Mohd Fauzi Othman

Comparison of Different Classification Techniques Using WEKA for Breast Cancer

The development of data-mining applications such as classification and clustering has shown the need for machine learning algorithms to be applied to large scale data. In this paper we present the comparison of different classifica- tion techniques using Waikato Environment for Knowledge Analysis or in short, WEKA. WEKA is an open source soft- ware which consists of a collection of machine learning algo- rithms for data mining tasks. The aim of this paper is to inves- tigate the performance of different classification or clustering methods for a set of large data. The algorithm or methods tested are Bayes Network, Radial Basis Function, Pruned Tree, Single Conjunctive Rule Learner and Nearest Neighbors Algo- rithm. A fundamental review on the selected technique is pre- sented for introduction purposes. The data breast cancer data with a total data of 6291 and a dimension of 699 rows and 9 columns will be used to test and justify the differences between the classification methods or algorithms. Subsequently, the classification technique that has the potential to significantly improve the common or conventional methods will be sug- gested for use in large scale data, bioinformatics or other gen- eral applications.

Probabilistic Neural Network for Brain Tumor Classification

In this paper, Probabilistic Neural Network with image and data processing techniques was employed to implement an automated brain tumor classification. The conventional method for medical resonance brain images classification and tumors detection is by human inspection. Operator-assisted classification methods are impractical for large amounts of data and are also non-reproducible. Medical Resonance images contain a noise caused by operator performance which can lead to serious inaccuracies classification. The use of artificial intelligent techniques for instant, neural networks, and fuzzy logic shown great potential in this field. Hence, in this paper the Probabilistic Neural Network was applied for the purposes. Decision making was performed in two stages: feature extraction using the principal component analysis and the Probabilistic Neural Network (PNN). The performance of the PNN classifier was evaluated in terms of training performance and classification accuracies. Probabilistic Neural Network gives fast and accurate classification and is a promising tool for classification of the tumors.

MRI brain classification using support vector machine

The field of medical imaging gains its importance with increase in the need of automated and efficient diagnosis in a short period of time. Other than that, medical image retrieval system is to provide a tool for radiologists to retrieve the images similar to query image in content. Magnetic resonance imaging (MRI) is an imaging technique that has played an important role in neuroscience research for studying brain images. Classification is an important part in retrieval system in order to distinguish between normal patients and those who have the possibility of having abnormalities or tumor. In this paper, we have obtained the feature related to MRI images using discrete wavelet transformation. An advanced kernel based techniques such as Support Vector Machine (SVM) for the classification of volume of MRI data as normal and abnormal will be deployed.

Global Path Planning for Autonomous Mobile Robot Using Genetic Algorithm

Mobile robots work in different kinds of environment, and it is necessary for them to move and maneuver in places with objects and obstacles. In order to navigate the robot in a collision free path, path planning algorithms have been presented. The main goal of path planning is to determine the optimal possible path between the initial point and the defined goal position in the minimal possible time. In this work, a path planning method by utilizing genetic algorithm (GA) is presented. The optimized path in terms of length and cost is generated by GA optimization. The proposed method is a global path planning method with hexagonal grid map modelling. It reads the map of the environment and plans the optimized path by using GA method simulated in MATLAB R2012b software. The simulation results are presented and analyzed.

An overview of MRI brain classification using FPGA implementation

The field of medical imaging gains its importance with increase in the need of automated and efficient diagnosis in a short period of time. Brain images have been selected for the image references because; the injuries to the brain tend to affect large areas of the organ. Magnetic resonance imaging (MRI) is an imaging technique that has been playing an important role in neuroscience research for studying brain images. The classifications of brain MRI data as normal and abnormal are important to prune the normal patient and to consider only those who have the possibility of having abnormalities or tumor. An advanced kernel based techniques such as Support Vector Machine (SVM) for the classification of volume of MRI data as normal and abnormal will be deployed. Image processing tasks can be characterized as being computationally intensive. One reason for this is the vast amount of data that requires the processing of more than seven million pixels per second for typical images sources. To keep up with this data rates, a careful and creative data management must be provided. Field Programmable Gate Array (FPGA) is one of the alternative that offer custom computing platforms, sufficiently flexible that new algorithms can be implemented on existing hardware and fast enough.

Optimization of fuel cost and transmission loss in power dispatch with renewable energy and energy storage

Minimizations of fuel cost and transmission loss during power dispatch are the main objectives of the problem described in this paper. The dispatch problem decides the amount of generation to be allocated to each generating unit including renewable sources so that the total fuel cost and transmission losses are minimized without violating the system constraints. This paper considers the dispatch problem for hybrid power system consists of thermal units, solar, wind and the storage. Consistent optimum results can be obtained by extracting maximum renewable energy during the available period and using it for both available and unavailable periods with the aid of energy storage. This paper illustrates the optimization of fuel cost and transmission losses with renewable storage using MATLAB simulations.

Application Of Artificial Immune System To Design Power Systems Stabilizer

Conventional power system stabilizers contain a phase lag/lead network for phase compensation and have played a very significant role to enhance the stability of power systems. Various new approaches have been proposed in the past 30 years to improve the performance of power system stabilizers such as modern control and artificial intelligence techniques. In this paper a new method of control will be implemented to a power systems stabilizer. This approach uses the artificial immune controller called the improved varela immune network controller or IVINC. The purposes of IVINC controller are to enhance the stability of power systems and to damp low frequency oscillations.

Stereo vision based robots: Fast and robust obstacle detection method

In this paper we present a new obstacle detection method, based on stereo vision, without combination with any other kind of sensors. The proposed method uses a differential image transform algorithm to gain robustness against illumination changes. This method increases the speed of program execution while keeping the performance of stereo vision algorithm in term of accuracy in the same level with the previous algorithms. Moreover, we implement this method into a stereo vision based robot while adding some new features to widen the depth detection range. With the help of the proposed method, the robot detects obstacles between 25cm to 400cm from robot cameras. The result shows the robot has the ability to work in a wide variety of lighting conditions, while the stereo vision part of the robot does the depth detection computation with the speed of 30FPS.

A New Fast and Robust Stereo Matching Algorithm for Robotic Systems

In this paper, we propose a new area-based stereo matching method by improving the classical Census transform. It is a difficult task to match corresponding points in two images taken by stereo cameras, mostly under variant illumination and non-ideal conditions. The classic Census nonparametric transform did some improvements in the accuracy of disparity map in these conditions but it also has some disadvantages. The results were not robust under different illumination, and because of the complexity the performance was not suitable for real-time robotic systems. In order to solve these problems, this paper presents an improved Census transform using Maximum intensity differences of the pixel placed in the center of a defined window and the pixels in the neighborhood to reduce complexity and obtain better performance and needs a smaller window size to obtain best accuracy compared to the Census transform. Experimental results show that the proposed method, achieves better efficiency in term of speed and robustness against illumination changes.

Environmental friendly power dispatch in Saudi Arabia with renewable energy and energy storage

Optimization of the total amount of pollutants emitted from the hybrid power plants is the main objective of the Environmental Friendly Dispatch (EFD). The EFD problem decides the amount of generation to be allocated to each generating unit including renewable sources so that the total emission of polluting gases is minimized without violating the system constraints. This type of optimization becomes more efficient in countries like Saudi Arabia where high potential of crude oil and renewable resources exists. This paper considers the problem of EFD for hybrid power system including solar, wind and the storage. High potential of solar and wind in Saudi Arabia ensures the availability of renewable sources to some extent. A consistent optimum EFD can be obtained by extracting maximum renewable energy during the available period and using it for both available and unavailable periods with the aid of energy storage. This paper illustrates the optimization of EFD with renewable storage using MATLAB simulation. The simulations have been done using IEEE-30 test bus data with 6 generators.