Nor Haizan Mohamed Radzi

Glowworm swarm optimization (GSO) for optimization of machining parameters

This study proposes glowworm swarm optimization (GSO) algorithm to estimate an improved value of machining performance measurement. GSO is a recent nature-inspired optimization algorithm that simulates the behavior of the lighting worms. To the best our knowledge, GSO algorithm has not yet been used for optimization practice particularly in machining process. Three cutting parameters of end milling that influence the machining performance measurement, minimum surface roughness, are cutting speed, feed rate and depth of cut. Taguchi method is performed for experimental design. The analysis of variance is applied to investigate effects of cutting speed, feed rate and depth of cut on surface roughness. GSO has improved machining process by estimating a much lower value of minimum surface roughness compared to the results of experimental and particle swarm optimization.

Glowworm Swarm Optimization (GSO) Algorithm for Optimization Problems: A State-of-the-Art Review

Glowworm Swarm Optimization (GSO) algorithm is a derivative-free, meta-heuristic algorithm and mimicking the glow behavior of glowworms which can efficiently capture all the maximum multimodal function. Nevertheless, there are several weaknesses to locate the global optimum solution for instance low calculation accuracy, simply falling into the local optimum, convergence rate of success and slow speed to converge. This paper reviews the exposition of a new method of swarm intelligence in solving optimization problems using GSO. Recently the GSO algorithm was used simultaneously to find solutions of multimodal function optimization problem in various fields in today industry such as science, engineering, network and robotic. From the paper review, we could conclude that the basic GSO algorithm, GSO with modification or improvement and GSO with hybridization are considered by previous researchers in order to solve the optimization problem. However, based on the literature review, many researchers applied basic GSO algorithm in their research rather than others.

Fingerprint classification using Support Vector Machine

Fingerprint is one of the widely used biometric identification to identify the identity of a person due reliability and acceptability. Fingerprint classes are divided into five such as, arch, tented arch, left loop, right loop and whorl. The fingerprint classification provides indexing to the database to reduce the searching and mapping process. There are many algorithms that have been used by researchers to develop fingerprint classification model, such as the Neural Network (NN) algorithm, Genetic algorithm and Support Vector Machine (SVM) algorithm. In this study, SVM algorithm is used for developing fingerprint classification model. Fingerprint dataset used in this study was obtained from the Fingerprint Verification Competition (FVC), FVC2000 and FVC2002. The result of this study shows that SVM gave a high percentage of accuracy of the fingerprint classification which was 92.5%.

A study of metaheuristic algorithms for high dimensional feature selection on microarray data

Microarray systems enable experts to examine gene profile at molecular level using machine learning algorithms. It increases the potentials of classification and diagnosis of many diseases at gene expression level. Though, numerous difficulties may affect the efficiency of machine learning algorithms which includes vast number of genes features comprised in the original data. Many of these features may be unrelated to the intended analysis. Therefore, feature selection is necessary to be performed in the data pre-processing. Many feature selection algorithms are developed and applied on microarray which including the metaheuristic optimization algorithms. This paper discusses the application of the metaheuristics algorithms for feature selection in microarray dataset. This study reveals that, the algorithms have yield an interesting result with limited resources thereby saving computational expenses of machine learning algorithms.

Police personality classification using principle component analysis-artificial neural network

Personality is the defining essence of an individual as it guides the way we think, act and interpret external stimuli. Classification of personality is important as it can serves as a framework in the job assignment task, particularly, in the high risk job including the Police Force. There are many attributes of individual traits but not all of them can be used to indicate individual personality. In this paper, two classification models were developed to predict individual personality for the Royal Malaysian police (RMP) based on Type A and Type B personality theory. Both classification models are based on Artificial Neural Network (ANN). But, the second model applied Principle Component Analysis or called as PCA-ANN model. The second classification model successfully reduces the number of personality features to six features compared to initial 10 features. Furthermore, PCA-ANN improves the classification accuracy to 98.6% compared to 94.4% classification accuracy found in the first ANN model.

Web based online bakery system with short messaging service and email notification

Online shopping is becoming trend nowadays. People like online shopping compared to the traditional way to safe their cost and time. Cakes By Fara (CBS) is an online bakery ordering system where various types of cakes are the main product to sell online. The paper is aiming to develop a web based online bakery system using Short Message Service (SMS) as well as email notification technology for order confirmation, order status notification and verify of customers status of registration. There are three main users for the system which are registered customer, non-registered customer and administrator. Registered customers have more privilege in the system compared to nonregistered customers as they able to purchase the product online and received the notification through email and SMS. Rational Unified Process (RUP) methodology is used to develop the system.