Marzuki Khalid

Self-tuning PID control: a multivariable derivation and application

Abstract In this paper, a multivariable self-tuning controller with a proportional plus integral plus derivative (PID) structure is derived. The algorithm features a combination of the self-tuning property, in which the controller parameters are tuned automatically on-line, and also the structure of a multivariable PID controller, making it more favourable for use in industry. The algorithm is applied to a microcomputer based multi-input multi-output (MIMO) furnace. Some experiments are conducted to observe the ability of the controller in the temperature control of MIMO furnace under set-point changes and its relative robustness as compared with a fixed-tuned multivariable PID (FTMPID) controller. The experimental results prove that the controller is capable of giving a good control result for the process.

An offline cursive handwritten word recognition system

This paper describes an offline cursive handwritten word recognition system that combines hidden Markov models (HMM) and neural networks (NN). Using a fast left-right slicing method, we generate a segmentation graph that describes all possible ways to segment a word into letters. The NN computes the observation probabilities for each letter hypothesis in the segmentation graph. Then, the HMM compute the likelihood for each word in the lexicon by summing the probabilities over all possible paths through the graph. We present the preprocessing and the recognition process as well as the training procedure for the NN-HMM hybrid system. Another recognition system based on discrete HMM is also presented for performance comparison. The latter is also used for bootstrapping the NN-HMM hybrid system. Recognition performances of the two recognition systems using two image databases of French isolated words are presented. This paper is one of the first publications using the IRONOFF database, and thus can be used as a reference for future work on this database.

Optimization of fuzzy model using genetic algorithm for process control application

Abstract A technique for the modeling of nonlinear control processes using fuzzy modeling approach based on the Takagi–Sugeno fuzzy model with a combination of genetic algorithm and recursive least square is proposed. This paper discusses the identification of the parameters at the antecedent and consequent parts of the fuzzy model. For the antecedent fuzzy parameters, genetic algorithm is used to tune them while at the consequent part, recursive least squares approach is used to identify the system parameters. This approach is applied to a process control rig with three subsystems: a heating element, a heat exchanger and a compartment tank. Experimental results show that the proposed approach provides better modeling when compared with Takagi Sugeno fuzzy modeling technique and the linear modeling approach.

Face Recognition System using Artificial Neural Networks Approach

Advances in face recognition have come from considering various aspects of this specialized perception problem. Earlier methods treated face recognition as a standard pattern recognition problem; later methods focused more on the representation aspect, after realizing its uniqueness using domain knowledge; more recent methods have been concerned with both representation and recognition, so a robust system with good generalization capability can be built by adopting state-of-the-art techniques from learning, computer vision, and pattern recognition. A face recognition system based on recent method which concerned with both representation and recognition using artificial neural networks is presented. This paper initially provides the overview of the proposed face recognition system, and explains the methodology used. It then evaluates the performance of the system by applying two (2) photometric normalization techniques: histogram equalization and homomorphic filtering, and comparing with euclidean distance, and normalized correlation classifiers. The system produces promising results for face verification and face recognition

Comparison of Feature Extractors in License Plate Recognition

Vehicle license plate recognition has been intensively studied in many countries. Due to the different types of license plates being used, the requirement of an automatic license plate recognition system is different for each country. In this paper, an automatic license plate recognition system is proposed for Malaysian vehicles with standard license plates using blob labeling and clustering for segmentation, seven popular and one proposed edge detectors for feature extraction and neural networks for classification. There were eight experiments conducted using eight different edge detectors: Kirsch, Sobel, Laplacian, Wallis, Prewitt, Frei Chen and a proposed edge detector. The result had shown kirsch edge detectors is the best technique for feature exractor while the proposed achieved better results compared to Prewitt, Frei Chen and Wallis

Evolutionary Fuzzy ARTMAP Neural Networks for Classification of Semiconductor Defects

Wafer defect detection using an intelligent system is an approach of quality improvement in semiconductor manufacturing that aims to enhance its process stability, increase production capacity, and improve yields. Occasionally, only few records that indicate defective units are available and they are classified as a minority group in a large database. Such a situation leads to an imbalanced data set problem, wherein it engenders a great challenge to deal with by applying machine-learning techniques for obtaining effective solution. In addition, the database may comprise overlapping samples of different classes. This paper introduces two models of evolutionary fuzzy ARTMAP (FAM) neural networks to deal with the imbalanced data set problems in a semiconductor manufacturing operations. In particular, both the FAM models and hybrid genetic algorithms are integrated in the proposed evolutionary artificial neural networks (EANNs) to classify an imbalanced data set. In addition, one of the proposed EANNs incorporates a facility to learn overlapping samples of different classes from the imbalanced data environment. The classification results of the proposed evolutionary FAM neural networks are presented, compared, and analyzed using several classification metrics. The outcomes positively indicate the effectiveness of the proposed networks in handling classification problems with imbalanced data sets.

Nonlinear Identification of a Magneto-Rheological Damper Based on Dynamic Neural Networks

Semi-active control of dynamic response of civil structures with magneto-rheological (MR) fluid dampers has emerged as a novel revolutionary technology in recent years for designing “smart structures.” A small-scale MR damper model with the valve mode mechanism has been examined in this research using dynamic recurrent neural network modeling approach to reproduce its hysteretic nonlinear behavior. Modified Bouc–Wen model based on nonlinear differential equations has not only been employed as the reference model to provide a comprehensive training data for the neural network but also for comparison purposes. A novel frequency and amplitude varying displacement input signal (modulated chirp signal) associated with a random supply voltage has been introduced for persistent excitation of the damper in such a way to cover almost all of its operating conditions. Finally a series of validation tests were conducted on the proposed model which proved the appropriate performance of the model in terms of accuracy and capability for realization.

A new readout approach in DNA computing based on real-time PCR with taqman probes

A new readout approach for the Hamiltonian Path Problem (HPP) in DNA computing based on the real-time polymerase chain reaction (PCR) is investigated. Several types of fluorescent probes and detection mechanisms are currently employed in real-time PCR, including SYBR Green, molecular beacons, and hybridization probes. In this study, real-time amplification performed using the TaqMan probes is adopted, as the TaqMan detection mechanism can be exploited for the design and development of the proposed readout approach. Double-stranded DNA molecules of length 120 base-pairs are selected as the input molecules, which represent the solving path for an HPP instance. These input molecules are prepared via the self-assembly of 20-mer and 30-mer single-stranded DNAs, by parallel overlap assembly. The proposed readout approach consists of two steps: real-time amplification in vitro using TaqMan-based real-time PCR, followed by information processing in silico to assess the results of real-time amplification, which in turn, enables extraction of the Hamiltonian path. The performance of the proposed approach is compared with that of conventional graduated PCR. Experimental results establish the superior performance of the proposed approach, relative to graduated PCR, in terms of implementation time.

Using Gabor Filters as Image Multiplier for Tropical Wood Species Recognition System

One of the main problems in wood species recognition systems is the lack of discriminative features of the texture images. In order to overcome this, we use Gabor filter in the pre-processing stage of the wood texture image to multiply the number of features for a single image, thus providing more information for feature extractor to capture. The textural wood features are extracted using two feature extraction methods which are co-occurrence matrix approach, known as grey level co-occurrence matrix (GLCM) and also Gabor filters to generate more variation of features and to improve the accuracy rate. The combined features extracted from GLCM and Gabor filters are sent to the classifier module. A multi-layer neural network based on the popular back propagation (MLBP) algorithm is used for classification. The results show that increasing the number of features by using Gabor filters as image multiplier and the combination of features from Gabor filters and GLCM feature extractors improved the accuracy rate of the wood species recognition system.

An analytical handwritten word recognition system with word-level discriminant training

We describe an analytical handwritten word recognition system combining neural networks (NN) and hidden Markov models (HMM). Using a fast left-right slicing method, we generate a segmentation graph that describes all possible ways to segment a word into characters. The NN computes the observation probabilities for each character hypothesis in the segmentation graph. Then, using concatenated character HMMs, a likelihood is computed for each word in the lexicon by multiplying the observation probabilities over the best path through the graph. The role of the NN is to recognize characters and to reject non-characters. We present our approach to globally train the word recognizer using isolated word images. Using a maximum mutual information (MMI) cost function at the word level, the discriminant training updates the parameters of the NN within a global optimization process based on gradient descent. The recognizer is bootstrapped from a baseline recognition system, which is based on character level training. The recognition performance of the globally trained system is compared to the baseline system.