Autism Spectrum Disorder Risk Gene Prediction Using Improved Salp Swarm Algorithm and Enhanced Convolution Neural Network Algorithm
A group of Neuro developmental disorders is Autism Spectrum Disorder (ASD) which is characterized by communication skills and social interaction difficulties. In past few years, there is a rapid increase in ASD and its root symptom’s cause is not yet determined. Comparatively large effort is needed in the existing system using Bayes network and there is no universally accepted technique to construct a network from data. An Enhanced Convolution Neural Network (ECNN) and Improved Salp Swarm Algorithm (ISSA) is proposed to solve these issues and for effective ASD classification. The task corresponds to classifying a long non-coding RNA (lncRNA) gene would cause a disease or not. After class balancing, discretization is applied for converting continuous values into discrete values and for optimal gene selection, ISSA algorithm is used. From genomic data, candidate gene biomarkers are identified using this gene selection. Every possible feature subset is computed for minimizing irrelevant features and error rate in gene data. It is focused to enhance ASD classification model’s accuracy. The Enhanced Convolutional Neural Network algorithm is used for ASD classification. The autism microarray dataset from the benchmark public repository, Gene Expression Omnibus (GEO) (National Center for Biotechnology Information (NCBI) is used for analysis. The proposed work using ISSA and ECNN exhibits better performance in terms of precision, accuracy, specificity, sensitivity and time complexity as indicated in the results.