| Abstract |
A cluster is a collection of data items. Clustering and outlier removal can be performed in various applications. A smart city makes use of data and technology to raise the standard of living for its citizens. Here, we are dealing with healthcare applications. Usually, clustering and outlier removal are done separately, but in this work, both topics are dealt with simultaneously. Clustering is performed by partitioning binary space and therefore the binary matrix is constructed. In this case, the similarity between the data points is determined by analyzing the distance measure. Two areas that are always gaining attention in the data mining field are cluster evaluation and outlier identification; it has a close relationship with one another. Inversely, outliers are points that belong to no clusters, making cluster structures vulnerable to them. Unfortunately, the majority of research in existence treats these two tasks independently without recognizing their linked relationship. In this work, the problem of simultaneous cluster evaluation and outlier identification is taken into account with regard to healthcare which comes up with the outlier removal using the clustering (COR) approach. In particular, the original space is transformed into a binary space by establishing basic partitions. Without incorporating many outlier candidates, holoentropy is used to assess each cluster’s degree of compactness. An auxiliary binary matrix is used to create a tidy and effective solution, fully eliminating the need for COR. © 2025 selection and editorial matter, Diptendu Sinha Roy, Mir Wajahat Hussain, K. Hemant Kumar Reddy, Deepak Gupta; individual chapters, the contributors. |
