LEVENBERG MARQUARDT AND BAYESIAN REGULARIZATION TRAINING ALGORITHM BASED MLP NETWORK PREDICTION FOR SHAPE AGGREGATE

Authors

  • Ja'afar Adnan Department of Electrical & Electronic Engineering, Faculty of Engineering, National Defence University of Malaysia, Sg. Besi Camp, 57000 Kuala Lumpur, Malaysia
  • Mohd Salman Mohd Sabri Department of Electrical & Electronic Engineering, Faculty of Engineering, National Defence University of Malaysia, Sg. Besi Camp, 57000 Kuala Lumpur, Malaysia
  • Syahrull Hi-Fi Syam Ahmad Jamil Department of Mathematics and Science Computer, Politeknik Tuanku Syed Sirajuddin, 02600 Arau, Perlis, Malaysia
  • Shanusi Ahmad School of Education, College of Arts and Sciences, Universiti Utara Malaysia, 06010 UUM Sintok, Kedah, Malaysia
  • Nazrul Fariq Makmor Department of Electrical & Electronic Engineering, Faculty of Engineering, National Defence University of Malaysia, Sg. Besi Camp, 57000 Kuala Lumpur, Malaysia

Keywords:

Aggregate, Multilayer Perceptron, Training Algorithm, Mean Square Error, Regression

Abstract

The assessment of aggregate quality is predicated on a combination of manual grading and mechanical filtering through established traditional methods. Aggregates are mandated to undergo a series of mechanical, physical, and chemical testing protocols to verify their compliance with predefined standards. The manual evaluation processes are intrinsically inefficient and subjective, resulting in significant temporal resource expenditure. This project aims to design an image processing system capable of categorizing aggregates into distinct classifications. The classification system leverages an artificial neural network (ANN) to perform image analysis for the identification of aggregate morphologies. The study systematically evaluates the performance of various training algorithms for the ANN, specifically juxtaposing Levenberg Marquardt (LM) against Bayesian Regularization (BR) as training paradigms. The findings demonstrate that BR training outperforms other methodologies, as evidenced by superior mean square error (MSE) metrics and improved regression results. The integration of the BR training algorithm with a multilayer perceptron (MLP) network achieves optimal performance in terms of regression accuracy and MSE assessment. Through the implementation of BR training, the network attained an MSE of 1.2042 and a regression coefficient of 0.9892, thereby validating its capability to classify aggregates through image analysis effectively. This novel approach provides researchers with a robust and objective solution that supersedes traditional manual classification methodologies.

Downloads

Download data is not yet available.

Downloads

Published

30-05-2025

How to Cite

Ja’afar Adnan, Mohd Salman Mohd Sabri, Syahrull Hi-Fi Syam Ahmad Jamil, Shanusi Ahmad, & Makmor, N. F. (2025). LEVENBERG MARQUARDT AND BAYESIAN REGULARIZATION TRAINING ALGORITHM BASED MLP NETWORK PREDICTION FOR SHAPE AGGREGATE. Zulfaqar Journal of Defence Science, Engineering & Technology, 8(1). Retrieved from https://zulfaqarjdset.upnm.edu.my/index.php/zjdset/article/view/141

Issue

Section

Articles