Welcome to the InfoSci Platform
Reference Hub5
Comparative Analysis of Bio-Inspired Optimization Algorithms in Neural Network-Based Data Mining Classification

Comparative Analysis of Bio-Inspired Optimization Algorithms in Neural Network-Based Data Mining Classification

Mathi Murugan T., Eppipanious Baburaj
Copyright: © 2022 |Volume: 13 |Issue: 1 |Pages: 25
ISSN: 1947-9263|EISSN: 1947-9271|EISBN13: 9781683181514|DOI: 10.4018/IJSIR.2022010103
Cite Article Cite Article

MLA

Mathi Murugan T., and Eppipanious Baburaj. "Comparative Analysis of Bio-Inspired Optimization Algorithms in Neural Network-Based Data Mining Classification." IJSIR vol.13, no.1 2022: pp.1-25. http://doi.org/10.4018/IJSIR.2022010103

APA

Mathi Murugan T. & Baburaj, E. (2022). Comparative Analysis of Bio-Inspired Optimization Algorithms in Neural Network-Based Data Mining Classification. International Journal of Swarm Intelligence Research (IJSIR), 13(1), 1-25. http://doi.org/10.4018/IJSIR.2022010103

Chicago

Mathi Murugan T., and Eppipanious Baburaj. "Comparative Analysis of Bio-Inspired Optimization Algorithms in Neural Network-Based Data Mining Classification," International Journal of Swarm Intelligence Research (IJSIR) 13, no.1: 1-25. http://doi.org/10.4018/IJSIR.2022010103

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

It always helps to determine optimal solutions for stochastic problems thereby maintaining good balance between its key elements. Nature inspired algorithms are meta-heuristics that mimic the natural activities for solving optimization issues in the era of computation. In the past decades, several research works have been presented for optimization especially in the field of data mining. This paper addresses the implementation of bio-inspired optimization techniques for machine learning based data mining classification by four different optimization algorithms. The stochastic problems are overcome by training the neural network model with techniques such as barnacles mating , black widow optimization, cuckoo algorithm and elephant herd optimization. The experiments are performed on five different datasets, and the outcomes are compared with existing methods with respect to runtime, mean square error and classification rate. From the experimental analysis, the proposed bio-inspired optimization algorithms are found to be effective for classification with neural network training.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.