Amirul Jamaludin

Mr. Amirul Jamaludin

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
6 March 2025 in IEEE Access
Verified
Journal Article
Open access
AJAmirul Jamaludin
Amirul Jamaludin
SRSyaimaa’ Solehah Mohd Radzi
Syaimaa’ Solehah Mohd Radzi
NYNorhidayah Mohamad Yatim
Norhidayah Mohamad Yatim
NMNazlee Azmeer Masuan
Nazlee Azmeer Masuan
NANorsharimie Mat Adam
Norsharimie Mat Adam
PSPazli Mohd Sulong
Pazli Mohd Sulong
Simultaneous Localization and Mapping (SLAM) algorithms based on visual and light detection and ranging (LiDAR) technologies have shown remarkable capabilities in applications for robot navigation, particularly for mapping and navigating unfamiliar environments. However, the performance of visual and LiDAR based SLAM in challenging settings, such as uneven terrains with complex environmental conditions, remains insufficiently explored. To address this challenge, the feasibility of two visual-based SLAM algorithms, i.e., real-time appearance-based mapping (RTAB-Map) and neuro-inspired 4DoF (degree of freedom) SLAM (NeuroSLAM), and two LiDAR-based SLAM algorithms, i.e., LiDAR inertial odometry via smoothing and mapping (LIO-SAM) and fast LiDAR-inertial odometry (FAST-LIO), were investigated. The algorithms were tested in uneven terrain within a palm oil plantation under varying illuminance conditions (morning and noon) and across trajectories of different lengths, corresponding to map sizes of 400 m (small), 600 m (medium), 1000 m (large), and 1200 m (extra-large). Performance metrics, including distance error and loop closure detection, were used to assess the impact of trajectory length and illuminance. Additionally, the consistency and stability of map estimation were analyzed. Ground-truth data was obtained using the GeoMax Zoom 10 Total Station to ensure high-precision reference measurement. Results revealed that LIO-SAM consistently achieved the lowest distance errors across all map sizes during morning condition of 0.17 m, 1.08 m, 0.52 m, and 0.71 m for small, medium, large, and extra-large maps, respectively. During noon, LIO-SAM also demonstrated superior performance for small, medium, and large map sizes, with distance error values of 0.11 m, 0.25 m, and 0.38 m, respectively. Furthermore, LIO-SAM recorded the highest successful loop closure rates by achieving 75% in the morning and 100% at noon. Overall, the findings highlights the superior performance of LiDAR-based SLAM algorithms over visual-based SLAM approaches in complex, uneven terrains under varying environmental conditions.

27 February 2023 in Micromachines
Verified
Journal Article
Open access
PDF file
AJAmirul Jamaludin
Amirul Jamaludin
NYNorhidayah Mohamad Yatim
Norhidayah Mohamad Yatim
ZNZarina Mohd Noh
Zarina Mohd Noh
NBNorlida Buniyamin
Norlida Buniyamin
Commonly, simultaneous localization and mapping (SLAM) algorithm is developed using high-end sensors. Alternatively, some researchers use low-end sensors due to the lower cost of the robot. However, the low-end sensor produces noisy sensor measurements that can affect the SLAM algorithm, which is prone to error. Therefore, in this paper, a SLAM algorithm, which is a Rao-Blackwellized particle filter (RBPF) integrated with artificial neural networks (ANN) sensor model, is introduced to improve the measurement accuracy of a low-end laser distance sensor (LDS) and subsequently improve the performance of SLAM. The RBPF integrated with the ANN sensor model is experimented with by using the Turtlebot3 mobile robot in simulation and real-world experiments. The experiment is validated by comparing the occupancy grid maps estimated by RBPF integrated with the ANN sensor model and RBPF without ANN. Both the results in simulation and real-world experiments show that the SLAM performance of RBPF integrated with the ANN sensor model is better than the RBPF without ANN. In the real-world experiment results, the performance of the occupied cells integrated with the ANN sensor model is increased by 107.59%. In conclusion, the SLAM algorithm integrated with the ANN sensor model is able to improve the accuracy of the map estimate for mobile robots using low-end LDS sensors.

1 October 2022 in Indonesian Journal of Electrical Engineering and Computer Science
Verified
Journal Article
Open access
PDF file
NHNur Farahin Bt Abdul Halim
Nur Farahin Bt Abdul Halim
RRRidza Azri Bin Ramlee
Ridza Azri Bin Ramlee
MMMohd Zaki Bin Mas’uD
Mohd Zaki Bin Mas’uD
AJAmirul Jamaludin
Amirul Jamaludin
Cholesterol is a type of lipid found in the human body and is susceptible to abnormalities. It can be detected via lipid profiling through blood sampling. In addition, cholesterol can be detected through the presence of a "sodium ring" in the eye iris called the corneal arcus (CA), presenting a new preliminary detection method that is less invasive. Therefore, this paper proposed a non-invasive method in detecting cholesterol based on convolutional neural network (CNN) model representation using 300 normal and 300 abnormal iris images from UBIRIS and medical web images. In this work, contrast-limited adaptive histogram (CLAHE) and unsharp masking process was applied first on CA images to enhance the quality of CA images. To detect the CA images, the dataset was trained and tested using three pre-trained CNN architectures; one is created from scratch, another are Resnet-50 and VGG-19 architectures that were fine-tuned to the CA images. The best result was exhibited by proposed pre-trained CNN model created from scratch with 10-fold cross-validation that produced high average detection accuracy at 98.81%. Thus, deeper network implementation is recommended in the future to further improve CA localization for optometrists used in their daily clinical tasks in detecting cholesterol.