Ismail Mohd Khairuddin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Ismail Mohd Khairuddin has a total of 52 co-authors. Here are the top co-authors by number of shared publications:
- Anwar P. P. Abdul Majeed
Sunway University
9 shared publications Mohd Azraai Mohd Razman
Faculty of Manufacturing and Mechatronics Engineering Technology, Universiti Malaysia Pahang, 26600 Pahang, Malaysia
5 shared publications- Mohd Azraai Mohd Razman
Universiti Malaysia Pahang Al-Sultan Abdullah
5 shared publications Anwar P. P. Abdul Majeed
School of Robotics, XJTLU Entrepreneur College (Taicang), Xi’an Jiatong-Liverpool University, Suzhou, 215123, P. R. China
4 shared publications- Muhammad Amirul Abdullah
Universiti Malaysia Pahang Al-Sultan Abdullah
4 shared publications Wan Hasbullah Mohd Isa
Faculty of Manufacturing and Mechatronics Engineering Technology, Universiti Malaysia Pahang, 26600 Pahang, Malaysia
3 shared publications
Latest Publications
- Open Access
- 21 January 2026
- Published by PeerJ in PeerJ Computer Science
- Vol. 12, e3496
Analyzing fish detection and classification in IoT-based aquatic ecosystems through deep learning
Fish, a crucial source of protein, contribute approximately 17% of the global animal protein intake. In Malaysia, the fisheries sector serves as a significant economic driver, contributing around 11.22 billion Malaysian ringgit to the nation’s GDP in 2021. However, overfishing poses a substantial threat, leading to the depletion of marine life, disruption of ecosystems, potential food shortages, and unemployment. The advent of the Internet of Things (IoT) offers transformative potential for aquaculture, enhancing productivity, reducing waste, and promoting sustainability. This research underscores the viability of IoT-based smart aquaculture, focusing on different species and colours, such as red tilapia, black tilapia, and sailfin catfish. For monitoring aquaculture activities, the ESP32 Devkit is employed to collect data on temperature, dissolved oxygen, and pH levels, as well as to operate fish pellet feeders. Fish detection is facilitated using the NVIDIA Jetson Nano, an underwater camera, and various Darknet architectures within the You Only Look Once (YOLO) version, including YOLOv3, YOLOv3-Tiny, YOLOv4, and YOLOv4-Tiny. Future enhancements aim to monitor fish growth sizes, behaviour, and diseases, as well as identify waterborne pathogens, control pH, dissolved oxygen, and chlorine levels. The ongoing evolution of machine learning, deep learning, and transfer learning can facilitate the production of safe, high-quality, and abundant protein sources in well-regulated environments. This integration of technology into aquaculture signifies a promising step towards sustainable fisheries management, potentially mitigating the adverse effects of overfishing while ensuring the continued provision of essential protein sources. The study’s findings highlight the transformative potential of IoT and machine learning technologies in enhancing aquaculture productivity and sustainability. Among the tested models, YOLOv4-Tiny demonstrated the highest Average Precision (AP) and F1-score (approximately 1.00), making it the most suitable for real-time implementation due to its balance of accuracy and computational efficiency.
- 21 January 2026
- Published by PeerJ in PeerJ Computer Science
- Vol. 12, e3496
Open AccessAnalyzing fish detection and classification in IoT-based aquatic ecosystems through deep learning
Fish, a crucial source of protein, contribute approximately 17% of the global animal protein intake. In Malaysia, the fisheries sector serves as a significant economic driver, contributing around 11.22 billion Malaysian ringgit to the nation’s GDP in 2021. However, overfishing poses a substantial threat, leading to the depletion of marine life, disruption of ecosystems, potential food shortages, and unemployment. The advent of the Internet of Things (IoT) offers transformative potential for aquaculture, enhancing productivity, reducing waste, and promoting sustainability. This research underscores the viability of IoT-based smart aquaculture, focusing on different species and colours, such as red tilapia, black tilapia, and sailfin catfish. For monitoring aquaculture activities, the ESP32 Devkit is employed to collect data on temperature, dissolved oxygen, and pH levels, as well as to operate fish pellet feeders. Fish detection is facilitated using the NVIDIA Jetson Nano, an underwater camera, and various Darknet architectures within the You Only Look Once (YOLO) version, including YOLOv3, YOLOv3-Tiny, YOLOv4, and YOLOv4-Tiny. Future enhancements aim to monitor fish growth sizes, behaviour, and diseases, as well as identify waterborne pathogens, control pH, dissolved oxygen, and chlorine levels. The ongoing evolution of machine learning, deep learning, and transfer learning can facilitate the production of safe, high-quality, and abundant protein sources in well-regulated environments. This integration of technology into aquaculture signifies a promising step towards sustainable fisheries management, potentially mitigating the adverse effects of overfishing while ensuring the continued provision of essential protein sources. The study’s findings highlight the transformative potential of IoT and machine learning technologies in enhancing aquaculture productivity and sustainability. Among the tested models, YOLOv4-Tiny demonstrated the highest Average Precision (AP) and F1-score (approximately 1.00), making it the most suitable for real-time implementation due to its balance of accuracy and computational efficiency.
- 1 October 2025
- Published by Springer Nature
- p. 387-399
Classification of Badminton Strokes Through IMU Data Using Supervised SVM and kNN Machine Learning Algorithms
- 1 October 2025
- Published by Springer Nature
- p. 387-399
Classification of Badminton Strokes Through IMU Data Using Supervised SVM and kNN Machine Learning Algorithms
- 13 August 2025
- Published by Springer Nature
- p. 181-190
Autonomous Mobile Robot for Obstacle Avoidance with Vision System
- 13 August 2025
- Published by Springer Nature
- p. 181-190
Autonomous Mobile Robot for Obstacle Avoidance with Vision System
- 31 May 2025
- Published by Springer Nature
- p. 313-322
Advanced Pill Identification Using Deep Learning Techniques
- 31 May 2025
- Published by Springer Nature
- p. 313-322
Advanced Pill Identification Using Deep Learning Techniques
- 27 February 2024
- Published by Springer Nature
- p. 15-25
Road Signage and Road Obstacle Detection Using Deep Learning Method
- 27 February 2024
- Published by Springer Nature
- p. 15-25
Road Signage and Road Obstacle Detection Using Deep Learning Method
- Open Access
- 29 November 2022
- Published by Universiti Malaysia Pahang Al-Sultan Abdullah Press (UMPSA Press) in MEKATRONIKA
- Vol. 4 (2) , 58-63
Artificial Intelligence Approach For Fire Monitoring and Warning System Design
Fire alarm system consist of several type of sensors that works togeher in order to detect a fire breakouts. But the systems itself consist of errors especially detecting smoke which sometimes could not lead to a potential fire breakouts instead causing a false alarm. Moreover, vision cameras are expensive to be installed and it takes a lot amount of money for maintenance alone. This causes many household does not equip with such devices making fire breakouts to be inevitable. In this research, the aim of this is to create a system that is cheap and could detect a potential fire before it could even happen by applying Fuzzy logic technique. By adding an Artificial Intelligence in a fire monitoring and warning systems, This could reduce error and predict the right event that could lead to a fire breakouts. With this, many household especially in Malaysia could have the safety to overcome this
- 29 November 2022
- Published by Universiti Malaysia Pahang Al-Sultan Abdullah Press (UMPSA Press) in MEKATRONIKA
- Vol. 4 (2) , 58-63
Open AccessArtificial Intelligence Approach For Fire Monitoring and Warning System Design
Fire alarm system consist of several type of sensors that works togeher in order to detect a fire breakouts. But the systems itself consist of errors especially detecting smoke which sometimes could not lead to a potential fire breakouts instead causing a false alarm. Moreover, vision cameras are expensive to be installed and it takes a lot amount of money for maintenance alone. This causes many household does not equip with such devices making fire breakouts to be inevitable. In this research, the aim of this is to create a system that is cheap and could detect a potential fire before it could even happen by applying Fuzzy logic technique. By adding an Artificial Intelligence in a fire monitoring and warning systems, This could reduce error and predict the right event that could lead to a fire breakouts. With this, many household especially in Malaysia could have the safety to overcome this
- Open Access
- 20 November 2022
- Published by Universiti Malaysia Pahang Al-Sultan Abdullah Press (UMPSA Press) in MEKATRONIKA
- Vol. 4 (2) , 24-31
Virtual Driving Simulation for Pedal Error Study
This paper is about the development of a virtual driving simulation for the pedal error study among Malaysian drivers. The project is in collaboration with the Malaysian Institute of Road Safety (MIROS) and The New Car Assessment Program for Southeast Asia (ASEAN NCAP) research grant. Instead of conducting the naturalistic driving test, the virtual driving simulation will be used in the current driving simulator developed for this project. Therefore, the aim of this study is to develop the virtual driving simulation which contain some emergency braking situations, determine the foot placement on the pedal (using video observation) and to measure the total pressure on the pedals during the normal driving and emergency braking situation among Malaysian drivers. This study is focused on automatic transmission car by Malaysian drivers who aged around 20 to 50 years old that have minimum two years driving experience. A questionnaire was also given to participants, asking them about their personal information, their driving behavior, infrastructure, and safety, as well as pedal misapplication. The virtual driving simulator was equipped with some devices such as camera, pressure sensor, screen monitor, steering wheel and driver’s pedal. A study was completed successfully to determine the position of the Malaysian driver's foot on the brake pedal during emergency braking. It has been discovered that roughly 6.67% of participants in a driving research use both legs while driving and use their left foot to hit the brake pedal during emergency braking. The study also found that about 26.67% of participants feel dizzy while driving and around 96.67% of participants were surprised by the obstacles.
- 20 November 2022
- Published by Universiti Malaysia Pahang Al-Sultan Abdullah Press (UMPSA Press) in MEKATRONIKA
- Vol. 4 (2) , 24-31
Open AccessVirtual Driving Simulation for Pedal Error Study
This paper is about the development of a virtual driving simulation for the pedal error study among Malaysian drivers. The project is in collaboration with the Malaysian Institute of Road Safety (MIROS) and The New Car Assessment Program for Southeast Asia (ASEAN NCAP) research grant. Instead of conducting the naturalistic driving test, the virtual driving simulation will be used in the current driving simulator developed for this project. Therefore, the aim of this study is to develop the virtual driving simulation which contain some emergency braking situations, determine the foot placement on the pedal (using video observation) and to measure the total pressure on the pedals during the normal driving and emergency braking situation among Malaysian drivers. This study is focused on automatic transmission car by Malaysian drivers who aged around 20 to 50 years old that have minimum two years driving experience. A questionnaire was also given to participants, asking them about their personal information, their driving behavior, infrastructure, and safety, as well as pedal misapplication. The virtual driving simulator was equipped with some devices such as camera, pressure sensor, screen monitor, steering wheel and driver’s pedal. A study was completed successfully to determine the position of the Malaysian driver's foot on the brake pedal during emergency braking. It has been discovered that roughly 6.67% of participants in a driving research use both legs while driving and use their left foot to hit the brake pedal during emergency braking. The study also found that about 26.67% of participants feel dizzy while driving and around 96.67% of participants were surprised by the obstacles.
- Open Access
- 4 October 2022
- Published by Universiti Malaysia Pahang Al-Sultan Abdullah Press (UMPSA Press) in MEKATRONIKA
- Vol. 4 (2) , 6-15
Design A Precision Motion Control of an Upper Limb Robotic Arm
Trajectory tracking is utilized in medical rehabilitation programs at the early stage of rehabilitation in order to track the performance of the patient in performing the prescribed task. The robotic arm has been utilized to accomplish this due to it precision and provide repetitive motion. The goal of this study is to design and simulate a two-degree-of-freedom robotic arm that can effectively track a trajectory. As a result, this study discusses the modelling, simulation, and control of a Two Degree of Freedom (2-DOF) Robot Arm to attain that goal. First, the robot specifications are provided, as well as the forward and inverse kinematics of a 2-DOF robot arm. The dynamics of the 2-DOF robot arm were then defined using the Euler- Lagrange Equation to obtain motion equations. A PID controller was used to construct a control design for the robot's controller. MATLAB is used to record all the data, including the margin of error, overshoot, and peak settling time. The data is identified using the PI and PID controllers, in which the error is smaller than 7 and 1.5, respectively. The controller was then used to create a prototype model by using MATLAB Sim Mechanics. The data obtained indicates that a PID controller is the best fit for this rehabilitation robot.
- 4 October 2022
- Published by Universiti Malaysia Pahang Al-Sultan Abdullah Press (UMPSA Press) in MEKATRONIKA
- Vol. 4 (2) , 6-15
Open AccessDesign A Precision Motion Control of an Upper Limb Robotic Arm
Trajectory tracking is utilized in medical rehabilitation programs at the early stage of rehabilitation in order to track the performance of the patient in performing the prescribed task. The robotic arm has been utilized to accomplish this due to it precision and provide repetitive motion. The goal of this study is to design and simulate a two-degree-of-freedom robotic arm that can effectively track a trajectory. As a result, this study discusses the modelling, simulation, and control of a Two Degree of Freedom (2-DOF) Robot Arm to attain that goal. First, the robot specifications are provided, as well as the forward and inverse kinematics of a 2-DOF robot arm. The dynamics of the 2-DOF robot arm were then defined using the Euler- Lagrange Equation to obtain motion equations. A PID controller was used to construct a control design for the robot's controller. MATLAB is used to record all the data, including the margin of error, overshoot, and peak settling time. The data is identified using the PI and PID controllers, in which the error is smaller than 7 and 1.5, respectively. The controller was then used to create a prototype model by using MATLAB Sim Mechanics. The data obtained indicates that a PID controller is the best fit for this rehabilitation robot.
- Open Access
- 23 March 2022
- Published by Elsevier in ICT Express
- Vol. 8 (4) , 513-517
Human activity recognition based on wrist PPG via the ensemble method
- 23 March 2022
- Published by Elsevier in ICT Express
- Vol. 8 (4) , 513-517
Open AccessHuman activity recognition based on wrist PPG via the ensemble method