Clustering Remotely Sensed Data with K-Means and Bat Algorithm

K-Means is an efficient clustering method commonly employed in data analysis, particularly in the field of remote sensing. However, selecting the right number of clusters (k) can be challenging. To tackle this challenge, we investigate the effectiveness of K-Means combined with the Bat Algorithm (KMBA), which leverages bat-inspired techniques. The results show promise for unsupervised classification using composite data images and remote sensing data.