MUHAMMAD NAZRI IN REJAB
@ptss.edu.my
Tuanku Syed Sirajuddin Polytechnic
Scopus Publications
Scopus Publications
Muhammad Nazri Rejab, Omar Mohd Faizan Marwah, Muhammad Akmal Johar, and Mohamed Najib Ribuan
MDPI AG
Harvesting energy from solar radiation in Malaysia attracts the attention of researchers to utilize the potential by ongoing improvement. Roofing material with low albedo absorbs the heat, that can then be harvested using a thermoelectric generator. Previous research only measured the open-circuit voltage with different thermoelectric generator configurations. Low power output limits the potential to be utilized. The low output power can be increased using a DC converter. However, the converter must be tuned concerning low- and high-voltage levels, bipolar, and the maximum power point tracking. Therefore, this paper presents a dual-level voltage bipolar (DLVB) thermal energy harvesting system. The circuit is tested at constant and various time intervals to evaluate the system’s functionality and performance. Experiment results show that the proposed harvesting system can boost from 0.6 and 1.6 V to achieve the optimum level. The mean efficiency of the harvesting circuit obtains 91.92% at various time intervals. Further, the field test result obtains output power from 1.45 to 66.1 mW, with the mean efficiency range of 89.62% to 92.98%. Furthermore, recommendations are listed for future research.
Muhammad Nazri Rejab and Muhammad Akmal Johar
Allerton Press
Muhammad Nazri Rejab and Muhammad Akmal Johar
IEEE
Solar radiation at the rooftop and attic area generated potential thermal energy. Thereby, TEG utilizes to harvest the thermal energy. However, the effect of TEG array configuration combined with different load resistance to the real-time temperature difference is evaluated. Furthermore, MATLAB Simulink was used to evaluate the array configuration of the performance in terms of output power according to the real-time data from the experiment. The absolute data analysis deals with bipolar temperature values, thus obtaining accurate results. Furthermore, the impedance matching of the TEG array configuration was determined to achieve optimal power transfer. In comparison, parallel configuration shows higher energy with 190 % than series. Interestingly, the morning and evening sections proved the availability of potential thermal energy at the attic area that can be harvested. Furthermore, the result indicates that the DC converter is needed to enhance the energy harvested.
Muhammad Nazri Rejab, Muhammad Akmal Johar, Wan Akashah Wan Jamaludin, and Umar Abubakar Saleh
IEEE
Uncomplicated thermoelectric generator setup used to determine the potential thermal energy harvesting at roof and attic area due to the solar radiation for 20 days. A theoretical method is used to determine the output power due to the temperature difference at the thermoelectric generator module. The equivalent load resistance value refers to the thermoelectric generator array configuration. From the result, the attic area shows the potential of thermal energy that can be harvested due to the slow convection of heat to the surrounding. In addition, the effect of solar radiation at the day section is observed.
Umar Abubakar Saleh, Muhammad Akmal Johar, Siti Amely Binti Jumaat, Muhammad Nazri Rejab, and Wan Akashah Wan Jamaludin
Institute of Research and Community Services Diponegoro University (LPPM UNDIP)
The development of renewable energy, especially solar, is essential for meeting future energy demands. The use of a wide range of the solar spectrum through the solar cells will increase electricity generation and thereby improve energy supply. However, solar photovoltaics (PV) can only convert a portion of the spectrum into electricity. Excess solar radiation is wasted by heat, which decreases solar PV cells’ efficiency and decreases their life span. Interestingly, thermoelectric generators (TEGs) are bidirectional devices that act as heat engines, converting the excess heat into electrical energy through thermoelectric effects through when integrated with a PV. These generators also enhance device efficiency and reduce the amount of heat that solar cells dissipate. Several experiments have been carried out to improve the hybrid PV-TEG system efficiency, and some are still underway. In the present study, the photovoltaic and thermoelectric theories are reviewed. Furthermore, different hybrid system integration methods and experimental and numerical investigations in improving the efficiency of PV-TEG hybrid systems are also discussed. This paper also assesses the effect of critical parameters of PV-TEG performance and highlights possible future research topics to enhancing the literature on photovoltaic-thermoelectric generator systems.
Md. Saidin Wahab, Muhammad Nazri Rejab, and Mohd Pahmi Saiman
Trans Tech Publications, Ltd.
Woven composite based on natural fiber increasingly used for many applications in industries because of their advantages such as good relative mechanical properties and renewable resources, but there are some issues as cost and protracted development period to perform reliability evaluation by experimental with real scale. Predictive modeling technique is use to minimize the need for physical testing, shorten design timescales and provide optimized designs. Mechanical properties of woven fabrics for technical textile depend on a) type of raw materials b) type and count of warp and weft yarns c) yarn density and d) the type of weave structure. The effect of fabric architecture to the mechanical properties is investigated. Woven kenaf composite is modeled using the modeling software to get the properties of the model. Further, the model is analyzed using finite element analysis to predict the mechanical properties of the woven kenaf composite. In addition, the effect of the combination of yarn size and weave pattern to the woven kenaf composite is stated base on the mechanical properties to predict the optimum structure of woven kenaf composite.
Muhammad Naufal Mansor and Mohd Nazri Rejab
Trans Tech Publications, Ltd.
Late of infant pain detection on the early stage may affect newborns growth. Regarding of this matter, different techniques have been proposed such as facial expressions, speech production variation, and physiological signals to detect the pain states of a person. For past 2 decades, the determination of pain state through images has been undergone substantial research and development. Various techniques are used in the literature to classify pain states on the basis of images. In this paper, a feature extraction method using Principal Component Analysis (PCA) was adopted for identifying the pain states of an infant. In this study images samples are taken from Classification of Pain Expressions (COPE) database. Fuzzy k-NN, k Nearest Neighbor (k-NN), Feed Forward Neural network (FFNN) and Linear Discriminant analysis (LDA) based classifier is used to test usefulness of suggested features. Experimental result shows that the suggested methods can be used to identify the pain states of an infant.
Muhammad Naufal Mansor and Mohd Nazri Rejab
Trans Tech Publications, Ltd.
Image analysis of infant pain has been proven to be an excellent tool in the area of automatic detection of pathological status of an infant. This paper investigates the application of parameter weighting for invariant moments to provide the robust representation of infant pain images. Two classes of infant images were considered such as normal images, and babies in pain. A Similar Classifier is suggested to classify the infant images into normal and pathological images. Similar Classifier is trained with different spread factor or smoothing parameter to obtain better classification accuracy. The experimental results demonstrate that the suggested features and classification algorithms give very promising classification accuracy of above 89.54% and it expounds that the suggested method can be used to help medical professionals for diagnosing pathological status of an infant from face images.
Muhammad Naufal Mansor and Mohd Nazri Rejab
Trans Tech Publications, Ltd.
Infant pain is a non-stationary made by infants in response to certain situations. This infant facial expression can be used to identify physical or psychology status of infant. The aim of this work is to compare the performance of features in infant pain classification. Fast Fourier Transform (FFT), and Singular value Decomposition (SVD) features are computed at different classifier. Two different case studies such as normal and pain are performed. Two different types of radial basis artificial neural networks namely, Probabilistic Neural Network (PNN) and General Regression Neural Network (GRNN) are used to classify the infant pain. The results emphasized that the proposed features and classification algorithms can be used to aid the medical professionals for diagnosing pathological status of infant pain.
Muhammad Naufal Mansor and Mohd Nazri Rejab
IEEE
Most of infant pain cause changes in the face. Clinicians use image analysis to characterize the pathological faces. Nowadays, infant pain research is increasing dramatically due to high demand from all medical team. This paper presents a sparse and naïve Bayes classifier for the diagnosis of infant pain disorders. Phase congruency image and local binary pattern are proposed. The proposed algorithms provide very promising classification rate.
Muhammad Naufal Mansor and Mohd Nazri Rejab
IEEE
This paper discussed the crucial demand regarding the scheme to translate the silence voice from the newborn. The infant can't afford to express their feeling of pain by voice. Hence, we proudly present an infant pain recognition system to overcome this matter. We employed the Single Scale Retinex (SSR) to remove the illumination level. Secondly, Gray-Level Co-occurrence Matrix (GLCM) was adopted as the feature extraction. We determine the condition of the infants (pain/no pain) with Hybrid Genetic Algorithm Neural Network (GANN) and Linear Discriminant Analysis (LDA). Several examples were conducted to evaluate the performance of the proposed method under different illumination levels.
Muhammad Naufal Mansor and Mohd Nazri Rejab
IEEE
In the last recent years, non-invasive methods through image analysis of facial have been proved to be excellent and reliable tool to diagnose of pain recognition. This paper proposes a new feature vector based Local Binary Pattern (LBP) for the pain detection. Different sampling point and radius weighted are proposed to distinguishing performance of the proposed features. In this work, Infant COPE database is used with illumination added. Multi Scale Retinex (MSR) is applied to remove the shadow. Two different supervised classifiers such as Gaussian and Nearest Mean Classifier are employed for testing the proposed features. The experimental results uncover that the proposed features give very promising classification accuracy of 90% for Infant COPE database.
Muhammad Naufal Mansor and Mohd Nazri Rejab
IEEE
This paper discussed the crucial demand regarding the scheme to translate the silence voice from the newborn. The infant can't afford to express their feeling of pain by voice. Hence, we proudly present an infant pain recognition system to overcome this matter. We employed Saliency Using Natural statistics (SUN) Saliency Map as the feature extraction. We determine the condition of the infants (pain/no pain) with Support Vector Machine (SVM) Classifier. Several examples were conducted to evaluate the performance of the proposed method.
Muhammad Naufal Mansor, Sazali Yaacob, Hariharan Muthusamy, Shafriza Nisha Basah, and Mohd Nazri Rejab
American Scientific Publishers
Muhammad Naufal Mansor, Sazali Yaacob, Hariharan Muthusamy, Shafriza Nisha Basah, and Mohd Nazri Rejab
American Scientific Publishers
What is SIDS? SIDS is known as Sudden Infant Death Syndrome or referred as the cot death; there are no explainable causes of death after the autopsy. No one knows what causes SIDS, however researchers have theorized that a dramatic drop in heart rate occurs just before death. Thousands of babies die from this phenomenon each year in the Malaysia. Very few babies who die of SIDS may have had one or more apparent life-threatening events (ALTE). During ALTE, a baby has abnormally long pauses in breathing (longer than 20 seconds). The skin changes color (bluish and blotchy) or becomes pale, and the body stiffens and then goes limp. The baby may also choke or gag. Machines (apnea monitors) that are commonly used to detect these periods of interrupted breathing have not been shown to prevent SIDS. Thus, all this minor change it's not visible to the human eye, but it's still there. We have developed algorithms to interpret the discoloration and translate them into AR Model coefficient motion pulses. It's widely assumed that baby's pulses motion slow down before SIDS, and this system could help prevent this.
M. N. Mansor, S. Yaacob, M. Hariharan, S. N. Basah, S. H. F. S. Ahmad Jamil, M. L. Mohd Khidir, M. N. Rejab, K. M. Y. Ku Ibrahim, A. H. F. S. Ahmad Jamil, J. Ahmad,et al.
Springer Berlin Heidelberg
In this paper, tremble stage assessment is explained and reviewed for detecting facial changes of patient in a hospital in Neonatal Intensive Care Unit (NICU). The facial changes are most widely represented by eyes and mouth movements. The proposed system uses color images and it consists of three modules. The first module implements skin detection method to detect the face. Secondly, extracts the features of faces by processing the image and measuring certain dimensions face regions. Finally a knn and Fuzzy k- NN classifier used to classify the movements. From the experiments, it is found that the identification rate of reaches 93.30% and 70.25% respectively.
M. N. Mansor, S. Yaacob, M. Hariharan, S. N. Basah, S. H. F. S. Ahmad Jamil, M. L. Mohd Khidir, M. N. Rejab, K. M. Y. Ku Ibrahim, A. H. F. S. Ahmad Jamil, J. Ahmad,et al.
Springer Berlin Heidelberg
This paper presents the management of sedation in critically ill infants is a complex issue for Intensive Care Units (ICU) worldwide. Notable complications of sedation practices have been identified and efforts to modify these practices in ICUs have begun. While sedation-scoring tools have been introduced into clinical practice in intensive care few have been tested for validity and reliability. One tool which has reliability and validity established is the Sedation-Agitation Scale (SAS). This study is an extension of a previous study by Riker, Picard and Fraser (1999) to determine whether doctors and nurses rate infants similarly using the SAS in a natural ICU setting. It is essential to establish whether these different professionals provide consistent scores and have a mutual understanding of the SAS and its constituent levels based on LDA and SVM Cassifier. This will help ensure that clinical decisions relating to sedation-needs can be made appropriately and consistently.
Muhammad Naufal Mansor, Muhammad Nazri Rejab, Syahrull Hi-Fi Syam, and Addzrull Hi-Fi Syam B
IEEE
Pain Assessment in Neonatal has been discussed recently nowadays. A rapid research, equipment and pain course has yet been improved. However, the robustness, accurate and fast pain scheme is yet far beyond the schedule comparing to the pain assessment for the adult patient. Thus, an infant pain detection scheme is been proposed based on Autoregressive Model (AR Model) and Fuzzy k-NN. The accuracy result is quite promising around 90.77%.
Muhammad Naufal Mansor, Shahryull Hi-Fi Syam Mohd Jamil, Mohd Nazri Rejab, and Addzrull Hi-Fi Syam Mohd Jamil
IEEE
This paper come out with an infant behavior recognition scheme based on neural network. In this study, the infant face region is segmented based on the Haar Cascade Method. Two types of features, namely Mean, Variance, Skewness and Kurtosis are then calculated based on the information available from the infant face regions. Since each type of features in turn contains several different values, given a single fifteen-frame sequence, the correlation coefficients between those features of the same type can form the attribute vector of pain and normal facial expressions. Fifteen infant facial expression classes have been defined in this study. LDA corresponding to each type of those features has been constructed in order to classify these facial expressions. The experimental results show that the proposed method is robust and efficient. The properties of the different types of features have also been analyzed and discussed.
Muhammad Naufal Mansor, Syahrull Hi-Fi Syam, Muhammad Nazri Rejab, and Addzrull Hi-Fi Syam B
IEEE
This paper presents a vision-based infant-pain monitoring system that adopts an infant behavior analysis approach to detect infant injuries. In our study, the system first pre-processes the input sequence to filter out the noise and reduce the effects of lights and shadows. Then, the infant's faces are detected from the input frames and feature extraction was done with SVD and FFT. A k-NN classifier was employed to describe pain over time. It is found that the identification rate of reaches 83.12%.
Muhammad Naufal Mansor, Shahryull Hi-Fi Syam Mohd Jamil, Mohd Nazri Rejab, and Addzrull Hi-Fi Syam Mohd Jamil
IEEE
This paper come out with an infant behaviour recognition scheme based on neural network. In this study, the infant face region is segmented based on the skin colour information. Two types of features, namely Singular Value Decomposition (SVD) and Power Spectrum are then calculated based on the information available from the infant face regions. Since each type of features in turn contains several different values, given a single fifteen-frame sequence, the correlation coefficients between those features of the same type can form the attribute vector of pain and normal facial expressions. Fifteen infant facial expression classes have been defined in this study. Neural Network corresponding to each type of those features has been constructed in order to classify these facial expressions. The experimental results show that the proposed method is robust and efficient. The properties of the different types of features have also been analyzed and discussed.
M. N. Mansor, M. N. Rejab, S. H-F Syam, and A. H-F Syam
IEEE
To deal with nonverbal life was a difficult task. To study their behaviour without knowing what their needs is another crucial issue. A lot of researches have been rapidly investigated. Thus, in this paper we proudly proposed a system to determine the hungry infant based on their facial expression. A Haar Cascade face detection method was implemented. Autoregressive Model (AR) was employed for the coefficient extraction. Some other statistical methods were used as the feature extraction. Finally Neural network (NN) with 93.78% accuracy was accepted.
Muhammad Naufal Mansor, Syahrull Hi-Fi Syam, Muhammad Nazri Rejab, and Addzrull Hi-Fi Syam B
IEEE
Both the timing of facial actions and the configuration are important in emotion expression and recognition. To investigate the timing and configuration of pain facial actions, in this paper, pain assessment is explained and reviewed for detecting based on skin detection using color detection and SVD as feature extraction. Finally a Neural Network classifier used to classify the movements. From the experiments, it is found that the identification rate of reaches 93.75%.
Muhammad Naufal Mansor, Shahryull Hi-Fi Syam Mohd Jamil, Mohd Nazri Rejab, and Addzrull Hi-Fi Syam Mohd Jamil
IEEE
This paper come out with an infant behaviour recognition scheme based on neural network. In this study, the infant face region is segmented based on the Haar Cascade Method. Two types of features, namely Singular Value Decomposition (SVD) and Power Spectrum are then calculated based on the information available from the infant face regions. Since each type of features in turn contains several different values, given a single fifteen-frame sequence, the correlation coefficients between those features of the same type can form the attribute vector of pain and normal facial expressions. Fifteen infant facial expression classes have been defined in this study. Fuzzy k-NN corresponding to each type of those features has been constructed in order to classify these facial expressions. The experimental results show that the proposed method is robust and efficient. The properties of the different types of features have also been analyzed and discussed.
Muhammad Naufal Mansor, Shahryull Hi-Fi Syam Mohd Jamil, Mohd Nazri Rejab, and Addzrull Hi-Fi Syam Mohd Jamil
IEEE
In this paper, pain assessment is explained and reviewed for detecting facial changes of patient in a hospital in Neonatal Intensive Care Unit (ICU). The facial changes are most widely represented by eyes and mouth movements. The proposed system uses color images and it consists of three modules. The first module implements skin detection to detect the face. Secondly, extracts the features of faces by processing the image and measuring certain dimensions face regions based on the FFT. Finally a knn classifier used to classify the movements. From the experiments, it is found that the identification rate of reaches 90.12%.