Conference Publications

;

Latifah Mohamed

;

;

Anita Ahmad

;

Ruzairi Abdul Rahim

This manuscript presents a new method to monitor and localize the moisture distribution in a rice silo based on tomography images. Because the rice grain is naturally hygroscopic, the stored grains’ quality depends on their level of moisture content. Higher moisture content leads to fibre degradation, making the grains too frail and possibly milled. If the moisture is too low, the grains become brittle and are susceptible to higher breakage. At present, the single-point measurement method is unreliable because the moisture build-up inside the silo might be distributed unevenly. In addition, this method mostly applies gravimetric analysis, which is destructive. Thus, we proposed a radio tomographic imaging (RTI) system to address these problems. Four simulated phantom profiles at different percentages of moisture content were reconstructed using Newton’s One-Step Error Reconstruction and Tikhonov Regularization algorithms. This simulation study utilized the relationship between the maximum voxel weighting of the reconstructed RTI image and the percentage of moisture content. The outcomes demonstrated promising results, in which the weighting voxel linearly increased with the percentage of moisture content, with a correlation coefficient higher than 0.95 was obtained. Therefore, the results support the possibility of using the RTI approach for monitoring and localizing the moisture distribution inside the rice silo.

Publication

An overview on overvoltage phenomena in power systems

( 2019-06-28)

N. S. Othman

;

Mohamad Nur Khairul Hafizi Rohani

;

Mustafa W. A.

;

Wooi Chin Leong

;

Afifah Shuhada Rosmi

;

Shakur N.F.M.

;

Juliangga R.

;

Wan Khairunizam Wan Ahmad

;

Zunaidi I.

;

Zuradzman Mohamad Razlan

;

Shahriman Abu Bakar

Overvoltage happens in a condition where the voltage is increased and exceed its design limit. This situation may lead to harmful damage to machines or related equipment that connected to the system. Overvoltage can exist in a form of transient, voltage spike or permanent, depending on its duration. Types of overvoltage consist of lightning overvoltage and switching overvoltage. Overvoltage that caused by lightning is considerate as natural phenomena, while switching overvoltage exists from the system itself, either by the interruption of faults or inappropriate connection of circuit breaker contacts. This paper is discussed about overvoltage phenomenon including causes and effects of overvoltage and overvoltage protection towards power system.

Publication

Analysis of WiFi Spatio-Temporal Data for Organic Fingerprinting-based Indoor Positioning System

( 2022-01-01)

;

Amirah Husna Mohd Hajazi

;

Muhamad Safwan Muhamad Azmi

;

Mohd Sani Mohamad Hashim

;

Mohd Nasir Ayob

;

Hassrizal Hassan Basri

The mobile robot navigation is the next huge topic after positioning utilizing fingerprinting-based Wireless Positioning System (WPS). Many of recent works does not discuss this topic yet since many open problems in positioning topic are not yet solved, for instance the issues on multi-devices heterogeneity, instability of WiFi signals, granularity problems in grid-based indoor environment and many others. However, we anticipate that both positioning and navigation works must run in parallel so that the succession are guaranteed. This paper describes the analysis of spatio-temporal data of the signal obtained from the WiFi Access Point. Initial results suggest that the difference between transmitter heights have an effect on the spatio-temporal data while the handover of maximum signal strengths is inherent when three WiFi APs are used.

Publication

Arcing fault diagnosis using first peak arrival of EM radiation signal

( 2021-06-11)

Melaty binti Amirruddin

;

Mohd Rafi Adzman

;

Nur Adyani Mohd Affendi

;

Azralmukmin Azmi

;

Muhd Hafizi Idris

;

Hana Abdull Halim

;

Muzamir Isa

;

Halim S.A.

The objective of this study was to diagnose the arcing fault signals based on the first peak of arrival method using antenna to assess its use as potential arcing fault detection in power system network. Square patch antenna and circle patch antenna were employed for detection on artificial arcing in real environment. First peak of arcing signal arrival was measured through an analysis over a range of time and amplitude signals detected. For accurate results, Discrete Wavelet Transform (DWT) denoising technique was applied to the arcing signals detected as denoising tools. Analysis of first peak of signal arrival time and amplitude were carried out using MATLAB software to measure the changes in signals detected caused by di different placements of antenna. The results revealed that the first peak of signal arrival time, amplitude, type of antenna used and placement of the antenna around arcing source point all reflect the signals measurement.

Publication

Assessment of Control Drive Technologies for Induction Motor: Industrial Application to Electric Vehicle

( 2021-06-11)

Ahmad Firdaus Ahmad Zaidi

;

Syahrul Ashikin Azmi

;

;

Leong Jenn Hwai , Jenn

;

Hasimah Ali

;

Mohd Shuhanaz Zanar Azalan

;

Zamri Che Mat Kasa

Nowadays electric vehicle has increasingly gained much popularity indicated by growing global share market targeted at 30% by 2030 after recording 7.2million global stock in 2019. Compared to Internal Combustion Engine (ICE) counterpart, Battery Electric Vehicles (BEV) produce zero tailpipe emission which greatly reducing carbon footprints. Induction motor has been widely used and its control technology has evolved from scalar type volt/hertz to recent predictive control technology. This allows induction motor's application to expand from being the workhorse of industry to become prime mover in electric vehicle, where high performance is expected. Among vector control scheme, Direct Torque Control (DTC) has gained interest over Field Oriented Control (FOC) with simpler structure, better robustness and dynamics performance yet suffer from high torque and flux ripple. In electric vehicle applications, high ripple at low speed is highly undesirable, potentially causing torsional vibration. High performance control requires speed sensor integration, which often increase complexity in the design. The work aims to review the best control technology for induction motor in electric vehicle application through performance parameter evaluation such as improvement on dynamic response, torque and flux ripple reduction, and component optimization. Several arise issues in motor control and possible methods to circumvent are highlighted in this work. In conclusion, model predictive torque control (MPTC) is the most promising scheme for electric vehicle with excellent dynamic response, good low speed performance, and 50% torque ripple reduction compared to conventional DTC and potential integration with sliding mode observer for sensorless solution.

Publication

Assessment of functional and dysfunctional on implant stability measurement for quality of life

( 2017)

Norshahrizan Nordin

;

Razli Che Razak

;

Mohd. Mustafa Al Bakri Abdullah

;

Muhammad Safizal Abdullah

;

Fauziah Che Mat

;

Abdul Hamid Adom

This study was conducted to investigate the effect of an implant wearer comprising among orthopedic patients as well as the use of implant dentistry in Northern Malaysia. A total of 100 questionnaires were distributed and 70 questionnaires can be used to record, analyze and test hypotheses. Data for all variables were collected through a questionnaire administered alone and analyzed by using SmartPLS V3. A total of four (4) hypotheses have been formulated and the results show that the hypothesis is supported. The results show that: (1) limit the functionality and quality of life was significantly (0.904) in connection with the implant wearer, (2) physical pain was significantly (0.845) relating to the quality of life, (3) physical discomfort was significantly (0.792) in connection with quality of life, and also (4) social discomfort is significant as well (0.809). This finding suggests that there are positive effects on the implant wearer who through life routine. The results of the study may also serve as a basis for reliable decisions related to quality of life and for the implementation of awareness campaign that increase how the need for humanity in the field of quality involvement.

Publication

Classification of Body Mass Index Based Facial Images using Empirical Mode Decomposition

( 2021-06-11)

Hasimah Ali

;

Yee, O.S.

;

Wan Khairunizam Wan Ahmad

Human faces contain rich information. Recent studies found that facial features have relation with human weight or body mass index (BMI). Decoding "facial information"from the face in predicting the BMI could be linked to the various health marker. This paper proposed the classification of body mass index (BMI) based on appearance based features of facial images using empirical mode decomposition (EMD) as feature extraction technique. The facial images that describe the body mass index was extracted using EMD to obtain a set of significant features. In this framework, the facial image was decomposed using EMD to produce a small set of intrinsic mode functions (IMF) via sifting process. The IMF features which exhibit the unique pattern were used to classify the BMI. The obtained features were then fed into machine learning classifier such as k-nearest neighbour and support vector machines (SVM) to classify the three BMI classes namely normal, overweight and obese. The obtained results show that the IMF2 feature using SVM classifier achieved recognition rate of 99.12% which show promising result.

Publication

Classification of human emotions using EEG Signals in a simulated environment

( 2022-01-01)

Hafiz Halin

;

Wan Khairunizam Wan Ahmad

;

Wan Azani Wan Mustafa

;

Muhajir Ab. Rahim

;

Zuradzman Mohamad Razlan

;

Shahriman Abu Bakar

The Brain-Computer Interface (BCI) is a computer-based system that acquires and analyses brain signals. The analysis of brain signals shows the physiological change that happens to the drivers. The physiological changes detected by the BCI system may not be visible to the naked eye. By using the BCI, it increases the diagnostic capability to detect the drivers' emotions. The negative drivers' emotions may cause bad decision making during driving the vehicle. The proposed method was developed to study the related emotions that occur during driving in the simulation environment. The experiments were designed in two situations, which are manual and autonomous drive. In the manual mode, the subjects will control the steering wheel and acceleration of the simulated vehicle. While in autonomous mode, all controls are disable and the subjects will experience the automatic simulation drive. The EEG data was recorded during the simulated drive (manual and autonomous). The EEG data from the subjects were then categorised into five emotions classifications.

Publication

Deep Neural Network for Localizing Gas Source Based on Gas Distribution Map

( 2022-01-01)

Zaffry Hadi Mohd Juffry

;

;

Abdul Hamid Adom

;

Mao X.

;

;

;

;

Abdullah A.N.

The dynamic characteristic of gas dispersal in uncontrolled environment always leads to inaccurate gas source localization prediction from gas distribution map. Gas distribution map is a representation of the gas distribution over an environment which helps human to observe the concentration of harmful gases at a contaminated area. This paper proposes the utilization of Deep Neural Network (DNN) to predict the gas source location in a gas distribution map. DNN learns from the previous gas distribution map data and patterns to generate a model that is able predict location of gas source. The results indicate that DNN is able to accurately predict the location within the range of 0.8 to 2 m from the actual gas source. This finding shows that DNN has a high potential for utilization in gas source localization application.

Publication

Deep Neural Network for Localizing Gas Source Based on Gas Distribution Map

( 2022-01-01)

Zaffry Hadi Mohd Juffry

;

;

Abdul Hamid Adom

;

Mao X.

;

;

;

;

Abdulnasser Nabil Abdullah

The dynamic characteristic of gas dispersal in uncontrolled environment always leads to inaccurate gas source localization prediction from gas distribution map. Gas distribution map is a representation of the gas distribution over an environment which helps human to observe the concentration of harmful gases at a contaminated area. This paper proposes the utilization of Deep Neural Network (DNN) to predict the gas source location in a gas distribution map. DNN learns from the previous gas distribution map data and patterns to generate a model that is able predict location of gas source. The results indicate that DNN is able to accurately predict the location within the range of 0.8 to 2 m from the actual gas source. This finding shows that DNN has a high potential for utilization in gas source localization application.

Publication

Development of Standstill Monitoring System (SMS) for Inhouse Agriculture Product Application

( 2022-01-01)

Sheikh Mohamad Naim Shikh Shatir

;

;

Akhtar M.N.

;

Abdullah M.N.

;

Bakar E.A.

This research is focus on developing a cost-effective and reliable Standstill Monitoring System (SMS) from entire concepts of smart farming system. The SMS architecture consists of several modules of sensors, wireless communication with the integration of normalized difference vegetation index (NDVI) imaging to analyze the health condition of a mango tree or any fruit bunch in terms of nutritional value and nutrition-deficiency related disease. The components are attached to a customized tripod, where the tripod then be placed at a mango farm for example, or any fruit bunch before crop harvesting process application. The system not only monitors the farm environment but also transmit data remotely as well as receive user’s input. To further enhance the data analysis, an expert’s advice is also taken into account regarding the age of mango trees as a case studies, moreover, the selection of type of fertilizer and type of soil is recorded for references in entire harvesting process. This ongoing project is still in prototype development stage and parameters and variables occur while the growing mango tree or any fruit bunch from initial stage of production, the emergence of portable and affordable but effective SMS for smart farming system would allow farmers to monitor their mango farm or any fruit bunch at distance while reaping the benefits.

Publication

Different Devices Behavior in Fingerprinting Indoor Positioning for Mobile Robot in Healthcare Industries

( 2022-01-01)

Ahmad Hakimi Ahmad Sa'ahiry

;

;

Toyoura M.

;

In the recent light of the 4th Industrial Revolution particularly in medical industries, the use of medical robot is an adaptable alternative to reduce the burden in medical services. A mobile robot is normally developed and embedded with numerous sensors especially for its indoor positioning system. This matter has hindered the use of such robots as it increases the development cost. One solution is to employ the readily available sensors such as Wi-Fi. Wi-Fi is widely deployed, and it does not have additional hardware to configure unlike Bluetooth. Despite the potential of Wi-Fi, some adjustment needs to be executed to provide a better accuracy. The Wi-Fi signal has their own disadvantage such as the multipath and shadowing effect making it stand-alone unreliable. Hence, the fingerprinting technique is proposed to solve this issue. The fingerprinting technique mainly used one device in collecting the fingerprinting database. Nonetheless, if the device is broken or new software needed to deploy, the device needs to be substituted. The contribution of this paper is to investigate the behavior of different devices in the fingerprinting method and evaluate the positioning result.

Publication

Effect of distributed generation to the faults in medium voltage network using ATP-EMTP simulation

( 2021-01-01)

Wan Syaza Ainaa Wan Salman

;

Mohd Rafi Adzman

;

Muzamir Isa

;

Nur Syazlin Bakhtiar Jamili

;

Muhd Hafizi Idris

;

Melaty binti Amirruddin

During past few years, distributed generation (DG) technology has been widely known in the industry as it can helps in providing backup power during high power demand. However, adding a new system may changes the traditional power system that are usually work in one direction which is from the generation to the consumer. When DG is added, the power flows from two direction. Therefore, a short circuit study was done to study the effects of DG to the local system during fault. An IEC Standard was also calculated as guidance to determine the thermally permissible of a cable.

Publication

Feature Extraction based on Empirical Mode Decomposition for Shapes Recognition of Buried Objects by Ground Penetrating Radar

( 2021-06-11)

Hasimah Ali

;

Mohd Shuhanaz Zanar Azalan

;

Ahmad Firdaus Ahmad Zaidi

;

Tengku Sarah Tengku Amran

;

Mohamad Ridzuan Ahmad

;

Mohamed Elshaikh Elobaid Said Ahmed

Ground penetrating radar (GPR) is one of the promising non-destructive imaging tools investigations for shallow subsurface exploration such as locating and mapping the buried utilities. In practical applications, GPR images could be noisy due to the system noise, the heterogeneity of the medium, and mutual wave interactions thus, it is a complex task to recognizing the hyperbolic signature of buried objects from GPR images. Therefore, this paper aims to develop nonlinear feature extraction technique of using Empirical Mode Decomposition (EMD) in recognizing the four geometrical shapes (cubic, cylindrical, disc and spherical) from GPR images. A pre-processing step of isolating hyperbolic signature from different background was first employed by mean of Region of Interest (ROI). The hyperbolic signature that describes the shapes was extracted using EMD decomposition to obtain a set of significant features. In this framework, the hyperbolic pattern was decomposed of using EMD, to produce a small set of intrinsic mode functions (IMF) via sifting process. The IMF properties of the signature that exhibit the unique pattern was used as potential features to differentiate the geometrical shapes of buried objects. The extracted IMF features were then fed into machine learning classifier namely Support Vector Machines. To evaluate the effectiveness of the proposed method, a set data collection of GPR-images has been acquired. The experimental results show that the recognition rate of using IMF features was achieved 99.12% accuracy in recognizing the shapes of buried objects whose shows the promising result.

Publication

Flashover voltage prediction on polluted cup-pin the insulators under polluted conditions

( 2021-01-01)

Salem A.A.

;

Abd-Rahman R.

;

Kamarudin M.S.

;

Othman N.A.

;

Jamail N.A.M.

;

Nuriziani Hussin

;

Haziah Abdul Hamid

;

Rawi I.M.

The natural pollution which is mainly affected by the weather conditions are the main cause of flashovers on high voltage insulators leading to outages in power systems. In this work, characteristics of flashover for contaminated cup-pin insulators have been studied based on experiential test and a mathematical model. Information from laboratory test combined with new mathematical model results are used to define Artificial Neural Network (ANN) algorithm and Adaptive Neuro-fuzzy Inference System (ANFIS) for calculated the flashover characteristics (current IF and voltage UF). several of experiments and measurement are carried out for 1:1, 5:1, 10:1 and 15:1 ratios of bottom to top surface salt deposit density on contaminated samples (z). Dimensional Analysis Method (DAM) was used to derive new model for the variables which often effective in the flashover phenomenon of polluted insulators. The model was derived by establishment the relationship between flashover voltage UF and current IF, length of pollution layer LP, exposure time t, arc constant A and layer pollution conductivity of insulator σ. The both arc constants A and n is computed using genetic algorithm. Comparative investigates have clearly shown that the approach AI-based method gives the agreeable results compared to the mathematical model.

Publication

Gas Source Localization via Mobile Robot with Gas Distribution Mapping and Deep Neural Network

( 2022-01-01)

Ahmad Shakaff Ali Yeon

;

;

;

Visvanathan R.

;

;

With the growth of artificial intelligence compute technology, the gas source localization problem would be solved by mobile robots equipped with gas sensing system and artificial intelligence compute units. This work presented a feasibility study of deep learning approach towards gas source localization by mobile robots. A deep neural network strategy was developed and incorporated with the Kernel DM+V gas distribution mapping method. The gas source localization work in this paper was performed on a controlled indoor testbed. From this work, it is shown that by incorporating the developed deep neural network model, it may help improved the gas source location prediction accuracy. A comparison of accuracy between Kernel DM+V and the neural network model is also presented to better visualize the improvement.

Publication

Gas Source Localization via Mobile Robot with Gas Distribution Mapping and Deep Neural Network

( 2022-01-01)

Ahmad Shakaff Ali Yeon

;

;

;

Visvanathan R.

;

;

With the growth of artificial intelligence compute technology, the gas source localization problem would be solved by mobile robots equipped with gas sensing system and artificial intelligence compute units. This work presented a feasibility study of deep learning approach towards gas source localization by mobile robots. A deep neural network strategy was developed and incorporated with the Kernel DM+V gas distribution mapping method. The gas source localization work in this paper was performed on a controlled indoor testbed. From this work, it is shown that by incorporating the developed deep neural network model, it may help improved the gas source location prediction accuracy. A comparison of accuracy between Kernel DM+V and the neural network model is also presented to better visualize the improvement.

Publication

Investigation of Spherical Electrode Grounding System under High Impulse Conditions with Different Polarities

( 2021-06-11)

Haziah Abdul Hamid

;

Mohd Rafi Adzman

;

Noor Hasnizam Hanafi

;

Nor N.M.

;

Abdullah S.

;

Reffin M.S.

;

Etobi N.A.

;

Abd-Rahman R.

There have been many studies in the pasts, which showed that under high impulse conditions, soil ionization process around the electrode would occur, which results in lower resistance and lower transient voltage on the electrode. Several factors have also been found to affect the ionization process in soil such as; soil types and its grain sizes, moisture contents in the soil, earth electrode configurations, impulse polarity, the location of the injection point, the shape of response time, etc. In this paper, spherical electrodes grounding is used to study the ionization process in the grounding system under different impulse polarity of the current. The experiment was done by field measurement using a commercially available impulse current generator. It was found that lower earth resistance was seen to decrease with increasing current magnitudes for both impulse polarities. In addition, it was found that at low impulse current with negative polarity has a higher resistance than that of positive polarity. This paper is, therefore, to investigate towards improvement on grounding electrode's design, which would consider soil ionization process

Publication

Non-Contact breathing monitoring using Sleep Breathing Detection Algorithm (SBDA) based on UWB radar sensors

( 2022)

Muhammad Husaini

;

;

;

Intan Kartika Kamarudin

;

Muhammad Amin Ibrahim

;

Hiromitsu Nishizaki

;

Masahiro Toyoura

;

Xiaoyang Mao

Ultra-wideband radar application for sleep breathing monitoring is hampered by the difficulty of obtaining breathing signals for non-stationary subjects. This occurs due to imprecise signal clutter removal and poor body movement removal algorithms for extracting accurate breathing signals. Therefore, this paper proposed a Sleep Breathing Detection Algorithm (SBDA) to address this challenge. First, SBDA introduces the combination of variance feature with Discrete Wavelet Transform (DWT) to tackle the issue of clutter signals. This method used Daubechies wavelets with five levels of decomposition to satisfy the signal-to-noise ratio in the signal. Second, SBDA implements a curve fit based sinusoidal pattern algorithm for detecting periodic motion. The measurement was taken by comparing the R-square value to differentiate between chest and body movements. Last but not least, SBDA applied the Ensemble Empirical Mode Decomposition (EEMD) method for extracting breathing signals before transforming the signal to the frequency domain using Fast Fourier Transform (FFT) to obtain breathing rate. The analysis was conducted on 15 subjects with normal and abnormal ratings for sleep monitoring. All results were compared with two existing methods obtained from previous literature with Polysomnography (PSG) devices. The result found that SBDA effectively monitors breathing using IR-UWB as it has the lowest average percentage error with only 6.12% compared to the other two existing methods from past research implemented in this dataset.

Publication

Optimization of Controller Design for Magnetic Levitation System by PSO, GSA and PSOGSA

( 2022-01-01)

Siti Marhainis Othman

;

Zuo W.W.

;

Russhabiahtul Adawiyah Rustam

;

Rahmat M.F.

;

Mohd Saifizi Saidon

;

Hassrizal Hasan Basri

;