Predicting Autism Spectrum Disorder in Children Using Glowworm Optimization With Extreme Learning Machine Networks

TL;DR

This paper introduces a new system using Glowworm Optimization and Extreme Learning Machine Networks to predict autism spectrum disorder in children more efficiently and accurately.

Contribution

The novel integration of Glowworm Optimization with Extreme Learning Machine Networks improves ASD prediction accuracy and efficiency.

Findings

The proposed GO-ELMN model achieves high accuracy in ASD prediction.

The system offers fast convergence and low computational cost.

The framework is effective for handling limited and imbalanced ASD data.

Abstract

The earlier prediction of autism spectrum disorder (ASD) placed a serious attention on ensuring the appropriate intervention to improve the child's behavioral, cognitive, and social development. The previous detection process is commonly time‐intensive, subjective, and highly dependent on the clinical professions, which leads to limited accessibility in rural areas. The difficulties are addressed by introducing effective ASD detection systems, which provide a scalable, objective, and fast solution, reducing the challenges in the healthcare environment.

This work integrates the Glowworm Optimization with Extreme Learning Machine Networks (GO‐ELMN) model to enhance the efficiency of ASD prediction. During the analysis, ASD screening data for children are collected and processed frequently to obtain behavioral, demographic, and medical features. The extracted features are processed by an extraction learning technique, in which the network hyperparameters are optimized using the glowworm optimization algorithm. The optimized classifier recognizes children's behavior by addressing the issues of limited and imbalanced data.

The efficiency of the system is evaluated using experimental results, in which the system ensures high accuracy and convergence speed.

The ASD detection model provides an interpretable, fast, and reliable solution that is effectively utilized in the pediatric healthcare domain.

The proposed framework for ASD detection has been illustrated. The process begins with dataset collection and preprocessing, followed by feature selection and hyperparameter optimization using GSO. The optimized features are classified through an ELM classifier, yielding high accuracy, fast convergence, and low computational cost for reliable ASD prediction.

Figures