Noorfadzli bin Abdul Razak

RESEARCH INTERESTS

Autonomous Control , Embedded System , Automation and Robotics

Scopus Publications

Vehicle-to-Vehicle Communication: A Review of Efficiency, Communication Medium and Action Signal
Nur Izzati Anaz Anizan, Fazlina Ahmat Ruslan, Noorfadzli Abdul Razak, Mohd Azri Abdul Aziz, and Juliana Johari
Universiti Malaysia Pahang Publishing
In an era marked by rapid advancement in technology, transportation systems are experiencing a revolutionary transformation. Vehicle-to-Vehicle (V2V) communication stands at the forefront of this transformative movement, with the potential to significantly change the ways how vehicles interact with one another and their surrounding environment. This newly developed technology has the capacity to significantly improve road safety, traffic efficiency, and every aspect of the driving experience. Thus, a review of V2V communication based on its safety, efficiency of traffic on the road, the medium of communication and the action signal have been made. The purpose of the review on this technology is to examine the possibility of enhancing safety measures that may include walking, motorcyclists, cyclists, and drivers on the road. A comprehensive review of publications about safety, technology for communication, and signal reception in vehicles was conducted, along with an analysis of the articles that followed. Notably, the quest encompassed three prominent databases – IEEE Xplore, ScienceDirect, and Web of Science – covering the period from 2002 to 2023. These repositories were deemed adequately comprehensive to envelop our literature review. Through the application of predefined criteria for inclusion and exclusion, a total of 125 articles were curated. Among this compilation, a majority (63 out of 125) were dedicated to studies centered around V2V communication systems. Furthermore, a significant subset (44 out of 125) revolved around tangible endeavors directed at the advancement of V2V communications. The remaining fraction (18 out of 125) comprised articles offering comprehensive assessments and survey analyses. Multiple investigations were conducted with a focus on automating the detection of V2V communications and their respective subcategories, all geared towards the enhancement of detection accuracy. Therefore, this systematic review is intended to provide pathways for researchers and encourage their motivation to address the identified problems and gaps.


Modelling and estimating trajectory points from RTK-GNSS based on an integrated modelling approach
Ravenny Sandin Nahar, Kok Mun Ng, Fadhlan Hafizhelmi Kamaruzaman, Noorfadzli Abdul Razak, and Juliana Johari
Institute of Advanced Engineering and Science
The sparse Gaussian process regression (GPR) has been used to model trajectory data from Real time kinematics-global navigation satellite system (RTK-GNSS). However, upon scrutinizing the model residuals; the sparse GPR model poorly fits the data and exhibits presence of correlated noise. This work attempts to address these issues by proposing an integrated modeling approach called GPR-LR-ARIMA where the sparse GPR was integrated with the linear regression with autoregressive integrated moving average errors (LR-ARIMA) to further enhance the description of the trajectory data. In this integrated approach, the predicted trajectory points from the GPR were further described by the LR-ARIMA. Simulation of the GPR-LR-ARIMA on three sets of trajectory data indicated better model fit, revealed in the normally distributed model residuals and symmetrically distributed scatter plots. Correlated noise was also successfully eliminated by the model. The GPR-LR-ARIMA outperformed both the GPR and LRARIMA by its ability to improve mean-absolute-error in 2-dimension positioning by up to 86%. The GPR-LR-ARIMA contributes to enhancement of positioning accuracy of dynamic GNSS measurements in localization and navigation system with good model fit.


Research on the Application of Adaptive Parameter Adjustment Strategy in RBF Kernel SVM Image Classification
Xu Zhipeng, Mohd Azri Abdul Aziz, and Noorfadzli Abdul Razak
IEEE
Support Vector Machine (SVM) is a powerful machine learning model with extensive applications in fields such as image classification. The reasonable setting of kernel parameters is crucial for the performance of RBF kernel functions in SVMs. Traditional methods require manually specifying parameters or obtaining parameters through grid search, which results in high computational costs and unsatisfactory results. Therefore, we propose an adaptive parameter adjustment strategy that dynamically adjusts the RBF kernel parameters based on the characteristics of training data, continuously optimizing the performance of SVM classifiers. We evaluated the proposed strategy on the autonomous vehicle dataset and found that compared with the default setting parameters or grid search parameters, this adaptive strategy can significantly improve the classification accuracy, reaching the best accuracy of 0.992 on the autonomous vehicle dataset. Its computational time is 2.443 seconds and better than grid search. This strategy has the advantages of no manual intervention and high computational efficiency, providing an effective parameter tuning scheme for the application of RBF kernel SVMs in image classification and other fields.


Performance Evaluation of Support Vector Machine Algorithm in Object Classification Using Different Preprocessing Methods
Xu Zhipeng, Mohd Azri Abdul Aziz, and Noorfadzli Abdul Razak
IEEE
Support Vector Machines (SVMs) are excellent tools in the field of machine learning that are well suited for classification and regression problems. However, SVM is highly sensitive to data. In recent years, many researchers have continued to use various data preprocessing methods to improve model performance. Nevertheless, there is a lack of comparison of multiple datasets preprocessing methods, and there is also a lack of experiments on classification targets. This research aims to compare the performance of different preprocessing methods by using vector machines with radial basis function (RBF) kernel support. Three data sets of pedestrians, vehicles, and traffic signs are classified, and four common data preprocessing methods are used: data cleaning, feature selection, feature scaling, and dimensionality reduction. Observing the results through the use of assessment metrics accuracy, precision, recall, and F1 score. The experiment shows that the preprocessing method of feature selection is superior to the other three preprocessing methods. It achieves an accuracy of 0.985, a precision of 0.986, a recall rate of 0.985 and an F1 score of 0.986. This research has important research significance for automatic driving target classification.


Characterization of Bio-Cement Reinforced with Eggshell Composites
R. Rosmamuhamadani
UiTM Press, Universiti Teknologi MARA
Eggshells are an interesting inorganic compound with a chemical composition and crystallographic structure similar to that of CaCO3. This study aims to acquire a better understanding of the use of eggshells, which are commercially incorporated into cement mixtures, to increase the mechanical strength of cement-eggshell composite. The cement mixture was prepared by incorporating different compositions (5, 10, and 15 wt.%) of eggshell powder. The raw eggshells were cleaned, crushed, dried, sieved into small pieces, and mixed with the cement according to the desired composition. Analysis of the eggshell powder showed similar peaks to CaCO3, indicating that eggshells can be used as a calcium source. The results indicated that the addition of 10 wt.% finely ground eggshell powder improved the compressive and flexural strength of the cement mix. It was also found that eggshell powder can potentially be used as a filler, as it exhibited the highest water absorption at 15 wt.%. The use of eggshells as a reinforcing component in environmentally friendly cement mixes has the potential to improve the environment by reducing waste, the need for conventional cement resources, and the pollution caused by excessive cement mining.


Dexmedetomidine and Propofol Sedation in Critically Ill Patients and Dose-associated 90-Day Mortality
Yahya Shehabi, Ary Serpa Neto, Rinaldo Bellomo, Belinda D. Howe, Yaseen M. Arabi, Michael Bailey, Frances E. Bass, Suhaini Bin Kadiman, Colin J. McArthur, Michael C. Reade,et al.
American Thoracic Society
RATIONALE Sedation Practice in Intensive Care Evaluation (SPICE-III) trial reported significant heterogeneity in mortality with dexmedetomidine treatment. Supplemental propofol was commonly used to achieve desirable sedation. OBJECTIVES to quantify the association of different infusion rates of dexmedetomidine or propofol, given in combination, with mortality and if this is modified by age. METHODS AND MEASUREMENTS We included 1177 patients randomized in SPICE-III to receive dexmedetomidine and given supplemental propofol, stratified by age (>65 or ≤65 years). We used double stratification analysis to produce quartiles of steady infusion rates of dexmedetomidine, while escalating propofol dose and vice versa. We used Cox proportional hazard and multivariable regression, adjusted for relevant clinical variable to evaluate the association of sedative dose with 90-day mortality. MAIN RESULTS Younger patients 598/1177(50.8%) received a significantly higher dose of both sedatives compared with older patients, to achieve comparable sedation depth. On double stratification analysis, escalating infusion rates of propofol to 1.27 mg/kg/h at a steady dexmedetomidine infusion rate (0.54 mcg/kg/h) was associated with reduced adjusted mortality in younger, but not older patients. This was consistent with multivariable regression modelling [hazard ratio: 0.59(95% Confidence Interval 0.43-0.78),P<0.0001], adjusted for baseline risk and interaction with dexmedetomidine dose. In contrast, among younger patients using multivariable regression, escalating dexmedetomidine infusion rate was associated with increased adjusted mortality [HR:1.30(95%CI 1.03-1.65), P=0.029]. CONCLUSION In patients ≤ 65 years sedated with dexmedetomidine and propofol combination, preferentially increasing the dose of propofol was associated with decreased adjusted 90-day mortality. Conversely, increasing dexmedetomidine may be associated with increased mortality. Clinical trial registration available at www. CLINICALTRIALS gov, ID: NCT01728558.


Switching Circuit For Automated Air Conditioner Control And Energy Saving In Classrooms
Nurwani Mohd Redzuan, Farah Yasmin Abdul Rahman, Norashikin M. Thamrin, Noorfadzli Abdul Razak, Megat Syahirul Amin Megat Ali, and Ihsan Mohd Yassin
IEEE
This project introduces an energy-efficient switching circuit designed for automating classroom air conditioning, thereby contributing to electricity conservation. With the growing demand for electricity worldwide, it is imperative to devise economical strategies for optimizing power usage. Recent advancements have resulted in intelligent technologies such as smart thermostats, power outlets, and lighting systems, all aimed at optimizing electricity consumption. Taking inspiration from smart thermostats, which modulate home heating and cooling based on ambient temperature, the proposed system employs a sound sensor to detect human presence within a classroom. When absence is detected, the air conditioning system is automatically deactivated, leading to significant energy savings. The circuit’s implementation is user-friendly, eliminating the need to replace the existing air conditioning switch. Therefore, this switch circuit presents an opportunity for classrooms to reduce their energy footprint without compromising on comfort.


Investigation of Object Detection and Identification at Different Lighting Conditions for Autonomous Vehicle Application
Noorfadzli Abdul Razak, Nur Alya Aqilah Sabri, Juliana Johari, Fazlina Ahmat Ruslan, Mahanijah Md. Kamal, and Mohd Azri Abdul Aziz
Universiti Malaysia Pahang Publishing
Ensuring the safety of autonomous vehicles requires effective detection and tracking of surrounding objects. This paper proposes the design and development of a driverless transportation system module focused on identifying obstacles around vehicles. By integrating computer vision with deep learning, the system presents a reliable and cost-effective solution for autonomous driving. Utilizing Raspberry Pi 4B and a USB webcam, a compact hardware setup is created for seamless implementation in autonomous vehicles. The algorithm presented in this study enables the detection, classification, and tracking of both moving and stationary objects, including cars, buses, trucks, people, and motorcycles. TensorFlow Lite, a deep-learning network, is employed for efficient object detection and classification. Leveraging Python as the primary programming language, known for its high-level object-oriented features and integrated semantics, the algorithm is tailored for web and application development. Experimental results demonstrate the system’s capability to concurrently detect and identify multiple local objects with an accuracy ranging from 50% to 80% in day and night conditions. These findings underscore the potential of deep learning in advancing autonomous vehicle technology.


Publication Management System using Scopus API
Badrul Hisham Fitri Mohd Ijazi, Syahrul Afzal Che Abdullah, Ng Kok Mun, Norashikin M. Thamrin, Noorfadzli Abdul Razak, and Zainal Hisham Che Soh
IEEE
Lecturers must conduct research and publish their findings. The reason is obvious, it is a medium of knowledge dissemination and as part of their Key Performance Indicators (KPIs). However, it is difficult for administrators to analyze the performance and publication output of all academic staff because the information available on the Scopus® website is displayed individually. To overcome this problem, administrators often employ dedicated staff to manually enter this information in Google spreadsheet, so that the information is available on demand. However, the information may not be the latest as the data on the Scopus® website is constantly updated when there are new publications. Therefore, an automatic retrieval system was developed using Python. The system automatically queries data from the Scopus® website using the Scopus® API. Then, the results will be saved to two different locations which are the Google spreadsheet and the MySQL database. The Google spreadsheet stores current publications while the database contains all publications by the academic staff. This mechanism allows administrators to monitor the performance and output of all academic staff of the School of Electrical Engineering through Google spreadsheet and the associated website.


Design and Development of Modular and Open System (MOST) for Pandemic Precaution
Noorfadzli Abdul Razak, Muhammad Rafie Bin Sazali, Juliana Johari, Noor Azlina Mohd Salleh, Yupiter Harangan Prasada Manurung, and Ng Kok Mun
Springer Singapore



Analysis of Training Function for NNARX in Solar Radiation Prediction Modeling
Mohd Rizman Sultan Mohd, Juliana Johari, Fazlina Ahmat Ruslan, Noorfadzli Abdul Razak, Salmiah Ahmad, and Ahmad Syahiman Mohd Shah
Springer Singapore



Development of Self-Operating Solar Energy Potential Measuring Devices using Simple Microcontroller Setup
Mohd Rizman Sultan Mohd, Muhammad Syakir Abdullah, Fazlina Ahmat Ruslan, Juliana Johari, Noorfadzli Abdul Razak, Salmiah Ahmad, and Ahmad Syahiman Mohd Shah
IEEE
Renewable energy known as green energy production had been rapidly developed to replace fossil fuel generators. Solar energy is one of the most utilized renewable energy because it can be obtained almost everywhere on earth. Solar energy is an unlimited energy source and it can be harvest in the safest way compared to other renewable energy source. Since the development of the photovoltaic system requires a lot of investment, preliminary testing had been carried out to uncover the solar energy potential based on the specific locations including the development of a solar energy potential measuring system. This paper presents the development of self-operating solar energy potential measuring system by using an ATmega 328P microcontroller-based setup. The system not only can measure the solar energy potential but using solar energy generates with its solar panel to operates the whole system. Based on the results, the system developed had successfully operated and measures the solar energy value at three different locations under different weather conditions.


Evaluation of Dynamic Measurements from RTK-GNSS Operating in Sub-urban Environment
R. S. Nahar, K. M. Ng, J. Johari, M. M. Kamal, and N.A. Razak
IEEE
Previous works that evaluated the performance of the EMLID Reach RS RTK-GNSS based on its accuracy and availability may not be sufficient to reveal further noise characteristics in the residual. Hence, it is noteworthy to further investigate correlated noise characteristics and the probabilistic distribution in the error residuals to assist in appropriate filtering and statistical description of the noise. In view of this, the authors aim to evaluate measurements from the EMLID Reach RS RTK-GNSS in terms of accuracy, availability, correlated noise characteristics and probabilistic distribution of the errors when operating dynamically in a sub-urban environment. Data logging was performed with the rover moving in two routes located in a residential area in Shah Alam, Malaysia with baseline of less than 200 m and above 200 m from the base station respectively. Seven sets of data were collected for both routes. The data collected was analyzed in comparison with ground truth to investigate accuracy and availability. Subsequently, the errors were evaluated using autocorrelation and partial correlation tests to reveal characteristics of correlated noise. A distribution fitter was used to identify the best type of distribution that can fit the error residuals. In terms of accuracy, MAE and RMSE are better in dynamic measurements with baseline less than 200 m compared to above 200 m. The autocorrelation and partial correlation plots for all data sets indicated the presence of correlated noise in the error residuals, which could be described using the non-parametric distribution. Hence, non-parametric probability density could be used to estimate the mean and the bounds in the error. On the other hand, appropriate filtering is needed to attenuate correlated noise.


Early sedation with dexmedetomidine in ventilated critically ill patients and heterogeneity of treatment effect in the SPICE III randomised controlled trial
Yahya Shehabi, , Ary Serpa Neto, Belinda D. Howe, Rinaldo Bellomo, Yaseen M. Arabi, Michael Bailey, Frances E. Bass, Suhaini Bin Kadiman, Colin J. McArthur,et al.
Springer Science and Business Media LLC
To quantify potential heterogeneity of treatment effect (HTE), of early sedation with dexmedetomidine (DEX) compared with usual care, and identify patients who have a high probability of lower or higher 90-day mortality according to age, and other identified clusters. Bayesian analysis of 3904 critically ill adult patients expected to receive invasive ventilation > 24 h and enrolled in a multinational randomized controlled trial comparing early DEX with usual care sedation. HTE was assessed according to age and clusters (based on 12 baseline characteristics) using a Bayesian hierarchical models. DEX was associated with lower 90-day mortality compared to usual care in patients > 65 years (odds ratio [OR], 0.83 [95% credible interval [CrI] 0.68–1.00], with 97.7% probability of reduced mortality across broad categories of illness severity. Conversely, the probability of increased mortality in patients ≤ 65 years was 98.5% (OR 1.26 [95% CrI 1.02–1.56]. Two clusters were identified: cluster 1 (976 patients) mostly operative, and cluster 2 (2346 patients), predominantly non-operative. There was a greater probability of benefit with DEX in cluster 1 (OR 0.86 [95% CrI 0.65–1.14]) across broad categories of age, with 86.4% probability that DEX is more beneficial in cluster 1 than cluster 2. In critically ill mechanically ventilated patients, early sedation with dexmedetomidine exhibited a high probability of reduced 90-day mortality in older patients regardless of operative or non-operative cluster status. Conversely, a high probability of increased 90-day mortality was observed in younger patients of non-operative status. Further studies are needed to confirm these findings.


Comparison between Ziegler-Nichols and AMIGO Tuning Techniques in Automated Steering Control System for Autonomous Vehicle
Nadia Nabilah Binti Mohd Mazlan, Norashikin M. Thamrin, and Noorfadzli Abdul Razak
IEEE
This paper presents the design of an automated steering control system with a PID controller for Autonomous Vehicle. It is mainly focusing on the implementation and evaluation of the tuning methods by using Ziegler-Nichols and Amigo in providing the important parameters to the PID controller namely, Kp, Ki, and Kd. The objectives of this project are to compare the performance of the Ziegler-Nichols and Amigo tuning method for the PID controller parameters to control the steering angle of the autonomous vehicle in real-time and to improve the vehicle steering dynamics performance. Both tuning methods are simulated in real-time in the laboratory by using a prototype buggy acts as the autonomous vehicle. It applies Raspberry Pi 3B+ as a controller, absolute encoder for feedback sensor, and Vexta brushless motor as the actuator. The system operates based on the input angle set by the user to turn the tire, which 0 degree is taken as the center of the turning point of this autonomous vehicle. When the set value is a positive number, the tire turns to the right. Otherwise, it turns to the left. As a result, the data without PID, using PID with Ziegler-Nichols and Amigo tuning methods are collected and plotted. It is found that the Amigo tuning method has a better response than the Ziegler-Nichols tuning method.


Real-Time Optimal Trajectory Correction (ROTC) for Autonomous Quadrotor
Noorfadzli Abdul Razak, Ramli Adnan, Norashikin M. Thamrin, Ng Kok Mun, and Juliana Johari
IEEE
This research proposes a new algorithm known as Real-Time Optimal Trajectory Correction. The algorithm works if the quadrotor undergoes a deviation, an admissible trajectory path is generated for the quadrotor rapidly return on the straight-line route. There are two stages implicated in the algorithm. The first stage comprises a deviation scheme used to sense a deviation and formulates a vector. The second stage focuses on using the vector to generate a path via a Hermite interpolation technique integrated with time and tangent transformation schemes. A Dead Reckoning navigation technique is employed to steer the quadrotor on the path. The scheme and algorithm have experimented in low, moderate and high categories of deviation acceleration via a customized quadrotor. Comparative performance of quadrotor navigation integrated with and without the algorithm are carried out. The parameters evaluated are focused on distance and time utilized by the quadrotor to return on the route after a deviation happened. The results signify fewer distances and time are consumed by the quadrotor navigation with the algorithm to return to the route after a deviation happened as compared to its navigation without it. Conclusively, the results show the designed algorithm is relevant to assist the quadrotor autonomous navigation in a windy environment.


Real-time optimal trajectory correction (ROTC) for autonomous omnidirectional robot
Noorfadzli Abdul Razak, Nor Hashim Mohd Arshad, Ramli bin Adnan, Norashikin M. Thamrin, and Ng Kok Mun
Springer Singapore
This paper proposed a Real-Time Optimal Trajectory Correction (ROTC) algorithm designed to be applied for autonomous omnidirectional robot. It is programmed to work when a robot undergoes a deviation, an admissible trajectory correction path is generated for the robot rapidly returns to the route line. For the algorithm to do this, initially a deviation scheme is employed to sense deviation and formulates a vector consists of displacement and angle. Via the vector, an admissible correction path is originated utilizing Hermite cubic spline method fused with time and tangent transformation schemes. A Dead Reckoning (DR) technique is applied for robot to pursue the path. Several experiments are arranged to evaluate the reliability of robot navigation with and without the algorithm. It motion is mapped in Graphical User Interface (GUI) window using data from Laser Range Finder (LRF) sensors as attached to the robot controller. Using the map, the performances of the algorithm are evaluated in terms of distance travel and duration to return on the line. The results signify robot navigation with the algorithm required shorter distance and duration as compared to robot navigation without ROTC. Thus, it justifies the algorithm is feasible in the navigation system where it can assist robot effectively to move back to the route line after experiencing a deviation caused by a disturbance.


Development and experimental study on pareto optimum design of cyclone separator
Kok Mun Ng, Ahmad Shafiee Harfin, N.A. Razak, and M.A. Masduki
IEEE
Economic growth in the course of industrial development is causing an increasingly severe environmental problem such as the emission of dust particles. One of the ways that technology can help in combating dust emission is by creating particle separator using cyclone. In this paper, Pareto optimum design guidelines of cyclone separator adapted from a previous simulation study is built and experimented. The goal is to determine the cyclone design parameters that have the maximum collection efficiency and whether the efficiency matches simulation studies. There were three different designs of the cyclone separator based on Pareto optimum design guidelines. These three cyclones have been fabricated using aluminum and polymerizing vinyl chloride (PVC). Experiments were conducted on these cyclones to determine their efficiencies due to different design parameters and the type of dust material used. The result shows that cyclone performance varies with cyclone design parameters. In addition, the size of dust particles could affect efficiency of cyclone separators.


Remote air quality monitoring system by using MyRIO-LabVIEW
Kok Mun Ng, Muhamad Azri Haziq Mohd Suhaimi, Adizul Ahmad, and N.A. Razak
IEEE
Air quality monitoring is essential to ensure that the places we work or live in are conducive for our health. Recent technologies have enabled remote monitoring of the conditions of our environment such as air and water. This paper presents a remote air quality monitoring based on myRIO-LabVIEW, which could monitor the quality of air via detection of Carbon Monoxide (CO) rate in indoor locations within buildings. The sensor use to detect the CO is the MQ-7 sensor that is connected to the Arduino Mega and MyRIO controllers; the outputs is processed by the LabViewsoftware on the user computer remotely. For the purpose of testing, the system was tested at three selected locations to detect the rate of change of CO for over an hour. MyRIO will continuously save the CO rate data when the substance exists around these locations. In this way, the LabViewcan process and display the data to the user wirelessly or remotely. Subsequently, the average CO rate could also be calculated. The system is working successfully as its detection and data logging by both hardware and software is functioning wirelessly and the result can be analyzed further by the users.


Coagulant from Leucaena leucocephala for Chromium Removal
N H Abd Razak, N Khairuddin, K N Ismail, and M Musa
IOP Publishing
This research investigated the effectiveness of leucaena leucocephala as a natural coagulant for chromium removal. Leucaena leucocephala is a permanent non-climbing shrub tree which is wild and abundant in Malaysia and commonly known as petai belalang. Coagulation experiment using jar test were performed where the effect of coagulant dosage and pH were examined. The parameters investigated were suspended solid (SS), chemical oxygen demand (COD), biological oxygen demand (BOD), turbidity and chromium content. The optimum of leucaena leucocephala coagulant dosage for removal of suspended solid, turbidity, COD, BOD and Chromium is at range 400-600 mg/L which yielded 45, 31.4, 38.5, 27.5 and 4.05% removal respectively. While the optimum pH is at pH 2-4 (acidic) which give 33.3, 26.8, 33.75, 31.4 and 14.06% removal of suspended solid, COD, BOD, turbidity and chromium content respectively. It is concluded that the leucaena leucocephala showed tremendous potential for chromium removal.


Deviation sensing and vector measurement technique for autonomous line tracking omnidirectional robot
Noorfadzli Abdul Razak, Nor Hashim Mohd Arshad, Ramli Adnan, Norashikin M. Thamrin, and Ng Kok Mun
IEEE
This paper presents an initial process to design a new corrective motion namely development of a deviation detection scheme and vector estimation technique. Scope of this research focuses to robot deviation that happens to the left and right when the robot moves in forward direction. Accelerometer outputs are used to sense the deviation and compute the vector comprises displacement and angle. In the scheme, double trapezoidal integration rule is employed to translate sensor acceleration data to displacement. Additionally, Kalman Filter (KF) is introduced to the outputs and integrand results to minimize the estimation error. An omnidirectional robot installed with the controller board implemented to perform autonomous line tracking technique is constructed. It is set to communicate wirelessly with a GUI (Graphical User Interface) window installed in a computer purposely to display and records deviation data. Several experiments in different deviation acceleration categories are carried out to test the scheme performance. Comparative performance between the scheme and LRF (Laser Range Finder) sensors to estimate the vector is also implemented. The results showed the scheme correctly senses and identify the direction of deviation. In estimating the vector, the scheme gained 80% accuracy compared to LRF sensors, which consistently attained more than 90% in each experiment. However, the scheme performance is accepted to be used for designing the corrective motion later.


Single Wireless Electrocardiogram Monitoring and Acquisition System (SIWEMS)
Noorfadzli Abdul Razak, Zarina Md Amin, Mohammad Farid Misnan, Suryani Ilias, Zunuwanas Mohamed, Norashikin M. Thamrin, and Robiah Udin
IEEE
Cardiovascular disease is the main cause of human casualty in the world as reported by World Health Organization (WHO). To facilitate in minimizing this cause, constant monitoring of the heart's rhythm appears to be essential in observing the condition of the heart by checking or recording the Electrocardiogram (ECG) signal. This paper presents a prototype design of Single Wireless Electrocardiogram Monitoring and Acquisition System (SIWEMS). The system is designed to implement Zigbee wireless technology for monitoring and storing an ECG signal remotely from a patient. The conceptual design of the system is discussed along with the circuits devised to generate a good-quality signal. Microcontrollers are employed to form a controller board for digitizing the signal and stored the signal in SD-card. Plus, the board is also interfaced with wireless module to transmit the signal to a Graphical User Interface (GUI) window. The GUI installed in laptop received the signal and concurrently displays it in real-time. Instead, the window does also provide data logger function. The proposed system is tested, and the results demonstrate it performs well to generate, displays and logs the ECG signal. Currently, this prototype is practically relevant to be employed for remote continuous dynamic monitoring and acquisition of ECG in healthcare.


Multi-agent wireless ECG monitoring system (MAWEMS)
Z. M. Amin, N.A Razak, M.F Misnan, S. Ilias, Z. Mohamed, and R. Udin
IEEE
Cardiovascular disease is the main cause of human casualty in the world as reported by World Health Organization (WHO). To facilitate in minimizing the causes, constant monitoring of the heart's rhythm appears as one alternative solution. This paper presents a convenient system which implements wireless network to monitor remote patient. The aim of this work is to design and implement a monitoring system of the desired signal Electrocardiogram (ECG) between several patients. The system provides observations of the patient by wearing a portable device which is equipped with the designed ZigBee wireless module. The formed system provides a real-time heart rate monitoring data, and the signal gathered is used for doctor's observation and analysis. In this system, the patient device sends ECG signal via wireless to the monitoring centre (PC). Moreover, a Graphic User Interface (GUI) is developed via Visual Basic (VB) to exhibit ECG processing task in monitoring centre.


A turning scheme in the headland of agricultural fields for autonomous robot




An embedded straight navigation system for inter-row tree tracking implementation in agricultural field
Norashikin M. Thamrin, Nor Hashim Mohd. Arshad, Ramli Adnan, Rosidah Sam, Noorfadzli A. Razak, Mohamad Farid Misnan, and Siti Fatimah Mahmud
IEEE
One of the unique features in the structured and well-organized agriculture field is the arrangement of the plants and crops in such long rows that leaves a small pathway in between them. This pathway is really important to facilitate the movement of the farmers or tractors in providing a maximum plant scouting and monitoring throughout the entire farm. Therefore, in this work, an embedded and automated navigation of the unmanned vehicle is developed to manipulate the minimal space in between the rows in order to navigate in the entire farm. A Bezier curve is applied to draft out the desired path and series of navigation schemes are deployed in order to maneuver the unmanned vehicle on the planned path as well as maintain its position to be in the middle of the path to avoid collision with the available trees or landmarks. Test results indicate that this work has demonstrated a simple and robust algorithm as well as low-level requirement for a small-scaled unmanned vehicle to travel between the crops in a straight navigation.

RECENT SCHOLAR PUBLICATIONS

Vehicle-to-Vehicle Communication: A Review of Efficiency, Communication Medium and Action Signal
NIA Anizan, FA Ruslan, NA Razak, MAA Aziz, J Johari
International Journal of Automotive and Mechanical Engineering 22 (1), 11986 2025



Research on the Application of Adaptive Parameter Adjustment Strategy in RBF Kernel SVM Image Classification
X Zhipeng, MAA Aziz, NA Razak
2024 IEEE 6th Symposium on Computers & Informatics (ISCI), 138-145 2024



Performance Evaluation of Support Vector Machine Algorithm in Object Classification Using Different Preprocessing Methods
X Zhipeng, MAA Aziz, NA Razak
2024 IEEE International Conference on Automatic Control and Intelligent 2024



On the Influence of Clamping Force
NA Alang, IU Ferdous, J Alias, NAA Razak
Proceedings of the 10th International Conference on Mechanical, Automotive 2024



On the Influence of Clamping Force and Contact Friction in Small Punch Test
NA Alang, IU Ferdous, J Alias, NAA Razak, AH Ahmad
International Conference on Mechanical, Automotive and Materials Engineering 2023



Switching Circuit For Automated Air Conditioner Control And Energy Saving In Classrooms
NM Redzuan, FYA Rahman, NM Thamrin, NA Razak, MSAM Ali, ...
2023 IEEE Symposium on Computers & Informatics (ISCI), 58-62 2023



Investigation of Object Detection and Identification at Different Lighting Conditions for Autonomous Vehicle Application
NA Razak, NAA Sabri, J Johari, FA Ruslan, MM Kamal, MAA Aziz
International Journal of Automotive and Mechanical Engineering 20 (3), 10649 2023



Application of response surface methodology for parameter optimization of aluminum 7075 thixoforming feedstock billet production
A Megalingam, AH Ahmad, NA Alang, J Alias, NAA Razak
Journal of Materials Engineering and Performance 32 (13), 5919-5931 2023



Publication Management System using Scopus API
BHFM Ijazi, SAC Abdullah, NK Mun, NM Thamrin, NA Razak, ZHC Soh
2022 IEEE 10th Conference on Systems, Process & Control (ICSPC), 313-318 2022



Design and Development of Modular and Open System (MOST) for Pandemic Precaution
NA Razak, MRB Sazali, J Johari, NAM Salleh, YHP Manurung, NK Mun
Proceedings of the 8th International Conference on Computational Science and 2022



Analysis of Training Function for NNARX in Solar Radiation Prediction Modeling
MRS Mohd, J Johari, FA Ruslan, NA Razak, S Ahmad, ASM Shah
Proceedings of the 8th International Conference on Computational Science and 2022



An evaluation of alternative fuels’ spray penetration at various spray cone angles and injection pressures using a simple evaporation model
J Lim, NA Razak, NM Mazlan
Biofuels 13 (3), 321-331 2022



Effect of Artificial Aging on the Microstructure and Mechanical Properties of AJ62 Magnesium Alloys
MIM Ramli, MAF Romzi, J Alias, NAA Razak
International Conference on Mechanical Engineering Research, 339-348 2021



Prediction of solvation properties of low transition temperature mixtures (LTTMs) using COSMO-RS and NMR approach
NR Yusuf, S Yusup, CL Yiin, PJ Ratri, AA Halim, NA Razak
IOP Conference Series: Materials Science and Engineering 1195 (1), 012006 2021



Evaluation of dynamic measurements from RTK-GNSS operating in sub-urban environment
RS Nahar, KM Ng, J Johari, MM Kamal, NA Razak
2021 IEEE 12th Control and System Graduate Research Colloquium (ICSGRC), 93-98 2021



Development of Self-Operating Solar Energy Potential Measuring Devices using Simple Microcontroller Setup
MRS Mohd, MS Abdullah, FA Ruslan, J Johari, NA Razak, S Ahmad, ...
2021 IEEE 12th Control and System Graduate Research Colloquium (ICSGRC), 51-56 2021



Qualitative Study of Prosthetic Liner Materials on Transtibial Amputees’ Satisfaction in Term of Positional Pain and Discomfort
MAM Nizam, NAA Razak, NAA Osman, RAM Jaladin
Kuala Lumpur International Conference on Biomedical Engineering, 205-216 2021



Analysis on parameter effect for solar radiation prediction modeling using NNARX
MRS Mohd, J Johari, FA Ruslan, NA Razak, S Ahmad, ASM Shah
2021 IEEE International Conference on Automatic Control & Intelligent 2021



Visual-based motorcycle detection using you only look once (yolo) deep network
FHK Zaman, SAC Abdullah, NA Razak, J Johari, I Pasya, KAA Kassim
IOP Conference Series: Materials Science and Engineering 1051 (1), 012004 2021



Thermal profile and microstructure of wrought aluminium 7075 for semisolid metal processing
NA Razak, AH Ahmad, MR Maarof
International Journal of Automotive and Mechanical Engineering 17 (2), 7842-7850 2020

MOST CITED SCHOLAR PUBLICATIONS

Physical and optical properties of Dy3+: Li2O–K2O–B2O3 glasses
SA Azizan, S Hashim, NA Razak, MHA Mhareb, YSM Alajerami, ...
Journal of Molecular Structure 1076, 20-25 2014
Citations: 130



Impact of Eu³⁺ Ions on Physical and Optical Properties of Li₂O-Na₂O-B₂O₃ Glass
NA Razak, S Hashim, MHA Mhareb, YSM Alajerami, SA Azizan, ...
Chinese Journal of Chemical Physics 29 (3), 395-400 2016
Citations: 42



Single infra-red sensor technique for line-tracking autonomous mobile vehicle
NM Arshad, MF Misnan, NA Razak
2011 IEEE 7th International Colloquium on Signal Processing and its 2011
Citations: 22



Comparison Between Ziegler-Nichols and AMIGO Tuning Techniques in Automated Steering Control System for Autonomous Vehicle
NNBM Mazlan, NM Thamrin, NA Razak
2020 IEEE International Conference on Automatic Control and Intelligent 2020
Citations: 20



Vision-based detection technique for effective line-tracking autonomus vehicle
NM Arshad, NA Razak
2012 IEEE 8th International Colloquium on Signal Processing and its 2012
Citations: 20



Remote air quality monitoring system by using MyRIO-LabVIEW
KM Ng, MAHM Suhaimi, A Ahmad, NA Razak
2018 9th IEEE Control and System Graduate Research Colloquium (ICSGRC), 105-109 2018
Citations: 18



Simultaneous localization and mapping based real-time inter-row tree tracking technique for unmanned aerial vehicle
NM Thamrin, NHM Arshad, R Adnan, R Sam, NA Razak, MF Misnan, ...
2012 IEEE International Conference on Control System, Computing and 2012
Citations: 18



Emotional intelligence from the perspectives of Malaysian helping professionals: A qualitative study
IHA Tharbe, M Sumari, KM Ng, NAA Razak, S Amat
Pertanika J. Soc. Sci. & Hum 28 (4), 1-18 2020
Citations: 13



Investigation of pouring temperature and holding time for semisolid metal feedstock production
NA Razak, AH Ahmad, MM Rashidi
IOP Conference Series: Materials Science and Engineering 257 (1), 012085 2017
Citations: 10



Fabricate optical microfiber by using flame brushing technique and coated with polymer polyaniline for sensing application
NA Razak, BA Hamida, N Irawati, MH Habaebi
IOP Conference Series: Materials Science and Engineering 210 (1), 012041 2017
Citations: 10



Application of response surface methodology for parameter optimization of aluminum 7075 thixoforming feedstock billet production
A Megalingam, AH Ahmad, NA Alang, J Alias, NAA Razak
Journal of Materials Engineering and Performance 32 (13), 5919-5931 2023
Citations: 8



Photoluminescence and thermoluminescence properties of Li₂O‐Na₂O‐B₂O₃ glass
NA Razak, S Hashim, MHA Mhareb, N Tamchek
Luminescence 31 (3), 754-759 2016
Citations: 8



A study of Kalman's filter in embedded controller for real-time quadrocopter roll and pitch measurement
NA Razak, NHM Arshad, R Adnan, MF Misnan, NM Thamrin, SF Mahmud
2012 IEEE International Conference on Control System, Computing and 2012
Citations: 8



Model identification and real-time linear position control of servomotor
N Ishak, SK Harun, H Ismail, NA Razak, R Adnan
2010 IEEE Control and System Graduate Research Colloquium (ICSGRC 2010), 71-74 2010
Citations: 8



Thermal profile and microstructure of wrought aluminium 7075 for semisolid metal processing
NA Razak, AH Ahmad, MR Maarof
International Journal of Automotive and Mechanical Engineering 17 (2), 7842-7850 2020
Citations: 7



Prediction of solvation properties of low transition temperature mixtures (LTTMs) using COSMO-RS and NMR approach
NR Yusuf, S Yusup, CL Yiin, PJ Ratri, AA Halim, NA Razak
IOP Conference Series: Materials Science and Engineering 1195 (1), 012006 2021
Citations: 6



Visual-based motorcycle detection using you only look once (yolo) deep network
FHK Zaman, SAC Abdullah, NA Razak, J Johari, I Pasya, KAA Kassim
IOP Conference Series: Materials Science and Engineering 1051 (1), 012004 2021
Citations: 6



An evaluation of alternative fuels’ spray penetration at various spray cone angles and injection pressures using a simple evaporation model
J Lim, NA Razak, NM Mazlan
Biofuels 13 (3), 321-331 2022
Citations: 5



An anthropomorphic transhumeral prosthesis socket developed based on an oscillometric pump and controlled by force-sensitive resistor pressure signals
NAA Razak, H Gholizadeh, N Hasnan, NAA Osman, SSM Fadzil, ...
Biomedical Engineering/Biomedizinische Technik 62 (1), 49-55 2017
Citations: 5



Tree diameter measurement using single infrared sensor for non-stationary vehicle context in agriculture field
NM Thamrin, NHM Arshad, R Adnan, R Sam, NA Razak, MF Misnan, ...
2013 IEEE 4th Control and System Graduate Research Colloquium, 38-42 2013
Citations: 5