Azian Azamimi Abdullah

Design and Development of Fuzzy Expert System for Diagnosis of Hypertension

The aim of this study is to design a Fuzzy Expert System (FES) for diagnosis of hypertension risk for patients aged between 20s, 30s and 40s years and is divided into male and female gender. The input data is collected from a total of 10 people which consists of male and female with different working background. The parameters used as input for this fuzzy expert system were age, Body Mass Index (BMI), blood pressure and heart rate. Hypertension is diagnosed if blood pressure is over than 140/90mmHg. Hypertension is called the silent killer because it has no symptoms and can cause serious disease if left untreated for a long time. Thus, an intelligent and accurate diagnostic system is needed in order to threat the hypertension patient. It is expected that our proposed Fuzzy Expert System can provide a faster, cheaper and more accurate result compared with other traditional methods.

Improving colour image segmentation on acute myelogenous leukaemia images using contrast enhancement techniques

Contrast enhancement and image segmentation play an important process in most medical image analysis tasks. One of the main tasks is the analyzing of white blood cells (WBC) where the WBC composition reveals important diagnostic information of a patient. This paper presents a two phase methodology in order to obtain a fully segmented abnormal white blood cell (blast) and nucleus in acute leukaemia images. In the first phase, the three contrast enhancement techniques which are partial contrast, bright stretching and dark stretching were used to improve the image quality. Contrast enhancement techniques enhanced the area of interest of acute leukaemia for easing the segmentation process. In the second phase, image segmentation based on HSI (Hue, Saturation, Intensity) colour space is proposed. The proposed technique helps to improve the image visibility and has successfully segmented the acute leukaemia images into two main components: blast and nucleus. The combination between contrast enhancements and image segmentation has good effect on improving the accuracy of segmentation. Hence, information gain from the resultant images would become useful for haematologists to further analysis the types of acute leukaemia.

Screening of bone marrow slide images for Leukemia using Multilayer Perceptron (MLP)

The ability to screen between normal and abnormal bone marrow slide images with high accuracy rate is very much needed before going for the classification of the types and subtypes of Leukemia. Beforehand, the bone marrow slide images will be implemented with digital image processing techniques which include image enhancement, image segmentation and feature extraction. They are 13 features that have been extracted from every white blood cell on both normal and abnormal bone marrow slide images. These extracted features include area, perimeter, radius, circularity, mean value for red, blue and green respectively, standard deviation and variance also from red, blue and green respectively. In this paper, the neural network based classifier, Multilayer Perceptron (MLP) is used for screening task. The MLP network is trained using the Levenberg Marquardt (LM) training algorithm. The extracted features were assigned as data input to the network and the result of the screening has been proven to have high accuracy rate which is 98.667% for training dataset and 94.5% for testing dataset.

Development of cellular neural network algorithm for detecting lung cancer symptoms

Lung cancer is the most common of lethal types of cancer. One of the most important and difficult tasks a doctor has to carry out is the detection and diagnosis of cancerous lung nodules from x-ray images result. Some of these lesions may not be detected because of camouflaged by the underlying anatomical structure, the low-quality of the images or the subjective and variable decision criteria used by doctors. Hence, a detection system using cellular neural network (CNN) is developed in order to help the doctors to recognize the doubtful lung cancer regions in x-ray films. In this study, a CNN algorithm for detecting the boundary and area of lung cancer in x-ray image has been proposed. Computer simulation result shows that our CNN algorithm is verified to detect some key lung cancer symptoms successfully and has been proved by radiologist.

Bacteria Classification Using Electronic Nose for Diabetic Wound Monitoring

Array based gas sensor technology namely Electronic Nose (E-nose) now offers the potential of a rapid and robust analytical approach to odor measurement for medical use. Wounds become infected when a microorganism which is bacteria from the environment or patients body enters the open wound and multiply. The conventional method consumes more time to detect the bacteria growth. However, by using this E-Nose, the bacteria can be detected and classified according to their volatile organic compound (VOC) in shorter time. Readings were taken from headspace of samples by manually introducing the portable e-nose system into a special container that containing a volume of bacteria in suspension. The data will be processed by using statistical analysis which is Principle Component Analysis (PCA) and Linear Discriminant Analysis (LDA) methods. The most common bacteria in diabetic foot are Staphylococcus aureus, Escherchia coli, Pseudomonas aeruginosa, and many more.

Synthesis and characterization of bioceramic from Malaysian cockle shell

Anadara granosa (Ag) is a marine bivalve cockles which can be found in the tidal mudflats bordering the coastal region of many south East Asian countries particularly Malaysia, Indonesia and Thailand. This research is aim to investigate the potential of Malaysian cockle (Anadara Granosa) shell to be used as bone substitute material. Therefore, in this study two types of bioceramic has been produced which made from a pure Anadara granosa (Ag) powder and the another one is a mixture of Ag and synthetic Hydroxyapatite (HAP) powder with a mix ratio of 3:7. Pellets of bioceramic from these powders were fabricated by uniaxial pressing technique followed by sintering process at different temperatures. Sintering of HAP-Anadara granosa (HAP-Ag) bioceramic samples at 700°C resulted in highest compressive strength without the effect of decomposition. The results indicated that the average apparent density of these samples was 1.45g/cm3 and the average compressive strength was 7.0 MPa. With the compressive strengths comparable to human bone, HAP-Ag is suggested to be used for injectable bone filler and bone graft for non-load bearing bone such as cervical and lumbar bone.

Design and development of an emotional stress indicator (ESI) kit

Emotional Stress Indicator (ESI) kit is a wearable sensor device that used to measure the human stress level. Many people out there do not aware about their level of stress that will give a big impact in their life. So this study is aimed to design and develop an Emotional Stress Indicator (ESI) kit which can display stress level among people. This ESI kit is constructed based on human skin resistance which is changed upon condition. Human skin offers some resistance to current and voltage. The skin resistance changes with the emotional state of the body. From galvanic skin response theory, resistance varies inversely proportional to the stress. Stress level is high when the resistance of skin is less. In the relaxed state, the resistance offered by the skin is as high as 2 mega-ohms or more, which reduces to 500 kilo-ohms or less when the emotional stress is too high. The reduction in skin resistance is caused by an increased blood flow and permeability followed by the physiological changes during high stress. This increases the electrical conductivity of the skin.

Evaluation of E-nose technology for detection of the causative bacteria in different culture media on diabetic foot infection

The three different culture media namely blood agar, Mueller Hinton and MacConkey were used in this study to identify and classify the causative bacteria on diabetic foot infection using electronic nose (E-nose). All the samples were taken from the clinical specimens using standard swabbing technique. E-nose consisting an array of 32 conducting polymer sensors was used to detect volatile organic compounds (VOCs) released by the bacteria in the infected areas. The VOC profiles of three bacterial groups from three genera namely Escherichia coli (ECOLI), Staphylococcus aureus (SAU) and Pseudomonas aeruginosa (PAE) were characterized using statistical classification technique called Linear Discriminant Analysis (LDA) to differentiate between different agars used with individual bacteria species which accounted for all the data. Although these methods are still fundamental, there is an increasing shift toward molecular diagnostics of bacteria. This investigation showed that the E-nose was able to correctly classify different bacterial species in all three culture media with up to 90% accuracy.

Performance Comparisons of New Excitation Coil Design Aspects in Magnetic Induction Tomography (MIT) Applications

Magnetic Induction Tomography (MIT) is a contactless method interested in conductivity properties of the object. In MIT system, excitation coil plays an important role since it generate primary field which then will propagate through the object (in this case is biological tissues) going to be imaged. The main problem in MIT is the magnitude of primary field is very large compare to secondary field generate by the tissue due to tissues low conductivity. This primary field besides disturb the detected secondary signal at the receiver, it also introduce interference to the neighbour’s circuit. The main objective of this research is to design an excitation coil which has the capability of focusing the primary field only to the object while at the same time reducing the interference to the neighbour’s circuit. The simulation results have shown that through the design, the primary field can be focused and the interference can be reduced.

Compaction Optimization of Sn-Cu-Si3N4 via Powder Metallurgy Route for Composite Solder Fabrication

The aim of this study was to optimize the compaction process of a composite solder fabricated via powder metallurgy route, before details study were conducted in the next stage. Powder of Sn, Cu and Si3N4 were carefully weighted, mixed and blended in a mechanical alloying machine. Si3N4 were added to the Sn-0.7Cu solder as reinforcement.After 6 hours of mixing and blending, the powders were later compacted into a thin disc at 5 different pressures. Densities and volumes of the compacted samples were then obtained by using MicromeriticsAccuPyc II 1340 Gas Pycnometer. All data were analyzed and compared with each other in order to select the best parameter for compaction pressure. Results showed that at 140 bars, the porosity percentage is the lowest. Hence, it was decided that 140 bars is the best parameter for compaction process.