Kamarulzaman Kamarudin
Thumbnail Image
Preferred name
Kamarulzaman Kamarudin
Official Name
Kamarudin, Kamarulzaman
Alternative Name
Kamarudin, K.
Kamaruddin, Kamarulzaman
Main Affiliation
Scopus Author ID
55193266400
Researcher ID
DVV-8479-2022

Research Output

Filters

26 1 1
26
Reset filters

Settings
Now showing 1 - 10 of 26
  • Publication
    Assessment of Control Drive Technologies for Induction Motor: Industrial Application to Electric Vehicle
    ( 2021-06-11)
    Ahmad Firdaus A.Z.
    ;
    Azmi S.A.
    ;
    Kamarulzaman Kamarudin
    ;
    Leong Jenn Hwai , Jenn
    ;
    Hasimah Ali
    ;
    Mohd Shuhanaz Zanar Azalan
    ;
    Kasa Z.C.M.
    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
    Performance analysis of the microsoft kinect sensor for 2D Simultaneous Localization and Mapping (SLAM) techniques
    ( 2014)
    Kamarulzaman Kamarudin
    ;
    Syed Muhammad Mamduh Syed Zakaria
    ;
    Ali Yeon Md Shakaff
    ;
    Ammar Zakaria
    This paper presents a performance analysis of two open-source, laser scanner-based Simultaneous Localization and Mapping (SLAM) techniques (i.e., Gmapping and Hector SLAM) using a Microsoft Kinect to replace the laser sensor. Furthermore, the paper proposes a new system integration approach whereby a Linux virtual machine is used to run the open source SLAM algorithms. The experiments were conducted in two different environments; a small room with no features and a typical office corridor with desks and chairs. Using the data logged from real-time experiments, each SLAM technique was simulated and tested with different parameter settings. The results show that the system is able to achieve real time SLAM operation. The system implementation offers a simple and reliable way to compare the performance of Windows-based SLAM algorithm with the algorithms typically implemented in a Robot Operating System (ROS). The results also indicate that certain modifications to the default laser scanner-based parameters are able to improve the map accuracy. However, the limited field of view and range of Kinect's depth sensor often causes the map to be inaccurate, especially in featureless areas, therefore the Kinect sensor is not a direct replacement for a laser scanner, but rather offers a feasible alternative for 2D SLAM tasks.
  • Publication
    Ganoderma boninense classification based on near-infrared spectral data using machine learning techniques
    ( 2023-01-15)
    Mohd Hilmi Tan M.I.S.
    ;
    Jamlos M.F.
    ;
    Omar A.F.
    ;
    Kamarulzaman Kamarudin
    ;
    Mohd Aminudin Jamlos
    Ganoderma boninense (G. boninense) infection reduces the productivity of oil palms and causes a severe threat to the palm oil industry. Early detection of G. boninense is vital since there is no effective treatment to stop the continuing spread of the disease unless ergosterol, a biomarker of G. boninense can be detected. There is yet a non-destructive and in-situ technique explored to detect ergosterol. Capability of NIR to detect few biomarkers such as mycotoxin and zearalenone (ZEN) has been proven to pave the way an effort to explore NIR's sensitivity towards detecting ergosterol, as discussed in this paper. A compact hand-held NIR with a measurement range of 900–1700 nm is utilized by scanning the leaves of three oil palm seedlings inoculated with G. boninense while the other three were non-inoculated from 16-weeks-old to 32-weeks-old. Significant changes of spectral reflectance have been notified occur at the wavelength of ∼1450 nm which reflectance of infected sample is higher 0.2–0.4 than healthy sample which 0.1–0.19. The diminishing of the spectral curve at approximately 1450 nm is strongly suspected to happened due to the loss of water content from the leaves since G. boninense attacks the roots and causes the disruption of water supply to the other part of plant. However, a few overlapped NIRs' spectral data between healthy and infected samples require for further validation which chemometric and machine learning (ML) classification technique are chosen. It is found the spectra of healthy samples are scattered on the negative sides of PC-1 while infected samples tend to be on a positive side with large loading coefficients marked significant discriminatory effect on healthy and infected samples at the wavelength of 1310 and 1452 nm. A PLS regression is used on NIR spectra to implement the prediction of ergosterol concentration which shows good corelation of R = 0.861 between the ergosterol concentration and oil palm NIR spectra. Four different ML algorithms are tested for prediction of G. boninense infection: K-Nearest Neighbour (kNN), Naïve Bayes (NB), Support Vector Machine (SVM) and Decision Tree (DT) are tested which depicted DT algorithm achieves a satisfactory overall performance with high accuracy up to 93.1% and F1-score of 92.6% compared to other algorithms. High accuracy shows the capability of the classification model to correctly predict the G. boninense detection while high F1-score indicates that the classification is able to validate the detection of G. boninense correctly with low misclassification rate. The result represents a significant step in the development of a non-destructive and in-situ detection system which validated by both chemometric and machine learning (ML) classification techniques.
  • Publication
    An improved mobile robot based gas source localization with temperature and humidity compensation via slam and gas distribution mapping
    ( 2016)
    Kamarulzaman Kamarudin
    This research is concerned with the problem of localizing gas source in indoor environment using a mobile robot. The problem could be seen as similar to the event of hazardous gas leak in a building. Since the environment is often unknown to the robot, the Simultaneous Localization and Mapping (SLAM) operation is required. Two open source SLAM techniques (i.e. Gmapping and Hector SLAM) were implemented to provide this crucial information. Extensive experiments and analysis on both SLAM techniques yielded that the Hector SLAM is more suitable for gas distribution mapping (GDM) application due to the improved robot pose estimation, less computational requirement and only performs map correction locally. Therefore, the Hector SLAM is combined with Kernel DM+V algorithm to achieve real-time SLAM-GDM for predicting gas source location. Rigorous real-time experiments were conducted to verify the performance of the proposed SLAM-GDM method in an uncontrolled office building with the presence of ethanol emission. The experimental results showed that the prediction of gas source location is often accurate to 0.5 to 2.0m. Furthermore, an Epanechnikov based Kernel DM+V algorithm was also introduced to limit extrapolation range in GDM computations. The observed advantages were lower computational requirement and slightly more accurate prediction on gas source location. More importantly, it was found that the maps produced were able to indicate the areas of unexplored gas distribution and therefore could be used for the robot‘s path planning. The final and the main part of the thesis deals with the effect of ambient temperature and humidity on metal oxide gas sensor (i.e. TGS 2600) response; which could affect the GDM results. Linear regression processes were conducted to create a model to correct the temperature and humidity drift of the gas sensor response. The model (i.e. function) was tested in various configurations and was found to minimize the effects of the two environmental factors on the gas sensor response in different gas concentrations. Finally, two versions of Kernel DM+V/T/H algorithms were proposed and coupled with the drift model to compensate for temperature and humidity variation during the GDM task. The experimental results showed that the Kernel DM+V/T/H algorithms were able to produce more stable gas distribution maps and improve the accuracy of gas source localization prediction by 34%.
  • Publication
    Gas Source Localization via Mobile Robot with Gas Distribution Mapping and Deep Neural Network
    ( 2022-01-01)
    Ahmad Shakaff Ali Yeon
    ;
    Ammar Zakaria
    ;
    Syed Muhammad Mamduh Syed Zakaria
    ;
    Visvanathan R.
    ;
    Kamarulzaman Kamarudin
    ;
    Latifah Munirah Kamarudin
    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.
      3
  • Publication
    Two-stream deep convolutional neural network approach for RGB-D face recognition
    ( 2021-07-21)
    Shunmugam P.
    ;
    Kamarulzaman Kamarudin
    ;
    Latifah Munirah Kamarudin
    ;
    Ammar Zakaria
    ;
    Nishizaki H.
    Two-dimensional face recognition has been researched for the past few decades. With the recent development of Deep Convolutional Neural Network (DCNN) deep learning approaches, two-dimensional face recognition had achieved impressive recognition accuracy rate. However, there are still some challenges such as pose variation, scene illumination, facial emotions, facial occlusions exist in the two-dimensional face recognition. This problem can be solved by adding the depth images as input as it provides valuable information to help model facial boundaries and understand the global facial layout and provide low-frequency patterns. RGB-D images are more robust compared to RGB images. Unfortunately, the lack of sufficient RGB-D face databases to train the DCNN are the main reason for this research to remain undiscovered. So, in this research, new RGB-D face database is constructed using the Intel RealSense D435 Depth Camera which has 1280 x 720-pixel depth. Twin DCNN streams are developed and trained on RGB images at one stream and Depth images at another stream, and finally combined the output through fusion soft-max layers. The proposed DCNN model shows an accuracy of 95% on a newly constructed RGB-D database.
      1
  • Publication
    Reinforcement Learning for Mobile Robot's Environment Exploration
    ( 2023-01-01)
    Teoh S.W.H.
    ;
    Kamarulzaman Kamarudin
    ;
    Ali N.A.N.
    ;
    Zainal M.M.M.
    ;
    Mohd Rizal Manan
    ;
    Syed Muhammad Mamduh Syed Zakaria
    Mobile robots are being are being applied in various industries to perform repetitive or dangerous tasks for humans to carry out. Autonomous mobile robots are more capable than automated guided vehicles (AGV) due to their ability to be adaptable to their environment which is important for exploration of unknown environments. It is difficult to program autonomous mobile robots to adapt to various situations it may face, thus machine learning can be applied to allow a mobile robot to learn how to navigate through environments by itself. Reinforcement learning is applied in this project so that a differential drive mobile robot can learn how to navigate through its environment while avoiding collision with surrounding walls and obstacles. The reinforcement learning process is simulated by using the Robot Operating System (ROS) and its simulator Gazebo. Controlled simulation environments are created using Gazebo for the purposes of training and performance testing. Simultaneous Localization and Mapping (SLAM) will be applied to generate a map of the environment. At the end of this project, the Turtlebot3 is able to map smaller controlled environments ranging between 18m2 to 27m2 without colliding with the surrounding walls.
      1
  • Publication
    Deep Neural Network for Localizing Gas Source Based on Gas Distribution Map
    ( 2022-01-01)
    Zaffry Hadi Mohd Juffry
    ;
    Kamarulzaman Kamarudin
    ;
    Abdul Hamid Adom
    ;
    Mao X.
    ;
    Latifah Munirah Kamarudin
    ;
    Ammar Zakaria
    ;
    Syed Muhammad Mamduh Syed Zakaria
    ;
    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.
      1
  • Publication
    Gas Source Localization via Mobile Robot with Gas Distribution Mapping and Deep Neural Network
    ( 2022-01-01)
    Ahmad Shakaff Ali Yeon
    ;
    Ammar Zakaria
    ;
    Syed Muhammad Mamduh Syed Zakaria
    ;
    Visvanathan R.
    ;
    Kamarulzaman Kamarudin
    ;
    Latifah Munirah Kamarudin
    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.
      1
  • Publication
    Assessment of Control Drive Technologies for Induction Motor: Industrial Application to Electric Vehicle
    ( 2021-06-11)
    Ahmad Firdaus Ahmad Zaidi
    ;
    Syahrul Ashikin Azmi
    ;
    Kamarulzaman Kamarudin
    ;
    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.
      3  2