Shazmin Aniza Abdul Shukor
Thumbnail Image
Preferred name
Shazmin Aniza Abdul Shukor
Official Name
Shazmin Aniza, Abdul Shukor
Alternative Name
Shukor, S. A.
Shukor, S. A.A
S. A.A, Shukor
Shukor, Shazmin Aniza Abdul
Abdul Shukor, Shazmin Aniza
Main Affiliation
Pusat Kecemerlangan Kecerdikan Robotik (COFRI)
Scopus Author ID
57214325384
Researcher ID
GSD-2143-2022

Research Output

Filters

25
Reset filters

Settings
Now showing 1 - 10 of 25
  • Publication
    Validation of Electrical Noise of a DC Motor through Controlled Varistor Cracking: An Experimental Study
    ( 2023-01-01)
    Mohd Rudzuan Mohd Nor
    ;
    Zainudin G.
    ;
    Wan Mohd Nooriman Wan Yahya
    ;
    Sofi Y.
    ;
    Nordiana S.
    ;
    Norlaili S.
    ;
    Shazmin Aniza Abdul Shukor
    ;
    Zuradzman Mohamad Razlan
    The varistor is an electronic component that protects the DC motor's circuitry from electrical noise or transients that can cause damage. It works as a voltage-dependent resistor that can change its resistance according to the applied voltage. Once the voltage surpasses a specific threshold, the varistor conducts and directs the excess voltage away from the motor's circuitry. In small DC motor manufacturing, ring varistors are vital for reducing electrical noise, minimizing spark-induced damage to the commutator and brush, and extending the motor's lifespan. Additionally, they prevent damage to electronic parts in the customer's mechanism set. The objective of this study is to investigate the impact of varistor cracks or chips that may occur during the soldering process of varistors to the commutator. To confirm the occurrence of cracks or chips, intentional damage will be inflicted on the varistors. The study aims to determine how the presence of cracked or chipped varistors affects the electrical noise produced by a DC motor during its operation. The resulting spark was observed through an oscilloscope, and it was found that the effect could be substantial, up to 5 to 10 times the rated voltage supplied to the motor. In the next phase of this study, further tests will be conducted on motors without varistors to provide a comparison.
  • Publication
    ORIENTATION-BASED PAIRWISE COARSE REGISTRATION with MARKERLESS TERRESTRIAL LASER SCANS
    ( 2019-10-01)
    Mohd Isa S.N.
    ;
    Shazmin Aniza Abdul Shukor
    ;
    Rahim N.A.
    ;
    Maarof I.
    ;
    Yahya Z.R.
    ;
    Zakaria A.
    ;
    Abdullah A.H.
    ;
    Wong R.
    In this paper, pairwise coarse registration is presented using real world point cloud data obtained by terrestrial laser scanner and without information on reference marker on the scene. The challenge in the data is because of multi-scanning which caused large data size in millions of points due to limited range about the scene generated from side view. Furthermore, the data have a low percentage of overlapping between two scans, and the point cloud data were acquired from structures with geometrical symmetry which leads to minimal transformation during registration process. To process the data, 3D Harris keypoint is used and coarse registration is done by Iterative Closest Point (ICP). Different sampling methods were applied in order to evaluate processing time for further analysis on different voxel grid size. Then, Root Means Squared Error (RMSE) is used to determine the accuracy of the approach and to study its relation to relative orientation of scan by pairwise registration. The results show that the grid average downsampling method gives shorter processing time with reasonable RMSE in finding the exact scan pair. It can also be seen that grid step size is having an inverse relationship with downsampling points. This setting is used to test on smaller overlapping data set of other heritage building. Evaluation on relative orientation is studied from transformation parameter for both data set, where Data set I, which higher overlapping data gives better accuracy which may be due to the small distance between the two point clouds compared to Data set II.
  • Publication
    Modelling small artefact for preservation – a case study of Perlis heritage
    (IOP Publishing, 2023)
    L Gopal
    ;
    Shazmin Aniza Abdul Shukor
    Heritage preservation is essential for preserving historical sites and cultural artefact for future generations. However, they are prone to damages and destructions due to weather conditions and other factors. 3D models and reconstructions can aid in the conservation of historical sites and artefact. LiDAR (light detection and ranging) technology can be utilized to obtain accurate 3D representation of object or area of interest. This project aims to preserve one of the historical artefact in Perlis, Malaysia which is known as ‘Batu Nisan Acheh’ or the Acheh Gravestone by using 3D model and reconstruction. iPhone 13 Pro Max LiDAR scanner is used to collect the raw dataset of the artefact with Scaniverse application. MATLAB is employed for data processing which includes data filtering, noise reduction, downsampling and 3D surface reconstruction. In addition, a GUI application is also developed in enabling users to upload their desired point cloud files and produce its 3D model for future usage. Results show that the accuracy, effectiveness, and usability of heritage preservation initiatives are improved by combining iPhone 13 Pro Max LiDAR scanning with MATLAB processing, which is useful for virtual displays, restoration, and future study.
  • Publication
    Detection of indoor building lighting fixtures in point cloud data using SDBSCAN
    (Iran University of Science and Technology, 2025-06)
    Humairah Mansor
    ;
    Shazmin Aniza Abdul Shukor
    ;
    Nurul Syahirah Khalid
    ;
    Razak Wong Chen Keng
    Building fixtures like lighting are very important to be modelled, especially when a higher level of modelling details is required for planning indoor renovation. LIDAR is often used to capture these details due to its capability to produce dense information. However, this led to the high amount of data that needs to be processed and requires a specific method, especially to detect lighting fixtures. This work proposed a method named Size Density-Based Spatial Clustering of Applications with Noise (SDBSCAN) to detect the lighting fixtures by calculating the size of the clusters and classifying them by extracting the clusters that belong to lighting fixtures. It works based on Density-Based Spatial Clustering of Applications with Noise (DBSCAN), where geometrical features like size are incorporated to detect and classify these lighting fixtures. The final results of the detected lighting fixtures to the raw point cloud data are validated by using F1-score and IoU to determine the accuracy of the predicted object classification and the positions of the detected fixtures. The results show that the proposed method has successfully detected the lighting fixtures with scores of over 0.9. It is expected that the developed algorithm can be used to detect and classify fixtures from any 3D point cloud data representing buildings.
  • Publication
    Surface Reconstruction from Unstructured Point Cloud Data for Building Digital Twin
    ( 2023-01-01)
    Ismail F.A.
    ;
    Shazmin Aniza Abdul Shukor
    ;
    Norasmadi Abdul Rahim
    ;
    Wong R.
    This study highlights on the methods used for surface reconstruction from unstructured point cloud data, characterized by simplicity, robustness and broad applicability from 3D point cloud data. The input data consists of unstructured 3D point cloud data representing a building. The reconstruction methods tested here are Poisson Reconstruction Algorithm, Ball Pivoting Algorithm, Alpha Shape Algorithm and 3D surface refinement, employing mesh refinement through Laplacian smoothing and Simple Smoothing techniques. Analysis on the algorithm parameters and their influence on reconstruction quality, as well as their impact on computational time are discussed. The findings offer valuable insights into parameter behavior and its effects on computational efficiency and level of detail in the reconstruction process, contributing to enhanced 3D modeling and digital twin for buildings.
      1
  • Publication
    Improved mobile robot based gas distribution mapping through propagated distance transform for structured indoor environment
    ( 2020-05-18)
    Visvanathan R.
    ;
    Kamarulzaman Kamarudin
    ;
    Syed Muhammad Mamduh Syed Zakaria
    ;
    Toyoura M.
    ;
    Ali Yeon A.S.
    ;
    Ammar Zakaria
    ;
    Latifah Munirah Kamarudin
    ;
    Mao X.
    ;
    Shazmin Aniza Abdul Shukor
    Mobile robot carrying gas sensors have been widely used in mobile olfaction applications. One of the challenging tasks in this research field is Gas Distribution Mapping (GDM). GDM is a representation of how volatile organic compound is spatially dispersed within an environment. This paper addresses the effect of obstacles towards GDM for indoor environment. This work proposes a solution by improvising the Kernel DM + V technique using propagated distance transform (DT) as the weighing function. Since DT computations are CPU heavy, parallel computing, using Compute Unified Device Architecture (CUDA) available in Graphics Processing Unit (GPU), is used to accelerate the DT computation. The proposed solution is compared with the Kernel DM + V algorithm, presenting that the proposed method drastically improves the quality of GDM under various kernel sizes. The study is also further extended towards the effect of obstacles on gas source localization task. The outcome of this work proves that the proposed method shows better accuracy for GDM estimation and gas source localization if obstacle information is considered.
      1  30
  • Publication
    IoT-based Carbon Monoxide (CO) Real-Time Warning System Application in Vehicles
    ( 2021-12-01)
    Kamarudin A.A.A.
    ;
    Nurul Syahirah Khalid
    ;
    Ismail Ishaq Ibrahim
    ;
    Muhammad Aizat Abu Bakar
    ;
    Mahadi M.Z.
    ;
    Shazmin Aniza Abdul Shukor
    ;
    Sukhairi Sudin
    ;
    Mohd Zamri Hasan
    ;
    Humairah Mansor
    The project is about develop a system and application for detect the presence of Carbon Monoxide(CO) in car, since recently there are many cases of drowning while sleeping in car due to inhaling CO. The build system are able to detect the presence of CO and provide warning about level of CO to the users. It uses Blynk application to monitors level of CO inside the vehicle, MQ-9 gas sensor as the input sensor, ESP 8266 as medium to send data to the application via IoT-based and the level concentration of CO is displayed on the LCD in real-time displayed. For the output, it has 3 different condition based on the level concentration of CO. This project has been testing in six different situation. Based on the result, ambience air and in car with open window situation have lowest of CO level. Meanwhile, the highest of CO level is detect in smoke that are produced from fuel combustion of the car exhaust at distance 5 cm. Additionally, Principal Component Analysis (PCA) is used to analysed the ability of this system in clustering for each situation. As a result, PCA have clearly clustering data for every situation with the value of PC1 is 71.82% and PC2 is 28.18%, hence it is verified that the build system is able to applied in detecting the presence of CO. This project is believed able in helping to reduce the numbers of cases people drowning while sleeping due to inhaling CO in the car.
      6  26
  • Publication
    An overview of object detection from building point cloud data
    ( 2021-06-11)
    Humairah Mansor
    ;
    Shazmin Aniza Abdul Shukor
    ;
    Wong R.
    3D laser scanner, also known as LiDAR (Light Detection and Ranging), is a device that able to collect dense representation of its surroundings. Its data in point cloud form is commonly used to monitor complex environments like the highways, infrastructures and buildings. The rapid development of 3D laser scanner nowadays has assisted the process of managing complicated and huge areas, especially in building and facility management. As the advancement in architectural and civil engineering increases, building spaces change frequently, as well as renovations work which consists of several items like structures (walls, ceilings, floors) and building fixtures (doors, windows). This has contributed towards complex and huge data to be processed which usually involves tedious and complicated work. Therefore, this data needs to be handled efficiently. Object recognition and classification is one of the most important process in point cloud data since it provides a full detail of building information. Object recognition is used to recognize multiple objects in point cloud data and classification process is used to classify the objects into a class based on the criteria of the objects. These processes reduce the noise and size of point cloud data to be processed. This paper provides an overview on data processing approaches, which focused on the process of object detection and classification, especially for buildings, as part of Building Information Management (BIM) and the possibility of future research in BIM modelling.
      1
  • Publication
    A study of heat insulation methods for enhancing the internal temperature on artificial stingless bee hive
    ( 2024)
    Muhammad Ammar Asyraf Che Ali
    ;
    Bukhari Ilias
    ;
    Norasmadi Abdul Rahim
    ;
    Shazmin Aniza Abdul Shukor
    ;
    Abdul Hamid Adom
    ;
    Mohd Fauzi Abu Hassan
    The stingless bees have gained a large popularity among the beekeepers, particularly in tropical and subtropical regions such as the Americas, Africa, and Southeast Asia. This is because the honey of stingless bees has a distinct flavour and is highly valued for its medicinal qualities. Traditionally, stingless bee colonies constructed from wood logs are fragile and vulnerable to outside attacks. These predator or parasite attacks can cause Colony Collapse Disorder (CCD) if not eliminated. Thus, a PVC, 3D-printed PET-G, and acrylic artificial hive has been created to replace the old one. According to earlier research, stingless bees are especially susceptible to temperatures above 38°C. This paper's main goal is to discuss the results of studies on the best artificial hive insulation method. Over a month and a half, clay, wood powder, polystyrene, bubble aluminium foil, and a water- cooling system were tested as insulators. Results shows that artificial hives with bubble aluminium foil have the biggest average difference between internal and external temperatures (6.4°C) and are closest to traditional hives (8.6°C). The average temperature difference between the artificial hive's exterior and inside was 2.9°C without heat insulation. Clay-insulated artificial hives have the lowest standard deviation value for humidity at 0.46. Since temperature is vital to stingless bee survival, bubble aluminium foil container is the best insulation solution since it increases heat resistance more than other materials.
      4  22
  • Publication
    Mitigating Overfitting in Extreme Learning Machine Classifier Through Dropout Regularization
    (Universiti Malaysia Perlis, 2024-02-14)
    Fateh Alrahman Kamal Qasem Alnagashi
    ;
    Norasmadi Abdul Rahim
    ;
    Shazmin Aniza Abdul Shukor
    ;
    Mohamad Hanif Abd Hamid
    Achieving optimal machine learning model performance is often hindered by the limited availability of diverse datasets, a challenge exacerbated by small sample sizes in real-world scenarios. In this study, we address this critical issue in classification tasks by integrating the Dropout technique into the Extreme Learning Machine (ELM) classifier. Our research underscores the effectiveness of Dropout-ELM in mitigating overfitting, especially when data is scarce, leading to enhanced generalization capabilities. Through extensive experiments on synthetic and real-world datasets, our findings consistently demonstrate that Dropout-ELM outperforms traditional ELM, yielding significant accuracy improvements ranging from 0.19% to 16.20%. By strategically implementing dropout during training, we promote the development of robust models that reduce reliance on specific features or neurons, resulting in increased adaptability and resilience across diverse datasets. Ultimately, Dropout-ELM emerges as a potent tool to counter overfitting and bolster the performance of ELM-based classifiers, particularly in scenarios with limited data. Its established efficacy positions it as a valuable asset for enhancing the reliability and generalization of machine learning models, providing a robust solution to the challenges posed by constrained training data.
      15  1