Mohd Hairi Mohd Zaman

Dr. Mohd Hairi Mohd Zaman

Universiti Kebangsaan Malaysia
orcid

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 September 2022 in Sensors
Verified
Journal Article
Open access
PDF file
EEElizar Elizar
Elizar Elizar
MZMohd Asyraf Zulkifley
Mohd Asyraf Zulkifley
RMRusdha Muharar
Rusdha Muharar
MZMohd Hairi Mohd Zaman
Mohd Hairi Mohd Zaman
SMSeri Mastura Mustaza
Seri Mastura Mustaza
In general, most of the existing convolutional neural network (CNN)-based deep-learning models suffer from spatial-information loss and inadequate feature-representation issues. This is due to their inability to capture multiscale-context information and the exclusion of semantic information throughout the pooling operations. In the early layers of a CNN, the network encodes simple semantic representations, such as edges and corners, while, in the latter part of the CNN, the network encodes more complex semantic features, such as complex geometric shapes. Theoretically, it is better for a CNN to extract features from different levels of semantic representation because tasks such as classification and segmentation work better when both simple and complex feature maps are utilized. Hence, it is also crucial to embed multiscale capability throughout the network so that the various scales of the features can be optimally captured to represent the intended task. Multiscale representation enables the network to fuse low-level and high-level features from a restricted receptive field to enhance the deep-model performance. The main novelty of this review is the comprehensive novel taxonomy of multiscale-deep-learning methods, which includes details of several architectures and their strengths that have been implemented in the existing works. Predominantly, multiscale approaches in deep-learning networks can be classed into two categories: multiscale feature learning and multiscale feature fusion. Multiscale feature learning refers to the method of deriving feature maps by examining kernels over several sizes to collect a larger range of relevant features and predict the input images’ spatial mapping. Multiscale feature fusion uses features with different resolutions to find patterns over short and long distances, without a deep network. Additionally, several examples of the techniques are also discussed according to their applications in satellite imagery, medical imaging, agriculture, and industrial and manufacturing systems.

28 October 2024 in IEEE Access
Verified
Journal Article
Open access
CYChen Yuanwei
Chen Yuanwei
MZMohd Hairi Mohd Zaman
Mohd Hairi Mohd Zaman
MIMohd Faisal Ibrahim
Mohd Faisal Ibrahim
With advancements in technology, deep learning has become increasingly widespread, particularly in fields like robot control, computer vision, and autonomous driving. In these areas, obtaining pose information of target objects, especially their spatial location, is crucial for robot grasping tasks. Although many effective implementations of six degrees of freedom (6D) pose estimation methods based on RGB images exist, challenges in this domain persist. This paper provides a comprehensive review of traditional 6D pose estimation methods, deep learning approaches, and point cloud techniques by analyzing their advantages and disadvantages. It also discusses evaluation metrics and performance on common datasets for 6D pose estimation. Furthermore, the paper offers a theoretical foundation for robot grasping and explores future directions for 6D pose estimation. Finally, it summarizes the current state and development trends of 6D pose estimation, aiming to help researchers better understand and learn about this field.

8 August 2020 in International Journal of Evaluation and Research in Education (IJERE)
Verified
Journal Article
Open access
PDF file
MZMohd Hairi Mohd Zaman
Mohd Hairi Mohd Zaman
MMMohd Hadri Hafiz Mokhtar
Mohd Hadri Hafiz Mokhtar
MIMohd Faisal Ibrahim
Mohd Faisal Ibrahim
AHAqilah Baseri Huddin
Aqilah Baseri Huddin
GBGan Kok Beng
Gan Kok Beng
Engineering students at an undergraduate level typically learn the design aspect and concept through lectures and practical sessions using computeraided software. However, the current computer-aided design and engineering (CAD/CAE) course did not expose the students to apply and relate the latest advanced technologies to solve global issues, for instance as listed in the United Nations Sustainable Development Goals (UN SDG). Therefore, an improved CAD/CAE course taken by the students of the Electrical and Electronic Engineering Programme in Universiti Kebangsaan Malaysia integrates 3D printing and conduct their project based on UN SDG themes. A total of 22 projects was produced, which involves both mechanical and electrical design with some of the physical models were 3D printed. Thus, students able to strengthen their understanding of the design concept through the integration of 3D printing and simultaneously aware of the current global issues.

8 August 2020 in International Journal of Evaluation and Research in Education (IJERE)
Verified
Journal Article
Open access
PDF file
MIMohd Faisal Ibrahim
Mohd Faisal Ibrahim
AHAqilah Baseri Huddin
Aqilah Baseri Huddin
FHFazida Hanim Hashim
Fazida Hanim Hashim
MAMardina Abdullah
Mardina Abdullah
ARAshrani Aizzuddin Abd Rahni
Ashrani Aizzuddin Abd Rahni
MZMohd Hairi Mohd Zaman
Mohd Hairi Mohd Zaman
This study examined the educational effects in strengthening programming skills among university’s undergraduate engineering students via integration of a robotics project and an experiential learning approach. In this study, a robotics project was conducted to close the gap of students’ difficulty in relating the theoretical concepts of programming and real-world problems. Hence, an experiential learning approach using the Kolb model was proposed to investigate the problem. In this project, students were split into groups whereby they were asked to develop codes for controlling the navigation of a wheeled mobile robot. They were responsible for managing their group’s activities, conducting laboratory tests, producing technical reports and preparing a video presentation. The statistical analysis performed on the students’ summative assessments of a programming course revealed a remarkable improvement in their problem-solving skills and ability to provide programming solutions to a real-world problem.

28 February 2021 in International Journal of Advanced Technology and Engineering Exploration
Verified
Journal Article
Closed access
NSNur Aliah Zakirah Sulaiman
Nur Aliah Zakirah Sulaiman
AIAhmad Asrul Ibrahim
Ahmad Asrul Ibrahim
MZMohd Hairi Mohd Zaman
Mohd Hairi Mohd Zaman

14 July 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
MZMohd Hairi Mohd Zaman
Mohd Hairi Mohd Zaman
MZMohd Hairi Mohd Zaman
Mohd Hairi Mohd Zaman
FZFeng Zhou
Feng Zhou
As the demand for high-precision and high-efficiency machining increases in modern industrial manufacturing, five-axis CNC systems have become the primary solution for complex surface processing. This study presents a dual NURBS curve interpolation algorithm specifically designed for five-axis synchronized motion. Unlike traditional linear and circular interpolation methods, the dual NURBS interpolation utilizes a master-slave curve strategy to achieve synchronous control of tool position and orientation. In the proposed method, the master curve determines the tool path, while the slave curve adjusts the tool’s posture in real-time. Simulation experiments were performed on three representative surface models: Spiral Surface, Blade Surface, and Freeform Surface. The results indicate that the maximum chord error of the dual NURBS method on the Spiral Surface is only 0.0006 mm, with an average error of 0.0004 mm, significantly lower than traditional OC methods (0.01876 mm) and equal chord length interpolation (0.01532 mm). Furthermore, error analysis demonstrated that the dual NURBS method reduced the chord error over 68.6% compared to conventional methods and achieved more than a 16% improvement in processing efficiency. In addition, the dual NURBS algorithm showed smooth velocity planning, with speed fluctuation controlled within 10 mm/s, significantly better than traditional OC and equal chord length methods. These improvements not only enhance path smoothness but also significantly reduce tool vibration and surface defects during machining. The findings verify the effectiveness of the dual NURBS interpolation algorithm in improving machining accuracy and efficiency for complex five-axis CNC operations, offering a robust solution for high-precision surface processing.