in this analysis makes it easier for policymakers to understand performance metrics. K-means clustering has been demonstrated to be a tool for analyzing countries' agricultural imports and a visualization tool for interpreting the results in this study. Authors have used agricultural imports from 190 nations from Knoema, a web-based open data platform. Cereals, meat, and coffee imports from 190 nations in 2016 are included in the …
Published in Journal of Artificial Intelligence Research & Advances · Vol. 11, Issue 1, 2024 · pp. 1–7 Read article