Ahmad Puad Ismail

Recognizing the ripeness of bananas using artificial neural network based on histogram approach

The main objective of this project is to develop a technique to classify the ripeness of bananas into 3 categories, which is unripe, ripe and overripe systematically based on their histogram RGB value components. This system involved the process of collecting samples with different level of ripeness, image processing and image classification by using artificial neural network. Collecting bananas sample is done by using Microsoft NX6000 webcam with 2 mega pixels. 32 samples were used as training samples for artificial neural network. In order to see whether the method mention above can classify the image correctly, another 28 images was used as a testing. From the result obtained, it was shown that the artificial neural network can generally classify the ripeness of bananas. This is because it can classify up to 25 samples correctly out of 28 samples. Developing a program totally by using Matlab version 7.0 can help classification process successfully.

Frontal view gait analysis of gender

The study aimed to investigate the potential of frontal view gait of human for gender recognition based on model based approach. Firstly, 128 features are extracted based on four parameters from the lower limb of human body specifically the left and right hip angles along with both left and right knee angles and these features are validated for gender recognition purpose. Next, statistical analysis and PSO are evaluated as feature selection in identifying the significant features amongst the original extracted gait features. Results attained with ANN as classifier proven that the original features extracted based on frontal view is capable to classify gender whilst PSO as subset selection showed promising accuracy rate with average of 85% for gender classification using the proposed front view gait technique.

Enhancement modeling method of human gait

Gait recognition is one of the identification techniques that can be utilized nowadays. Hence in this study the six features of anatomical of human body are evaluated as feature extraction to develop the modeling of human walking gait. In addition, the proposed model is compared with the standard stick figure model specifically during walking by focusing both thigh and knee angles. Based on analyzing walking gait with CASIA database as input, it is observed that the proposed model worked well and is comparable with the standard stick model. This confirmed that the proposed model is indeed suitable to be used for human gait analysis and recognition and will be further evaluated in the next stage of work.

Model-based gait analysis for gender recognition

Gender classification via model-based human gait data is still immature. Hence in this research, the possibility of side view human gait silhouette to be used as gender recognition is evaluated using model-based approach. Firstly, six attributes located at lower part of human gait specifically from below waist onwards have been identified as the significant points are skeletonized based on the human gait silhouette attained. Next the vertical angles of both hip and knee with respect to thigh for 32 image sequences are extracted as feature vectors followed by feature selection via statistical analysis specifically analysis of variance along with multiple comparison procedure. Further, the resultant of feature selection acted as inputs to the artificial neural network classifier. Initial findings with accuracy of 90% and above confirmed that the proposed method suited to be utilized as gender recognition based on human gait.

Analysis of Walking and Running Based on Markerless Model

This research investigated the possibility of side view human gait silhouette to be used for recognition of walking and running gait based on model-based approach. Markerless model with model based is used to produce the vertical angles of both hip and knee with respect to thigh for 32 image sequences as feature vectors for both legs for one complete cycle sequences. Overall, a total of 128 features are extracted based on four parameters from the lower limb of human body are validated for walking speed classification purpose. Further, the gait features extracted from different gait speeds is classified as walking and running gait using ANN and KNN. Initial findings with accuracy of almost 100% confirmed that the proposed method suited to be utilized as walking speed classification based on human gait.

Condition monitoring of electrical supply voltage quality to electrical machines using RBF neural network

Three phase electrical machines are normally exposed to lowered levels of supply voltage quality conditions which can appear simultaneously due to voltage disturbances of overvoltage or undervoltage, voltage unbalance and voltage waveform distortions. These voltage disturbances can cause effects of seriously overheating winding insulation resulting in degradation and reduced lifespan of the machines. The supply of electrical power with proper rated voltages and acceptable voltage waveforms can significantly improve the satisfactory operation and life span of the machines. The proper application of supply voltage quality levels can reduce the downtime and operating expenses of the electrical machines, thus improving return of investment on assets managed by the organization. In this paper, a control methodology for the early detection and classification of the electrical voltage supply condition in electrical machines based on radial based function (RBF) neural networks is presented. The condition of the supply voltage quality to electrical machines is diagnosed and classified using RBF neural networks. It will be shown that the developed method is simple in dealing with any supply voltage condition to detect and allows for the ease in classification of the supply voltage pattern. Test results for the classified patterns have shown that the method used for this classification scheme able to correctly identify supply voltage conditions, and the adopted RBF neural network condition monitoring based method is efficient.

Voltage sags and transient detection and classification using half/one-cycle windowing techniques based on continuous s-transform with neural network

This paper was conducted to detect and classify the different power quality disturbance (PQD) using Half and One-Cycle Windowing Technique (WT) based on Continuous S-Transform (CST) and Neural Network (NN). The system using 14 bus bars based on IEEE standard had been designing using MATLAB©/Simulink to provide PQD data. The datum of PQD is analyzed by using WT based on CST to extract features and it characteristics. Besides, the study focused an important issue concerning the identification of PQD selection and detection, the feature and characteristics of two types of signals such as voltage sag and transient signal are obtained. After the feature extraction, the classified process had been done using NN to show the percentage of classification PQD either voltage sags or transients. The analysis show which selection of cycle for windowing technique can provide the smooth detection of PQD and the suitable characteristic to provide the highest percentage of classification of PQD.This paper was conducted to detect and classify the different power quality disturbance (PQD) using Half and One-Cycle Windowing Technique (WT) based on Continuous S-Transform (CST) and Neural Network (NN). The system using 14 bus bars based on IEEE standard had been designing using MATLAB©/Simulink to provide PQD data. The datum of PQD is analyzed by using WT based on CST to extract features and it characteristics. Besides, the study focused an important issue concerning the identification of PQD selection and detection, the feature and characteristics of two types of signals such as voltage sag and transient signal are obtained. After the feature extraction, the classified process had been done using NN to show the percentage of classification PQD either voltage sags or transients. The analysis show which selection of cycle for windowing technique can provide the smooth detection of PQD and the suitable characteristic to provide the highest percentage of classification of PQD.

I D -V D and I D -V G analysis of 45nm NMOS with strained silicon on insulator (sSOI) by using simulation

SILVACO TCAD simulator which is consisting of a process simulator, ATHENA and device simulator, ATLAS were used to simulate and analyze the electrical characterization of 45nm NMOS with strained silicon on insulator (sSOI). In this paper, the process parameters with halo implantation and sSOI were used. The effective simulation was performed by using ATHENA process simulator to modify theoretical values. While the electrical characteristics of the device was produce out by ATLAS simulator which are the variation of ID-VD and ID-VG were produced. These two modules were combined to aid in design and optimizer the process parameters. The threshold voltage (VTH) result was compare with the 45nm NMOS device.

Front view markerless model for human identification

Based on previous work done by researchers, human can be identified using their gait. Hence, in this paper, six features from human body anatomical are evaluated as feature extraction to model the front view of human gait. Further, 128 features are extracted from the proposed markerless front model which is based on four parameters from the lower limb of human body specifically the left and right hip angles along with both left and right knee angles. Next the extracted features acted as features to the KNN classifier. From the result, it can be observed that KNN is capable to identify perfectly human gait based on the proposed model for both Cityblock and Euclidean distance metric.