Mohd Afzan Othman
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
Mohd Afzan Othman has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Usman Ullah Sheikh
Universiti Teknologi Malaysia
3 shared publications - Fatima Aliyu Shugaba
Department of Computer Engineering, University of Maiduguri, Maiduguri, Nigeria
2 shared publications - Muhammad Habibullah Abdulfattah
Faculty of Electrical Engineering, Universiti Teknologi Malaysia, Johor Bahru, Malaysia
2 shared publications Nurulaqilla Khamis
2 shared publications- Abdul Mutalib Embong
Universiti Malaysia Terengganu (UMT), Malaysia
1 shared publication - Alhassan Haruna Umar
Department of Computer Science, Jigawa State Polytechnic Dutse Nigeria
1 shared publication
Latest Publications
- Open Access
- 7 April 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (5) , 207
Handwritten Arabic Text Recognition: A Review of Recent Trends and Future Direction
- 7 April 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (5) , 207
Open AccessHandwritten Arabic Text Recognition: A Review of Recent Trends and Future Direction
- Open Access
- 16 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 91834-91845
Assessing the Detection Capabilities of RGB and Infrared Models for Robust Occluded and Unoccluded Pedestrian Detection
Pedestrian detection is a critical component of autonomous vehicle systems, particularly under challenging conditions where visibility may be compromised due to occlusion or low-light. This study presents a comparative analysis of RGB (visible spectrum) and infrared (IR) modalities, each employed independently to detect pedestrians under various conditions. By evaluating single-modal models on both occluded and unoccluded pedestrians, we aim to provide insights into each modality’s strengths and limitations. Through extensive training, validation, and testing phases on the FLIR dataset, the RGB model achieved mean Average Precision (mAP@0.5) of 0.8711, and 0.8739 during training and testing, while the IR model recorded a higher training mAP@0.5 of 0.9020, and 0.8729 during testing. Notably, the IR model achieves higher mAP@0.5, indicating greater robustness in scenarios with relaxed bounding box precision requirements. These findings suggest that integrating RGB and IR modalities in a complementary manner could enhance detection reliability across diverse real-world conditions. This work provides a foundation for developing more resilient and accurate pedestrian detection systems in autonomous vehicles, capable of operating effectively under both occluded and unoccluded conditions.
- 16 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 91834-91845
Open AccessAssessing the Detection Capabilities of RGB and Infrared Models for Robust Occluded and Unoccluded Pedestrian Detection
Pedestrian detection is a critical component of autonomous vehicle systems, particularly under challenging conditions where visibility may be compromised due to occlusion or low-light. This study presents a comparative analysis of RGB (visible spectrum) and infrared (IR) modalities, each employed independently to detect pedestrians under various conditions. By evaluating single-modal models on both occluded and unoccluded pedestrians, we aim to provide insights into each modality’s strengths and limitations. Through extensive training, validation, and testing phases on the FLIR dataset, the RGB model achieved mean Average Precision (mAP@0.5) of 0.8711, and 0.8739 during training and testing, while the IR model recorded a higher training mAP@0.5 of 0.9020, and 0.8729 during testing. Notably, the IR model achieves higher mAP@0.5, indicating greater robustness in scenarios with relaxed bounding box precision requirements. These findings suggest that integrating RGB and IR modalities in a complementary manner could enhance detection reliability across diverse real-world conditions. This work provides a foundation for developing more resilient and accurate pedestrian detection systems in autonomous vehicles, capable of operating effectively under both occluded and unoccluded conditions.
- 24 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 21 (17) , 18353-18367
Dielectrics for Non-Contact ECG Bioelectrodes: A Review
Sensing of bioelectrical potentials using a non-contact method remains promising for the long-term recording of heart biopotential signals. Recording electrocardiogram (ECG) in non-contact mode incorporates dielectric materials into capacitive bioelectrodes. Dielectrics have a strong influence on non-contact bioelectrodes because the coupling capacitance relies primarily on the dielectric properties of the material. This review seeks to present an evaluation of relevant literature concerning various dielectrics that have been documented. It examines the extent of existing constraints in biosensing performance, biocompatibility, bioelectrode ergonomics, skin contact impedance and biosignal processing, and how they affect capacitive ECG measurement. It is also discussed that the performance of bioelectrodes is determined by materials' dielectric properties, making the choice of materials an essential factor in non-contact ECG recording applications. Finally, suggestions to enable the development of non-contact bioelectrodes with improved performance were highlighted.
- 24 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 21 (17) , 18353-18367
Dielectrics for Non-Contact ECG Bioelectrodes: A Review
Sensing of bioelectrical potentials using a non-contact method remains promising for the long-term recording of heart biopotential signals. Recording electrocardiogram (ECG) in non-contact mode incorporates dielectric materials into capacitive bioelectrodes. Dielectrics have a strong influence on non-contact bioelectrodes because the coupling capacitance relies primarily on the dielectric properties of the material. This review seeks to present an evaluation of relevant literature concerning various dielectrics that have been documented. It examines the extent of existing constraints in biosensing performance, biocompatibility, bioelectrode ergonomics, skin contact impedance and biosignal processing, and how they affect capacitive ECG measurement. It is also discussed that the performance of bioelectrodes is determined by materials' dielectric properties, making the choice of materials an essential factor in non-contact ECG recording applications. Finally, suggestions to enable the development of non-contact bioelectrodes with improved performance were highlighted.
- 10 October 2020
- Published by Springer Nature in Neural Computing and Applications
- Vol. 33 (11) , 6233-6246
Mental imagery classification using one-dimensional convolutional neural network for target selection in single-channel BCI-controlled mobile robot
- 10 October 2020
- Published by Springer Nature in Neural Computing and Applications
- Vol. 33 (11) , 6233-6246
Mental imagery classification using one-dimensional convolutional neural network for target selection in single-channel BCI-controlled mobile robot
- Open Access
- 1 September 2019
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 15 (3) , 1223-1231
Portable cardiac self-stress test device development based on metabolic equivalent (MET)
Cardiovascular disease (CVD) is the main cause of death worldwide and the type varies depending on symptom and causes. There are several procedures to determine the type of CVD such as blood test, holter monitoring, cardiac stress test and many more. Cardiac stress test is a procedure to exert pressure on the heart by doing physical activities to determine heart functionality and abnormal heart activity. It is done to gather information on heart condition supported by evidence in the form of electrocardiogram (ECG) signal. However, patients with heart problem will have to take turns to run the test due to limited access to the equipment especially in government hospital. Therefore, this paper proposed the development of cardiac self-stress test device to provide a pre-diagnosis result based on metabolic equivalent (MET) value. The device named “i-STress device” is a stand-alone device integrating the use of software application and hardware. The software was built by using MIT App Inventor 2 and the hardware built based on Arduino 101 and Sparkfun Heart Monitor AD 8232 and the test result saved in SD card. The device will be useful to sort out patient’s case priority as well as providing pre-diagnosis result before conducting a real cardiac stress test.
- 1 September 2019
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 15 (3) , 1223-1231
Open AccessPortable cardiac self-stress test device development based on metabolic equivalent (MET)
Cardiovascular disease (CVD) is the main cause of death worldwide and the type varies depending on symptom and causes. There are several procedures to determine the type of CVD such as blood test, holter monitoring, cardiac stress test and many more. Cardiac stress test is a procedure to exert pressure on the heart by doing physical activities to determine heart functionality and abnormal heart activity. It is done to gather information on heart condition supported by evidence in the form of electrocardiogram (ECG) signal. However, patients with heart problem will have to take turns to run the test due to limited access to the equipment especially in government hospital. Therefore, this paper proposed the development of cardiac self-stress test device to provide a pre-diagnosis result based on metabolic equivalent (MET) value. The device named “i-STress device” is a stand-alone device integrating the use of software application and hardware. The software was built by using MIT App Inventor 2 and the hardware built based on Arduino 101 and Sparkfun Heart Monitor AD 8232 and the test result saved in SD card. The device will be useful to sort out patient’s case priority as well as providing pre-diagnosis result before conducting a real cardiac stress test.
- 1 January 2015
- Published by Springer Nature
- p. 19-22
Human Heart Oscillatory Behavior during Atrial Fibrillation Based on Second Order System
- 1 January 2015
- Published by Springer Nature
- p. 19-22
Human Heart Oscillatory Behavior during Atrial Fibrillation Based on Second Order System
- Open Access
- 1 January 2014
- Published by Natural Sciences Publishing in Applied Mathematics & Information Sciences
- Vol. 8 (1) , 229-233
Broadcasting Communication in High Degree Modified Chordal Rings Networks
- 1 January 2014
- Published by Natural Sciences Publishing in Applied Mathematics & Information Sciences
- Vol. 8 (1) , 229-233
Open AccessBroadcasting Communication in High Degree Modified Chordal Rings Networks