Efficient Evolutionary Based Clustering Approaches for Health Care Data

Abstract

Good health care is one of the most significant factors which can make a contribution to the individual well-being of everyone in the modern world. The detection of diseases is a crucial and difficult task in healthcare. The recognition of diseases from numerous features or signs is a prime issue which is not free from false presumptions frequently followed with the aid of unpredictable effects. The healthcare enterprise gathers large amounts of disease data that unfortunately, are not mined to decide concealed facts for effective diagnosing. As the quantity of stored data increases, clustering play a vital role in extracting knowledge and finding patterns to provide better care and effective diagnostic capabilities. Clustering aims to arrange a set of data objects into clusters; such that objects inside a cluster are “similar” to each other than they are to objects in the different clusters. There are various numbers of applications for clustering which includes marketing, scientific and engineering, ecommerce, image segmentation business etc. The current work in the thesis focuses on the two diseases namely Wisconsin Breast Cancer and Epileptic seizure. The work relies on the finding the optimal solution based on clustering techniques. The proposed clustering techniques based evolutionary algorithms namely GA-clustering, PSO-clustering and DE-clustering are applied on breast cancer wisconsin dataset and their effectiveness is evaluated on the basis of DB index and classification parameters. In another work, a novel partitioning based clustering using DE approach is proposed that is applied on epileptic seizure recognition dataset and its results are compared with DE-clustering approach on the basis of cluster validity measures namely DB index, Dunn index and computational time. So, clustering techniques are of vital importance that it organizes the data, thereby generating patterns that can be further utilized for better analysis of diseases.