Investigations of swarm intelligence and meta heuristic algorithm as feature selection for enhancement of classifiers performance in detection of diabetes from microarray gene data
Loading...
Date
item.page.authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Diabetes mellitus poses a significant global health challenge, particularly in low- and middle-income countries such as India, where its prevalence is rapidly increasing. This thesis addresses the critical need for significant and early detection of diabetes using microarray gene data, aiming to advance the state of the art in diabetes detection through innovative methodologies. The research addresses the high dimensionality nature of microarray data by employing various Dimensionality Reduction (DR) techniques, including Bessel Function (BF), Detrended Fluctuation Analysis (DFA), Chi-square probability density function (Chi 2 pdf), Firefly Algorithm (FA), Cuckoo Search (CS), Discrete Cosine Transform (DCT), Least Square Linear Regression (LSLR), and Artificial Algae Algorithm (AAA). These techniques aim to extract the most relevant features and reduce data size while preserving essential information for enhanced diabetes classification.
newline