부산대학교 도서관

Tuberous sclerosis Complex (TSC) disease is a multi-system genetic disorder that broadly affect the central nervous system resulting in Epilepsy, seizures, behavior problems, skin abnormalities, kidney disease etc. This hazardous disease is caused by defects or mutations of two genes: TSC1 and TSC2. The key challenge is to analyzing the hidden information that lies into TSC1 and TSC2 gene sequence which can reveal significant information to properly diagnosis the disease. Efficient data mining techniques can play a pivotal role in analyzing the attributes of TSCs in an automatic manner. For efficient classification of TSC, this paper proposes an optimized-CNN algorithm which is a hybridization of Convolution Neural Network (CNN) with Particle Swarm Optimization (PSO). Experimental analysis reveals that the proposed algorithm outperforms other traditional data mining techniques. The paper also generates analysis rules by applying Apriori and Decision Tree algorithms. The promising result of the proposed algorithm makes it a suitable candidate to be used by the medical experts for the diagnosis of the disease.