Search
2 articles for “centroids”
-
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
-
Optimization of Biohybrid Polymer Synthesis Using Fuzzy Inference Systems
Abstract: This investigation proposes a methodology to optimize biohybrid polymer synthesis using fuzzy inference systems (FIS). The study combines fuzzy logic principles with mathematical calculations for finding the best synthesis parameters to enhance the synthesis quality. This study consists on a sample about the use of FIS on optimisation of polymer synthesis, where they show the process of fuzzification, rule base creation, inference mechanism and defuzzification using the centroid method through …
Published in Journal of Polymer & Composites · Vol. 12, Issue 5, 2024 · pp. 36–47 Read article