Jasmy Yunus

Non‐imaging Focusing Heliostat

A non-imaging focusing heliostat for effective use of thermal solar energy is proposed. The heliostat consists of a number of grouped slave mirrors, which are able to move according to a proposed formula to eliminate the first order aberration. The master mirror tracks the sun by a proposed rotation-elevation mode to project solar rays together with the rest of slave mirrors into a fixed target. The merit of this design is that it may benefit the use of solar energy in high temperature applications by allowing a single stage collector to replace a conventional double stage structure; it may also benefit high concentration applications, e.g., solar powered Stirling engines, solar pumped lasers, etc. The feasibility and a reliability test of the proposed method by a prototype heliostat in the University of Technology, Malaysia is reported.

Extraction of dynamic features from hand drawn data for the identification of children with handwriting difficulty

Studies have shown that differences between children with and without handwriting difficulties lie not only in the written product (static data) but also in dynamic data of handwriting process. Since writing system varies among countries and individuals, this study was conducted to determine the feasibility of using quantitative outcome measures of childrens drawing to identify children who are at risk of handwriting difficulties. A sample of 143 first graders of a normal primary school was investigated regarding their handwriting ability. The children were divided into two groups: test and control. Ten children from test group and 40 children from control group were individually tested for their Visual Motor Integration skills. Analysis on dynamic data indicated significant differences between the two groups in temporal and spatial measures of the drawing task performance. Thus, kinematic analysis of childrens drawing is feasible to provide performance characteristic of handwriting ability, supporting its use in screening for handwriting difficulty.

The use of graphic rules in grade one to help identify children at risk of handwriting difficulties.

Previous researches on elementary grade handwriting revealed that pupils employ certain strategy when writing or drawing. The relationship between this strategy and the use of graphic rules has been documented but very little research has been devoted to the connection between the use of graphic rules and handwriting proficiency. Thus, this study was conducted to investigate the relative contribution of the use of graphic rules to the writing ability. A sample of 105 first graders who were average printers and 65 first graders who might experience handwriting difficulty, as judged by their teachers, of a normal primary school were individually tested on their use of graphic rules. It has been found that pupils who are below average printers use more non-analytic strategy than average printers to reproduce the figures. The results also reveal that below average printers do not acquire the graphic principles that foster an analytic approach to production skills. Although the findings are not sufficient to allow definitive conclusions about handwriting ability, it can be considered as one of the screening measures in identifying pupils who are at risk of handwriting difficulties.

Speaker-independent Malay vowel recognition of children using multi-layer perceptron

Most of the speech recognitions are based on adult speech sounds. Less research is done in the recognition of children speech sounds. The speech of children is more dynamic and inconsistent if compared to adults speech. This paper investigates the use of neural networks in recognizing 6 Malay vowels of Malay children in a speaker-independent manner. Multi-layer perceptron with one hidden layer was used to recognize these vowels. The multi-layer perceptron was trained and tested with speech samples of Malay children with their ages between seven and ten years old. A single frame of cepstral coefficients was extracted around the vowel onset point using linear predictive coding. The vowel length was examined from 5 ms to 70 ms. Experiments were conducted to determine the optimal vowel length as well as the number of cepstral coefficients.

Feature Extraction of Kidney Ultrasound Images Based on Intensity Histogram and Gray Level Co-occurrence Matrix

This study proposes an approach of feature extraction of kidney ultrasound images based on five intensity histogram features and nineteen gray level co-occurrence matrix (GLCM) features. Kidney ultrasound images were divided into four different groups; normal (NR), bacterial infection (BI), cystic disease (CD) and kidney stones (KS). Before feature extraction, the images were initially preprocessed for preserving pixels of interest prior to feature extraction. Preprocessing techniques including region of interest cropping, contour detection, image rotation and background removal, have been applied. Test result shows that kurtosis, mean, skewness, cluster shades and cluster prominence dominates over other parameters. After normalization, KS group has highest value of kurtosis (1.000) and lowest value of cluster shades (0.238) and mean (0.649) while NR group has highest value of mean (1.000), skewness (1.000), cluster shades (1.000) and cluster prominence (1.000). CD group has the lowest value of skewness (0.625) and BI has the lowest value of kurtosis (0.542). This shows that these features can be used to classify kidney ultrasound images into different groups for creating database of kidney ultrasound images with different pathologies.

Cervix Detection Using Squared Error Subtraction

In order to reduce uncomfortable cervix screening either using Pap smear or transvaginal ultrasound scanning, an autonomous transabdominal ultrasound scanning is proposed. This requires an exact probe position and angulation to capture the cervix image. In this paper, we present a new method to detect cervix in the best position and angulation. More than 100 samples were processed and analyzed. Image enhancement of the ultrasound image data was performed before further processing and cervix detection. The best cervix ultrasound image was used as a reference template for analysis. The correlation between template and target image was compared using squared error subtraction of histograms. Test results show that taking a different rate threshold at 0.075, an accuracy of 100% for cervix identification is achieved. This method is very efficient since it uses a simple algorithm and requires low memory capacity. This technique will be powerful to be used for real time autonomous scanning of cervix for surgical monitoring or acceptable operator-independent cervix screening.

Thermal distribution analysis of three-dimensional tumor-embedded breast models with different breast density compositions

Breast cancer is the most common cancer among women globally, and the number of young women diagnosed with this disease is gradually increasing over the years. Mammography is the current gold-standard technique although it is known to be less sensitive in detecting tumors in woman with dense breast tissue. Detecting an early-stage tumor in young women is very crucial for better survival chance and treatment. The thermography technique has the capability to provide an additional functional information on physiological changes to mammography by describing thermal and vascular properties of the tissues. Studies on breast thermography have been carried out to improve the accuracy level of the thermography technique in various perspectives. However, the limitation of gathering women affected by cancer in different age groups had necessitated this comprehensive study which is aimed to investigate the effect of different density levels on the surface temperature distribution profile of the breast models. These models, namely extremely dense (ED), heterogeneously dense (HD), scattered fibroglandular (SF), and predominantly fatty (PF), with embedded tumors were developed using the finite element method. A conventional Pennes’ bioheat model was used to perform the numerical simulation on different case studies, and the results obtained were then compared using a hypothesis statistical analysis method to the reference breast model developed previously. The results obtained show that ED, SF, and PF breast models had significant mean differences in surface temperature profile with a p value <0.025, while HD breast model data pair agreed with the null hypothesis formulated due to the comparable tissue composition percentage to the reference model. The findings suggested that various breast density levels should be considered as a contributing factor to the surface thermal distribution profile alteration in both breast cancer detection and analysis when using the thermography technique.

Speaker-independent phonation recognition for Malay plosives using neural networks

The paper investigates the use of neural networks in recognizing the phonation of the speech sounds. The proposed method classifies the Malay plosive sounds of adults and children based on phonation in a speaker-independent manner. The proposed method achieves encouraging result with an average accuracy of 98%.

Computer-based Malay articulation training for Malay plosives at isolated, syllable and word level

This paper describes the use of computer as an articulation training system for Malay plosives at isolated, syllable and word level. The proposed system is more convenient than the traditional speech analyzing tools such as electropalatograph, where the latter requires an external electronic circuit to be attached into the mouth of client. The system is designed in a way that is user friendly and easy to use for the speech-language pathologist or even the client. The client undergoes speech training by just talking into the microphone and the system is able to recognize the sounds and classify them accordingly. Audio and visual feedback is used to help the client to identify his or her articulation errors as well as to make comparisons between his/her articulation models with the standard model. The system can be used for both children and adults.

Speaker-independent Malay isolated sounds recognition

This paper simply describes the use of neural networks in recognizing some Malay isolated sounds of Malay children in a speaker-independent manner. The isolated sounds are Malay plosive sounds, which are comprised of /b/, /d/, /g/, /p/, /t/ and /k/. A three-layer Multi-layer Perceptron (MLP) is used to train and recognize the speech sounds. The MLP output layer has an output layer of 6 neurons, which correspond to the 6 isolated plosive sounds. Network parameters such as hidden neuron number and error function, were investigated to achieve the optimal performance of the MLP. The proposed system was able to achieve the highest accuracy of 84.67%.