Mohd Na’im Abdullah

Quadrotor unmanned aerial vehicles (UAVs) are increasingly deployed in industrial and agricultural operations, where structural integrity and flight stability are critical. Minor mechanical defects, such as small propeller bends and chips, can cause subtle vibration irregularities that are difficult to detect using conventional inspection techniques. This study investigates the application of supervised machine learning to classify vibration signals collected from a custom low-cost acquisition system for the early identification of structural damage. Vibration data were acquired under normal conditions and for multiple damage cases, stored in Excel format, and processed using time-domain feature extraction methods. Four classifiers, namely K-Nearest Neighbours, Support Vector Machine, Decision Tree, and Random Forest, were trained and evaluated to differentiate between healthy, bent, and chipped propeller states. The models achieved pooled classification accuracies ranging from 80.0% to 93.3%, with Random Forest achieving the highest pooled accuracy of 93.3%. These findings support the feasibility of machine-learning-based vibration analysis as a proof-of-concept approach for pre-flight UAV fault screening using low-cost sensing hardware.

The study investigated how Big Data technologies can enhance education quality assessment methods by examining the impact of data analytics and AI-driven approaches on the precision, effectiveness, and thoroughness of educational evaluations. Traditional assessment methods relying on subjective evaluations, small-scale surveys and delayed feedback mechanisms have been criticized for their inability to provide comprehensive, timely and impartial evaluations of educational quality. The research employed a mixed-methods approach combining systematic literature review with data analytics, utilizing machine learning techniques, natural language processing and predictive analytics to evaluate data from learning management systems, institutional databases and online learning platforms collected between January and December 2024. Educational institutions implementing Big Data-centric assessment methodologies demonstrated a 15–25% reduction in overall assessment errors, a 10% increase in student engagement, and a 7% decrease in course withdrawal rates, with one prominent public university achieving a 20% decrease in dropout rates among at-risk students through predictive modeling. The findings revealed that real-time data interpretation enabled timely intervention for learning difficulties, while predictive analytics and personalized learning pathways allowed educators to proactively address academic challenges, resulting in measurable improvements in retention rates and academic performance across multiple institutional benchmarks.

Corrosion in metallic materials is a critical challenge in maintenance and safety, and traditional visual inspection methods are often time-consuming, labor-intensive, and dependent on human expertise, highlighting the need for more efficient and reliable solutions. Deep learning, particularly convolutional neural networks (CNNs), provides a promising approach by enabling automated and accurate image-based classification. This study investigates binary image classification of corrosion using four pre-trained CNN architectures, namely ResNet50, MobileNetV2, NASNetMobile, and EfficientNetV2B0, and integrates explainable artificial intelligence (XAI) techniques to provide interpretability and insight into each model’s decision-making process. A curated dataset of 4012 images, divided between corroded and non-corroded surfaces, was pre-processed, and augmented images resulted in a total of 9636 images used to train and evaluate the models. Performance was assessed through accuracy, confusion matrices, computational timing, receiver operating characteristic curves, precision–recall curves, and Cohen’s Kappa. In this paper, Gradient-weighted Class Activation Mapping (Grad-CAM) visualizations are incorporated as an XAI technique to provide interpretable insight into the model’s reasoning process, enabling clear identification of corrosion regions and offering justification for each prediction produced by the system. A key contribution of this work is the integration of Grad-CAM to enhance explainability. The results showed that EfficientNetV2B0 demonstrates stable training with minimal sign overfitting compared to other models. MobileNetV2 achieved the lowest time to train with the datasets given, and ResNet50 achieved the highest classification performance in terms of confusion matrix, with an accuracy of 96.58%. Through Grad-CAM reasoning, EfficientNetV2B0 shows a specific high activation towards corroded regions compared to the other three models that were evaluated.

Geopolymers have emerged as promising materials for their superior thermal and mechanical properties, offering sustainable alternatives to conventional coatings. This study investigates the potential of Palm Oil Fuel Ash (POFA) as a raw material for fire-resistant geopolymer coatings. Through the optimization of POFA-to-alkaline activator (AA) ratios, NaOH concentrations, and curing temperatures, POFA-based coatings were synthesized and applied to mild steel substrates. Fire resistance testing revealed that the optimal formulation (0.35 POFA ratio, 8 M NaOH concentration, and curing at 65 °C) achieved a temperature at equilibrium (TAE) of 151.2 °C, significantly outperforming other compositions by reducing heat transfer during fire exposure. Thermal imaging and SEM analysis demonstrated that the optimized coating (GP-POFA8) exhibited a more uniform and stable intumescent layer, leading to lower peak temperatures (909 °C) compared to less optimized samples. Thermogravimetric Analysis (TGA) further confirmed that GP-POFA8 retained approximately 80% of its original mass at temperatures beyond 600 °C, highlighting its superior thermal stability. These findings underscore the potential of POFA-based geopolymers as effective, eco-friendly solutions for fire-resistant applications in construction and industrial sectors, contributing to sustainable waste management.

The utilization of natural fibers as sustainable materials in composites has gained significant attention in recent years. This study investigates the tensile and low-velocity impact behavior of flax fiber-reinforced composites modified with multi-walled carbon nanotubes (MWCNTs). The primary objective is to evaluate the mechanical performance enhancements achieved by incorporating MWCNTs into woven flax fibers through a vacuum bagging process. Flax fiber with varying MWCNT concentrations (0-3 wt.%) were fabricated and subjected to tensile and drop-weight impact tests. The tensile test results revealed that the incorporation of MWCNTs significantly improved the tensile strength of the composites, with the FF/PE-CNT3 sample exhibiting a 6.23% increase compared to the control sample (FF/PE). Scanning Electron Microscopy (SEM) analysis demonstrated better dispersion and interaction of MWCNTs within the composite matrix, leading to enhanced load transfer and mechanical properties. Impact tests showed a marked increase in energy absorption with higher MWCNT content. The FF/PE-CNT3 sample absorbed 43.81 J at 30 J impact energy, indicating a 31.81% improvement over the control sample. The enhanced energy absorption is attributed to the excellent interfacial bonding and effective load distribution facilitated by the MWCNTs. These findings suggest that MWCNT-modified flax fiber composites exhibit superior mechanical properties, making them promising candidates for applications requiring high strength and impact resistance. The study contributes to the development of advanced natural fiber-reinforced composites with improved performance for sustainable engineering applications.

Rotor imbalance in quadrotor UAVs poses a critical challenge, compromising flight stability, increasing maintenance demands, and reducing overall operational efficiency. Traditional vibration analysis methods, such as Fast Fourier Transform (FFT) and wavelet analysis, often struggle with non-stationary signals and real-time data processing, limiting their effectiveness under dynamic UAV operating conditions. To address these challenges, this study develops a machine learning-based vibration analysis system using a Multi-Layer Perceptron (MLP) neural network for real-time rotor imbalance detection. The system integrates Micro-Electro-Mechanical Systems (MEMS) sensors for vibration data acquisition, preprocessing techniques for noise reduction and feature extraction, and an optimized MLP architecture tailored to high-dimensional vibration data. Experimental validation was conducted under controlled flight scenarios, collecting a comprehensive dataset of 800 samples representing both balanced and imbalanced rotor conditions. The optimized MLP model, featuring five hidden layers, achieved a Root Mean Squared Error (RMSE) of 0.1414 and a correlation coefficient (R²) of 0.9224 on the test dataset, demonstrating high accuracy and reliability. This study highlights the potential of MLP-based diagnostics to enhance UAV reliability, safety, and operational efficiency, providing a scalable and effective solution for rotor imbalance detection in dynamic environments. The findings offer significant implications for improving UAV performance in addition to minimizing downtime in various industrial and commercial applications.

The detection of impact and depth defects in Glass Fiber Reinforced Polymer (GFRP) composites has been extensively studied to develop effective, reliable, and cost-efficient assessment methods through various Non-Destructive Testing (NDT) techniques. Challenges in detecting these defects arise from varying responses based on the geometrical shape, thickness, and defect types. Long Pulse Thermography (LPT), utilizing an uncooled microbolometer and a low-resolution infrared (IR) camera, presents a promising solution for detecting both depth and impact defects in GFRP materials with a single setup and minimal tools at an economical cost. Despite its potential, the application of LPT has been limited due to susceptibility to noise from environmental radiation and reflections, leading to blurry images. This study focuses on optimizing LPT parameters to achieve accurate defect detection. Specifically, we investigated 11 flat-bottom hole (FBH) depth defects and impact defects ranging from 8 J to 15 J in GFRP materials. The key parameters examined include the environmental temperature, background reflection, background color reflection, and surface emissivity. Additionally, we employed image processing techniques to classify composite defects and automatically highlight defective areas. The Tanimoto Criterion (TC) was used to evaluate the accuracy of LPT both for raw images and post-processed images. The results demonstrate that through parameter optimization, the depth defects in GFRP materials were successfully detected. The TC success rate reached 0.91 for detecting FBH depth defects in raw images, which improved significantly after post-processing using Canny edge detection and Hough circle detection algorithms. This study underscores the potential of optimized LPT as a cost-effective and reliable method for detecting defects in GFRP composites.