Noor Ezan Abdullah

Classification of Rubber Tree Leaf Diseases Using Multilayer Perceptron Neural Network

This paper presents about classification of rubber tree leaf diseases through automation and utilizing primary RGB color model. Several rubber tree leaf diseases are been studied for digital RGB color extraction where three sets of rubber tree leaf diseases image are digitally captured under standard and control environment. The identified regions of interest (ROI) of these diseases images are then processed to quantify the normalized indices from the RGB color distribution. This system involved the process of image classification by using artificial neural network where 600 samples were used as training while another 200 samples were for testing. The optimized ANN model in this work has two method which based only on the dominant pixel RGB (mean) and applying principle component analysis (PCA) on the pixel gradation values of each image. The optimized model was evaluated and validated through analysis of the performance indicators. Findings in this work have shown that both models have produced about 70% in diagnostic accuracy with more than 80% achievement for sensitivity. However, model with the applied PCA has lower network size.

A statistical approach for orchid disease identification using RGB color

This paper presented a statistical approach for recognition of orchid diseases using RGB color analysis. As for features, the scale infection and black leaf spot disease of the orchid have been chosen in this study. Orchid plant with these two category disease samples were taken from a local home orchid collector and captured using digital camera in a controlled environment. The RGB components are extracted as features and statistical analysis specifically error plot and T-Test are utilized for differentiation between orchid either with scale or black leaf spot disease. Initial findings showed that the proposed method is capable to differentiate these two category diseases.

Classification of watermelon leaf diseases using neural network analysis

This paper mainly discussed the process to classify Anthracnose and Downey Mildew, watermelon leaf diseases using neural network analysis. A few of infected leaf samples were collected and they were captured using a digital camera with specific calibration procedure under controlled environment. The classification on the watermelons leaf diseases is based on color feature extraction from RGB color model where the RGB pixel color indices have been extracted from the identified Regions of Interest (ROI). The proposed automated classification model involved the process of diseases classification using Statistical Package for the Social Sciences (SPSS) and Neural Network Pattern Recognition Toolbox in MATLAB. Determinations in this work have shown that the type of leaf diseases achieved 75.9% of accuracy based on its RGB mean color component.

Modern Control Systems in Electrical Engineering course assessment using the Outcome Based Education approach

In the year 2004, Outcome-Based Education (OBE) has been adopted by the Engineering Accreditation Council (EAC) in accrediting Electrical Engineering Programmes for universities in Malaysia. To fulfill the requirement, Faculty of Electrical Engineering (FEE), Universiti Teknologi MARA (UiTM) has taken necessary steps to implement OBE in each programme offered. An OBE measurement tool known as Summative Assessment Dynamic Model with OBE compliance (SAMOBEC 2.0) was developed by the faculty OBE Committees to facilitate lecturers to conduct their teaching and assessment activities in alignment with the course and programme outcomes. This paper focuses on analyzing the outcome of the course assessment of Modern Control Systems in Electrical Engineering using the available tool. It was found that the tool has provided detailed information from the designing phase until result achievements. From the available plots, the Programme Outcomes of this course has yet to achieve the target set by the faculty. However, few recommendations has been made for continual improvements in the future.

High speed with low power folding and interpolating ADC using two types of comparator in CMOS 0.18um technology

This paper describes the design of a 8-bit CMOS folding and interpolating Analog to Digital Converter (ADC) with high speed comparator. The objective of this paper is to design and identify the performance of the ADC with two types of comparator. Another objective of this paper is to minimize the power consumption of the ADC circuit from a comparator. Flash ADC is one of the faster ways to convert any analog signal to a digital signal. It uses folding and interpolating techniques allow each comparator of the ADC to be reused several times over the full scale input range. In addition, interpolating technique can reduce the number of folding circuit required in a folding ADC hence further improve the performance of the ADC in term of capacitive loading and power consumption. Besides that, 70 percent speed of the ADC also depends on the comparator. If we use very fast and stable comparator, the ADC will be more fast and effectively to do the next applications. The simulation results indicate that the comparator design 1 achieved lower power operation rather than comparator design 2 with a minimum number of transistors used, 2GHz of input signal and 497.02mW of power consumption from a single 2V supply based to Gateway Silvaco EDA tools simulation result.

A characterization of watermelon leaf diseases using Fuzzy Logic

This paper presents a characterization of watermelon leaf diseases through the RGB color. The aim of this study is to perform identification of selected critical watermelon leaf diseases in Malaysia namely the Downy Mildew and Anthracnose diseases. Several samples of infected leaves images were put under digital RGB color extraction where the images were captured under standardized and controlled environment. This study involves 200 samples of infected leaves of which the classification of the diseases was carried out using Fuzzy Logic technique. Fuzzy Logic was used to handle the uncertainty and vagueness as it provides a means of translating qualitative and imprecise information into quantitative (linguistic) terms. The results have shown that the percentage of accuracy for both types of disease were more than 67%.

A Statistical Approach for Rubber Seed Clones Classification Using Reflectance Index

This paper presents a statistical study for rubber seed clones classification. There are five types of clones from the same series of rubber seed being used as samples in this work which are the PB360, RRIM2009, RRIM2011, RRIM2016 and RRIM2025. The main objective is to identify significant features based on reflectance indices of both lateral and dorsal of the rubber seed surfaces from the application of ZEISS spectrometer instrument. The instrument measures the percentage of reflectance with respect to intensity of safe radiation light being reflected from the seed surface. Empirical analysis is done using SPSS software in order to identify discrimination between the clones. From the observed error plots and one-way ANOVA measurements, it is shown that reflectance indices of lateral surface can be used to recognize significantly the RRIM2009 from the other rubber seed clones.

A Rudimentary Optical System in Detecting Ripeness of Red Watermelon

The purpose of this project is to detect the ripeness and quality of the watermelon particularly for red watermelon. The ripeness of the watermelon will be evaluated by using near-infrared spectroscopy sensor (NRIS). The color wavelength will classify the ripeness of the watermelon. An infrared light will be used to get the appropriate wavelength from the watermelon either from the rind or inner of it and the signal received will be analyzed. An appropriate algorithm is used to extract the information of the inner of the watermelon. A microcontroller namely Programmable Interface Controller (PIC) will be used to execute the algorithm and the result will be displayed on Liquid Crystal Display (LCD). Based on the result obtain from the device, the data is computed by using Statistical Package for the Social Sciences (SPSS). This approach is vital to verify the relationship between unripe and ripeness of red watermelon. The objective of this project is to produce an efficient system to detect the ripeness of the watermelon.

A study on palmistry color reflectance related to personality of subject

Palmistry technique is traditionally known as an ancient art of reading the palm and it can be found in many parts of the world. Since blood circulation in the palm contains valuable information about the health condition of a person, this technique acts as one of the aid tools for diagnosing purposes. This paper presents a novel study on palmistry color reflectance related to personality of subject. The main objective is to collect personality and health information as well as to capture palm images digitally from sample of subjects representing various faculties at Universiti Teknologi Mara. Afterwards, appropriate statistical tools will be used for significant information that can relate personality and health index. This paper focus on contribution in the field of color image processing of palmistry with the help of advanced RGB color image processing techniques in order to study the personality index of a subject. In this work, samples of palm images are digitally captured under standard and control environment. Other characteristic parameters representing the subjects personality are also taken. Statistical tools are applied to the quantified color component indices from the processed image for significant findings that can relate color of palm with respect to the subjects character. As the conclusion, the non-social group can be discriminated from all other groups based on all color components.

Fuzzification of rubber tree white root disease based on leaf's discolouration

This paper describes research work in developing an intelligent model for detecting white root disease stages by using fuzzy logic. In this work, classification of three stages of white root disease is based on discolouration of the trees leaf. These stages are healthy, medium & worse and each of them were tested with respect to vein, main vein and peteolute. The reflectance of the leaves discolouration sample is measured by using MCS600 Carl Zeiss spectrometer. Analysis and justification are done statistically for features extraction and selection as input for fuzzy system. From the statistical result there is strong evidence that the stages of the white root disease can be discriminated from each other. Input value for the fuzzy system, based on the selection of the result from statistic software. Two inputs have been selected to be the input for the fuzzy system which are main vein and vein. Overall performance of the system is 78.33% accuracy after being tested with 300 samples in order to distinguish healthy, medium and worse respectively.