IJACSA Vol. 17 Issue 7 (2026)

1

Vision Transformers and Convolutional Neural Networks for Land Use Scene Classification

Author 1: Arun D. Kulkarni

Land use scene classification (LUSC) from remote sensing imagery plays a critical role in environmental monitoring, urban planning, and sustainable resource management. In recent years, deep learning methods have significantly advanced the state-of-the-art, with Convolutional Neural Networks (CNNs) dominating the field because of their strong ability to capture local spatial… Read full abstract & cite →

Convolutional Neural Networks (CNNs) deep learning land use scene classification remote sensing Vision Transformers (ViTs)

Abstract doi.org/10.14569/IJACSA.2026.0170701 PDF

2

Privacy-Preserving Financial Fraud Detection Using Federated Heterogeneous Temporal GraphSAGE

Author 1: Sabab Islam Author 2: Md. Abul Kalam Azad Author 3: Abdul Kadar Muhammad Masum Author 4: Ramona Birau Author 5: Virgil Popescu Author 6: Roxana Mihaela Nioata (Chireac) Author 7: Gabriela Ana Maria Lupu (Filip)

Digital financial ecosystems face mounting exposure to fraudulent transactions that collectively account for trillions of dollars in losses each year. Existing approaches suffer from three recurring deficiencies: they represent all transaction participants within a single undifferentiated node space, rely on fixed decision boundaries incapable of accommodating evolving fraud distributions, and… Read full abstract & cite →

Financial fraud detection federated learning heterogeneous temporal graph GraphSAGE privacy-preserving machine learning graph neural networks

Abstract doi.org/10.14569/IJACSA.2026.0170702 PDF

3

Attention-Augmented PointNet with Hybrid Ant Colony Optimization and Bayesian Hyperparameter Search for Robust 3D Point Cloud Classification in Augmented Reality Applications

Author 1: Ahmed Almaghthawi Author 2: Fahad Alharbi Author 3: Radwan M. Batyha Author 4: Suhaila Abuowaida

Three-dimensional point cloud classification is a foundational task for augmented reality (AR), autonomous navigation, and robotics, yet remains challenging due to the inherent irregularity, sparsity, and permutation invariance of point set data. PointNet, the seminal architecture for this task, processes points independently through shared multi-layer perceptrons (MLPs) and aggregates with… Read full abstract & cite →

3D point cloud classification augmented reality multi-head self-attention PointNet Ant Colony Optimization Bayesian optimization hyperparameter search ModelNet40 neural architecture search

Abstract doi.org/10.14569/IJACSA.2026.0170703 PDF

4

Ordinal Factor Analysis with Robust Estimation and Predictive Models

Author 1: Abuelgasim Osman Author 2: Zahayu Binti Md Yusof

Ordinal survey indicators are common in behavioral and social science research. Still, they violate continuous normal assumptions when category spacing is unequal, response distributions are skewed, or categories are sparse. This study evaluates a practical workflow for ordinal factor analysis that combines robust confirmatory factor analysis (CFA) estimation with complementary… Read full abstract & cite →

Ordinal data confirmatory factor analysis polychoric correlation WLSMV DWLS bootstrap machine learning deep learning cross-validation

Abstract doi.org/10.14569/IJACSA.2026.0170704 PDF

5

Neural Network Implementation of the Renormalization Group for Fault Diagnosis with Class Imbalance

Author 1: Evgeny Nikulchev Author 2: Dmitry Ilin

The application of machine learning models in practical tasks faces challenges such as class imbalance and multidimensional noise. This study proposes RGNet, a neural network architecture based on the concept of the renormalization group (RG), for hierarchical coarse-graining of the feature space. The model sequentially compresses the input dimensionality and… Read full abstract & cite →

Renormalization group coarse-graining fault prediction neural network implementation RG-flows class imbalance

Abstract doi.org/10.14569/IJACSA.2026.0170705 PDF

6

MatchIA-GCL: A Hybrid Graph Contrastive Learning Approach for Semantic Schema Matching

Author 1: Mohamed Raoui Author 2: Moulay Hafid El Yazidi Author 3: Ahmed Zellou

Schema matching remains a fundamental challenge for achieving data interoperability across heterogeneous information systems. Existing deep learning-based approaches often suffer from semantic drift, overlook the structural topology of schemas, and operate as black-box models with limited interpretability. This study introduces MatchIA-GCL, an explainable hybrid framework for semantic schema matching that… Read full abstract & cite →

Schema matching data interoperability graph contrastive learning Graph Attention Networks Large Language Models explainable artificial intelligence semantic data integration

Abstract doi.org/10.14569/IJACSA.2026.0170706 PDF

7

Optimized Lattice-Based Ciphertext Policy Attribute-Based Encryption for Quantum-Resistant Secure Data Sharing

Author 1: Purnima Author 2: Tejaswi Khanna Author 3: Deepak Kumar Verma

The practical utilization of the conventional Ciphertext-Policy Attribute-Based Encryption (CP-ABE) systems in a vast cloud has the constraint of the high cost of computation and the high risk of quantum-powered adversaries. This research introduces a novel Hybrid Lattice-Based CP-ABE (HL-CP-ABE) architecture that is focused on the hardness assumptions of Ring… Read full abstract & cite →

LWE Ring-LWE post-quantum cryptography attribute based encryption parallel processing

Abstract doi.org/10.14569/IJACSA.2026.0170707 PDF

8

Binary Enhanced White Shark Optimization Algorithm and Its Application to Semi-Supervised Feature Selection

Author 1: Jian Zhou Author 2: Jiawen Yang

With the development of information technology, the generation and storage of data have become convenient, resulting in a large amount of high-dimensional data. Due to the high acquisition cost of labeled data, semi-supervised learning of partially labeled data has emerged. Feature selection aims to select the most representative and informative… Read full abstract & cite →

Feature selection semi-supervised learning meta-heuristic algorithm white shark optimization

Abstract doi.org/10.14569/IJACSA.2026.0170708 PDF

9

NADOS: Reliability-Gated Difficulty-Aware Oversampling for Noisy Imbalanced Classification

Author 1: Ednel Ashraff Misran Author 2: Syahid Anuar Author 3: Adam Mohd Khairuddin

Class imbalance becomes more challenging when minority underrepresentation is accompanied by label noise, because synthetic oversampling may amplify unreliable local structures if noisy minority samples are used as interpolation seeds. This study proposes Noise-Aware Adaptive-Difficulty Oversampling (NADOS), which separates the assessment of seed trustworthiness from the allocation of synthesis effort… Read full abstract & cite →

Imbalanced classification label noise oversampling SMOTE noisy data minority learning

Abstract doi.org/10.14569/IJACSA.2026.0170709 PDF

10

A RAG-Enhanced Human-in-the-Loop Framework for Automated Assessment of Engineering Laboratory Reports

Author 1: Amina Abbi Author 2: Mohammed Skouri Author 3: Mustapha Raoufi

Recent developments in Large Language Models (LLMs) have created new opportunities to automate educational assessment and reduce workload for instructors. However, concerns regarding grading consistency, transparency, and pedagogical reliability continue to limit the adoption of fully automated assessment systems. In this study, we propose a Human-in-the-Loop framework for the automated… Read full abstract & cite →

Large Language Models Retrieval-Augmented Generation Human-in-the-Loop automated assessment engineering education laboratory report evaluation rubric-based grading educational artificial intelligence

Abstract doi.org/10.14569/IJACSA.2026.0170710 PDF

11

Detecting Metadata-Conditioned Response Drift in AI-Generated Visual Information Systems: A Two-Phase Human–Computer Interaction Framework

Author 1: Yu Jia Author 2: Shaojie Zhang Author 3: Na Li

AI-generated visual information systems often present images with authorship metadata, yet such labels may shape the evaluation data they are intended to contextualize. Existing work has seldom offered a system-level procedure for measuring metadata-conditioned response drift under unchanged visual input. This study develops a two-phase evaluation framework combining blind presentation… Read full abstract & cite →

AI-generated visual information systems metadata disclosure response drift user-response logs human-computer interaction authorship labeling mixed-effects modeling

Abstract doi.org/10.14569/IJACSA.2026.0170711 PDF

12

Hybrid Machine Learning and Reinforcement Learning for IoT Device Classification and Bandwidth Optimization

Author 1: Manjunatha T N Author 2: Vidyalakshmi K Author 3: Dankan Gowda V

Increased traffic in the Internet of Things (IoT) network results in a large amount of network data that should be processed efficiently in order to manage IoT network resources properly. Hence, bandwidth management and resource allocation are key challenges in managing large-scale IoT networks. In this study, a novel hybrid… Read full abstract & cite →

IoT device classification bandwidth allocation machine learning algorithms support vector machines Random Forest K-Nearest Neighbors Neural Networks network optimization IoT traffic resource management

Abstract doi.org/10.14569/IJACSA.2026.0170712 PDF

13

Pattern Analysis of Global AI Adoption and Digital Literacy Development in Science Education: Basis for a Recommender System Framework

Author 1: Honelly Mae S. Cascolan

The rapid growth of artificial intelligence (AI) technologies has transformed educational environments and created new opportunities for enhancing digital literacy in science education. However, variations in technological readiness, infrastructure, educational development, and AI adoption continue to influence the effectiveness of digital transformation initiatives across regions. This study analyzed global AI… Read full abstract & cite →

Artificial intelligence adoption digital literacy Educational Data Mining explainable artificial intelligence Intelligent Recommender System

Abstract doi.org/10.14569/IJACSA.2026.0170713 PDF

14

Automated Multi-Task Deep Learning Framework for Simultaneous Identification of Dental Pathologies and Arch Localization in Orthopantomograms (OPG)

Author 1: Hatim Elhag Author 2: Norehan Binti Mokhtar Author 3: Siti Noor Fazliah Binti Mohd Noor Author 4: Gururajaprasad Kaggal Lakshmana Rao Author 5: Nordin Zakaria Author 6: Fakhitah Ridzuan Author 7: Mohammed Bin Salah

Interpreting orthopantomograms (OPGs) accurately and efficiently remains challenging due to overlapping anatomical structures and the subtle presentation of many dental pathologies. While deep learning (DL) has shown considerable potential in dental imaging, most existing models focus on single-task detection and do not address the need for simultaneous analysis of both… Read full abstract & cite →

Orthopantomogram (OPG) deep learning (DL) multi-task learning YOLOv11 object detection dental pathology arch classification Computer-Aided Diagnosis (CAD)

Abstract doi.org/10.14569/IJACSA.2026.0170714 PDF

15

Inclusive Digital Health Platform for Well-Being and Loneliness in SOGIESC Older Adults

Author 1: Yada Atanan Author 2: Titikarn Assatarakul Author 3: Akara Metasuk

This research and development (R&D) project aims to design, test, and enhance a digital platform for assessing and promoting the health of late middle-aged and older adults who are diverse in sexual orientations, gender identities, gender expressions, and sex characteristics (SOGIESC). It displays people's opinions regarding a personal health reporting… Read full abstract & cite →

Digital health platform friendly space well-being and loneliness LGBTQ older adults

Abstract doi.org/10.14569/IJACSA.2026.0170715 PDF

16

Image-Based Iron Ore Feed Load Classification Using EfficientNet-B0 with Region-Density Attention and Hierarchical Feature Fusion

Author 1: Sami F Karali Author 2: Fawaz Alanazi Author 3: Eman Ramadan Elsharkawy Author 4: Asma A. Alhashmi Author 5: Abed Saif Ahmed Alghawli Author 6: Imen B. Mohamed Author 7: Chams Sallami Author 8: Abdulbasit A. Darem

Iron ore estimation is a significant part of mineral exploration, as it supports determining both the quantity and quality of available mineral resources. Precise estimation facilitates effective mine planning, production management, and sustainable usage of natural resources. Conventional systems are mostly based on laboratory measurements and geological surveys that are… Read full abstract & cite →

Mineral exploration Iron Ore Load Prediction EfficientNet-B0 Adam optimizer deep learning resource utilization

Abstract doi.org/10.14569/IJACSA.2026.0170716 PDF

17

An Intelligent Writing Tutor for ESL Learners: A Rule-Based and NLP-Assisted Feedback Framework

Author 1: Ruth L. Ladwingon

Writing remains one of the most challenging skills for English as a Second Language (ESL) learners because it requires the coordinated application of grammar, vocabulary, and written discourse conventions. This study proposes an Intelligent Writing Tutor that integrates corpus-informed error analysis, natural language processing (NLP), and rule-based reasoning to generate… Read full abstract & cite →

Corpus-informed instruction educational technology English as a Second Language Intelligent Writing Tutor natural language processing rule-based feedback

Abstract doi.org/10.14569/IJACSA.2026.0170717 PDF

18

Migration Method for Parametric Features in Heterogeneous CAD Systems

Author 1: Gang WANG Author 2: Guangfa ZHANG

Parametric feature migration across different Computer-Aided Design (CAD) systems is a core technology that supports cross-platform collaborative design and product data reuse. Addressing the fundamental limitation of traditional geometry-based data exchange methods—their inability to transfer high-level design intent information such as construction history, parametric constraints, and feature dependency relationships—this study… Read full abstract & cite →

Heterogeneous CAD feature migration JSON neutral file information extraction topology identification

Abstract doi.org/10.14569/IJACSA.2026.0170718 PDF

19

Automated Classification of Moroccan Procedural Court Orders Using CAMeL-BERT

Author 1: Saliha YASSINE Author 2: Ouafaa IBRIHICH Author 3: Mohammed ESSOUJAA Author 4: Mustapha ESGHIR

The digitization of judicial systems creates new opportunities for automating document management tasks that have traditionally relied on manual processing. This study addresses the automated classification of Arabic procedural court orders issued by Moroccan courts of first instance into seven official procedural categories, a low-resource legal document type characterized by… Read full abstract & cite →

Arabic legal NLP CAMeL-BERT judicial document classification Moroccan courts procedural court orders

Abstract doi.org/10.14569/IJACSA.2026.0170719 PDF

20

A Hybrid SMOTE-Ensemble Framework for Robust Speech Emotion Recognition on Imbalanced Data

Author 1: Eyad Megdadi Author 2: Mariam Aljouhi Author 3: Zainab Alblooshi Author 4: Khaled Shaalan

Speech Emotion Recognition (SER) has attracted considerable attention in recent years because of its potential applications in healthcare, intelligent assistants, customer service, and human-computer interaction. However, the performance of SER systems is often affected by the imbalance of emotion classes in benchmark datasets, where minority emotions are underrepresented and difficult… Read full abstract & cite →

IEMOCAP dataset Speech Emotion Recognition (SER) class imbalance SMOTE

Abstract doi.org/10.14569/IJACSA.2026.0170720 PDF

21

XPA-FedCBR: A Federated Case-Based Reasoning System for Explainable and Privacy-Aware Lung Cancer Diagnosis

Author 1: Devyani Rawat Author 2: Shuchi Bhadula Author 3: Sachin Sharma

Lung cancer is among the deadliest cancers worldwide, largely because it is usually caught too late. Building AI tools for earlier, stage-aware diagnosis is hard in practice: patient scans are scattered across hospitals that cannot share them freely, and clinicians are reluctant to trust models that cannot explain their reasoning… Read full abstract & cite →

Case-based reasoning federated learning explainable AI lung cancer clinical decision support medical imaging

Abstract doi.org/10.14569/IJACSA.2026.0170721 PDF

22

Enhanced Simple Linear Iterative Clustering (ESLIC) for Precise Skin Lesion Segmentation in Dermoscopic Images

Author 1: Leni Natalia Zulita Author 2: Sarjon Defit Author 3: Sumijan

The main challenge in dermoscopy image analysis lies in the lesion segmentation process, which is often affected by variations in color, texture, lighting, and irregular lesion boundaries. The Simple Linear Iterative Clustering (SLIC) method is widely used for superpixel-based segmentation, but it still faces limitations in preserving the morphological details… Read full abstract & cite →

ESLIC dermoscopy melanoma SLIC superpixel CNN

Abstract doi.org/10.14569/IJACSA.2026.0170722 PDF

23

Adaptive Mirage Search Optimization for Educational Workload Scheduling in Multi-Cloud Environments

Author 1: Mohammed A.S. Mosleh Author 2: Elham Alzain Author 3: Hesham M.A. Abdullah Author 4: Ali Alshebami

AI-driven educational platforms increasingly rely on heterogeneous cloud workloads, including real-time tutoring, adaptive assessments, and large-scale learning analytics, which impose diverse and conflicting quality-of-service (QoS) requirements. Conventional cloud scheduling approaches fail to address such heterogeneity, often leading to service-level agreement (SLA) violations, increased execution cost, and poor resource utilization. This… Read full abstract & cite →

Multi-cloud computing task scheduling Quality of Service (QoS) multi-objective optimization mirage search optimization AI-powered education SLA-aware scheduling metaheuristic algorithms

Abstract doi.org/10.14569/IJACSA.2026.0170723 PDF

24

HISaaS: A Cloud-Based Framework for Semantic Enrichment of Legacy Health Databases Using OpenAI Embeddings

Author 1: Toufik Salmi Author 2: Abdeslem Dennai

Legacy Information Systems (LIS) confront significant interoperability challenges, particularly at the database level. If existing solutions focus on data exchange, they fail to address the fundamental structural incompatibilities of Legacy Databases (LDBs). In this article, we present Health Information System as a Service (HISaaS), an innovative dual solution based on… Read full abstract & cite →

Information systems interoperability database cosine measurement cloud computing OpenAI embeddings NLP

Abstract doi.org/10.14569/IJACSA.2026.0170724 PDF

25

HETRA: A Real-Time Traffic Detection and Directional Counting System Using YOLOv8 and DeepSORT

Author 1: Kuldeep Kumar Shukla Author 2: Ajai Kumar Singh

Rapid urbanization and economic growth in developing countries such as India have increased the demand for automated traffic analysis systems. However, heterogeneous traffic conditions present significant challenges to automated traffic analysis. This study proposes HETRA (HEterogeneous TRaffic Analysis), a real- time traffic monitoring framework that integrates YOLOv8 and DeepSORT for… Read full abstract & cite →

Heterogeneous traffic YOLOv8 DeepSORT traffic counting intelligent transportation system

Abstract doi.org/10.14569/IJACSA.2026.0170725 PDF

26

Improving Arabic Relational Aggregated Search Using a Hybrid RAG and AraBERT Framework

Author 1: Sara Saad Sedhom Author 2: Ahmed Younes Author 3: Islam Elkabani Author 4: Ashraf Elsayed

Aggregated search is challenged by data heterogeneity, redundancy, and irrelevant information, particularly in Arabic because of its rich morphology and dialectal diversity. This study proposes an AI-driven framework to enhance Arabic aggregated search by integrating Retrieval-Augmented Generation (RAG) with semantic clustering. The framework employs RAG to retrieve relevant information from… Read full abstract & cite →

Relational Aggregated Search (RAS) information retrieval Natural Language Processing (NLP) Retrieval-Augmented Generation (RAG) AraBERT embedding feature extraction stacked autoencoders K-Means

Abstract doi.org/10.14569/IJACSA.2026.0170726 PDF

27

Design, Implementation, and Evaluation of a Mobile Application for Real-Time Incident Management in Local Government

Author 1: Marleny Peralta Ascue Author 2: Luis Bryan Caballero Pinto Author 3: José Luis Poluco Sicos Author 4: José Luis Merma Aroni

The increasing occurrence of incidents related to public safety, environmental issues, transportation, and civil defense requires more efficient response mechanisms from local governments. However, the absence of an integrated digital tool makes it difficult to accurately identify the location, timing, and frequency of critical incidents in real time, thereby limiting… Read full abstract & cite →

Mobile application incident management local government Agile Scrum usability evaluation CSUQ digital transformation

Abstract doi.org/10.14569/IJACSA.2026.0170727 PDF

28

EduDarijaBERT: An Applied Transformer-Based Framework for Sentiment Analysis in Moroccan Arabic Educational Discourse

Author 1: Abderrahim Ait Ichou Author 2: Ali Ouacha

Students' opinions play a pivotal role in the formulation of successful educational policies. However, the computational analysis of the Moroccan Arabic Dialect remains widely viewed as problematic due to a focus on complex morphology and the absence of specific datasets. To close this gap, we propose an end-to-end system for… Read full abstract & cite →

Sentiment analysis system Moroccan Arabic dialect social media analytics educational data mining data engineering framework

Abstract doi.org/10.14569/IJACSA.2026.0170728 PDF

29

MAMGAT-Net: A Multimodal Graph Attention and Multi-Scale Feature Fusion Framework for Early Breast Cancer Diagnosis from Mammography and Histopathological Images

Author 1: Mohammad Riyaz Belgaum

Breast cancer is one of the major causes of death among women worldwide, and timely and accurate diagnosis has proven to play a critical role in increasing breast cancer patient survival. Traditional single-modality diagnostic systems, however, tend to be unable to capture both the macro-level structural abnormalities that can be… Read full abstract & cite →

Breast cancer cross-modal attention explainable artificial intelligence graph attention network histopathology mammography multimodal learning

Abstract doi.org/10.14569/IJACSA.2026.0170729 PDF

30

An Intelligent System for Energy-Aware Flexible Fault Tolerance in Cloud

Author 1: Moin Hasan Author 2: Shailee Lohmor Choudhary Author 3: Rinku Sharma Dixit Author 4: Sujith Jayaprakash

Fault tolerance in cloud computing environments has matured significantly, and most cloud service providers now offer highly available and reliable services. However, such high levels of fault tolerance are often achieved through resource replication, which consequently increases overall energy consumption. Existing research primarily relies on conventional energy management techniques when… Read full abstract & cite →

Cloud computing energy-aware computing fault tolerance artificial intelligence service reliability sustainable computing

Abstract doi.org/10.14569/IJACSA.2026.0170730 PDF

31

INSPIRE: Understanding Local-Global Representation Learning via Controlled Self-Supervised Training and Representation Interpretability

Author 1: Reem Alharthi Author 2: Rashid Mehmood Author 3: Aiiad Albeshri Author 4: Abdulaziz A. Almuzaini

Self-supervised learning (SSL) has become a powerful paradigm for visual representation learning, yet it remains insufficiently understood how different training strategies shape the balance between global semantic structure and local visual detail. This study introduces the INSPIRE Framework, a unified framework for systematically investigating local-global representation learning in SSL through… Read full abstract & cite →

Self-supervised learning visual representation learning local-global representation learning representation interpretability contrastive learning spatial sensitivity image representation representation analysis computer vision

Abstract doi.org/10.14569/IJACSA.2026.0170731 PDF

32

Enhancing Diabetic Retinopathy Classification Through Advanced Deep Convolutional Neural Network Architectures

Author 1: Sifeddine Elkardoudi Author 2: Khalil Ladrham Author 3: Ahmed Eddaoui Author 4: Mohamed Talea

Diabetic retinopathy is one of the major causes of vision loss in the world; thus, the development of early diagnosis systems based on artificial intelligence is a medical and scientific necessity. If detected late, it can lead to permanent vision loss and is considered one of the most serious vascular… Read full abstract & cite →

Diabetic retinopathy fundus images deep learning xception inception-v3 mobilenet-v3 resnet-50 training time

Abstract doi.org/10.14569/IJACSA.2026.0170732 PDF

33

The Evolution of Clinical Intelligence Through GenAI Co-pilots: A Systematic Review and Thematic Synthesis

Author 1: Li-Chen Cheng Author 2: Chia-Yu Hung Author 3: Te-Nien Chien

Generative artificial intelligence (GenAI), large language models (LLMs), and multimodal foundation models are rapidly transforming healthcare by extending artificial intelligence beyond traditional predictive analytics toward collaborative clinical intelligence. Recent advances have enabled applications in clinical decision support, medical documentation, workflow optimization, patient communication, and personalized care planning. However, the existing… Read full abstract & cite →

Generative artificial intelligence clinical co-pilot large language models clinical decision support human-AI collaboration

Abstract doi.org/10.14569/IJACSA.2026.0170733 PDF

34

Localized Actionable Explainability for MOOC Dropout Intervention Using Clickstream Learning Analytics

Author 1: Mohamed Amine OUASSIL Author 2: Mohammed JEBBEARI Author 3: Mouaad ERRAMI Author 4: Rabia Rachidi Author 5: Soufiane HAMIDA Author 6: Bouchaib CHERRADI Author 7: Abdelhadi RAIHANI

Massive Open Online Courses (MOOCs) have expanded access to learning, but learner dropout remains a persistent challenge in online education. Most dropout prediction studies transform learner traces into behavioral features and train machine learning or deep learning models to identify at-risk learners. Although this predictive layer is useful, it remains… Read full abstract & cite →

MOOC dropout prediction learning analytics explainable artificial intelligence SHAP localized explanation actionable intervention

Abstract doi.org/10.14569/IJACSA.2026.0170734 PDF

35

Counterfeit Currency Detection Through Deep Convolutional Generative Adversarial Network

Author 1: Salman Jan Author 2: Fara Gul Author 3: Mohammad Riyaz Belgaum Author 4: Shahid Kamal Author 5: Afaq Ahmad Author 6: Muhammad Bilal Author 7: Atif Khan

Worldwide, individuals, businesses, and economies are being affected by counterfeit currency significantly. Numerous models generate content that mimics the original, and existing solutions fall short in detecting the difference between real and fake. This study presents a detection system using three deep learning models: Deep Convolutional Generative Adversarial Network (DCGAN)… Read full abstract & cite →

CNN counterfeit DCGAN Fake Money FCNN fraud detection

Abstract doi.org/10.14569/IJACSA.2026.0170735 PDF

36

FGHA-Net: Hybrid Attention Learning for Froth Flotation Recovery Prediction in Mineral Beneficiation

Author 1: Mohammed I Thanoon Author 2: Fawaz Alanazi Author 3: Shaaban M. Shaaban Author 4: Asma A. Alhashmi Author 5: Abed Saif Ahmed Alghawli Author 6: Ahlem Fatnassi Author 7: Majed Nawaz Author 8: Abdulbasit A. Darem

Froth flotation recovery prediction plays an important role in mineral processing because it can improve operational efficiency, reduce mineral loss, and support more effective decision-making during flotation operations. However, accurate recovery prediction remains challenging because flotation processes are highly dynamic and nonlinear, sensor data may contain noise, and process variables… Read full abstract & cite →

Froth flotation mineral beneficiation iron-ore processing recovery prediction soft sensor BiLSTM transformer fine-grained attention deep learning

Abstract doi.org/10.14569/IJACSA.2026.0170736 PDF

37

From Cloud to On-Premises: A Systematic Review of Cloud Repatriation Drivers, Strategies, and Governance Challenges

Author 1: Amzari Mohd Roslan Author 2: Fazlina Mohd Ali Author 3: Faizan Qamar Author 4: Liyana Safra Zaabar Author 5: Nur Arzilawati Md Yunus

Cloud repatriation is the migration of workloads from public cloud to private, on-premises, and hybrid clouds. Despite the growing adoption of cloud computing, there are many issues associated with operational expenditure, the unpredictable performance of cloud services, compliance concerns, vendor dependency, and data sovereignty concerns. Thus, cloud repatriation has become… Read full abstract & cite →

Cloud repatriation on-premises transition systematic literature review data security hybrid cloud data sovereignty vendor lock-in governance implementation limitations

Abstract doi.org/10.14569/IJACSA.2026.0170737 PDF

38

Multi-Agent Crowd-Risk Prioritization for Large-Scale Events: A Hybrid ML–Agent Approach

Author 1: Najwa Samrgandi

Managing crowd safety during large-scale gatherings such as Hajj requires timely assessment of multiple risk factors, including crowd conditions, environmental factors, and health-related indicators. Many existing approaches address these aspects separately, making it difficult to obtain a unified operational view of risk. This study presents a multi-agent framework that combines… Read full abstract & cite →

Multi-agent systems crowd-risk prioritization intelligent crowd management real-time IoT monitoring SMOTE XGBoost safety-critical systems

Abstract doi.org/10.14569/IJACSA.2026.0170738 PDF

39

Model-Augmented Masked Autoencoder with Domain-Adaptive Denoising for Robust Brain Tumor MRI Analysis

Author 1: Indrakumar K Author 2: Ravikumar M Author 3: Mohammed A.S Al-mohamadi Author 4: Khalid N. R. Alharbi Author 5: Asma A. Alhashmi Author 6: Shouki A. Ebad Author 7: Abdulbasit A. Darem

This work presents a Model-Augmented Masked Autoencoder (MAE) framework, augmented with domain-adaptive denoising and multi-level feature fusion, for self-supervised representation learning in MRI-based brain tumor analysis. The proposed approach enhances feature robustness under limited annotation by learning structure-preserving representations through masked reconstruction while explicitly addressing scanner-induced variability. Unlike conventional MAE… Read full abstract & cite →

Self-supervised learning Masked Autoencoder MRI domain adaptation feature representation medical imaging

Abstract doi.org/10.14569/IJACSA.2026.0170739 PDF

40

A Statistical Filtering Algorithm for Tender Price Evaluation Using the J-Selaras Framework

Author 1: Mustafa Man Author 2: Wan Aezwani Wan Abu Bakar Author 3: Mohd Kamir Yusof Author 4: Mohd Nasir Saari Author 5: Nor Arzalifah Abd. Razak Author 6: Nor Zuraiya Mt Amin

Accurate evaluation of tender prices is critical in construction procurement, particularly in public sector projects where financial efficiency and transparency are essential. However, traditional evaluation methods are often affected by abnormal bids, leading to inconsistent and potentially biased decision-making. This study proposes the J-Selaras Statistical Filtering Algorithm (JSFA), a data-driven… Read full abstract & cite →

Construction procurement cost normalization digital procurement system outlier detection statistical filtering tender price evaluation Z-score analysis

Abstract doi.org/10.14569/IJACSA.2026.0170740 PDF

41

Prompt Literacy and Generative AI Readiness for AI-Assisted Animation Creative Workflows in Higher Education

Author 1: Loh Ngiik Hoon Author 2: Natasha Binti Rusdy Wong Author 3: Marzie Hatef Jalil

Generative AI technologies are increasingly being adopted within creative learning environments, particularly in animation and digital media education. As AI-assisted tools become more accessible, there is a growing need to understand how students perceive and adapt to these technologies in their creative workflows. This study explores prompt literacy and generative… Read full abstract & cite →

Generative AI prompt literacy AI readiness animation education creative workflows higher education

Abstract doi.org/10.14569/IJACSA.2026.0170741 PDF

42

CDNet: Complex-Valued Deep Unrolled Composite Denoising Network for Accelerated Magnetic Resonance Image Reconstruction

Author 1: David Muigai Author 2: Elijah Mwangi Author 3: Henry Kiragu

Magnetic resonance imaging (MRI) is an essential modality in contemporary medical diagnosis, offering high-resolution images with excellent soft-tissue contrast of internal organs in a non-invasive, non-ionizing, and non-carcinogenic manner. However, the primary drawback of this technique is a lengthy data-acquisition process, which raises the possibility of picking up artefacts as… Read full abstract & cite →

Accelerated MRI reconstruction composite priors iterative three-operator splitting compressed sensing deep unfolding composite denoising network

Abstract doi.org/10.14569/IJACSA.2026.0170742 PDF

43

Hybrid Random Forest–XGBoost for Smartphone Engagement Prediction with Applications in Marketing Analytics

Author 1: Ace John Mark P. Liwanag

This study presents a machine learning framework for predicting smartphone engagement intensity using behavioral smartphone usage data. The study utilized the Smartphone Usage and Addiction Analysis dataset containing 7,500 user records with demographic, behavioral, lifestyle, and engagement-related variables. The binary variable addicted_label was employed as a proxy measure of smartphone… Read full abstract & cite →

Cellphone marketing prediction consumer engagement feature importance hybrid model machine learning mobile marketing predictive analytics Random Forest smartphone usage behavior XGBoost

Abstract doi.org/10.14569/IJACSA.2026.0170743 PDF

44

A Blockchain and AI Integrated Framework for Dynamic Land Registration and Smart Urban Zoning

Author 1: Shushma R Author 2: S R Nagaraja

Land registration and urban zoning are very important jobs for the government, but in many places, they still have problems with old processes, corruption, and a lack of openness. Urbanization and population growth are putting more and more pressure on systems that need to be smarter and more flexible to… Read full abstract & cite →

Blockchain artificial intelligence smart zoning land registration urban planning smart contracts GIS Integration Explainable AI (XAI) decentralized governance dynamic land use management

Abstract doi.org/10.14569/IJACSA.2026.0170744 PDF

45

Segmented Lung CT Image Refinement Through Hybrid Edge-Preserving De-Noising and Variance-Regulated Adaptive Histogram Equalization

Author 1: T. Bhuvaneshwari Author 2: Rohini Pinapatruni

Lung diseases are detected effectively by Chest CT Medical im-ages. Chest CT images are 3D, and they are used for detecting abnormalities in the lungs like pneumonia, tuberculosis, tumors, etc. Chest CT images suffer from different types of noise. The presence of various types of noise, such as Gaussian noise… Read full abstract & cite →

Chest CT Images lung segmentation medical image denoising adaptive edge preserving hybrid filter variance regulated adap-tive histogram equalization VRAHE contrast enhancement low-dose CT noise suppression

Abstract doi.org/10.14569/IJACSA.2026.0170745 PDF

46

Design and Implementation of Rule-Based and Time-Based Logic in a PAC-Based Precision Irrigation Control System

Author 1: Djohar Syamsi Author 2: Mimin Muhaemin Author 3: Oviyanti Mulyani Author 4: Hanif Fakhrurroja Author 5: Puput Dani Prasetyo Adi

This study aims to design and functionally validate a prototype precision fertigation control system based on a Programmable Automation Controller (PAC) capable of managing water and nutrient delivery through two approaches: a time-based approach as the basic control and a rule-based approach as a corrective response based on sensor data… Read full abstract & cite →

HMI precision fertigation PAC preliminary field testing time-based control rule based control

Abstract doi.org/10.14569/IJACSA.2026.0170746 PDF

47

Advancing Ecological Informatics: A Tool for Implementing the Abundance–Preference Approach in Assemblage Analysis

Author 1: Mohamed El Farouki Author 2: Mohamed Dakki Author 3: Meryem Ennakri Author 4: Soumia Ziti

Although the Abundance-Preference Diagram (APD) was introduced four decades ago as an entropy-based framework for classifying species along habitat-preference gradients, its uptake by the ecological community has remained marginal. The cause is not theoretical but operational: no existing software (e.g., vegan, ade4, CANOCO, PC-ORD, BIOMAPPER) implements the Degree of Preference… Read full abstract & cite →

Ecological informatics web application algorithm assemblage ecology species preference abundance-preference diagram

Abstract doi.org/10.14569/IJACSA.2026.0170747 PDF

48

Blockchain-Based Trusted Data Sharing Framework for Secure and Auditable AI Model Training

Author 1: Sherif Amin

AI models are highly effective and reliable based on integrity, provenance, and controlled usage of training data. The use of data sharing between several stakeholders in collaborative and distributed settings poses risks of unauthorized access, data tampering, and data poisoning that undermine trust and accountability in AI systems. To overcome… Read full abstract & cite →

Blockchain AI secure data sharing data integrity smart contracts auditable AI pipelines access control AI model training distributed systems

Abstract doi.org/10.14569/IJACSA.2026.0170748 PDF

49

Shortest Path Algorithms for Smart City Emergency Routing: Scalability and Scenario-Based Analysis

Author 1: Aleksandra Stojanova Ilievska Author 2: Natasha Stojkovikj Author 3: Limonka Koceva Lazarova Author 4: Arta Aliu Author 5: Krume Tasev Author 6: Teona Aleksova

Shortest path algorithms play an essential role in intelligent transportation systems, emergency response planning, and numerous Smart City services. This study investigates the applicability of three well-established graph-based algorithms, namely Dijkstra, Bellman-Ford, and A*, within an emergency transportation framework inspired by the urban road network of Skopje. A two-stage evaluation… Read full abstract & cite →

Shortest path algorithms dijkstra bellman-ford A* smart city emergency routing intelligent transportation systems simulation

Abstract doi.org/10.14569/IJACSA.2026.0170749 PDF

50

Implementation and Evaluation of a Dynamic Multi-Grid Pattern Authentication for Secure Financial Applications

Author 1: Amjad Qashlan Author 2: Qamar H. Naith Author 3: Fatimah Alakeel Author 4: Malak B Alharbi

Authentication plays an important role in online banking services. Nowadays, many online services still use password-based and One-Time Password (OTP) codes as authentication methods, but this is no longer secure, especially with the increase in financial fraud. In this research, a novel pattern-based password approach that relies on the random… Read full abstract & cite →

Authentication cyberattack financial fraud multiple grids pattern-based password testing

Abstract doi.org/10.14569/IJACSA.2026.0170750 PDF

51

Unsanctioned Intelligence: Mitigating the Risks of ‘Shadow AI’ and Proprietary Data Leaks in the Remote Workforce

Author 1: Adel Saad Assiri

The high implementation of remote working models has only increased the pace of using artificial intelligence tools by employees to improve their productivity, automate routine tasks, and aid in decision-making. Non-committal application of AI tools, or Shadow AI, has, however, become a major organizational risk, especially when the processed information… Read full abstract & cite →

Shadow AI remote workforce security data leakage prevention AI governance trustworthy AI enterprise risk management policy compliance uncertainty-aware systems

Abstract doi.org/10.14569/IJACSA.2026.0170751 PDF

52

Dual-Attention Framework for Enhanced Road Obstacle Segmentation and Anomaly Detection

Author 1: Priyanka G Author 2: Silvia Gaftandzhieva Author 3: Mariya Zhekova

Autonomous driving systems rely heavily on semantic segmentation to understand road environments; however, existing methods often fail to detect unseen road obstacles that are absent from training datasets, limiting their use in safety-critical applications. This study proposes a lightweight attention map-based framework for road obstacle segmentation that addresses the mismatch… Read full abstract & cite →

Road obstacle detection attention map ground truth annotations semantic segmentation reward map

Abstract doi.org/10.14569/IJACSA.2026.0170752 PDF

53

Anomaly-Score-Augmented Random Forest for Permission-Based Android Malware Detection: An Empirical Study on 29,999 Apps

Author 1: Harikrishnan P R Author 2: P. Periyasamy

Permission-based static analysis is still the workhorse of low-cost Android malware detection. But most published evaluations live on small curated subsets, report a single train-test split, and skip statistical analysis altogether. This study takes a different cut. We run a 5-fold stratified cross-validation across five random seeds, 25 training runs… Read full abstract & cite →

Android security malware detection permission analysis isolation forest random forest LightGBM XGBoost anomaly score augmentation empirical evaluation SHAP

Abstract doi.org/10.14569/IJACSA.2026.0170753 PDF

54

Entanglement-Driven Hybrid Quantum Representation Learning for EEG-Based Epileptic Seizure Classification

Author 1: Athigiri Arulalan A S Author 2: Senthilkumar G Author 3: Jabasheela L Author 4: Sangeetha K Author 5: Subedha V Author 6: Sathiya V

Automated epileptic seizure detection from electroencephalogram (EEG) recordings remains a challenging biomedical signal analysis task because of the nonlinear, non-stationary, and high-dimensional characteristics of neural activity. Although deep learning has substantially improved automated seizure classification, conventional architectures may exhibit limited capability in modeling complex latent feature interactions while maintaining computational… Read full abstract & cite →

Electroencephalography (EEG) epileptic seizure detection hybrid quantum–classical learning Quantum Convolutional Neural Network (QCNN) variational quantum machine learning Continuous Wavelet Transform (CWT) quantum representation learning biomedical signal classification Explainable Artificial Intelligence (XAI)

Abstract doi.org/10.14569/IJACSA.2026.0170754 PDF

55

EDM-Based Graduate Curriculum Planning Framework

Author 1: Levi E. Elipane Author 2: Antriman V. Orleans Author 3: Adonis P. David Author 4: Wilma S. Reyes Author 5: Crist John Pastor Author 6: Felina P. Espique Author 7: Juan Primitivo P. Petrola

Graduate curriculum planning is critical to ensuring that teacher education programs remain responsive to professional standards, workplace demands, and emerging educational priorities. This study applies Educational Data Mining (EDM) techniques as an exploratory decision-support approach for graduate curriculum planning for in-service teachers in the Philippines. Using survey data from 624… Read full abstract & cite →

Educational data mining graduate curriculum planning teacher professional development curriculum analytics random forest curriculum needs assessment graduate education

Abstract doi.org/10.14569/IJACSA.2026.0170755 PDF

56

Arki-Nexus AI: A Framework for Integrating Artificial Intelligence Competencies Into NEUST College of Architecture

Author 1: GREGORIO L. VILLAVIZA JR

The rapid expansion of Artificial Intelligence (AI) is reshaping architectural education and practice, yet its systematic curricular integration remains limited in many higher education settings. This study developed the proposed Arki-Nexus AI Framework to guide the structured integration of AI competencies into the curriculum of the NEUST College of Architecture… Read full abstract & cite →

Artificial intelligence architecture education self-reported AI competency curriculum integration curriculum framework digital transformation future-ready architects

Abstract doi.org/10.14569/IJACSA.2026.0170756 PDF

57

Secure Heart Disease Status Classification Using Machine Learning and Blockchain-Based EHR Integrity Verification

Author 1: Haya H. Alsharif Author 2: Sabah M. Alzahrani

Heart disease remains one of the leading causes of mortality worldwide, motivating the development of accurate and scalable screening-support tools. This study presents an integrated framework for heart-disease status classification using the Heart 2020 Cleaned dataset, derived from the CDC Behavioral Risk Factor Surveillance System (BRFSS), a telephone-based survey of… Read full abstract & cite →

Heart-disease status classification machine learning ensemble model random forest XGBoost LightGBM Blockchain Electronic Health Records (EHR)

Abstract doi.org/10.14569/IJACSA.2026.0170757 PDF

58

Digital Technologies Enabling Smart Circular Waste Management: A Systematic Literature Review

Author 1: Pristi Sukmasetya Author 2: Harry Budi Santoso Author 3: Zainal Arifin Hasibuan Author 4: Yun Arifatul Fatimah

This study aims to identify and classify the technologies used across the waste-management lifecycle, qualitatively synthesize the types of operational and circularity-related outcomes reported in the literature, and examine the technical challenges and research gaps that must be addressed to develop interoperable, scalable, secure, and empirically validated systems. The study… Read full abstract & cite →

Artificial Intelligence (AI) circular economy digital technology Internet of Things (IoT) smart waste management

Abstract doi.org/10.14569/IJACSA.2026.0170758 PDF

59

Arabic News Text Classification Using Deep Learning Models with Dynamic N-grams

Author 1: Ahmed I.Taloba Author 2: George Samy Rady Author 3: Khaled F. Hussain

The complexity and morphological richness of the Arabic language pose significant challenges in natural language processing (NLP), including issues with contextual understanding and feature extraction. Traditional deep learning architectures such as CNNs, LSTMs, and GRUs often struggle to effectively model these linguistic intricacies, limiting their performance on Arabic text analysis… Read full abstract & cite →

Dynamic n-grams GRU-CNN hybrid Arabic NLP sequential dependencies text classification

Abstract doi.org/10.14569/IJACSA.2026.0170759 PDF

60

8C SPS Model: A Seller Product Selection Model for Home-Based Business Sellers Using a Multi-Criteria Decision-Making Approach

Author 1: Selvia Lorena Br Ginting Author 2: Zulaiha Ali Othman

Home-based businesses are becoming a necessary tool for sellers of home-based businesses to determine which products they might be able to sell well. Otherwise, most of the sellers still choose products by trial and error, which may bring low demand as well as stock that doesn't sell, resulting in wasted… Read full abstract & cite →

Seller product selection home-based business online marketplace multi-criteria decision-making multi-objective optimization based on ratio analysis analytic hierarchy process product ranking

Abstract doi.org/10.14569/IJACSA.2026.0170760 PDF

61

Hierarchical Workforce Dynamics and Risk-Aware Gated Deep Learning Framework for Employee Attrition Prediction

Author 1: Chen Yang

Human resource management is a key factor in organizational success. Understanding and predicting employee attrition is important for improving workforce planning and decision-making. In this study, we propose a Hierarchical Workforce Dynamics – Temporal Risk-Aware Gated model named HWD-TRAG deep learning framework for accurate and transparent attrition prediction. The proposed… Read full abstract & cite →

Employee attrition prediction human resource analytics deep learning explainable AI workforce analysis risk prediction attention mechanism ensemble learning classification predictive analytics

Abstract doi.org/10.14569/IJACSA.2026.0170761 PDF

62

Adaptive Grammar Correction with Error-Type Diagnosis and Learner-Centered Feedback Using Proficiency-Aware Transformer Learning

Author 1: Xinxin Sun Author 2: Peng Guo

Grammar error correction systems are widely used to improve learner-written English. However, many existing systems mainly provide corrected sentences and do not explain the reason behind the correction. This limits their usefulness in language learning. This study proposes AGC-LCFNet, an Adaptive Grammar Correction with Learner-Centered Feedback Network. The model corrects… Read full abstract & cite →

Grammar error correction learner-centered feedback FLAN-T5 error-type classification proficiency-aware gating adaptive feedback generation English language learning intelligent tutoring system natural language processing automated writing support

Abstract doi.org/10.14569/IJACSA.2026.0170762 PDF

63

MACN: A Modality-Aware Cross-Attention Transformer for Non-Invasive Hemoglobin Estimation and Anemia Classification Using Multi-Region Physiological Images

Author 1: Chaitra S P Author 2: D R Ramesh Babu

Anemia is a major health concern among pregnant women in rural areas. Early detection and timely treatment are necessary to reduce maternal and infant mortality. Many non-invasive techniques have been proposed to solve the problem of unavailability of laboratory-based hemoglobin testing in rural areas. But their accuracy is limited due… Read full abstract & cite →

Anemia hemoglobin deep learning cross-attention fusion multimodality

Abstract doi.org/10.14569/IJACSA.2026.0170763 PDF

64

Low-Latency FPGA-Based PCA Acceleration for Hyperspectral Image Dimensionality Reduction

Author 1: Hana Ben Fredj Author 2: Ahlem kehili Author 3: Amani Chabbeh Author 4: Jamel Baili Author 5: Chokri Souani

Remote sensing systems generate large volumes of high-dimensional data, which creates significant challenges for onboard processing and data transmission under computational, memory, and energy constraints. Dimensionality reduction is therefore essential for enabling efficient embedded remote sensing applications. This work presents a hardware-accelerated implementation of Principal Component Analysis (PCA) on an… Read full abstract & cite →

Remote sensing hyperspectral data dimensionality reduction Principal Component Analysis (PCA) FPGA hardware–software co-design

Abstract doi.org/10.14569/IJACSA.2026.0170764 PDF

65

Multiscale Image Enhancement and Visualization Analysis for Historical Map/s

Author 1: Guilei Ren

Based on the degradation of historical maps, such as fading, stains, creases, blurred lines, and text adhesion, multi-scale image enhancement and spatial element visualization analysis are studied. This study constructs a technical process consisting of sample division, image preprocessing, multi-scale enhancement, quality evaluation, and spatial feature extraction, and further evaluates… Read full abstract & cite →

Historical maps multiscale image enhancement image restoration spatial feature recognition visualization analysis

Abstract doi.org/10.14569/IJACSA.2026.0170765 PDF

66

Statistical Security Analysis NIST and Security Enhancement of CBT Cipher for Secure Data and Image Transmission

Author 1: Walid W. Souror Author 2: Mohamed Fouad Author 3: Ali E. Takieldeen

Strong cybersecurity measures are essential in our digital world. This study presents a new cryptographic algorithm called CBT “Combined Blowfish Trilogy” which greatly improves the security of the traditional Blowfish algorithm without compromising computational efficiency. The encryption algorithm proposed herein presents a hybrid system which combines carefully designed countermeasures against… Read full abstract & cite →

Cyber security cryptography blowfish counter-measure SCA attacks combined blowfish trilogy

Abstract doi.org/10.14569/IJACSA.2026.0170766 PDF

67

Unsupervised Hybrid Approach for Intrusion Detection Based on Information System Log Files

Author 1: Sena Apeke Author 2: Nadjime Pindra Author 3: Sèmèvo A. R. M. Ahouandjinou

Intrusion detection in web traffic remains a challenging task due to the high dimensionality, heterogeneity, and imbalance of normal and malicious requests. This study investigates a hybrid anomaly detection framework combining an Autoencoder (AE), Density-Based Spatial Clustering of Applications with Noise (DBSCAN), and Isolation Forest (IF) for intrusion detection in… Read full abstract & cite →

Intrusion detection DBSCAN Isolation Forest Autoencoder server log files anomaly

Abstract doi.org/10.14569/IJACSA.2026.0170767 PDF

68

Artificial Intelligence Guided Crowd Counting and Density Estimation with Enhanced CSRNet

Author 1: Muhammad Jawad Babar Author 2: Malik Muhammad Saad Missen Author 3: Hannan Adeel Author 4: Muhammad Usman Author 5: Muzammil Malik

Estimating crowd size in dense environments re-mains a complex problem, yet it holds critical value for safety monitoring, city infrastructure design, and large-scale gathering coordination. Leveraging contemporary developments in neural network architectures and machine intelligence, researchers have markedly enhanced the precision of population counts derived from both still imagery and… Read full abstract & cite →

Crowd counting machine learning image processing CSRNet density estimation deep learning face detection

Abstract doi.org/10.14569/IJACSA.2026.0170768 PDF

69

FSCM-Net: Frequency-Spatial Collaborative Modeling for Traffic Scene Semantic Segmentation

Author 1: Wei Zhao Author 2: Yi Dong Author 3: Lingchao Wang Author 4: Qiang Ai

To address the challenges of insufficient global semantic modeling and blurred boundaries in urban traffic scene segmentation, this study proposes a frequency-spatial collaborative framework based on DeepLabV3+. A Spectral Decoupling Adaptive Modulation (SDAM) module enhances low-frequency semantics and high-frequency details in the frequency domain. A Hierarchical Spatial Dependency Modeling (HSDM)… Read full abstract & cite →

Frequency-domain modeling spatial dependency modeling local-global attention structure-guided fusion feature enhancement

Abstract doi.org/10.14569/IJACSA.2026.0170769 PDF

70

LAURA: An Awareness-Oriented Explainable AI Framework for Academic Stress in Higher Education

Author 1: Ahmed Almathami Author 2: Richard Stone

Academic stress represents a significant challenge in higher education, especially for students navigating unfamiliar academic environments. In such contexts, difficulties in understanding expectations, feedback, and performance standards can affect engagement, participation, academic performance, and decision-making. Despite significant advances in learning analytics and artificial intelligence, current educational systems remain limited in… Read full abstract & cite →

Explainable Artificial Intelligence (XAI) academic stress student awareness interpretable models human-centered AI higher education

Abstract doi.org/10.14569/IJACSA.2026.0170770 PDF

71

A Model-Free AI Framework for Robust PQRST Complex Detection in ECG Signals

Author 1: Arthorn Luangsodsai Author 2: Manh Duong Dang Author 3: Krung Sinapiromsaran

Accurate delineation of PQRST complex is essential for clinical ECG analysis, but remains challenging due to waveform variability, low amplitude, and polarity inversions. This work presents PAD-PQRST, a model-free Polarity-Adaptive Delineation method for PQRST complex. This approach leverages search windows based on established cardiac physiology. The Q and S waves… Read full abstract & cite →

ECG signal processing PQRST detection model-free AI Polarity-Adaptive Delineation method

Abstract doi.org/10.14569/IJACSA.2026.0170771 PDF

72

Privacy-Preserving Feature Engineering Framework for Real-World Vulnerability Risk Prediction

Author 1: Jawharah Albarakati Author 2: Tawfiq Hasanin Author 3: Suaad Alarifi

This study introduces a privacy-preserving data preparation and feature engineering framework designed for machine learning-based cybersecurity vulnerability risk prediction, utilizing real-world enterprise scan data from an operational cloud environment. To transform raw vulnerability records into a structured, machine-readable format while complying with personal data protection regulations, the framework integrates systematic… Read full abstract & cite →

Data pre-processing machine learning protecting sensitive data stemming pseudonymization

Abstract doi.org/10.14569/IJACSA.2026.0170772 PDF

73

From Method-Centric Optimisation to Failure-Oriented Robustness: A Framework for Industrial Inspection Systems

Author 1: Ying Zhou Author 2: Mei Choo Ang Author 3: Ummul Hanan Mohamad Author 4: Ah-Lian Kor Author 5: Kok Weng Ng Author 6: Saraswathy Shamini Gunasekaran Author 7: Halimah Badioze Zaman

Robust inspection of aeroengine turbine blades remains a critical challenge in safety-critical industrial environments, where limited data availability, class imbalance, optimisation bias, and imaging degradation can reduce the reliability of learning-based inspection systems. Existing studies mainly improve robustness through isolated algorithmic optimisation, while providing limited understanding of why inspection failures… Read full abstract & cite →

Industrial inspection robustness Failure-Oriented Framework deep learning computer vision turbine blade inspection artificial intelligence

Abstract doi.org/10.14569/IJACSA.2026.0170773 PDF

74

SpaTempNet: Deep Spatiotemporal Forecasting of River Morphological Evolution of the Padma River in Bangladesh

Author 1: S. S. Mahmud Turza Author 2: Md. Kaoser Ahamed Anik Author 3: Md. Shadmim Hasan Sifat Author 4: Mahruba Sharmin Chowdhury Author 5: Khandokar Md. Rahat Hossain Author 6: Abdullah Al Noman

Rivers are dynamic geomorphological systems experiencing continuous transformation through erosion and sediment transport. In Bangladesh, these processes displace 50,000-200,000 people annually, causing severe losses along the Padma River according to Natural Resources Defense Council (NRDC). Traditional monitoring via field surveys and manual remote sensing proves costly, spatially limited, and unsuitable… Read full abstract & cite →

River morphology riverbank erosion forecasting spatiotemporal neural networks ConvLSTM U-Net Swin Transformer Vision Transformer satellite remote sensing MNDWI disaster management

Abstract doi.org/10.14569/IJACSA.2026.0170774 PDF

75

Hardware-Software Co-Design of K-Means Clustering on Zynq FPGAs via OpenCL

Author 1: Eya JABALLI Author 2: Soufien GDAIM Author 3: Noureddine LIOUANE

Clustering algorithms such as K-means are widely employed in machine learning and data analytics; however, their computational complexity becomes a significant limitation when applied to large-scale or latency-sensitive workloads. To over-come this challenge, this study presents a hardware-accelerated K-means clustering implementation using Field-Programmable Gate Arrays (FPGAs) within the Open Computing… Read full abstract & cite →

FPGAs Hardware acceleration high-level synthesis OpenCL K-means reconfigurable hardware

Abstract doi.org/10.14569/IJACSA.2026.0170775 PDF

76

Challenges of AI Adoption in the Saudi Arabian Healthcare Sector: A Comprehensive Study

Author 1: Radwan M. Batyha Author 2: Ahmed Almaghthawi Author 3: Fahad Alharbi Author 4: Suhaila Abuowaida

This research examines the challenges of AI adoption in Saudi Arabia healthcare sector in terms of the framework defined by the Vision 2030 healthcare transformation agenda. We utilized the Analytic Hierarchy Process (AHP) methodology to collect and analyze data from 27 managerial-level executives tasked with AI implementation in Saudi Arabia… Read full abstract & cite →

Artificial Intelligence (AI) healthcare transformation Saudi Arabia Vision 2030 Analytic Hierarchy Process (AHP) Saudi Arabia

Abstract doi.org/10.14569/IJACSA.2026.0170776 PDF

77

Multimodal Pneumoconiosis Screening on a Real-World Vietnamese Occupational Health Dataset with Incomplete Metadata and Class Imbalance

Author 1: Luong Thi Bich Phuong Author 2: Nguyen Hoang Anh Author 3: Au Xuan Manh Author 4: Truong Thanh Nam Author 5: Tran Tien Cong Author 6: Nguyen Trong Khanh

Pneumoconiosis remains a major occupational lung disease among workers exposed to silica, coal, and other in-organic dusts. Although chest X-ray screening is widely used in clinical practice, diagnostic performance is often affected by image variability and the limited availability of contextual occupational information. This study presents a multimodal framework that… Read full abstract & cite →

Pneumoconiosis multimodal learning chest X-ray convolutional neural network early fusion occupational lung disease

Abstract doi.org/10.14569/IJACSA.2026.0170777 PDF

78

BEAT: An Integrated Blockchain-Edge AI Trust Framework for IoT Security - Design, Prototype, and Performance Evaluation

Author 1: Pavansai Ramarao Maddali Author 2: Vijay Kumar Damera Author 3: Ratna Kumar Prathipati

Trust management in heterogeneous Internet of Things (IoT) deployments remains unresolved because most frameworks treat blockchain reputation persistence and edge-AI anomaly detection as separate subsystems, so the graded evidence a detection model produces cannot be indexed or propagated by a ledger that was built without reference to it. This study… Read full abstract & cite →

Blockchain trust management edge AI security GAT-LSTM anomaly detection Hyperledger Fabric gossip-accelerated reputation IoT admission control Byzantine fault tolerance

Abstract doi.org/10.14569/IJACSA.2026.0170778 PDF

79

A Hybrid Autoencoder-Random Forest Framework for Intrusion Detection in Internet of Medical Things Network

Author 1: Sophia ALAMI-KAMOURI Author 2: Ridouan LACHGAR Author 3: Mohamed AFIF

With the widespread adoption of the Internet of Medical Things (IoMT), hospitals have become prime targets for cyberattacks. To overcome the limitations of traditional defenses and computationally heavy deep learning models, a hybrid Artificial Intelligence architecture is presented. By coupling a deep Autoencoder for feature extraction with a Random Forest… Read full abstract & cite →

Cybersecurity artificial intelligence IoMT hybrid model Edge Computing SHAP

Abstract doi.org/10.14569/IJACSA.2026.0170779 PDF

80

Development of an Automated Network Forensics Analysis Tool Using PCAP Data

Author 1: Ashwag Alotaibi Author 2: Huda Aldawghan Author 3: Abdullah Albuali

Network forensic investigation often requires analysts to inspect packet captures manually, construct protocol filters, correlate traffic events, and prepare evidence summaries. That workflow is powerful for expert investigators but difficult for novice analysts and users with limited forensic experience. Net-Forensics was designed to simplify the forensic workflow for such users… Read full abstract & cite →

Network forensics PCAP PCAPNG incident response DDoS detection port scanning traffic anomaly detection Flask Scapy digital forensics dashboard visualization

Abstract doi.org/10.14569/IJACSA.2026.0170780 PDF

81

A Probabilistic Instance Generator for Multimodal Urban Transportation Networks Addressing Data Scarcity in Metropolitan Transport Systems Integrating the Formal and Informal Sectors

Author 1: Oumar KONE Author 2: Kouassi Hilaire Edi Author 3: Yapi Fiacre Aristide Edi Author 4: Pawoumodom Matthias Takouda

Multimodal urban transport networks that combine formal and informal sectors remain severely constrained by the scarcity of reliable operational data. Informal systems, in particular, largely evade conventional data-collection methods. This study presents a probabilistic instance generator that produces realistic test instances for multimodal urban transportation optimization models. Journey components (travel… Read full abstract & cite →

Instance generation multimodal urban transportation informal transport data scarcity operations research probabilistic modeling network optimization

Abstract doi.org/10.14569/IJACSA.2026.0170781 PDF

82

On Practical Considerations for the Adoption of Worst-Case Optimal Joins in RDBMSs

Author 1: Ayoub Berdai Author 2: Kawtar Younsi Dahbi Author 3: Dalila Chiadmi Author 4: Slimane Bah

Worst-case optimal join (WCOJ) algorithms have attracted significant interest in both academia and industry due to their strong asymptotic performance guarantees. However, their integration into mature relational database management systems (RDBMSs) remains severely limited. Unlike prior theoretical surveys, this study analyzes the practical considerations for WCOJ adoption across three core… Read full abstract & cite →

Worst-case optimal join AGM-bound join algorithms query processing

Abstract doi.org/10.14569/IJACSA.2026.0170782 PDF

83

A Behavioral Analysis of Machine Learning for Intrinsic 3D Tree Branching Structures

Author 1: M. Charitha Lakshan Author 2: K. Damitha Sandaruwan Author 3: L. N. C. De Silva

Modeling realistic tree structures remains a challenging problem in computer graphics due to the complex interaction between intrinsic growth patterns and environmental influences. Traditional procedural methods provide strong control over environmental adaptation, while learning-based approaches aim to capture branching behavior directly from data. However, learning-based methods typically entangle intrinsic and… Read full abstract & cite →

Tree modeling machine learning intrinsic branching feature representation 3D tree reconstruction synthetic data behavioral analysis hybrid modeling

Abstract doi.org/10.14569/IJACSA.2026.0170783 PDF

84

A Genetic Algorithm-Driven Framework for Convolutional Kernel Selection in Lightweight Plant Disease Classifiers

Author 1: El houssaine HSSAYNI

Foliar pathogens destroy roughly a third to two-fifths of harvestable crops each year, yet the deep convolutional classifiers that have proven most effective at automated leaf-image diagnosis carry parameter counts in the tens of millions prohibitive for the microcontrollers and low-power accelerators aboard agricultural drones and field-deployed IoT nodes. To… Read full abstract & cite →

Plant disease detection convolutional filter selection binary optimisation genetic algorithm structural redundancy

Abstract doi.org/10.14569/IJACSA.2026.0170784 PDF

85

A Binary Cascade Framework for Gut Microbiome Classification in Inflammatory Bowel Disease: Few-Shot LLMs, Co-Abundance Graphs, and Clinical Narrative Encoding

Author 1: Nouhaila En Najih Author 2: Ahmed Moussa

Subtyping inflammatory bowel disease (IBD) from gut microbiome sequencing data is a clinically demanding problem. Cross-cohort variability is large, and models trained on one dataset often fail on another. In this work, we propose a binary cascade pipeline that splits the three-class problem —healthy control, Crohn’s disease (CD), and ulcerative… Read full abstract & cite →

Inflammatory bowel disease gut microbiome large language models few-shot learning graph neural networks 16S rRNA clinical narrative encoding binary cascade centroid selection

Abstract doi.org/10.14569/IJACSA.2026.0170785 PDF

86

Learning When to Wait: A Lightweight Binary Decision Framework for Container Migration in Edge Computing

Author 1: Yasmeen Abu-Haltem Author 2: Sawsan AlShattnawi

Container migration is one of the important techniques used to provide the continuity of services in Multi-access Edge Computing environments. Services are migrated from edge servers to follow the mobility of users among the available edge servers. Nevertheless, current strategies do not take into account the cost that a container… Read full abstract & cite →

Multi-access Edge Computing container migration machine learning Decision Tree mobility management service continuity

Abstract doi.org/10.14569/IJACSA.2026.0170786 PDF

87

A Geospatially-Aware Hybrid Deep Learning Framework for Violence Detection and Sentiment Analysis in Airline Reviews

Author 1: Fahad Alanazi Author 2: Osama Rabie Author 3: Wafi Bedewi

Passenger reviews and feedback provide valuable operational insights for the aviation industry. However, existing sentiment analysis approaches rarely capture safety-related signals such as aggressive or violent language, and they often overlook the integration of geographic context. This study pro-poses a geospatially-aware deep learning framework for sentiment classification and violence detection… Read full abstract & cite →

Hybrid deep learning ensemble learning natural language processing geospatial intelligence violence detection passenger experience

Abstract doi.org/10.14569/IJACSA.2026.0170787 PDF

88

Regulatory-Compliant EEG Stress Recognition Using CNN–Transformer Models with Feature Unlearning

Author 1: Yusra Author 2: Riaz UlAmin

Stress recognition based on EEG data can be useful for healthcare, workplace safety, and mental health monitoring, among other applications. However, most studies do not consider how sensitive EEG data can reveal users’ cognitive and affective information. Existing models also do not offer participant data erasure methods that address compliance… Read full abstract & cite →

EEG Mental stress recognition CNN-transformer machine unlearning privacy GDPR compliance

Abstract doi.org/10.14569/IJACSA.2026.0170788 PDF

89

Hybrid State Estimation and Recurrent Neural Networks for Supply Chain Disruption Detection

Author 1: Mohamed Amine Frikha Author 2: Mariem Mrad Author 3: Younes Boujelbene Author 4: Yasser Mohamed Ayad Soliman

Ensuring robust and resilient operational performance in modern supply chains is increasingly important as logistics systems become more digitalized, interconnected, and data-driven. Although these technological advances improve efficiency and visibility, they also introduce new vulnerabilities to supply chain fraud, inventory manipulation, procurement irregularities, and operational disruptions. In response to these… Read full abstract & cite →

Supply chain fraud operational risk management dynamic state estimation LSTM networks innovation residuals anomaly detection state estimation

Abstract doi.org/10.14569/IJACSA.2026.0170789 PDF

90

Predicting Temporal Exploitation of Software Vulnerabilities Using Knowledge-Fused Neural Learning

Author 1: Mounir Belmahjoub Author 2: Lamia Benhiba

Despite over 25,000 Common Vulnerabilities and Exposures (CVEs) being disclosed annually, fewer than 5% are exploited in real attacks, making vulnerability prioritization a persistent challenge. Existing methods, including the Common Vulnerability Scoring System (CVSS) and Exploit Prediction Scoring System (EPSS), treat exploitation prediction as binary classification, discarding the temporal dimension… Read full abstract & cite →

Vulnerability exploitation prediction temporal risk classification cybersecurity knowledge graph CWE CAPEC BERT Node2Vec CVE prioritization

Abstract doi.org/10.14569/IJACSA.2026.0170790 PDF

91

Deep Learning-Based Image Recognition and Brand Identity Design for Intangible Cultural Heritage in Southern Sichuan

Author 1: Zhihong Chen

The increasing emphasis on digital protection and creative transformation of intangible cultural heritage highlights the urgent need to apply artificial intelligence to accurately identify and brand rich cultural heritage resources in southern Sichuan. This study puts forward an image recognition and brand design model suitable for intangible cultural heritage in… Read full abstract & cite →

Deep learning southern Sichuan’s intangible cultural heritage image recognition brand identity design

Abstract doi.org/10.14569/IJACSA.2026.0170791 PDF