Rohaiza Baharudin

Preliminary study of recognizing alphabet letter via hand gesture

Communication is one of human basic necessity. People with disabilities usually use sign language to communicate with others. The study identifies the alphabet letters from the finger spelling based on American Sign Language (ASL) standard. The bending sensors were attached to three fingers of spelling glove where the bending movement of each finger contributes different resistance value of the bending sensors. The combinations of resistance value from each finger were detected from microcontrollers library and alphabet letters will be displayed. This study assists normal person who are new to sign language to understand the spelling letters when communicate with the disabilities.

Microwave Absorber Coating Material Using Oil Palm Ash

The most important part to be highlighted in developing a reliable microwave absorber is the material used to fabricate the absorber. As an alternative in managing the increase of the oil palm residues throughout the country, this study is focusing on developing a microwave absorber coating using oil palm fly ash. The software uses for design and simulation of microwave absorber is CST Microwave Studio (CST MWS) which enables the fast and accurate analysis of high frequency devices. The simulation design is fabricated to a number of layers which is coated by oil palm ash as a lossy element. The measurement and performance are carried out in the high broadband frequency of 8 to 12 GHz (X-band).

Characteristic Evaluation of Multiple Layers Microwave Absorber Coated with Biomass Composite

Radiation Absorbing Material (RAM) is used to absorb radiations of electromagnetic wave surrounding us. Thus, the multiple layers’ microwave absorber using biomass composite materials could be one of the solutions to address the problem. In order to effectively absorb the radiation of electromagnetic wave, the multiple layers’ absorber is characterized to optimize the performance of the absorber. The characterization is made by varying biomass composite material contents, thickness and other possible considerations. CST Microwave Studio software is first used to design and simulate the multiple layers’ absorber to estimate its performance. Development of multiple layers’ prototype is carried out to test its performance at free space environment. Free space dielectric measurement method is used to determine the value of multiple layers’ absorber dielectric. The dielectric value is then used in CST software in order to make the simulation more precise. Free space arch which is connected to Agilent Analyzer is used to measure absorption of multiple layers’ microwave absorber.

Comparisons of MLP transfer functions for different classification classes

This paper presents a comparison study of two different MLP transfer functions for three different classification cases of breast cancer, thyroid disease and weather classification. The transfer functions under investigation are sigmoid and hyperbolic tangent. In the study, MLP network was trained and tested to investigate the ability of the network to classify the breast cancer correctly between benign cell and malignant cell, classifying thyroid disease into normal, hyper or hypo thyroid and classifying weather conditions into four types; rain, cloudy, dry day and storm. Levenberg-Marquardt algorithm is adopted to train MLP network since it is the fastest training and ensure the best converges towards a minimum error. The performance of MLP networks was evaluated in terms of percentages for correct classification of the target outputs. Both functions are able to give accuracies up to 99% for classifying correctly. The hyperbolic tangent function had shown the capability of achieving the highest accuracy of an MLP performance with less number of hidden nodes.

Performance of Hybrid Radial Basis Function network: Adaptive Fuzzy K-Means versus Moving k-Means Clustering as centre positioning algorithms on cervical cell precancerous stage classification

Cervical cancer been known to be the cause of many deaths each year. Screening tests, such as the Pap smear test used for the detection of the precancerous stage are able to avoid the occurrence of cervical cancer. However, the Pap smear test does have some disappointing disadvantages such as the fact that it has less effective slide preparation and also that it is laden with human error. Therefore, a computer-aided diagnosis system is introduced as a solution to the problem. Recently, artificial neural networks have been widely implemented as a cervical cancer diagnosis system i.e. to classify cervical cancer into normal and abnormal cells. In this recent study, neural network architecture i.e. the Hybrid Radial Basis Function (HRBF) network with Adaptive Fuzzy K-Means Clustering (AFKM) asa centre positioning algorithm is used to diagnose cervical cancer. Four extracted features of cervical cell are used as input data to the networks, which are the size of nucleus and cytoplasm and its grey level. Cells from normal, Low-grade Squamous Intraepithelial Lesion (LSIL) and High-grade Squamous Intraepithelial Lesion (HSIL) categories are used as the training as well as the testing data. The data are fed randomly into the neural networks via 5-folds cross validation techniques. The network performance is compared with the HRBF network with the Moving K-Means algorithm as the centre positioning algorithm. The proposed network produces better accuracy, sensitivity and specificity which illustrates the promising capability of the network to be implemented as cervical cancer diagnosis system for Pap test performance improvement.

Development of remote laboratory for temperature control frequency response analysis

Control System Theory is a compulsory subject to be taken by engineering students in various disciplines. However to relate the theoretical knowledge with the real control system application is very challenging in a conventional faced to faced pedagogy due to the time, facilities, cost and location constraint. This paper discusses the design and implementation of a web based to support theoretical knowledge during lecture session. This project uses the capabilities of LabVIEW software and data acquisition card to obtain the measurement of the actual hardware in the and make it available through the web. As a result, instructors are able to demonstrate the integration of theoretical knowledge and actual application through web-based experiments with a significant reduced in time requirement and cost.

Design and development of an adjustable angle sensor based on rotary potentiometer for measuring finger flexion

In this paper, an adjustable angle sensor based on rotary potentiometer for measuring and monitoring finger flexion is proposed. Most of the current system is unadjustable, inaccurate, costly and hard to calibrate. The proposed system in this study consists of a rotary potentiometers and adjustable case, which makes it adjustable, compact and lightweight with the ability to produce a better measurement result. As the rotary potentiometer rotated due to the motion of the finger, the joint angles are calculated by measuring the change in resistance of the rotary potentiometer. The proposed system can widely be applied for the angle measurement systems at small and complex structure surface such as finger joint, which require to measure finger flexion for developing related device such as robotic hand control system, virtual reality or teleoperation systems. The experiment study shows that the proposed system is adjustable and has better accuracy, small repeatability error and more reliable compared to the popular flex sensor.

Delivering a frequency response laboratory in a web-based learning environment

A virtual laboratory experiment has gradually growing on demand as preferable technical exposure method in many universities. This is due to time, facilities, cost and location limitation. This study focuses on the architecture, performance and effectiveness of a web-based laboratory in assisting students to relate theoretical knowledge learnt during lecture session with real application. With the capabilities of Laboratory Virtual Instrument Engineering Workbench (LabVIEW) and the Data Acquisition (DAQ) card, the measurement of the actual hardware in the laboratory is obtained and published through the web.

Improvement study of the reflectivity for hollow pyramidal shape absorbers

This paper presents an investigation of the reflectivity performance for hollow pyramidal shape microwave absorbers. The pyramidal absorbers used in this study is constructed using four 15cm-pyramidal absorbers stacked on each other to equal the height of one single 45cm-absorber. The wave frequency ranging from 8GHz to 12 GHz was chosen for simulation and measurement of the absorber performance. The reflectivity performances of the stacked pyramidal absorbers were compared to single level pyramidal absorbers in term of their reflectivity performances. The result shows that the stacked pyramidal absorber has higher absorption level an average absorption of −24 dB for the above frequency range.

Performance study of preliminary mini anechoic chamber fitted with coconut shell coated absorbers

An anechoic chamber is considered good when there is no signal reflection inside the chamber and also when there is no incoming signal from outside the chamber. The key element inside an anechoic chamber is the absorbing material. The evaluations of mini anechoic chamber fitted with coated absorbers were carried out by analyzing the absorption performance. The study includes the comparison of measurement with and without coated absorbers. The evaluations were carried out using 500 MHz, 2 GHz and 10GHz frequencies. The most significant result shows an absorption level of up to approximately 75% when the chamber was fitted with coated absorbers for 10 GHz.