Hazry Desa
Thumbnail Image
Preferred name
Hazry Desa
Official Name
Desa, Hazry
Alternative Name
Desa, H.
Hazry, Desa
Desa, Hazy
Hazry, D.
Main Affiliation
Scopus Author ID
16642497100

Research Output

Filters

14
14
Reset filters

Settings
Now showing 1 - 10 of 14
  • Publication
    Aerial image semantic segmentation based on 3D fits a small dataset of 1D
    ( 2023-12-01)
    Ahmed S.A.
    ;
    Hazry Desa
    ;
    Hussain A.S.T.
    Time restrictions and lack of precision demand that the initial technique be abandoned. Even though the remaining datasets had fewer identified classes than initially planned for the study, the labels were more accurate. Because of the need for additional data, a single network cannot categorize all the essential elements in a picture, including bodies of water, roads, trees, buildings, and crops. However, the final network gains some invariance in detecting these classes with environmental changes due to the different geographic positions of roads and buildings discovered in the final datasets, which could be valuable in future navigation research. At the moment, binary classifications of a single class are the only datasets that can be used for the semantic segmentation of aerial images. Even though some pictures have more than one classification, images of roads and buildings were only found in a significant number of samples. Then, the building datasets were pooled to produce a larger dataset and for the constructed models to gain some invariance on image location. Because of the massive disparity in sample size, road datasets needed to be integrated.
  • Publication
    Experimental Analysis of Flight Altitude for Enhanced Agricultural Drone Spraying Performance
    ( 2023-01-01)
    Hazry Desa
    ;
    Muhammad Azizi Azizan
    ;
    Nurfadzillah Ishak
    ;
    Hang T.X.
    Effective rice field management and the proper application of agricultural chemicals are crucial for ensuring agricultural product quality. These chemicals control weeds and protect against insect pests, which can harm crop yields and quality. This research explores the relationship between the altitude at which agricultural drones spray chemicals, spray uniformity, and chemical dispersion. The study assesses drone operations at heights of 1m, 1.5m, and 2m above hollow cone nozzles in 2.8m/s wind conditions. It aims to evaluate droplet uniformity and dispersion on water-sensitive paper placed on paddy plants, analyzed with ImageJ software. Results show that at 1.5m height, there's a significantly higher average droplet density, with 162.7 deposits/cm² in the upper region and 161.8 deposits/cm² in the lower region. Additionally, coverage is notably increased, at 55.21% for the upper region and 51.4% for the lower region. This research highlights the importance of optimal drone altitude for efficient chemical application in rice fields, improving crop protection and yield.
  • Publication
    Classification of semantic segmentation using fully convolutional networks based unmanned aerial vehicle application
    ( 2023-06-01)
    Ahmed S.A.
    ;
    Hazry Desa
    ;
    Hussain A.S.T.
    The classification of semantic segmentation-based unmanned aerial vehicle (UAV) application based on the datasets used in this work and the necessary data preprocessing steps for the optimization and implementation of the models are also involved. The optimization of the various models was done using the evaluation metrics and loss functions because deep neural networks (DNNs) are just about writing a cost function and its subsequent optimization. convolutional neural network (CNN) is a common type of artificial neural network (ANN) that has found application in numerous tasks, such as image and video recognition, image classification, recommender systems, financial time series, medical image analysis, and natural language processing. CNN is developed to automatically and adaptively learn spatial feature hierarchies via backpropagation using numerous building blocks, such as pooling, convolution, and fully connected layers. The result of identification was excellent. The image segmentation was detected and comprehend the actual components of an image down to the pixel level. The result created an entire image segmentation masks with instances using the new label editor in the label box.
  • Publication
    Object Detection and Instance Segmentation with YOLOV8: Progress and Limitations
    ( 2024-01-01)
    Lee L.J.
    ;
    Hazry Desa
    ;
    Muhammad Azizi Azizan
    ;
    Hussain A.S.T.
    ;
    Tanveer M.H.
    This research employs object detection and instance segmentation algorithms to distinguish between objects and backgrounds and to interpret the detected objects. The YOLOV8 (You Only Look Once) framework and COCO dataset are utilized for detecting and interpreting the objects. Additionally, the accuracy of detection, segmentation, and interpretation is tested by placing objects at various distances from the camera. The algorithm's performance was evaluated, and the results were documented. In the experiments, a sample of 11 objects was tested, and 8 of them were successfully detected at distances of 45cm, 75cm, 105cm, and 135cm. For instance, segmentation, segmentation maps appeared clean when detecting a single object but faced challenges when multiple objects overlapped.
  • Publication
    Investigating the Engineering Interventions in the Conservation of Malaysia Heritage Structures: A Review on Preserving Historical Edifices Through Advanced Civil Engineering Techniques
    ( 2024-01-01)
    Muhammad Azizi Azizan
    ;
    Nurfadzillah Ishak
    ;
    Hazry Desa
    This review delves into the realm of Malaysia's heritage conservation, spotlighting the transformative impact of advanced civil engineering techniques. Through the integration of Fiber-Reinforced Polymers (FRP) and nanotechnology, historical edifices are fortified, seamlessly blending modern engineering with architectural elegance. Non-destructive testing (NDT) methods, including ground-penetrating radar and Finite Element Analysis (FEA),empower conservationists with deep insights into structural intricacies, guiding targeted interventions. In the digital sphere, 3D laser scanning captures intricate details, while Virtual Reality (VR) simulations facilitate immersive exploration and informed decision-making. Beyond preservation, these technologies foster public engagement, ensuring a collective understanding of Malaysia's cultural heritage. This harmonious fusion of tradition and cutting edgeengine ering ensures the enduring legacy of Malaysia's architectural treasures.
  • Publication
    Experimenting with Variable Arm Quadrotors: Realizing Dynamic Configurations for Enhanced Flight Performance
    ( 2024-01-01)
    Hazry Desa
    ;
    Azizi M.
    This paper introduces two innovative concepts for variable arms designed for a quadrotor, enabling precise control of its movement through manipulation of the bending moment via varying arm lengths. The primary objective of this research is to develop and identify the most suitable variable arm configuration that facilitates smooth and stable quadrotor movement. The study delves into two concept designs that are well-suited for the quadrotor application. By employing a suitable variable arm, the quadrotor’s maneuverability can be effectively regulated based on the bending moment adjustments made possible by the variable arm. Ultimately, the paper presents the design and performance testing of two types of variable arms. The obtained results confirm that the variable arm of the electric actuator with linear guide-Type 2 exhibits smooth and stable movement.
  • Publication
    Implementation of deep neural networks learning on unmanned aerial vehicle based remote-sensing
    ( 2024-03-01)
    Ahmed S.A.
    ;
    Hazry Desa
    ;
    Hussain A.S.T.
    ;
    Taha T.A.
    Due to efficient and adaptable data collecting, unmanned aerial vehicle (UAV) has been a popular topic in computer vision (CV) and remote sensing (RS) in recent years. Inspiring by the recent success of deep learning (DL), several enhanced object identification and tracking methods have been broadly applied to a variety of UAV-related applications, including environmental monitoring, precision agriculture, and traffic management. In this research, we present efficient neural network (ENet), a unique deep neural network architecture designed exclusively for jobs demanding low latency operation. ENet is up to quicker, takes fewer floating-point operations per second (FLOPs), has fewer parameters, and offers accuracy comparable to or superior to that of previous models. We have tested it on the street and cityscapes reports on comparisons with current state-of-the-art approaches and the tradeoffs between a network's processing speed and accuracy. We give measurements of the proposed architecture's performance on embedded devices and offer software enhancements that might make ENet even quicker.
  • Publication
    Roof Re-measurement in Building Works Using Un-manned Aerial Vehicle (UAV) Application System
    ( 2021-01-01)
    Romeli N.
    ;
    Hazry Desa
    ;
    Muhammad Azizi Azizan
    ;
    Halil F.M.
    The diversities of contractual terms in construction projects leads to a diversified contractual interpretation in one project. In the long term, the contractual discrepancies would result the project suffered from the dispute. Given the circumstances of measurement contracts, which refers to re – measurement or measure and value contracts are normally used when the quantity of the project can’t be describe in the exact amount. In the construction projects that involving complicated design, the difficulty may rose from the initial stage of architectural features. Often, the re-measuring’s fatality occurred when the elements finishes in the building has been over claimed by the contractor. Even so, the uncertainties of client’s instruction have always contributing to the excessive utilization of the fancy finishes in the construction projects. As a result, a dispute ascended due to payments, claim and work done issue. Site re-measurement can be done. However, in regard to almost completed building construction, the site re-measurement may get difficult as human can’t reach the building that has been constructed. Thus, issues on safety and accuracy may followed. Advance technology has provided the ability to implement the building survey without risking of manpower which is using the application of Unmanned Aerial Vehicle (UAV). Therefore, the research is carried out to identify the attributes of UAV application in roof re – measurement in building works and investigate the implementation of the UAV application. Using the literature search, the attributes of UAV application has been identified and the prototype case study has been selected to investigate the process of UAV application for roof site re-measurement. The results indicated that the utilization of UAV application is feasible as the tools for re – measurement of building works as the issues on the safety and accuracy are safeguarded.
  • Publication
    Development of Variable Arm to Control the Manoeuvrability of Quadrotor
    ( 2024-01-01)
    Hong L.Y.
    ;
    Hazry Desa
    ;
    Muhammad Azizi Azizan
    ;
    Tanveer M.H.
    This paper introduces the concept of a variable arm for a quadrotor which is able to perform the manoeuvrability of the quadrotor by changing the arm length’s. The variation in arm’s length affects the bending moment generated by the thrust force, resulting in the tilting and movement of the quadrotor. The primary goal of this project is to develop a quadrotor with an adjustable arm length to control its manoeuvrability effectively, thus minimizing the need for additional thrust force during flight control. The study focuses on designing a quadrotor with the capability to extend or retract its arms. The proposed concept relies on altering the bending moment through the variable arm to control the quadrotor's manoeuvrability. A quadrotor equipped with a variable arm was successfully designed and tested, with its performance evaluated in executing agile maneuvers. The experiment demonstrated that the variable arm induced body rotation in the quadrotor, effectively regulating its manoeuvrability and the study validates the potential of the variable arm approach for controlling quadrotor movement.
  • Publication
    Review on Patch Antennas for Unmanned Aerial Vehicle Application
    ( 2023-11-01)
    Nur Hidayah Ramli
    ;
    Seng L.Y.
    ;
    Liyana Zahid
    ;
    Hazry Desa
    The wide-ranging Unmanned Aerial Vehicle (UAV) applications make them one of the Internet of Things promising technologies. The vast potential of monitoring and surveillance for public safety threats using drones is a current issue for researchers. Antennas play an important part in UAV to create reliable communication links. There are different types of antennas that can be used for UAV application depending on antennas size, efficiency, gain, angle of radiation pattern, polarization, etc. This paper mainly focuses on patch antennas for UAV applications. In general, there are two types of patch antenna described which are single patch antenna and array antenna. The review of patch antennas can be a useful guideline to choose or design antenna for UAV applications in the future.