Many advances in computer science over the last two decades have been based on the observation and emulation of natural world processes. Nature-inspired methods, such as ant-based clustering techniques, have proven effective in solving clustering problems. They have received special consideration in the research. community in recent years because these methods are particularly well suited to exploratory data analysis examination Clustering is an important technique that has been studied in a variety of fields and has a wide range of applications. Image processing, marketing, data mining, and information retrieval are just a few examples. Recently, various nature-inspired algorithms have been used for clustering. Data clustering is a useful process for extracting meaning from unlabeled data sets or for pattern recognition. This paper investigates the behavior of clustering procedures using two approaches: the ant-based clustering algorithm and the K-harmonic means clustering algorithm. Two well-known benchmark data sets were used to evaluate the two algorithms. Empirical results clearly show that the ant clustering algorithm outperforms another technique known as the K-Harmonic means clustering algorithm.
Author (s) DetailsM. Divyavani
Department of Computer Application, Bharathiar University, Coimbatore, India.
T. Amudha
Department of Computer Application, Bharathiar University, Coimbatore, India.
View Book : https://stm.bookpi.org/TPMCS-V11/article/view/1313
No comments:
Post a Comment