Engineering Technology & Applied Science Research

Predicting student dropout in higher education is challenging due to class imbalance and class overlap, particularly in multiclass classification. This study presents a hybrid method that combines weight-based oversampling and energy-based cleaning to address class imbalance and class overlap. The method generates synthetic minority samples using neighborhood information and interpolation directi…

Salinity intrusion in the Vietnamese Mekong Delta (VMD) poses severe threats to agricultural productivity, water security, and ecosystem stability. This phenomenon is driven by a complex interplay of climate change-induced sea-level rise, upstream hydropower development, sediment depletion, land subsidence, and altered hydrological regimes. This review evaluates the effectiveness, trade-offs, and…

In this paper, a novel compact two-port multi-band terahertz (THz) Multiple-Input Multiple-Output (MIMO) antenna based on the dual-polarized slot technique is designed for 6G and beyond wireless communication systems. The proposed antenna is designed and simulated on a quartz substrate using a graphene-based radiating element and operates at seven distinct resonance frequencies, i.e., 5.804, 6.36…

This study presents a reproducible end-to-end deep learning pipeline for proof-of-concept classification of anemia-related and control-like blood cell images using a publicly accessible online dataset. The workflow integrates online data download, automatic extraction, dataset restructuring, class balancing, augmentation-enhanced preprocessing, transfer-learning-based model training, visualizatio…

In the current age of ubiquitous internet-based communication, the transmission of images is very common and important. Images require specialized encryption algorithms due to their inherent properties. This study proposes a new lightweight, Non-Linear Feedback Shift Register (NLFSR)-based image encryption scheme. The proposed NLFSR scheme is used to generate secret pseudo-random sequences to per…

The primary aim in the oil and gas industry is to optimize drilling operations to reduce costs and time. Accurate Rate of Penetration (ROP) prediction is essential for optimizing operations and directly influences the cost spent and non-productive time on the rig. Multiple mechanical and geological factors complicate the prediction of ROP, and standard empirical models often fail to capture the c…

Ultrasonic Welding (UW) is used to assemble additively manufactured thermoplastic parts in applications such as robotics, automotive components, and custom mechanical systems. This study investigates permanent joints of thermoplastic components manufactured by Fused Deposition Modeling (FDM) and assembled using UW. The objective of this work is to determine the optimal joint interface geometry wi…

Speech topic classification aims to identify the dominant thematic category of spoken content and plays a key role in applications such as speech analytics, content indexing, and information retrieval. Despite recent progress in speech representation learning, accurately inferring topics from raw speech remains challenging due to semantic variability, long-duration dependencies, and the absence o…

This study proposed a hybrid physics-guided residual multi-task neural network framework based on a large-scale simulated J-V dataset, comprising approximately 2.47 million samples. Physics-based descriptors were constructed, and residual learning with a heuristic empirical baseline was adopted through carrier transport and interfacial contact mechanisms. The model achieved a test coefficient of …

Debris flows in mountainous regions commonly consist of water, sediment, coarse particles, and woody debris, resulting in complex transport behavior. Beam-type sabo dams are widely used to reduce debris-flow hazards by retaining coarse particles while allowing finer materials to pass through structural openings. However, the influence of woody debris on boulder trapping efficiency remains insuffi…

This study investigates the condition sensitivity of a camera-based traffic monitoring pipeline that combines YOLOv8s detection with SORT tracking for real-time vehicle counting. Video data were collected from a pedestrian bridge above a two-lane highway in Győr, Hungary, under multiple weather conditions (clear, rainy, foggy), lighting (day, night) conditions, and viewpoint (central, moderate sh…

This study introduces a novel Logistic Spline Quantum Coherent Extreme Neural Learning (LSQC-ENL) model designed to enhance prenatal diagnosis of chromosomal abnormalities using ultrasound fetal images. The proposed approach aims to overcome the limitations and potential risks of existing diagnostic techniques by enabling more accurate and early detection. The LSQC-ENL model is structured into th…

This study develops an integrated flood-inundation simulation using the Storm Water Management Model (SWMM), the Hydrologic Engineering Center’s River Analysis System (HEC-RAS), and ArcGIS, and estimates flood-related economic losses using the Economic Commission for Latin America and the Caribbean’s (ECLAC) Damage and Loss Assessment (DaLA) approach. The study was conducted in the Gajah Putih Wa…

Blockchain consensus mechanisms are important to ensure the safe validation of transactions. However, the limitations of high computational complexity, energy consumption, and mining latency restrict the scalability of blockchain in large-scale IP-based and wireless network environments. Current methods mainly rely on single optimization methods without jointly optimizing miner selection and hash…

Cardiovascular Disease (CVD) remains one of the leading causes of mortality worldwide, emphasizing the need for accurate and early diagnostic solutions. Recent advances in Machine Learning (ML) and Deep Learning (DL) have shown significant potential to support clinical decision-making through data-driven prediction models. This study presents a robust Ensemble Learning (EL) framework for the pred…

The Two-Echelon Vehicle Routing Problem with Drones (2E VRP-D) model can initiate flights from the truck, complete several deliveries to different customer locations, and then rendezvous with the truck again. In addition to economic benefits, logistics providers must consider the environmental impacts of the order-fulfillment process. A novel multi-objective optimization framework is established …

Computerized Adaptive Testing (CAT) is a key component of large-scale digital assessment systems, where high measurement accuracy must be achieved under constraints of test length, computational cost, and sustainable item bank usage. Although classical 3PL-IRT Item Selection Rules (ISRs) are efficient and interpretable, their effectiveness varies across test stages and ability regions, especially…

This study implemented a nonlinear control method on a higher-Degree-of-Freedom (DOF) underactuated model, namely a Double Inverted Pendulum (DIP) on a cart. The high-DOF underactuated nonlinear model is well known for its control challenges. Thus, in this research, a nonlinear Backstepping (BSP) controller was successfully designed and applied to address this issue. To evaluate the control quali…

Sugarcane yield is reduced by leaf diseases such as mosaic, red rot, rust, and yellow leaf, whose overlapping symptoms make early field diagnosis difficult. This paper presents UniDetNet-MAF, a lightweight unified detection framework that simultaneously localizes and classifies sugarcane leaf diseases. Three components drive its performance: MAF-Conv (a multi-dimensional attention convolution act…

Brain tumors require accurate and early diagnosis to support effective treatment decisions. Magnetic Resonance Imaging (MRI) is widely used for brain tumor assessment; however, many deep learning-based approaches remain black-box systems with limited clinical interpretability. This study proposes Explainable Artificial Intelligence Vision Transformer (XAIViT), a hybrid Convolutional Neural Networ…