Habibollah Haron

Intelligent Information and Database Systems

A multiple constrained fuzzy controller design methodology is developed in this paper to achieve state variance constraint and passivity constraint for a model car system. The model car system considered in this paper is represented by a discrete-time Takagi-Sugeno fuzzy model with multiplicative disturbance. The proposed fuzzy controller is accomplished by using the technique of parallel distributed compensation. Based on the parallel distributed compensation technique, the sufficient conditions are derived to achieve variance constraint, passivity constraint and stability performance constraint, simultaneously. By solving these sufficient conditions with linear matrix inequality technique, the multiple constrained fuzzy controllers can be obtained for the model car system. At last, a numerical simulation example is provided to illustrate the feasibility and validity of the proposed fuzzy control method.

Statistical Learning Theory and Support Vector Machines

It has been more than 30 years that statistical learning theory (SLT) has been introduced in the field of machine learning. Its objective is to provide a framework for studying the problem of inference that is of gaining knowledge, making predictions, making decisions or constructing models from a set of data. Support Vector Machine, a method based on SLT, then emerged and becoming a widely accepted method for solving real-world problems. This paper overviews the pattern recognition techniques and describes the state of art in SVM in the field of pattern recognition.

Optimization of process parameters in the abrasive waterjet machining using integrated SA-GA

In this study, Simulated Annealing (SA) and Genetic Algorithm (GA) soft computing techniques are integrated to estimate optimal process parameters that lead to a minimum value of machining performance. Two integration systems are proposed, labeled as integrated SA-GA-type1 and integrated SA-GA-type2. The approaches proposed in this study involve six modules, which are experimental data, regression modeling, SA optimization, GA optimization, integrated SA-GA-type1 optimization, and integrated SA-GA-type2 optimization. The objectives of the proposed integrated SA-GA-type1 and integrated SA-GA-type2 are to estimate the minimum value of the machining performance compared to the machining performance value of the experimental data and regression modeling, to estimate the optimal process parameters values that has to be within the range of the minimum and maximum process parameter values of experimental design, and to estimate the optimal solution of process parameters with a small number of iteration compared to the optimal solution of process parameters with SA and GA optimization. The process parameters and machining performance considered in this work deal with the real experimental data in the abrasive waterjet machining (AWJ) process. The results of this study showed that both of the proposed integration systems managed to estimate the optimal process parameters, leading to the minimum value of machining performance when compared to the result of real experimental data.

Supervised, Unsupervised, and Semi-Supervised Feature Selection: A Review on Gene Selection

Recently, feature selection and dimensionality reduction have become fundamental tools for many data mining tasks, especially for processing high-dimensional data such as gene expression microarray data. Gene expression microarray data comprises up to hundreds of thousands of features with relatively small sample size. Because learning algorithms usually do not work well with this kind of data, a challenge to reduce the data dimensionality arises. A huge number of gene selection are applied to select a subset of relevant features for model construction and to seek for better cancer classification performance. This paper presents the basic taxonomy of feature selection, and also reviews the state-of-the-art gene selection methods by grouping the literatures into three categories: supervised, unsupervised, and semi-supervised. The comparison of experimental results on top 5 representative gene expression datasets indicates that the classification accuracy of unsupervised and semi-supervised feature selection is competitive with supervised feature selection.

Accumulated risk of body postures in assembly line balancing problem and modeling through a multi-criteria fuzzy-genetic algorithm

Monotonous body postures during repetitive jobs negatively affect assembly-line workers with the developing of Work-related Musculoskeletal Disorders (WMSDs). Ergonomics specialists have offered auxiliary posture diversity to deal with the lack of varieties, especially for high-risk ones. Meanwhile, Assembly Line Balancing (ALB) problem has been recognized as a prior thinking to (re)configure assembly lines via the balancing of their tasks among their workstations. Some conventional criteria, cycle time and overall workload are often considered during the balancing. This paper presents a novel model of ALB problem that incorporates assembly worker postures into the balancing. In addition to the conventional ALB criteria, a new criterion of posture diversity is defined and contributes to enhance the model. The proposed model suggests configurations of assembly lines via the balancing; so that the assigned workers encounter the opportunities of changing their body postures, regularly. To address uncertainties in the conventional criteria, a fuzzy goal programming is used, and an appropriate genetic algorithm is developed to deal with the model. Various computational tests are performed on the different models made with combinations of the three criteria mentioned above. Comparing the pay-offs among the combinations, results show that well balanced task allocation can be obtained through the proposed model.

Fuzzy logic for modeling machining process: a review

The application of artificial intelligence (AI) techniques in modeling of machining process has been investigated by many researchers. Fuzzy logic (FL) as a well-known AI technique is effectively used in modeling of machining processes such as to predict the surface roughness and to control the cutting force in various machining processes. This paper is started with the introduction to definition of FL and machining process, and their relation. This paper then presents five types of analysis conducted on FL techniques used in machining process. FL was considered for prediction, selection, monitoring, control and optimization of machining process. Literature showed that milling contributed the highest number of machining operation that was modeled using FL. In terms of machining performance, surface roughness was mostly studied with FL model. In terms of fuzzy components, center of gravity method was mostly used to perform defuzzification, and triangular was mostly considered to perform membership function. The reviews extend the analysis on the abilities, limitations and effectual modifications of FL in modeling based on the comments from previous works that conduct experiment using FL in the modeling and review by few authors. The analysis leads the author to conclude that FL is the most popular AI techniques used in modeling of machining process.

Surface reconstruction techniques: a review

Surface reconstruction means that retrieve the data by scanning an object using a device such as laser scanner and construct it using the computer to gain back the soft copy of data on that particular object. It is a reverse process and is very useful especially when that particular object original data is missing without doing any backup. Hence, by doing so, the data can be recollected and can be stored for future purposes. The type of data can be in the form of structure or unstructured points. The accuracy of the reconstructed result should be concerned because if the result is incorrect, hence it will not exactly same like the original shape of the object. Therefore, suitable methods should be chosen based on the data used. Soft computing methods also have been used in the reconstruction field. This papers highlights the previous researches and methods that has been used in the surface reconstruction field.

Parameterization Method on B-Spline Curve

The use of computer graphics in many areas allows a real object to be transformed into a three-dimensional computer model (3D) by developing tools to improve the visualization of two-dimensional (2D) and 3D data from series of data point. The tools involved the representation of 2D and 3D primitive entities and parameterization method using B-spline interpolation. However, there is no parameterization method which can handle all types of data points such as collinear data points and large distance of two consecutive data points. Therefore, this paper presents a new parameterization method that is able to solve those drawbacks by visualizing the 2D primitive entity of scanned data point of a real object and construct 3D computer model. The new method has improved a hybrid method by introducing exponential parameterization method in the beginning of the reconstruction process, followed by computing B-spline basis function to find maximum value of the function. The improvement includes solving a linear system of the B-spline basis function using numerical method. Improper selection of the parameterization method may lead to the singularity matrix of the system linear equations. The experimental result on different datasets show that the proposed method performs better in constructing the collinear and two consecutive data points compared to few parameterization methods.

Genetic Algorithm and Simulated Annealing to estimate optimal process parameters of the abrasive waterjet machining

In this study, two computational approaches, Genetic Algorithm and Simulated Annealing, are applied to search for a set of optimal process parameters value that leads to the minimum value of machining performance. The objectives of the applied techniques are: (1) to estimate the minimum value of the machining performance compared to the machining performance value of the experimental data and regression modeling, (2) to estimate the optimal process parameters values that has to be within the range of the minimum and maximum coded values for process parameters of experimental design that are used for experimental trial and (3) to evaluate the number of iteration generated by the computational approaches that lead to the minimum value of machining performance. Set of the machining process parameters and machining performance considered in this work deal with the real experimental data of the non-conventional machining operation, abrasive waterjet. The results of this study showed that both of the computational approaches managed to estimate the optimal process parameters, leading to the minimum value of machining performance when compared to the result of real experimental data.

SIMULATED ANNEALING TO ESTIMATE THE OPTIMAL CUTTING CONDITIONS FOR MINIMIZING SURFACE ROUGHNESS IN END MILLING Ti-6Al-4V

This study presents the estimation of the optimal effect of the radial rake angle of the tool, combined with cutting speed and feed in influencing the surface roughness result. Studies on optimization of cutting conditions for surface roughness in end milling involving radial rake angle are still lacking. Therefore, considering the radial rake angle, this study applied simulated annealing in determining the solution of the cutting conditions to obtain the minimum surface roughness when end milling Ti-6Al-4V. Considering a set of experimental machining data, the regression model is developed. The best regression model was considered to formulate the fitness function of the simulated annealing. It was recommended that the cutting conditions should be set at highest cutting speed, lowest feed and highest radial rake angle in order to achieve the minimum surface roughness of 0.1385 µm. Subsequently, it was found that by using simulated annealing, the minimum surface roughness was much lower than the experimental sample data, regression modelling and response surface methodology technique by about 27%, 26% and 50%, respectively.