| Abstract |
The notion of smart cities has garnered significant momentum worldwide in recent times, primarily due to the growing interest in utilizing technology to tackle diverse urban issues, especially in the healthcare sector. Smart cities have been demonstrated to be game-changing, employing a wide range of technology tools and procedures to optimize patient outcomes and lower costs, increase overall efficiency, and improve accessibility to healthcare. In the last decade, several clusters have been developed to help classify the different types of cancer by looking at gene expression data. The study of cancer subtypes identified by cluster analysis has garnered a lot of interest recently. Conventional clustering techniques are still used for grouping cancer samples, nevertheless. No research into cluster weights has proved the greater performance of various clustering approaches. Several issues and challenges must be resolved while dealing with feature weights. However, a careful investigation reveals that no cluster-weighted clustering methods have yet been proposed. In this chapter, we introduce cluster-weighting, a brand-new universal clustering technique that includes a step where weights are distributed throughout the clusters. The weights of each cluster are calculated using the median weighting approach, silhouette weighting approach, nearest centroid weighting approach, and sum of distances weighting approach. We compare the performance of our novel method to well-established clustering algorithms like K-means, X-means, and feature-weighted K-means. Our technique outperforms X-means, K-means, and feature-weighted K-means significantly. © 2025 selection and editorial matter, Diptendu Sinha Roy, Mir Wajahat Hussain, K. Hemant Kumar Reddy, Deepak Gupta; individual chapters, the contributors. |
