A Modified Particle Swarm Optimization with Neural Network via Euclidean Distance

Authors

DOI:

https://doi.org/10.3991/ijes.v6i1.8080

Abstract


In this paper, a new modified model of Feed Forward Neural Network with Particle Swarm Optimization via using Euclidean Distance method (FNNPSOED) is used to better handle a classification problem of the employee’s behavior. The Particle Swarm Optimization (PSO) as a natural inspired algorithm is used to support the Feed Forward Neural Network (FNN) with one hidden layer in obtaining the optimum weights and biases using different hidden layer neurons numbers. The key reason of using ED with PSO is to take the distance between each two-feature value then use this distance as a random number in the velocity equation for the velocity value in the PSO algorithm. The FNNPSOED is used to classify employees’ behavior using 29 unique features. The FNNPSOED is evaluated against the Feed Forward Neural Network with Particle Swarm Optimization (FNNPSO). The FNNPSOED produced satisfactory results.

Author Biography

Tarik A. Rashid, University of Kurdistan

Dr. Tarik Ahmed Rashid received his Ph.D. in Computer Science and Informatics degree from College of Engineering, Mathematical and Physical Sciences, University College Dublin (UCD) in 2001-2006. He pursued his Post-Doctoral Follow at the Computer Science and Informatics School, College of Engineering, Mathematical and Physical Sciences, University College Dublin (UCD) from 2006-2007. He was a Professor at Salahaddin University-Erbil, Hawler, Kurdistan. He Joined the University of Kurdistan Hewlêr (UKH) in 2017.

Downloads

Published

2018-03-19

How to Cite

Jabar, A. L., & Rashid, T. A. (2018). A Modified Particle Swarm Optimization with Neural Network via Euclidean Distance. International Journal of Recent Contributions from Engineering, Science & IT (iJES), 6(1), pp. 4–18. https://doi.org/10.3991/ijes.v6i1.8080

Issue

Section

Papers