IJACSA Vol. 16 Issue 1 (2025)

1

Advanced Machine Learning Approaches for Accurate Migraine Prediction and Classification

Author 1: Chokri Baccouch Author 2: Chaima Bahar

Migraine is a neurovascular disorder with a prevalence that exceeds 1 billion individuals worldwide, but it has long been recognized to have unique diagnostic challenges due to its heterogeneous pathophysiology and dependence on subjective assessments. As has been extensively documented by a number of international law bodies, migraine in the… Read full abstract & cite →

Headache classification migraine migraine diagnosis migraine classification

Abstract doi.org/10.14569/IJACSA.2025.0160101 PDF

2

A Comparative Study of Predictive Analysis Using Machine Learning Techniques: Performance Evaluation of Manual and AutoML Algorithms

Author 1: Karim Mohammed Rezaul Author 2: Md. Jewel Author 3: Anjali Sudhan Author 4: Mifta Uddin Khan Author 5: Maharage Roshika Sathsarani Fernando Author 6: Kazy Noor e Alam Siddiquee Author 7: Tajnuva Jannat Author 8: Muhammad Azizur Rahman Author 9: Md Shabiul Islam

In this study, we have compared manual machine learning with automated machine learning (AutoML) to see which performs better in predictive analysis. Using data from past football matches, we tested a range of algorithms to forecast game outcomes. By exploring the data, we discovered patterns and team correlations, then cleaned… Read full abstract & cite →

Machine learning predictive analytics sports forecasting automated machine learning (AutoML) feature engineering model evaluation data pre-processing algorithm comparison football analytics sports betting team performance metrics exploratory data analysis (EDA) cross-validation techniques

Abstract doi.org/10.14569/IJACSA.2025.0160102 PDF

3

Detection of DDoS Cyberattack Using a Hybrid Trust-Based Technique for Smart Home Networks

Author 1: Oghenetejiri Okporokpo Author 2: Funminiyi Olajide Author 3: Nemitari Ajienka Author 4: Xiaoqi Ma

As Smart Home Internet of Things (SHIoT) continue to evolve, improving connectivity and security whilst offering convenience, ease, and efficiency is crucial. SHIoT networks are vulnerable to several cyberattacks, including Distributed Denial of Service (DDoS) attacks. The ever-changing landscape of Smart Home IoT threats presents many problems for current cybersecurity… Read full abstract & cite →

Trust smart home IoT DDoS denial of service DoS cyber threats techniques

Abstract doi.org/10.14569/IJACSA.2025.0160103 PDF

4

Forecasting the Emergence of a Dominant Design by Classifying Product and Process Patents Using Machine Learning and Text Mining

Author 1: Koji Masuda Author 2: Yoshinori Hayashi Author 3: Shigeyuki Haruyama

Forecasting the emergence of a dominant design in advance is important because the emergence of the dominant design can provide useful information about the external environment for the product launch. Although the emergence of the dominant design can only be determined as a result of the introduction of the product… Read full abstract & cite →

Dominant design patent analysis technological innovation machine learning text mining classification

Abstract doi.org/10.14569/IJACSA.2025.0160104 PDF

5

Control Interface for Multi-User Video Games with Hand or Head Gestures in Directional Key-Based Games

Author 1: Oscar Ramirez-Valdez Author 2: César Baluarte-Araya Author 3: Rodrigo Castillo-Lazo Author 4: Italo Ccoscco-Alvis Author 5: Alexander Valdiviezo-Tovar Author 6: Alexander Villafuerte-Quispe Author 7: Dylan Zuñiga-Huraca

This paper describes the development and implementation of a hand or head gesture-based control interface for video games, enhanced for games that use directional keys. The objective is to develop an adaptive control system for a multiplayer video game that allows users to choose between the use of traditional directional… Read full abstract & cite →

Control interface video games artificial vision gesture-based interface directional commands human-computer interaction deep learning algorithms accessibility real-time pattern recognition

Abstract doi.org/10.14569/IJACSA.2025.0160105 PDF

6

Teaching Programming in Higher Education: Analyzing Trends, Technologies, and Pedagogical Approaches Through a Bibliometric Lens

Author 1: Mariuxi Vinueza-Morales Author 2: Jorge Rodas-Silva Author 3: Cristian Vidal-Silva

In today’s information society, developing programming competencies is essential in higher education. Numerous studies have been conducted on effective strategies for fostering these skills. This study performs a bibliometric analysis of research on teaching strategies for programming in higher education, using data from the SCOPUS and Web of Science (WOS)… Read full abstract & cite →

Programming higher education teaching strategies bibliometrics

Abstract doi.org/10.14569/IJACSA.2025.0160106 PDF

7

Harnessing the Power of Federated Learning: A Systematic Review of Light Weight Deep Learning Protocols

Author 1: Haseeb Khan Shinwari Author 2: Riaz Ul Amin

With rapid proliferation in using smart devices, real time efficient sentiment analysis has gained considerable popularity. These devices generate variety of data. However, for resource con-strained devices to perform sentiment analysis over multimodal data using conventional modals that are computationally complex and resource hungry, is challenging. This challenge may be… Read full abstract & cite →

Light weight protocols Sentiment analysis federated learning deep learning

Abstract doi.org/10.14569/IJACSA.2025.0160107 PDF

8

SEC-MAC: A Secure Wireless Sensor Network Based on Cooperative Communication

Author 1: Yassmin Khairat Author 2: Tamer O. Diab Author 3: Ahmed Fawzy Author 4: Samah Osama Author 5: Abd El- Hady Mahmoud

Wireless Sensor Networks (WSNs) are essential for a wide range of applications, from environmental monitoring to security systems. However, challenges such as energy efficiency, throughput, and packet delivery delay need to be addressed to enhance network performance. This paper introduces a novel Medium Access Control (MAC) protocol that utilizes cooperative… Read full abstract & cite →

Wireless Sensor Networks (WSNs) energy efficiency Media Access Control (MAC) cooperative communication handshaking algorithm

Abstract doi.org/10.14569/IJACSA.2025.0160108 PDF

9

Digital Twin Model from Freehanded Sketch to Facade Design, 2D-3D Conversion for Volume Design

Author 1: Kohei Arai

The article proposes a method for creating digital twins from freehand sketches for facade design, converting 2D designs to 3D volumes, and integrating these designs into real-world GIS systems. It outlines a process that involves generating 2D exterior images from sketches using generative AI (Gemini 1.5 Pro), converting these 2D… Read full abstract & cite →

BIM AI GIS digital twins metaverse generative AI GauGAN TriPo SketchUp IFC format GeoTiff

Abstract doi.org/10.14569/IJACSA.2025.0160109 PDF

10

Marked Object-Following System Using Deep Learning and Metaheuristics

Author 1: Ken Gorro Author 2: Elmo Ranolo Author 3: Lawrence Roble Author 4: Rue Nicole Santillan Author 5: Anthony Ilano Author 6: Joseph Pepito Author 7: Emma Sacan Author 8: Deofel Balijon

This paper presents a deep learning methodology for a marked object-following system that incorporates the YOLOv8 (You Only Look Once version 8) object identification model and an inversely proportional distance estimation algorithm. The primary aim of this study is to develop a marked object-following algorithm capable of autonomously tracking a… Read full abstract & cite →

Object detection YOLOv8 distance estimation A-star tabu search

Abstract doi.org/10.14569/IJACSA.2025.0160110 PDF

11

Hawk-Eye Deblurring and Pose Recognition in Tennis Matches Based on Improved GAN and HRNet Algorithms

Author 1: Weixin Zhao

In tennis matches, the Hawk-eye system causes blurry trajectory judgment and low accuracy in player posture recognition due to rapid movement and complex backgrounds. Therefore, the research improves the backbone network and iterative attention feature fusion mechanism of deblur generative adversarial network version. At the same time, Ghost, Sandglass module… Read full abstract & cite →

DeblurGANv2 HRNet tennis hawk-eye system deblurring pose recognition

Abstract doi.org/10.14569/IJACSA.2025.0160111 PDF

12

A Highly Functional Ensemble of Improved Chaos Sparrow Search Optimization Algorithm and Enhanced Sun Flower Optimization Algorithm for Query Optimization in Big Data

Author 1: Mursubai Sandhya Rani Author 2: N. Raghavendra Sai

Numerous systems have to provide the highest level of performance feasible to their users due to the present accessibility of enormous datasets and scalability needs. Efficiency in big data is measurable in terms of the speed at which queries are executed physically. It is too demanding on big data for… Read full abstract & cite →

Big data (BD) query optimization Improved Chaos Sparrow Search Optimization Algorithm (ICSSOA) Enhanced Sun Flower Optimization Algorithm (ESOA) ResNet50V2 DBSCAN

Abstract doi.org/10.14569/IJACSA.2025.0160112 PDF

13

IT Spin-Offs Challenges in Developing Countries

Author 1: Mahmoud M. Musleh Author 2: Ibrahim Mohamed Author 3: Hasimi Sallehudin Author 4: Hussam F. Abushawish

IT-enabled spin-off ventures in developing countries’ higher learning institutions have the potential to transform academic research into commercially viable products, thereby fostering economic and technological progress. However, practical implementation faces significant challenges, particularly in conflict areas, such as limited resources, socio-political instability, skill gaps, weak intellectual property laws, and inadequate… Read full abstract & cite →

IT spin-off framework higher learning IT challenges spin-off framework developing countries entrepreneurship innovation

Abstract doi.org/10.14569/IJACSA.2025.0160113 PDF

14

Multi-Factors Analysis Using Visualizations and SHAP: Comprehensive Case Analysis of Tennis Results Forecasting

Author 1: Yuan Zhang

Explainable Artificial Intelligence (XAI) enhances interpretability in data-driven models, providing valuable insights into complex decision-making processes. By ensuring transparency, XAI bridges the gap between advanced Artificial Intelligence (AI) techniques and their practical applications, fostering trust and enabling data-informed strategies. In the realm of sports analytics, XAI proves particularly significant, as… Read full abstract & cite →

Artificial intelligence data analytics machine learning match result prediction XAI SHAP

Abstract doi.org/10.14569/IJACSA.2025.0160114 PDF

15

Exploring Diverse Conventional and Deep Linguistic Features for Sentiment Analysis of Online Content

Author 1: Yajun Tang

Social media has changed the world by providing the facility to common person to share their views and generate their own content, known as Users Generated Content (UGC). Due to huge volume of UGC data being created at great velocity, so to analysis this big data, latest AI (Artificial Intelligence)… Read full abstract & cite →

Artificial intelligence sentiment analysis machine learning word embeddings natural language programming

Abstract doi.org/10.14569/IJACSA.2025.0160115 PDF

16

An AI-Driven Approach for Advancing English Learning in Educational Information Systems Using Machine Learning

Author 1: Xue Peng Author 2: Yue Wang

In current era of globalization, English language learning is important as it has become a global language and helps people to communicate from various regions and languages. For vocational students whose main aim is to get skills and get employed, learning English for communication is important. We here present a… Read full abstract & cite →

Artificial intelligence information system machine learning English language learning natural language processing

Abstract doi.org/10.14569/IJACSA.2025.0160116 PDF

17

Investigating Immersion and Presence in Virtual Reality for Architectural Visualization

Author 1: Athira Azmi Author 2: Sharifah Mashita Syed Mohamad

The architecture industry increasingly relies on virtual reality (VR) for architectural visualization, yet there is a critical issue of insufficient user involvement in the design process. This study investigates the sense of immersion and presence in the virtual environment among 60 Malaysian participants aged 20 to 40. The study utilized… Read full abstract & cite →

Virtual environment virtual reality human-computer interaction architectural visualization sense of presence

Abstract doi.org/10.14569/IJACSA.2025.0160117 PDF

18

Data Mining MRO-BP Network-Based Evaluation Effectiveness of Music Teaching

Author 1: Yifan Fan

This study addresses the need for data analysis in evaluating the teaching outcomes of higher music education. It proposes a solution using data-driven algorithms to measure and analyze these outcomes. This study focuses on the issue of measuring and evaluating the outcomes of music education teaching. It analyzes the process… Read full abstract & cite →

Mushroom propagation optimisation algorithm BP neural network higher music education teaching outcomes measurement algorithm evaluation

Abstract doi.org/10.14569/IJACSA.2025.0160118 PDF

19

Employing Data-Driven NOA-LSSVM Algorithm for Indoor Spatial Environment Design

Author 1: Di Wang Author 2: Hui Ma Author 3: Tingting Lv

This study aims to enhance the precision and efficiency of indoor spatial design for college physical bookstores in the context of the new media environment. To achieve this, a novel intelligent analysis model was developed by integrating the Navigator Optimization Algorithm (NOA) with the Least Squares Support Vector Machine (LSSVM)… Read full abstract & cite →

New media environments data-driven algorithms indoor spatial environment design mariner optimization method

Abstract doi.org/10.14569/IJACSA.2025.0160119 PDF

20

Enhancing Customer Churn Prediction Across Industries: A Comparative Study of Ensemble Stacking and Traditional Classifiers

Author 1: Nurul Nadzirah bt Adnan Author 2: Mohd Khalid Awang

Predicting customer churn is essential in sectors such as banking, telecommunications, and retail, where retaining existing customers is more cost-effective than acquiring new ones. This paper proposes an enhanced ensemble stacking methodology to improve the prediction performance of ensemble methods. Classic ensemble classifiers and individual models are undergoing enhancements to… Read full abstract & cite →

Customer churn single classifier ensemble classifier stacking accuracy

Abstract doi.org/10.14569/IJACSA.2025.0160120 PDF

21

Hotspots and Insights on Quality Evaluation of Study Tours: Visual Analysis Based on Bibliometric Methodology

Author 1: Meihua Deng

In this paper, taking 474 articles about quality evaluation of study tours in Web of Science (WOS) database as the research object, quantitatively analyze them with the help of CiteSpace 6.3.R1 software and excel data statistics, and analyze the impact of the literature data, authors' cooperation network, issuing institutions, journal… Read full abstract & cite →

Research tourism tourism quality evaluation visualization analysis

Abstract doi.org/10.14569/IJACSA.2025.0160121 PDF

22

Internet of Things (IoT) Driven Logistics Supply Chain Management Coordinated Response Mechanism

Author 1: Chong Li

This study explores the development of an IoT-driven logistics supply chain coordination and response mechanism aimed at achieving real-time information sharing, precise forecasting, and rapid decision-making among supply chain nodes. By employing a hierarchical system construction method, SQL database techniques for data management, and an evaluation model combining AHP and… Read full abstract & cite →

IoT logistics supply chain management coordination response mechanism

Abstract doi.org/10.14569/IJACSA.2025.0160122 PDF

23

Big Data Analytics of Knowledge and Skill Sets for Web Development Using Latent Dirichlet Allocation and Clustering Analysis

Author 1: Karina Djunaidi Author 2: Dine Tiara Kusuma Author 3: Rahma Farah Ningrum Author 4: Puji Catur Siswipraptini Author 5: Dina Fitria Murad

Web development is a data-centric field and fundamental component of data science. The advent of big data analytics has significantly transformed the processes, knowledge domains, and competencies associated with Web development. Accordingly, educational programs must adjust to contemporary advancements by initially determining the abilities required for big data web developers… Read full abstract & cite →

Big data analytics hierarchical clustering Latent Dirichlet Allocation web development knowledge skill

Abstract doi.org/10.14569/IJACSA.2025.0160123 PDF

24

Optimizing Multi-Dimensional SCADA Report Generation Using LSO-GAN for Web-Based Applications

Author 1: Fanxiu Fang Author 2: Guocheng Qi Author 3: Haijun Cao Author 4: He Huang Author 5: Lingyi Sun Author 6: Jingli Yang Author 7: Yan Sui Author 8: Yun Liu Author 9: Dongqing You Author 10: Wenyu Pei

This paper addresses the challenges of custom-generating multi-dimensional data SCADA (Supervisory Control And Data Acquisition) reports using web technologies. To improve efficiency, reduce maintenance costs, and enhance scalability, the paper proposes a custom generation method based on the LSO-GAN (Light Spectrum Optimizer - Generative Adversarial Network) model. The study begins… Read full abstract & cite →

Web technologies SCADA systems report customisation spectral optimisation algorithms adversarial generative networks

Abstract doi.org/10.14569/IJACSA.2025.0160124 PDF

25

Optimizing Decentralized Exam Timetabling with a Discrete Whale Optimization Algorithm

Author 1: Emily Sing Kiang Siew Author 2: San Nah Sze Author 3: Say Leng Goh

In recent years, there has been increasing interest in intelligent optimization algorithms, such as the Whale Optimization Algorithm (WOA). Initially proposed for continuous domains, WOA mimics the hunting behavior of humpback whales and has been adapted for discrete domains through modifications. This paper presents a novel discrete Whale Optimization Algorithm… Read full abstract & cite →

Examination timetabling discrete whale optimization algorithm variable neighborhood descent capacitated decentralized

Abstract doi.org/10.14569/IJACSA.2025.0160125 PDF

26

Fusion of Multimodal Information for Video Comment Text Sentiment Analysis Methods

Author 1: Jing Han Author 2: Jinghua Lv

Sentiment analysis of video comment text has important application value in modern social media and opinion management. By conducting sentiment analysis on video comments, we can better understand the emotional tendency of users, optimise content recommendation, and effectively manage public opinion, which is of great practical significance to the push… Read full abstract & cite →

Video commentary text sentiment analysis multimodal information fusion M-S multimodal sentiment model convolutional neural network

Abstract doi.org/10.14569/IJACSA.2025.0160126 PDF

27

Enhancing Stock Market Forecasting Through a Service-Driven Approach: Microservice System

Author 1: Asaad Algarni

Predicting stock market is a difficult task that involves not just a knowledge of financial measures but also the ability to assess market patterns, investor sentiment, and macroeconomic factors that can affect the movement of stock prices. Traditional stock recommendation systems are built as monolithic applications, with all components closely… Read full abstract & cite →

Stock market microservice architecture deep learning technical indicators sentiment analysis

Abstract doi.org/10.14569/IJACSA.2025.0160127 PDF

28

Improved Whale Optimization Algorithm with LSTM for Stock Index Prediction

Author 1: Yu Sun Author 2: Sofianita Mutalib Author 3: Liwei Tian

After the COVID-19 pandemic, the global economy began to recover. However, stock market fluctuations continue to affect economic stability, making accurate predictions essential. This study proposes an Improved Whale Optimization Algorithm (IWOA) to optimize the parameters of the Long Short-Term Memory (LSTM) model, thereby enhancing stock index predictions. The IWOA… Read full abstract & cite →

Long short-term memory network chaotic mapping dynamic adjustment mechanism improved whale optimization algorithm financial time series forecasting

Abstract doi.org/10.14569/IJACSA.2025.0160128 PDF

29

Multinode LoRa-MQTT of Design Architecture and Analyze Performance for Dual Protocol Network IoT

Author 1: Rizky Rahmatullah Author 2: Hongmin Gao Author 3: Ryan Prasetya Utama Author 4: Puput Dani Prasetyo Adi Author 5: Jannat Mubashir Author 6: Rachmat Muwardi Author 7: Widar Dwi Gustian Author 8: Hanifah Dwiyanti Author 9: Yuliza

LoRaWAN networks and large places do not support Wi-Fi for multiple points. An architecture that offers dual networks to alter their supporting networks is needed for IoT device installation. The novelty in this research is that designing an architecture for multimode LoRa-MQTT with a mechanism for testing LoRa data transmission… Read full abstract & cite →

LoRa MQTT multinode QOS LoRaWAN

Abstract doi.org/10.14569/IJACSA.2025.0160129 PDF

30

Machine Learning-Based Fifth-Generation Network Traffic Prediction Using Federated Learning

Author 1: Mohamed Abdelkarim Nimir Harir Author 2: Edwin Ataro Author 3: Clement Temaneh Nyah

The rapid development and advancement of 5G technologies and smart devices are associated with faster data transmission rates, reduced latency, more network capacity, and more dependability over 4G networks. However, the networks are also more complex due to the diverse range of applications and technologies, massive device connectivity, and dynamic… Read full abstract & cite →

5G Mobile network machine learning federated learning parallel hybrid LSTM+GRU network traffic prediction centralized learning dynamic network condition

Abstract doi.org/10.14569/IJACSA.2025.0160130 PDF

31

CN-GAIN: Classification and Normalization-Denormalization-Based Generative Adversarial Imputation Network for Missing SMES Data Imputation

Author 1: Antonius Wahyu Sudrajat Author 2: Ermatita Author 3: Samsuryadi

Quality data is crucial for supporting the management and development of SMES carried out by the government. However, the inability of SMES actors to provide complete data often results in incomplete dataset. Missing values present a significant challenge to producing quality data. To address this, missing data imputation methods are… Read full abstract & cite →

Missing values GAIN method normalization-denormalization imputation UMKM data

Abstract doi.org/10.14569/IJACSA.2025.0160131 PDF

32

An Agile Approach for Collaborative Inquiry-Based Learning in Ubiquitous Environment

Author 1: Bushra Fazal Khan Author 2: Sohaib Ahmed

The use of collaborative inquiry-based learning has been prevalent in educational contexts particularly in science education. Using such collaborative environments, learners can increase their engagement, knowledge and critical thinking skills about science. With the advancement of technologies, ubiquitous learning environments have been designed for facilitating learning in real-time contexts. Over… Read full abstract & cite →

K12 education agile ubiquitous collaborative learning inquiry based learning

Abstract doi.org/10.14569/IJACSA.2025.0160132 PDF

33

M-COVIDLex: The Construction of a Domain-Specific Mixed Code Sentiment Lexicon

Author 1: Siti Noor Allia Noor Ariffin Author 2: Sabrina Tiun Author 3: Nazlia Omar

Sentiment lexicons serve as essential components in lexicon-based sentiment analysis models. Research on sentiment analysis based on the Malay lexicon indicates that most existing sentiment lexicons for this language are developed from official text corpora, general domain social media text corpora, or domain-specific social media text corpora. Nonetheless, none of… Read full abstract & cite →

Malay social media text mixed-code sentiment lexicon sentiment analysis domain-specific lexicon-based informal Malay Malay part-of-speech public health emergencies COVID-19 Malaysia

Abstract doi.org/10.14569/IJACSA.2025.0160133 PDF

34

Optimized Hybrid Deep Learning for Enhanced Spam Review Detection in E-Commerce Platforms

Author 1: Abdulrahman Alghaligah Author 2: Ahmed Alotaibi Author 3: Qaisar Abbas Author 4: Sarah Alhumoud

Spam reviews represent a real danger to e-commerce platforms, steering consumers wrong and trashing the reputations of products. Conventional Machine learning (ML) methods are not capable of handling the complexity and scale of modern data. This study proposes the novel use of hybrid deep learning (DL) models for spam review… Read full abstract & cite →

Spam review detection CNN-LSTM CNN-RNN CNN-GRU big data deep learning amazon product review dataset

Abstract doi.org/10.14569/IJACSA.2025.0160134 PDF

35

Optimization of Fourth Party Logistics Routing Considering Infection Risk and Delay Risk

Author 1: Guihua Bo Author 2: Sijia Li Author 3: Mingqiang Yin Author 4: Mingkun Chen Author 5: Xin Liu

In the context of the rapid development of e-commerce and the increasing demands for logistics services, particularly in the face of challenges posed by public health emergencies, this paper explores how to integrate supply chain resources and optimize delivery processes. It provides an in-depth analysis of the characteristics of the… Read full abstract & cite →

Logistics services public health emergencies logistics routing optimization improved Q-learning algorithm CVaR infection risk

Abstract doi.org/10.14569/IJACSA.2025.0160135 PDF

36

Convolutional Neural Network and Bidirectional Long Short-Term Memory for Personalized Treatment Analysis Using Electronic Health Records

Author 1: Prasanthi Yavanamandha Author 2: D. S. Rao

Correct precision techniques have far not been introduced for modeling the modality risk in Intensive Care Unit (ICU) patients. Traditional mortality risk prediction techniques effectively extract the data in longitudinal Electronic Health Records (EHRs), that ignore the difficult relationship and interactions among variables and time dependency in longitudinal records. The… Read full abstract & cite →

Bidirectional-long short-term memory circle chaotic map convolutional neural network electronic medical records Intensive Care Unit (ICU) ladybug beetle optimization

Abstract doi.org/10.14569/IJACSA.2025.0160136 PDF

37

Spam Detection Using Dense-Layers Deep Learning Model and Latent Semantic Indexing

Author 1: Yasser D. Al-Otaibi Author 2: Shakeel Ahmad Author 3: Sheikh Muhammad Saqib

In the digital age, online shoppers heavily depend on product feedback and reviews available on the corresponding product pages to guide their purchasing decisions. Feedback is used in sentiment analysis, which is helpful for both customers and company management. Spam feedback can have a negative impact on high-quality products or… Read full abstract & cite →

Spam supervised learning methods unsupervised learning methods LSI dense deep learning

Abstract doi.org/10.14569/IJACSA.2025.0160137 PDF

38

A Deep Learning for Arabic SMS Phishing Based on URLs Detection

Author 1: Sadeem Alsufyani Author 2: Samah Alajmani

The increasing use of SMS phishing messages in Arab communities has created a major security threat, as attackers exploit these SMS services to steal users' sensitive and financial data. This threat highlights the necessity of designing models to detect SMS messages and distinguish between phishing and non-phishing messages. Given the… Read full abstract & cite →

Phishing URL phishing SMS phishing GRU BiGRU CNN

Abstract doi.org/10.14569/IJACSA.2025.0160138 PDF

39

Jordanian Currency Recognition Using Deep Learning

Author 1: Salah Alghyaline

Automatic Currency Recognition (ACR) has a significant role in various domains, such as assessment of visually impaired people, banking transactions, counterfeit detection, digital transformation, currency exchange, vendor machines, etc. Therefore, developing an accurate ACR system enhances efficiency across several domains. The contribution of this paper is three-fold; it proposed a… Read full abstract & cite →

Automatic currency recognition deep learning VGG

Abstract doi.org/10.14569/IJACSA.2025.0160139 PDF

40

Foreground Feature-Guided Camouflage Image Generation

Author 1: Yuelin Chen Author 2: Yuefan An Author 3: Yonsen Huang Author 4: Xiaodong Cai

In the field of visual camouflage, generating a high-quality background image that seamlessly blends with complex foreground objects and diverse background environments is a critical task. When dealing with such complex scenes, the existing techniques have insufficient foreground feature extraction, resulting in insufficient fusion of the generated background image with… Read full abstract & cite →

Camouflage image foreground features object enhancement detail optimization

Abstract doi.org/10.14569/IJACSA.2025.0160140 PDF

41

Adoption of Generative AI-Enhanced Profit Sharing Digital Systems in MSMEs: A Comprehensive Model Analysis

Author 1: Mardiana Andarwati Author 2: Galandaru Swalaganata Author 3: Sari Yuniarti Author 4: Fandi Y. Pamuji Author 5: Edward R. Sitompul Author 6: Kukuh Yudhistiro Author 7: Puput Dani Prasetyo Adi

Adopting digital finance solutions is crucial for enhancing efficiency and competitiveness within the financial services industry, particularly for Micro, Small, and Medium Enterprises (MSMEs). This study examines the factors influencing the use and acceptance of a sharing-based digital system enhanced with a Generative AI website (E-Mudharabah), employing the Technology Acceptance… Read full abstract & cite →

Digital finance Generative AI TAM UTAUT MSMEs

Abstract doi.org/10.14569/IJACSA.2025.0160141 PDF

42

DeepLabV3+ Based Mask R-CNN for Crack Detection and Segmentation in Concrete Structures

Author 1: Yuewei Liu

In order to solve the problem of concrete structure crack detection and segmentation and improve the efficiency of detection and segmentation, this paper proposes a crack detection and segmentation method for concrete structure based on DeepLabV3+ and Mask R-CNN algorithm. Firstly, a crack detection and segmentation scheme is designed by… Read full abstract & cite →

DeepLabV3+ Mask R-CNN concrete structure crack detection and segmentation deep learning algorithm

Abstract doi.org/10.14569/IJACSA.2025.0160142 PDF

43

Multi-Objective Optimization of Construction Project Management Based on NSGA-II Algorithm Improvement

Author 1: Yong Yang Author 2: Jinrui Men

In the building industry, one of the key components to ensuring a project's successful completion is multi-objective project management. However, due to its own limitations, the traditional multi-objective management approach for projects is no longer able to meet the requirements of building construction and urgently needs to be improved. This… Read full abstract & cite →

NSGA-II algorithm improvement strategy construction engineering project management multi-objective optimization

Abstract doi.org/10.14569/IJACSA.2025.0160143 PDF

44

Performance Evaluation of Efficient and Accurate Text Detection and Recognition in Natural Scenes Images Using EAST and OCR Fusion

Author 1: Vishnu Kant Soni Author 2: Vivek Shukla Author 3: S. R. Tandan Author 4: Amit Pimpalkar Author 5: Neetesh Kumar Nema Author 6: Muskan Naik

Scene texts refer to arbitrary text found in images captured by cameras in real-world settings. The tasks of text detection and recognition are critical components of computer vision, with applications spanning scene understanding, information retrieval, robotics, and autonomous driving. Despite significant advancements in deep learning methods, achieving accurate text detection… Read full abstract & cite →

Scene text recognition optical character recognition deep learning feature extraction scene text detection

Abstract doi.org/10.14569/IJACSA.2025.0160144 PDF

45

AI-Powered Learning Pathways: Personalized Learning and Dynamic Assessments

Author 1: Mohammad Abrar Author 2: Walid Aboraya Author 3: Rawad Abdulghafor Author 4: Kabali P Subramanian Author 5: Yousuf Al Husaini Author 6: Mohammed Al Husaini

Integrating artificial intelligence (AI) in education has introduced innovative approaches, particularly in personalized learning and dynamic assessment. Conventional teaching models often struggle to address learners' diverse needs and abilities, underscoring the necessity for AI-driven flexible learning frameworks. This study explores how AI-aided smart learning paths and dynamic assessments enhance learning… Read full abstract & cite →

AI-powered learning adaptive learning dynamic assessments education technology personalized learning pathways student engagement

Abstract doi.org/10.14569/IJACSA.2025.0160145 PDF

46

Feature Reduction and Anomaly Detection in IoT Using Machine Learning Algorithms

Author 1: Adel Hamdan Author 2: Muhannad Tahboush Author 3: Mohammad Adawy Author 4: Tariq Alwada’n Author 5: Sameh Ghwanmeh

Anomaly detection in IoT is a hot topic in cybersecurity. Also, there is no doubt that the increased volume of IoT trading technology increases the challenges it faces. This paper explores several machine-learning algorithms for IoT anomaly detection. The algorithms used are Naïve Bayesian (NB), Support Vector Machine (SVM), Decision… Read full abstract & cite →

Machine learning Internet of Things (IoT) anomaly detection feature reduction Naïve Bayesian (NB) Support Vector Machine (SVM) Decision Tree (DT) XGBoost Random Forest (RF) K-Nearest Neighbor (K-NN)

Abstract doi.org/10.14569/IJACSA.2025.0160146 PDF

47

Network Security Based on GCN and Multi-Layer Perception

Author 1: Wei Yu Author 2: Huitong Liu Author 3: Yu Song Author 4: Jiaming Wang

With the continuous progress of network technology, network security has become a critical issue at present. There are already many network security intrusion detection models, but these detection models still have problems such as low detection accuracy and long interception time of intrusion information. To address these drawbacks, this study… Read full abstract & cite →

Network security graph convolutional network multi-layer perceptron intrusion detection model

Abstract doi.org/10.14569/IJACSA.2025.0160147 PDF

48

An Ensemble Semantic Text Representation with Ontology and Query Expansion for Enhanced Indonesian Quranic Information Retrieval

Author 1: Liza Trisnawati Author 2: Noor Azah Binti Samsudin Author 3: Shamsul Kamal Bin Ahmad Khalid Author 4: Ezak Fadzrin Bin Ahmad Shaubari Author 5: Sukri Author 6: Zul Indra

This study explores the effectiveness of an ensemble method for Quranic text retrieval, aimed at improving the relevance and accuracy of verses retrieved for specific themes. The ensemble approach integrates three semantic models—Word2Vec, FastText, and GloVe—through a voting mechanism that considers verse frequency and semantic alignment with the query topics… Read full abstract & cite →

Ensemble method query expansion ontology Al-Quran search engine

Abstract doi.org/10.14569/IJACSA.2025.0160148 PDF

49

A Review of Reinforcement Learning Evolution: Taxonomy, Challenges and Emerging Solutions

Author 1: Ji Loun Tan Author 2: Bakr Ahmed Taha Author 3: Norazreen Abd Aziz Author 4: Mohd Hadri Hafiz Mokhtar Author 5: Muhammad Mukhlisin Author 6: Norhana Arsad

Reinforcement Learning (RL) has become a rapidly advancing field inside Artificial Intelligence (AI) and self-sufficient structures, revolutionizing the manner in which machines analyze and make selections. Over the past few years, RL has advanced notably with the improvement of more sophisticated algorithms and methodologies that address increasingly complicated actual-world troubles… Read full abstract & cite →

Artificial intelligence autonomous systems decision-making optimization reinforcement learning robotics

Abstract doi.org/10.14569/IJACSA.2025.0160149 PDF

50

Towards Transparent Traffic Solutions: Reinforcement Learning and Explainable AI for Traffic Congestion

Author 1: Shan Khan Author 2: Taher M. Ghazal Author 3: Tahir Alyas Author 4: M. Waqas Author 5: Muhammad Ahsan Raza Author 6: Oualid Ali Author 7: Muhammad Adnan Khan Author 8: Sagheer Abbas

This study introduces a novel approach to traffic congestion detection using Reinforcement Learning (RL) of machine learning classifiers enhanced by Explainable Artificial Intelligence (XAI) techniques in Smart City (SC). Conventional traffic management systems rely on static rules, and heuristics face challenges in dynamically addressing urban traffic problems' complexities. This study… Read full abstract & cite →

Reinforcement learning Explainable Artificial Intelligence (XAI) Smart City (SC) IoT Machine Learning (ML)

Abstract doi.org/10.14569/IJACSA.2025.0160150 PDF

51

Strategic Supplier Selection in Advanced Automotive Production: Harnessing AHP and CRNN for Optimal Decision-Making

Author 1: Karim Haricha Author 2: Azeddine Khiat Author 3: Yassine Issaoui Author 4: Ayoub Bahnasse Author 5: Hassan Ouajji

This study presents a novel supplier selection methodology that integrates the Analytic Hierarchy Process (AHP) with a Convolutional Recurrent Neural Network (CRNN) to address the complexities of decision-making in dynamic industrial environments. The AHP component provides a systematic and transparent framework for evaluating many factors, ensuring consistency and minimizing subjective… Read full abstract & cite →

Supplier selection analytic hierarchy process convolutional recurrent neural network sustainability decision-making

Abstract doi.org/10.14569/IJACSA.2025.0160151 PDF

52

Understanding Art Deeply: Sentiment Analysis of Facial Expressions of Graphic Arts Using Deep Learning

Author 1: Fei Wang

Art serves as a profound medium for humans to express and present their thoughts, emotions, and experiences in aesthetically and captivating means. It is like a universal language transcending the limitations of language enabling communication of complex ideas and feelings. Artificial Intelligence (AI) based data analytics are being applied for… Read full abstract & cite →

Artificial intelligence deep learning sentiment analysis art detection image processing convolutional network

Abstract doi.org/10.14569/IJACSA.2025.0160152 PDF

53

A Hybrid Transformer-ARIMA Model for Forecasting Global Supply Chain Disruptions Using Multimodal Data

Author 1: Qingzi Wang

This study presents a robust forecasting model for global supply chain disruptions: port delays, natural disasters, geopolitical events, and pandemics. An integrated solution combining the help of transformer-based models for unstructured textual data preprocessing and ARIMA for structured time series analysis is referred to as a hybrid model. This model… Read full abstract & cite →

Supply chain disruptions forecasting models hybrid model transformer architecture ARIMA multimodal data integration

Abstract doi.org/10.14569/IJACSA.2025.0160153 PDF

54

Marine Predator Algorithm and Related Variants: A Systematic Review

Author 1: Emmanuel Philibus Author 2: Azlan Mohd Zain Author 3: Didik Dwi Prasetya Author 4: Mahadi Bahari Author 5: Norfadzlan bin Yusup Author 6: Rozita Abdul Jalil Author 7: Mazlina Abdul Majid Author 8: Azurah A Samah

The Marine Predators Algorithm (MPA) is classified under swarm intelligence methods based on its type of inspiration. It is a population-based metaheuristic optimization algorithm inspired by the general foraging behavior exhibited in the form of Levy and Brownian motion in ocean predators supported by the policy of optimum success rate… Read full abstract & cite →

Exploitation-exploration marine predator algorithm metaheuristic algorithms metaheuristic-hybridization meta-heuristics optimization predator prey systems

Abstract doi.org/10.14569/IJACSA.2025.0160154 PDF

55

The Current Challenges Review of Deep Learning-Based Nuclei Segmentation of Diffuse Large B-Cell Lymphoma

Author 1: Gei Ki Tang Author 2: Chee Chin Lim Author 3: Faezahtul Arbaeyah Hussain Author 4: Qi Wei Oung Author 5: Aidy Irman Yazid Author 6: Sumayyah Mohammad Azmi Author 7: Haniza Yazid Author 8: Yen Fook Chong

Diffuse Large B-Cell Lymphoma stands as the most prevalent form of non-Hodgkin lymphoma worldwide, constituting approximately 30 percent of cases within this diverse group of blood cancers affecting the lymphatic system. This study addresses the challenges associated with the accurate DLBCL segmentation and classification, including difficulties in identifying and diagnosing… Read full abstract & cite →

Deep learning Diffuse Large B-Cell Lymphoma (DLBCL) lymphoma cancer HoVerNet

Abstract doi.org/10.14569/IJACSA.2025.0160155 PDF

56

User Interface Design of Digital Test Based on Backward Chaining as a Measuring Tool for Students’ Critical Thinking

Author 1: I Putu Wisna Ariawan Author 2: P. Wayan Arta Suyasa Author 3: Agus Adiarta Author 4: I Komang Gede Sukawijana Author 5: Nyoman Santiyadnya Author 6: Dewa Gede Hendra Divayana

Assessing students' critical thinking skills is challenging due to the limitations of current measurement tools. Therefore, there is a need for a digital testing instrument that can effectively evaluate students' critical thinking abilities. The proposed digital test should be designed to present questions in a tiered manner, using a backward… Read full abstract & cite →

User interface design digital test backward chaining critical thinking differentiated learning

Abstract doi.org/10.14569/IJACSA.2025.0160156 PDF

57

Early Alzheimer’s Disease Detection Through Targeting the Feature Extraction Using CNNs

Author 1: D Prasad Author 2: K Jayanthi Author 3: Pradeep Tilakan

Alzheimer's Disease (AD) is a persistent, irreversible, and degenerative neurological disorder of the brain that currently has no effective therapy. This condition is identified by pathological abnormalities in the hippocampal area, which may develop up to 10 years prior to the onset of clinical symptoms. Timely detection of pathogenic abnormalities… Read full abstract & cite →

Alzheimer's Disease (AD) convolutional neural networks (CNN) Support Vector Machine (SVM) Directed Acyclic Graph (DAG) Late Mild Cognitive Impairment (LMCI) Alzheimer's Disease Neuroimaging Initiative (ADNI)

Abstract doi.org/10.14569/IJACSA.2025.0160157 PDF

58

Enhancement of Coastline Video Monitoring System Using Structuring Element Morphological Operations

Author 1: I Gusti Ngurah Agung Pawana Author 2: I Made Oka Widyantara Author 3: Made Sudarma Author 4: Dewa Made Wiharta Author 5: Made Widya Jayantari

Coastal monitoring is vital in environmental management, disaster mitigation, and addressing climate change impacts. Traditional methods are time-consuming and error-prone, prompting the need for innovative systems. This study introduces the Coastal Video Monitoring System (CoViMos), a novel framework for real-time shoreline detection in tropical regions, specifically at Kedonganan Beach, Bali… Read full abstract & cite →

Coastline detection image processing Video Monitoring System (CoViMoS) morphological operations

Abstract doi.org/10.14569/IJACSA.2025.0160158 PDF

59

Application of MLP-Mixer-Based Image Style Transfer Technology in Graphic Design

Author 1: Qibin Wang Author 2: Xiao Chen Author 3: Huan Su

The rapid advancement of the digital creative industry has highlighted the growing importance of image style transfer technology as a bridge between traditional art and modern design, driving innovation in graphic design. However, conventional style transfer methods face significant challenges, including low computational efficiency and unnatural style transformation in complex… Read full abstract & cite →

MLP-Mixer image style transfer graphic design neural networks artistic rendering

Abstract doi.org/10.14569/IJACSA.2025.0160159 PDF

60

Integrating Blockchain and Edge Computing: A Systematic Analysis of Security, Efficiency, and Scalability

Author 1: Youness Bentayeb Author 2: Kenza Chaoui Author 3: Hassan Badir

The integration of blockchain and edge computing presents a transformative potential to enhance security, computing efficiency, and data privacy across diverse industries. This paper begins with an overview of blockchain and edge computing, establishing the foundational technologies for this synergy. It explores the key benefits of their integration, such as… Read full abstract & cite →

Blockchain edge computing security computing efficiency data privacy

Abstract doi.org/10.14569/IJACSA.2025.0160160 PDF

61

Enhancing COVID-19 Detection in X-Ray Images Through Deep Learning Models with Different Image Preprocessing Techniques

Author 1: Ahmad Nuruddin bin Azhar Author 2: Nor Samsiah Sani Author 3: Liu Luan Xiang Wei

The identification of COVID-19 using chest X-ray (CXR) images plays a critical role in managing the pandemic by providing a rapid, non-invasive, and accessible diagnostic tool. This study evaluates the impact of different image preprocessing techniques on the performance of deep learning models for COVID-19 classification based on COVID-19 Radiography… Read full abstract & cite →

X-ray COVID-19 image enhancement Contrast Limited Adaptive Histogram Equalization Histogram Equalization

Abstract doi.org/10.14569/IJACSA.2025.0160161 PDF

62

Deep Learning-Based Automatic Cultural Translation Method for English Tourism

Author 1: Jianguo Liu Author 2: Ruohan Liu

The general LSTM-based encoder-decoder model has the problems of not being able to mine the sentence semantics and translate long text sequences. This study presents a neural machine translation model utilizing LSTM with improved attention, incorporating multi-head attention and multi-skipping attention mechanisms into the LSTM baseline model. By adding multi-head… Read full abstract & cite →

LSTM-based encoder-decoder model tourism English culture automatic translation enhanced attention mechanism

Abstract doi.org/10.14569/IJACSA.2025.0160162 PDF

63

A Novel Metric-Based Counterfactual Data Augmentation with Self-Imitation Reinforcement Learning (SIL)

Author 1: K. C. Sreedhar Author 2: T. Kavya Author 3: J. V. S. Rajendra Prasad Author 4: V. Varshini

The inherent biases present in language models often lead to discriminatory predictions based on demographic attributes. Fairness in NLP refers to the goal of ensuring that language models and other NLP systems do not produce biased or discriminatory outputs that could negatively affect individuals or groups. Bias in NLP models… Read full abstract & cite →

Natural language processing fairness robustness Word Embedding Association Test (WEAT) SMART testing

Abstract doi.org/10.14569/IJACSA.2025.0160163 PDF

64

Segmentation of Nano-Particles from SEM Images Using Transfer Learning and Modified U-Net

Author 1: Sowmya Sanan V Author 2: Rimal Isaac R S

Nanomaterials, owing to their distinctive features, are crucial across numerous scientific domains, especially in materials science and nanotechnology. Precise segmentation of Scanning Electron Microscope (SEM) images is essential for evaluating attributes such as nanoparticle dimensions, morphology, and distribution. Conventional image segmentation techniques frequently prove insufficient for managing the intricate textures… Read full abstract & cite →

Nanomaterial segmentation ResNet 50 modified UNet transfer learning SEM

Abstract doi.org/10.14569/IJACSA.2025.0160164 PDF

65

Application of Big Data Mining System Integrating Spectral Clustering Algorithm and Apache Spark Framework

Author 1: Yuansheng Guo

Spectral clustering algorithm is a highly effective clustering algorithm with broad application prospects in data mining. To improve the efficient data processing capability of big data mining systems, a big data mining system that integrates spectral clustering algorithm and Apache Spark framework is proposed. It is applied in the big… Read full abstract & cite →

Spectral clustering algorithm apache spark big data data mining

Abstract doi.org/10.14569/IJACSA.2025.0160165 PDF

66

Large Language Models for Academic Internal Auditing

Author 1: Houda CHAMMAA Author 2: Rachid ED-DAOUDI Author 3: Khadija BENAZZI

This research examines the application of Artificial Intelligence in internal auditing, focusing on document management and information retrieval in academic institutions. The study proposes using Large Language Models to streamline document processing during audit preparation, addressing inefficiencies in traditional document handling methods. Through experimental evaluation of three embedding models (BGE-M3… Read full abstract & cite →

Large language models internal auditing information retrieval embedding models academic institutions

Abstract doi.org/10.14569/IJACSA.2025.0160166 PDF

67

Enhanced Facial Expression Recognition Based on ResNet50 with a Convolutional Block Attention Module

Author 1: Liu Luan Xiang Wei Author 2: Nor Samsiah Sani

Deep learning techniques are becoming increasingly important in the field of facial expression recognition, especially for automatically extracting complex features and capturing spatial layers in images. However, previous studies have encountered challenges such as complex data sets, limited model generalization, and lack of comprehensive comparative analysis of feature extraction methods… Read full abstract & cite →

Data science computer vision deep learning facial expression recognition

Abstract doi.org/10.14569/IJACSA.2025.0160167 PDF

68

YOLO-WP: A Lightweight and Efficient Algorithm for Small-Target Detection in Weld Seams of Small-Diameter Stainless Steel Pipes

Author 1: Huaishu Hou Author 2: Yukun Sun Author 3: Chaofei Jiao

To address the low detection efficiency and high computational resource demands of current welded pipe defect detection algo-rithms for small target defects, this paper proposes the YO-LO-WP algorithm based on YOLOv5s. The improvements of YOLO-WP are mainly reflected in the following aspects: First, an innovative GhostFusion architecture is introduced in… Read full abstract & cite →

Welded pipe lightweight model defect detection deep learning feature extraction attention mechanism

Abstract doi.org/10.14569/IJACSA.2025.0160168 PDF

69

Determination of Pre Coding Elements and Activities for a Pre Coding Program Model for Kindergarten Children Using the Fuzzy Delphi Method (FDM)

Author 1: Siti Naimah Rahman Author 2: Norly Jamil Author 3: Intan Farahana Abdul Rani Author 4: Hafizul Fahri Hanafi

Computational thinking (CT) skills are becoming increasingly crucial in education, particularly in early childhood education. Pre coding, which involves hands-on activities with real objects, has been shown to be quite effective in fostering kindergarten children's computational skills. Pre coding, on the other hand, is essential for boosting children’s CT skills… Read full abstract & cite →

Expert consensus pre coding element activity kindergarten children

Abstract doi.org/10.14569/IJACSA.2025.0160169 PDF

70

A Novel Internet of Things and Cloud Computing-Driven Deep Learning Framework for Disease Prediction and Monitoring

Author 1: Bo GUO Author 2: Lei NIU

In smart cities, the e-healthcare systems aided by Internet of Things (IoT) technologies play a significant role in proficient health monitoring services. The sensitivity and number of users in health networks highlights the necessity of treating security attacks. In the era of rapid internet connectivity and cloud computing services, patient… Read full abstract & cite →

IoT-driven healthcare deep learning fuzzy entropy secure data storage cryptography

Abstract doi.org/10.14569/IJACSA.2025.0160170 PDF

71

Comparison of Artificial Neural Network and Long Short-Term Memory for Modelling Crude Palm Oil Production in Indonesia

Author 1: Brodjol Sutijo Suprih Ulama Author 2: Robi Ardana Putra Author 3: Fausania Hibatullah Author 4: Mochammad Reza Habibi Author 5: Mochammad Abdillah Nafis

Indonesia is one of the largest producers and exporters of Crude Palm Oil (CPO), making CPO production crucial to the country's economic stability. Accurate forecasting of CPO production is essential for effective inventory management, export-import strategy, and economic planning. Traditional time series methods like ARIMA have limitations in modeling nonlinear… Read full abstract & cite →

Artificial Neural Network (ANN) Crude Palm Oil (CPO) Long Short-Term Memory (LSTM)

Abstract doi.org/10.14569/IJACSA.2025.0160171 PDF

72

Enhanced Jaya Algorithm for Quality-of-Service-Aware Service Composition in the Internet of Things

Author 1: Yan SHI

The Internet of Things (IoT) has shifted how devices and services interact, resulting in diverse innovations ranging from health and smart cities to industrial automation. Nevertheless, at its core, IoT continues to face one of the major tough tasks of Quality of Service-aware Service Composition (QoS-SC), as these IoT settings… Read full abstract & cite →

Service composition internet of things quality of service Jaya algorithm optimization

Abstract doi.org/10.14569/IJACSA.2025.0160172 PDF

73

Enhancing Facial Expressiveness in 3D Cartoon Animation Faces: Leveraging Advanced AI Models for Generative and Predictive Design

Author 1: Langdi Liao Author 2: Lei Kang Author 3: Tingli Yue Author 4: Aiting Zhou Author 5: Ming Yang

An advanced system for facial landmark detection and 3D facial animation rigging is proposed, utilizing deep learning algorithms to accurately detect key facial points, such as the eyes, mouth, and eyebrows. These landmarks enable precise rigging of 3D models, facilitating realistic and controlled facial expressions. The system enhances animation efficiency… Read full abstract & cite →

Facial landmark detection 3D animation deep learning AI-assisted rigging emotion recognition

Abstract doi.org/10.14569/IJACSA.2025.0160173 PDF

74

A Lightweight Anonymous Identity Authentication Scheme for the Internet of Things

Author 1: Zhengdong Deng Author 2: Xuannian Lei Author 3: Junyu Liang Author 4: Hang Xu Author 5: Zhiyuan Zhu Author 6: Na Lin Author 7: Zhongwei Li Author 8: Jingqi Du

With the rapid growth of Internet of Things (IoT) devices, many of which are resource-constrained and vulnerable to attacks, current identity authentication methods are often too resource-intensive to provide adequate security. This paper proposes an efficient identity authentication scheme that integrates Physical Unclonable Functions (PUFs), Chebyshev chaotic maps, and fuzzy… Read full abstract & cite →

Internet of Things identity authentication Physical Unclonable Functions fuzzy extractors chaotic maps

Abstract doi.org/10.14569/IJACSA.2025.0160174 PDF

75

Comparative Analysis of Feature Selection Based on Metaheuristic Methods for Human Heart Sounds Classification Using PCG Signal

Author 1: Motaz Faroq A Ben Hamza Author 2: Nilam Nur Amir Sjarif

Cardiovascular disease is a critical threat to human health, as most death cases are due to heart disease. Although several doctors employ stethoscopes to auscultate heart sounds to detect abnormalities, the accuracy of the approach is considerably dependent upon the experience and skills of the physician. Consequently, optimal methods are… Read full abstract & cite →

Cardiovascular Diseases (CVDs) Phonocardiogram (PCG) signal processing Wavelet Scattering Transform (WST) Metaheuristic Methods Harris Hawks Optimisation (HHO) Dragonfly Algorithm (DA) Grey Wolf Optimiser (GWO) Salp Swarm Algorithm (SSA) Whale Optimisation Algorithm (WOA) Bidirectional Long Short-Term Memory (Bi-LSTM)

Abstract doi.org/10.14569/IJACSA.2025.0160175 PDF

76

Developing an Integrated Platform to Track Real Time Football Statistics for Somali Football Federation (SFF)

Author 1: Bashir Abdinur Ahmed Author 2: Husein Abdirahman Hashi Author 3: Abdifatah Abdilatif Ahmed Author 4: Abdikani Mahad Ali

The integration of technology in sports has revolutionized how stakeholders interact with and perceive the game. This thesis presents the development of an integrated platform aimed at tracking real-time football statistics for the Somali Football Federation (SFF). Football, being one of the most popular sports globally, relies heavily on accurate… Read full abstract & cite →

Real-time football statistics Integrated sports platform Somali Football Federation (SFF) user engagement sports technology

Abstract doi.org/10.14569/IJACSA.2025.0160176 PDF

77

Elevator Abnormal State Detection Based on Vibration Analysis and IF Algorithm

Author 1: Zhaoxiu Wang

Elevators play a crucial role in daily life, and their safety directly impacts the personal and property safety of users. To detect abnormal states of elevators and ensure people's personal safety, the acceleration signal of elevators is decomposed and Weiszfeld algorithm is used to estimate gravity acceleration. In addition, the… Read full abstract & cite →

Vibration analysis IF algorithm elevator abnormal detection

Abstract doi.org/10.14569/IJACSA.2025.0160177 PDF

78

LFM Book Recommendation Based on Fusion of Time Information and K-Means

Author 1: Dawei Ji

To meet the growing demand in the field of book recommendation, the research focuses on meeting the personalized needs, behavioral patterns, and interests of readers. A book recommendation algorithm that combines K-means clustering with time information is proposed to provide more convenient and efficient book recommendation services and enhance readers'… Read full abstract & cite →

Book recommendation K-means time information latent factor model preference matrix

Abstract doi.org/10.14569/IJACSA.2025.0160178 PDF

79

A Proposed Approach for Agile IoT Smart Cities Transformation– Intelligent, Fast and Flexible

Author 1: Othman Asiry Author 2: Ayman E. Khedr Author 3: Amira M. Idrees

Smart city architectures have been varying from one community to another. Each community leader develops their own perspective of smart cities. Some of these communities focus on data management, while others focus on provided services and infrastructure. In this research, an attempt to propose a clear, complete, and efficient perspective… Read full abstract & cite →

Smart city agility Internet of Things cloud computing intelligent systems

Abstract doi.org/10.14569/IJACSA.2025.0160179 PDF

80

A Novel Optimization Strategy for CNN Models in Palembang Songket Motif Recognition

Author 1: Yohannes Author 2: Muhammad Ezar Al Rivan Author 3: Siska Devella Author 4: Tinaliah

Palembang Songket is an essential part of Indonesian cultural heritage, and its introduction and preservation present challenges, particularly in recognizing various motifs. This research introduces a novel strategy to optimize the performance of Convolutional Neural Networks (CNNs) by presenting a hierarchical integration of Ghost Module operations and Max Pooling, referred… Read full abstract & cite →

Convolutional neural network ghost module palembang songket motif recognition

Abstract doi.org/10.14569/IJACSA.2025.0160180 PDF

81

A Novel Hybrid Algorithm Based on Butterfly and Flower Pollination Algorithms for Scheduling Independent Tasks on Cloud Computing

Author 1: Huiying SHAO

Cloud computing is an Internet-based computing paradigm where virtual servers or workstations are offered as platforms, software, infrastructure, and resources. Task scheduling is considered one of the major NP-hard problems in cloud environments, posing several challenges to efficient resource allocation. Many metaheuristic algorithms have been extensively employed to address these… Read full abstract & cite →

Task scheduling cloud computing butterfly optimization algorithm flower pollination algorithm mutualism

Abstract doi.org/10.14569/IJACSA.2025.0160181 PDF

82

Task Scheduling in Fog Computing-Powered Internet of Things Networks: A Review on Recent Techniques, Classification, and Upcoming Trends

Author 1: Dongge TIAN

The Internet of Things (IoT) phenomenon influences daily activities by transforming physical equipment into smart objects. The IoT has achieved a wealth of technological innovations that were previously unimaginable. IoT application areas cover various sectors, including medical care, home automation, smart grids, and industrial operations. The massive growth of IoT… Read full abstract & cite →

Internet of Things task scheduling fog computing quality of service network congestion optimization

Abstract doi.org/10.14569/IJACSA.2025.0160182 PDF

83

A System Dynamics Model of Frozen Fish Supply Chain

Author 1: Leni Herdiani Author 2: Maun Jamaludin Author 3: Iman Sudirman Author 4: Widjajani Author 5: Ismet Rohimat

The system dynamics methodology examines the intricate behaviors of complex systems through time, incorporating inventories, transfers, feedback cycles, lookup functions, and temporal delays. In fisheries systems, the interaction between resources and management entities is intricate, with the dynamics of fisheries significantly influencing the formulation of effective policies. Fisheries hold a… Read full abstract & cite →

Supply chain system dynamics frozen fish six sub-models simulation policy scenario

Abstract doi.org/10.14569/IJACSA.2025.0160183 PDF

84

Methodological Review of Social Engineering Policy Model for Digital Marketing

Author 1: Wenni Syafitri Author 2: Zarina Shukur Author 3: Umi Asma’ Mokhtar Author 4: Rossilawati Sulaiman

Social engineering attacks are recognized as human-based threats and continue to increase, despite studies focusing on prevention methods that do not rely on the human aspect. The impacts of these attacks are felt across various industries and organizations. To solve this issue, a social engineering policy model must be proposed… Read full abstract & cite →

Digital marketing social engineering attack prevention review study security policy model

Abstract doi.org/10.14569/IJACSA.2025.0160184 PDF

85

Comprehensive Bibliometric Literature Review of Chatbot Research: Trends, Frameworks, and Emerging Applications

Author 1: Nazruddin Safaat Harahap Author 2: Aslina Saad Author 3: Nor Hasbiah Ubaidullah

This study aims to conduct a comprehensive bibliometric literature review of chatbot research by examining key trends, frameworks, and influential applications across various domains. It seeks to map the evolution of chatbot technologies, identify influential works, and analyze how the research focus has shifted over time, particularly towards AI-driven chatbot… Read full abstract & cite →

Chatbot research bibliometric literature review retrieval and generative trend visualization

Abstract doi.org/10.14569/IJACSA.2025.0160185 PDF

86

Application of Collaborative Filtering Optimization Algorithm Based on Semantic Relationships in Interior Design

Author 1: Kai Zhao Author 2: Lei Wang

Due to the diversity of interior design, it is difficult for users to mine target data, so personalized recommendation systems for users are particularly important. Therefore, an optimized collaborative filtering recommendation system is proposed. Firstly, a random walk recommendation model based on category combination space is constructed, abandoning the traditional… Read full abstract & cite →

Semantic relationships category combination space random walks collaborative filtering temporal recommendations

Abstract doi.org/10.14569/IJACSA.2025.0160186 PDF

87

Hybrid Clustering Framework for Scalable and Robust Query Analysis: Integrating Mini-Batch K-Means with DBSCAN

Author 1: Sridevi K N Author 2: Rajanna M

Query clustering is a significant task in information retrieval. Research gaps still exist due to high-dimensional datasets, noise detection, and cluster interpretability. Solving these challenges will support large language models with faster and more efficient responses. This study aims to develop a hybrid clustering approach combining Mini-Batch K-means (MBK) and… Read full abstract & cite →

Hybrid clustering information retrieval mini-batch k-means query analysis

Abstract doi.org/10.14569/IJACSA.2025.0160187 PDF

88

Modified Moth-Flame Optimization Algorithm for Service Composition in Cloud Computing Environments

Author 1: Yeling YANG Author 2: Miao SONG

Cloud computing service composition integrates services, distributed and diverse by nature, into an integrated entity that can meet a user's requirement with better effectiveness. However, some obstacles regarding high latency and suboptimal Quality of Service (QoS) still exist in a dynamic multi-cloud environment. This study addresses the limitations of traditional… Read full abstract & cite →

Cloud computing quality of service service composition edge cloud moth-flame optimization

Abstract doi.org/10.14569/IJACSA.2025.0160188 PDF

89

Enhanced Task Scheduling Algorithm Using Harris Hawks Optimization Algorithm for Cloud Computing

Author 1: Fang WANG

Amongst the most transformational technologies nowadays, cloud computing can provide resources such as CPU, memory, and storage over secure internet connections. Due to its flexibility and resource availability with guaranteed QoS, cloud computing allows comprehensive business and research adoptions. Despite the rapid development, resource management remains one of the significant… Read full abstract & cite →

Cloud computing optimization task scheduling Harris Hawks Optimization resource allocation quality of service

Abstract doi.org/10.14569/IJACSA.2025.0160189 PDF

90

PCE-BP: Polynomial Chaos Expansion-Based Bagging Prediction Model for the Data Modeling of Combine Harvesters

Author 1: Liangyi Zhong Author 2: Mengnan Deng Author 3: Maolin Shi Author 4: Ting Lou Author 5: Shaoyang Zhu Author 6: Jingwen Zhan Author 7: Zishang Li Author 8: Yi Ding

With the rapid developments of measurement and monitoring techniques, massive amounts of in-situ data have been recorded and collected from the measurement system of combine harvesters in their working process and/or field experiments. However, the relationship between the operation parameters and the performance index such as clearing loss usually changes… Read full abstract & cite →

Combine harvester data modeling polynomial chaos expansion decision tree bagging

Abstract doi.org/10.14569/IJACSA.2025.0160190 PDF

91

Detecting Emotions with Deep Learning Models: Strategies to Optimize the Work Environment and Organizational Productivity

Author 1: Cantuarias Valdivia Luis Alberto de Jesús Author 2: Gómez Human Javier Junior Author 3: Sierra-Liñan Fernando

This study proposes the implementation of a facial emotion recognition system based on Convolutional Neural Networks to detect emotions in real time, aiming to optimize the workplace environment and enhance organizational productivity. Six deep learning models were evaluated: Standard CNN, AlexNet, VGG16, InceptionV3, ResNet152 and DenseNet201, with DenseNet201 achieving the… Read full abstract & cite →

Facial recognition real-time emotions convolutional neural networks work environment artificial intelligence in human resources

Abstract doi.org/10.14569/IJACSA.2025.0160191 PDF

92

Sentiment and Emotion Analysis with Large Language Models for Political Security Prediction Framework

Author 1: Liyana Safra Zaabar Author 2: Adriana Arul Yacob Author 3: Mohd Rizal Mohd Isa Author 4: Muslihah Wook Author 5: Nor Asiakin Abdullah Author 6: Suzaimah Ramli Author 7: Noor Afiza Mat Razali

The increasing spread of textual content on social media, driven by the rise of Large Language Models (LLMs), has highlighted the importance of sentiment analysis in detecting threats, racial abuse, violence, and implied warnings. The subtlety and ambiguity of language present challenges in developing effective frameworks for threat detection, particularly… Read full abstract & cite →

Political security large language models sentiment analysis emotion analysis BERT threat prediction

Abstract doi.org/10.14569/IJACSA.2025.0160192 PDF

93

Text-to-Image Generation Method Based on Object Enhancement and Attention Maps

Author 1: Yongsen Huang Author 2: Xiaodong Cai Author 3: Yuefan An

In the task of text-to-image generation, common issues such as missing objects in the generated images often arise due to the model's insufficient learning of multi-object category information and the lack of consistency between the text prompts and the generated image contents. To address these challenges, this paper proposes a… Read full abstract & cite →

Multi-object category text-to-image generation object enhancement attention maps

Abstract doi.org/10.14569/IJACSA.2025.0160193 PDF

94

Enhanced Traffic Congestion Prediction Using Attention-Based Multi-Layer GRU Model with Feature Embedding

Author 1: Sreelekha M Author 2: Midhunchakkaravarthy Janarthanan

Intelligent Transportation Systems (ITS) are crucial for managing urban mobility and addressing traffic congestion, which poses significant challenges to modern cities. Traffic congestion leads to increased travel times, pollution, and fuel consumption, impacting both the environment and quality of life. Traditional traffic management solutions often fall short in predicting and… Read full abstract & cite →

Intelligent transportation system traffic congestion urban mobility deep learning gated recurrent unit

Abstract doi.org/10.14569/IJACSA.2025.0160194 PDF

95

Robust Joint Detection of Coronary Artery Plaque and Stenosis in Angiography Using Enhanced DCNN-GAN

Author 1: M. Jayasree Author 2: L. Koteswara Rao

Timely detection and diagnosis of coronary artery segment plaque and stenosis in X-ray angiography is of great significance, however, the image quality variation, noise, and artifacts in the original image cause definitive difficulties to the current algorithms. These problems pose a challenge to meaningful analysis via traditional approaches, which compromises… Read full abstract & cite →

DCNN-GAN angiography coronary artery plaque stenosis joint conditional detection

Abstract doi.org/10.14569/IJACSA.2025.0160195 PDF

96

Design and Research of Accounting Automation Management System Based on Swarm Intelligence Algorithm and Deep Learning

Author 1: Dan Gui Author 2: Wei Ma Author 3: Wanfei Chen

In the current research, the application verification of traditional algorithms in actual accounting management is insufficient, and deep learning data processing capabilities need to be fully optimized in complex accounting scenarios. Given the challenges of efficiency and accuracy faced by the current accounting industry in the context of big data… Read full abstract & cite →

Swarm intelligence algorithm deep learning accounting automation management

Abstract doi.org/10.14569/IJACSA.2025.0160196 PDF

97

Enhancing Road Safety: A Multi-Modal Drowsiness Detection System for Drivers

Author 1: Guirrou Hamza Author 2: Mohamed Zeriab Es-Sadek Author 3: Youssef Taher

Driver drowsiness is a major contributing factor in road accidents, emphasizing the need for enhanced detection measures to improve car safety. This paper describes a multi-modal fatigue detection system that uses data from an internal camera, a front camera, and vehicle factors to reliably assess driver alertness. The technology outperforms… Read full abstract & cite →

Component fatigue detection drowsiness monitoring ADAS

Abstract doi.org/10.14569/IJACSA.2025.0160197 PDF

98

Decoding Face Attributes: A Modified AlexNet Model with Emphasis on Correlation-Heterogeneity Relationship Between Facial Attributes

Author 1: Abdelaali Benaiss Author 2: Otman Maarouf Author 3: Rachid El Ayachi Author 4: Mohamed Biniz Author 5: Mustapha Oujaoura

Face attribute estimation has several applications in computer vision, biometric systems, face verification /identification and image retrieval. The performance of face attribute estimation has been improved by using machine learning algorithms. In recent years, most algorithms have addressed this problem in multiple binary problem. Specifically, CNN-based approaches, which we can… Read full abstract & cite →

Face attribute estimation biometrics Convolutional Neural Network (CNN) face verification computer vision

Abstract doi.org/10.14569/IJACSA.2025.0160198 PDF

99

Evaluation of Eye Movement Features and Visual Fatigue in Virtual Reality Games

Author 1: Yuwei Ji

VR games make people happy physically and mentally, but also lead to eye health problems. At present, the existing VR systems lack fatigue detection technology, which makes it difficult to help users use their eyes reasonably. In order to improve the user experience of VR gamers, this paper proposes a… Read full abstract & cite →

Virtual reality games eye movement features visual fatigue

Abstract doi.org/10.14569/IJACSA.2025.0160199 PDF

100

High-Accuracy Vehicle Detection in Different Traffic Densities Using Improved Gaussian Mixture Model with Cuckoo Search Optimization

Author 1: Nor Afiqah Mohd Aris Author 2: Siti Suhana Jamaian

Background subtraction plays a critical role in computer vision, particularly in vehicle detection and tracking. Traditional Gaussian Mixture Models (GMM) face limitations in dynamic traffic scenarios, leading to inaccuracies. This study proposes an Improved GMM with adaptive time-varying learning rates, exponential decay, and outlier processing to enhance performance across light… Read full abstract & cite →

Gaussian mixture model vehicle detection adaptive time-varying learning rate exponential decay outlier processing cuckoo search optimization

Abstract doi.org/10.14569/IJACSA.2025.01601100 PDF

101

PSR: An Improvement of Lightweight Cryptography Algorithm for Data Security in Cloud Computing

Author 1: P. Sri Ram Chandra Author 2: Syamala Rao Author 3: Naresh K Author 4: Ravisankar Malladi

Data security in cloud storage is a pressing concern as organizations increasingly rely on cloud computing services. Transitioning to cloud-based solutions underscores the need to safeguard sensitive information against data breaches and unauthorized access. Traditional cryptography algorithms are vulnerable to brute-force attacks and mathematical breakthroughs, necessitating large key sizes for… Read full abstract & cite →

Cryptography cloud security PSR encryption decryption avalanche effect

Abstract doi.org/10.14569/IJACSA.2025.01601101 PDF

102

Optimizing Feature Selection in Intrusion Detection Systems Using a Genetic Algorithm with Stochastic Universal Sampling

Author 1: RadhaRani Akula Author 2: GS Naveen Kumar

The current study presents a hybrid framework integrating the Genetic optimization algorithm with Stochastic Universal Sampling (GA-SUS) for feature selection and Deep Q-Networks (DQN) for fine-tuning an ensemble of classifiers to enhance network intrusion detection. The proposed method enhances genetic algorithms with stochastic universal sampling (GA-SUS) combined with recursive feature… Read full abstract & cite →

GA-SUS anomaly detection IDS RFE DQN

Abstract doi.org/10.14569/IJACSA.2025.01601102 PDF

103

Optimizing Route Planning for Autonomous Electric Vehicles Using the D-Star Lite Algorithm

Author 1: Bhakti Yudho Suprapto Author 2: Suci Dwijayanti Author 3: Desi Windisari Author 4: Gatot Aria Pratama

Every vehicle, including autonomous vehicles, requires a route to navigate its journey. Route planning is a critical aspect of autonomous vehicle operations, as these vehicles rely on guided paths or sequential steps to move effectively. Ensuring that the route is optimal is a key consideration. This study tests the D-Star… Read full abstract & cite →

Autonomous vehicle D-Star Lite path planning realtime replanning route optimal route

Abstract doi.org/10.14569/IJACSA.2025.01601103 PDF

104

Stacking Regressor Model for PM2.5 Concentration Prediction Based on Spatiotemporal Data

Author 1: Mitra Unik Author 2: Imas Sukaesih Sitanggang Author 3: Lailan Syaufina Author 4: I Nengah Surati Jaya

This study presents the development of a predictive model for PM2.5 concentrations resulting from forest and peatland fires in Riau Province, utilizing the stacking regressor technique within an ensemble learning framework. The model integrates spatiotemporal data from remote sensing and ground-based sensors at a resolution of 1 km x 1… Read full abstract & cite →

Ensemble learning PM2.5 prediction remote sensing stacking regressor spatio-temporal data

Abstract doi.org/10.14569/IJACSA.2025.01601104 PDF

105

Feature Substitution Using Latent Dirichlet Allocation for Text Classification

Author 1: Norsyela Muhammad Noor Mathivanan Author 2: Roziah Mohd Janor Author 3: Shukor Abd Razak Author 4: Nor Azura Md. Ghani

Text classification plays a pivotal role in natural language processing, enabling applications such as product categorization, sentiment analysis, spam detection, and document organization. Traditional methods, including bag-of-words and TF-IDF, often lead to high-dimensional feature spaces, increasing computational complexity and susceptibility to overfitting. This study introduces a novel Feature Substitution technique… Read full abstract & cite →

Feature extraction feature selection Latent Dirichlet Allocation text classification Hidden Markov Model dimensionality reduction

Abstract doi.org/10.14569/IJACSA.2025.01601105 PDF

106

Multilabel Classification of Bilingual Patents Using OneVsRestClassifier: A Semiautomated Approach

Author 1: Slamet Widodo Author 2: Ermatita Author 3: Deris Stiawan

In response to the increasing complexity and volume of patent applications, this research introduces a semiautomated system to streamline the literature review process for Indonesian patent data. The proposed system employs a synthesis of multilabel classification techniques based on natural language processing (NLP) algorithms. This methodology focuses on developing an… Read full abstract & cite →

Multilabel patent classification Natural Language Processing (NLP) OneVsRestClassifier TF–IDF vectorisation bilingual patent analysis

Abstract doi.org/10.14569/IJACSA.2025.01601106 PDF

107

Dolphin Inspired Optimization for Feature Extraction in Augmented Reality Tracking

Author 1: Indhumathi S Author 2: Christopher Clement J

Feature extraction has the prominent role in Augmented Reality (AR) tracking. AR tracking monitor the position and orientation to overlay the 3D model in real-world environment. This approach of AR tracking, encouraged to propose the optimum feature extraction model by embedding the dolphin grouping system. We implemented dolphin grouping algorithm… Read full abstract & cite →

Feature descriptor dolphin optimization feature extraction augmented reality tracking

Abstract doi.org/10.14569/IJACSA.2025.01601107 PDF

108

Empirical Analysis of Variations of Matrix Factorization in Recommender Systems

Author 1: Srilatha Tokala Author 2: Murali Krishna Enduri Author 3: T. Jaya Lakshmi Author 4: Koduru Hajarathaiah Author 5: Hemlata Sharma

Recommender systems recommend products to users. Almost all businesses utilize recommender systems to suggest their products to customers based on the customer’s previous actions. The primary inputs for recommendation algorithms are user preferences, product descriptions, and user ratings on products. Content-based recommendations and collaborative filtering are examples of traditional recommendation… Read full abstract & cite →

Recommendations matrix factorization content-based collaborative filtering RMSE

Abstract doi.org/10.14569/IJACSA.2025.01601108 PDF

109

Efficient Tumor Detection in Medical Imaging Using Advanced Object Detection Model: A Deep Learning Approach

Author 1: Taoufik Saidani

Timely and accurate tumor detection in medical imaging is crucial for improving patient outcomes and reducing mortality rates. Traditional methods often rely on manual image interpretation, which is time-intensive and prone to variability. Deep learning, particularly convolutional neural networks (CNNs), has revolutionized tumor detection by automating the process and achieving… Read full abstract & cite →

Tumor detection medical imaging YOLOv11 deep learning real-time detection

Abstract doi.org/10.14569/IJACSA.2025.01601109 PDF

110

Efficient Anomaly Detection Technique for Future IoT Applications

Author 1: Ahmad Naseem Alvi Author 2: Muhammad Awais Javed Author 3: Bakhtiar Ali Author 4: Mohammed Alkhathami

Internet of Things (IoT) provides smart wireless connectivity and is the basis of many future applications. IoT nodes are equipped with sensors that obtain application-related data and transmit to the servers using IEEE 802.15.4-based wire-less communications, thus forming a low-rate wireless personal area network. Security is a major challenge in… Read full abstract & cite →

Anomaly detection IoT networks security

Abstract doi.org/10.14569/IJACSA.2025.01601110 PDF

111

GRACE: Graph-Based Attention for Coherent Explanation in Fake News Detection on Social Media

Author 1: Orken Mamyrbayev Author 2: Zhanibek Turysbek Author 3: Mariam Afzal Author 4: Marassulov Ussen Abdurakhimovich Author 5: Ybytayeva Galiya Author 6: Muhammad Abdullah Author 7: Riaz Ul Amin

Detecting fake news on social media is a critical challenge due to its rapid dissemination and potential societal impact. This paper addresses the problem in a realistic scenario where the original tweet and the sequence of users who retweeted it, excluding any comment section, are available. We propose a Graph-based… Read full abstract & cite →

Graph neural network dual attention NLP semantics social network

Abstract doi.org/10.14569/IJACSA.2025.01601111 PDF

112

Intelligent Fault Diagnosis for Elevators Using Temporal Adaptive Fault Network

Author 1: Zhiyu Chen

Contemporary cities depend on elevators for vertical mobility in residential, commercial, and industrial buildings. However, elevator system malfunctions may cause operational interruptions, economic losses, and safety dangers, requiring advanced tools for detection. High-dimensional sensor data, temporal interdependence, and fault dataset imbalances are common problems in fault detection algorithms. These restrictions… Read full abstract & cite →

Elevator fault diagnosis temporal adaptive fault network predictive maintenance multivariate time-series data feature refinement fault classification

Abstract doi.org/10.14569/IJACSA.2025.01601112 PDF

113

High-Precision Multi-Class Object Detection Using Fine-Tuned YOLOv11 Architecture: A Case Study on Airborne Vehicles

Author 1: Nasser S. Albalawi

The widespread adoption of airborne vehicles, including drones and UAVs, has brought significant advancements to fields such as surveillance, logistics, and disaster response. Despite these benefits, their increasing use poses substantial challenges for real-time detection and classification, particularly in multi-class scenarios where precision and scalability are essential. This paper proposes… Read full abstract & cite →

Airborne vehicles YOLOv11 object detection surveillance

Abstract doi.org/10.14569/IJACSA.2025.01601113 PDF

114

AI-Driven Image Recognition System for Automated Offside and Foul Detection in Football Matches Using Computer Vision

Author 1: Qianwei Zhang Author 2: Lirong Yu Author 3: WenKe Yan

Integrating artificial intelligence (AI) and computer vision in sports analytics has transformed decision-making pro-cesses, enhancing fairness and efficiency. This paper proposes a novel AI-driven image recognition system for automatically detecting offside and foul events in football matches. Unlike conventional methods, which rely heavily on manual intervention or traditional image processing… Read full abstract & cite →

Artificial intelligence image recognition automation foul detection deep learning computer vision

Abstract doi.org/10.14569/IJACSA.2025.01601114 PDF

115

Deep Q-Learning-Based Optimization of Path Planning and Control in Robotic Arms for High-Precision Computational Efficiency

Author 1: Yuan Li Author 2: Byung-Won Min Author 3: Haozhi Liu

Optimizing path planning and control in robotic arms is a critical challenge in achieving high-precision and efficient operations in various industrial and research applications. This study proposes a novel approach leveraging deep Q-learning (DQL) to enhance robotic arm movements’ computational efficiency and precision. The proposed framework effectively ad-dresses key challenges… Read full abstract & cite →

Optimization deep Q-learning path planning robotic arms precision computational efficiency kinematic

Abstract doi.org/10.14569/IJACSA.2025.01601115 PDF

116

Android Malware Detection Through CNN Ensemble Learning on Grayscale Images

Author 1: El Youssofi Chaymae Author 2: Chougdali Khalid

With Android’s widespread adoption as the leading mobile operating system, it has become a prominent target for malware attacks. Many of these attacks employ advanced obfuscation techniques, rendering traditional detection methods, such as static and dynamic analysis, less effective. Image-based approaches provide an alternative for effective detection that addresses some… Read full abstract & cite →

Android malware detection image-based analysis Convolutional Neural Networks (CNN) grayscale image transformation weighted voting ensemble Bayesian optimization

Abstract doi.org/10.14569/IJACSA.2025.01601116 PDF

117

Cross-Domain Health Misinformation Detection on Indonesian Social Media

Author 1: Divi Galih Prasetyo Putri Author 2: Savitri Citra Budi Author 3: Arida Ferti Syafiandini Author 4: Ikhlasul Amal Author 5: Revandra Aryo Dwi Krisnandaru

Indonesia is among the world’s most prolific countries in terms of internet and social media usage. Social media serves as a primary platform for disseminating and accessing all types of information, including health-related data. However, much of the content generated on these platforms is unverified and often falls into the… Read full abstract & cite →

Health misinformation machine learning social media

Abstract doi.org/10.14569/IJACSA.2025.01601117 PDF

118

Comparison of Machine Learning Algorithms for Malware Detection Using EDGE-IIoTSET Dataset in IoT

Author 1: Jawaher Alshehri Author 2: Almaha Alhamed Author 3: Mounir Frikha Author 4: M M Hafizur Rahman

The growth of IoT devices has presented great vulnerabilities leading to many malware attacks. Existing IoT malware detection methods face many challenges; including: device heterogeneity, device resource restrictions, and the complexity of encrypted malware payloads, thus leading to less effective conventional cybersecurity techniques. This study’s objective is to reduce these… Read full abstract & cite →

IoT malware machine learning malware detection IoT security EDGE-IIoTSET

Abstract doi.org/10.14569/IJACSA.2025.01601118 PDF

119

Building Detection from Satellite Imagery Using Morphological Operations and Contour Analysis over Google Maps Roadmap Outlines

Author 1: Arbab Sufyan Wadood Author 2: Ahthasham Sajid Author 3: Muhammad Mansoor Alam Author 4: Mazliham MohD Su’ud Author 5: Arshad Mehmood Author 6: Inam Ullah Khan

One such research area is building detection, which has a high influence and potential impact in urban planning, disaster management, and construction development. Classifying buildings using satellite images is a difficult task due to building designs, shapes, and complex backgrounds which lead to occlusion between buildings. The current study introduces… Read full abstract & cite →

Building detection satellite imagery urban planning disaster response image processing machine learning morphological operations contour detection aspect ratio

Abstract doi.org/10.14569/IJACSA.2025.01601119 PDF

120

Exploring Machine Learning in Malware Analysis: Current Trends and Future Perspectives

Author 1: Noura Alyemni Author 2: Mounir Frikha

Sophisticated cyberattacks are an increasing concern for individuals, businesses, and governments alike. Detecting malware remains a significant challenge, particularly due to the limitations of traditional methods in identifying new or unexpected threats. Machine Learning (ML) has emerged as a powerful solution, capable of analyzing large datasets, recognizing complex patterns, and… Read full abstract & cite →

Machine learning malware analysis cybersecurity

Abstract doi.org/10.14569/IJACSA.2025.01601120 PDF

121

SM9 Key Encapsulation Mechanism for Power Monitoring Systems

Author 1: Chao Hong Author 2: Peng Xiao Author 3: Pandeng Li Author 4: Zhenhong Zhang Author 5: Yiwei Yang Author 6: Biao Bai

The boundaries of the new power system network are blurred, and data privacy and security are threatened. Although the SM9 algorithm is widely used in power systems to protect data security, its efficiency and security remain the main issues in application. Therefore, an SM9 key encapsulation mechanism (OSM9-KEM-CRF) was proposed… Read full abstract & cite →

SM9 Outsourced decryption cryptographic reverse firewall power monitoring systems

Abstract doi.org/10.14569/IJACSA.2025.01601121 PDF

122

A Review of Analyzing Different Agricultural Crop Yields Using Artificial Intelligence

Author 1: Vijaya Bathini Author 2: K. Usha Rani

The advancement of Artificial Intelligence (AI), in particular Deep Learning (DL), has made it possible to interpret gathered data more quickly and effectively in this new digital era. To draw attention to development advancements in deep learning across many industries. Agriculture has been one of the most affected areas in… Read full abstract & cite →

Agriculture artificial intelligence deep learning crop yields management

Abstract doi.org/10.14569/IJACSA.2025.01601122 PDF

123

LMS-YOLO11n: A Lightweight Multi-Scale Weed Detection Model

Author 1: YaJun Zhang Author 2: Yu Xu Author 3: Jie Hou Author 4: YanHai Song

With the advancement of precision agriculture, efficient and accurate weed detection has emerged as a pivotal task in modern crop management. Current weed detection methods face dual challenges: inadequate extraction of detailed features and edge information, coupled with the necessity for real-time performance. To address these issues, this paper pro-poses… Read full abstract & cite →

You-only-look-once-11 weed lightweight group convolution

Abstract doi.org/10.14569/IJACSA.2025.01601123 PDF

124

DBYOLOv8: Dual-Branch YOLOv8 Network for Small Object Detection on Drone Image

Author 1: Yawei Tan Author 2: Bingxin Xu Author 3: Jiangsheng Sun Author 4: Cheng Xu Author 5: Weiguo Pan Author 6: Songyin Dai Author 7: Hongzhe Liu

Object detection based on drone platforms is a valuable yet challenging research field. Although general object detection networks based on deep learning have achieved breakthroughs in natural scenes, drone images in urban environments often exhibit characteristics such as a high proportion of small objects, dense distribution, and significant scale variations… Read full abstract & cite →

Drone images dual-branch small object detection YOLOv8

Abstract doi.org/10.14569/IJACSA.2025.01601124 PDF

125

Eagle Framework: An Automatic Parallelism Tuning Architecture for Semantic Reasoners

Author 1: Haifa Ali Al-Hebshi Author 2: Muhammad Ahtisham Aslam Author 3: Kawther Saeedi

Parallel semantic reasoners use parallel architectures to improve the efficiency of reasoning tasks. Studies in semantic reasoning rely on manual tuning to configure the degree of parallelism. However, manual tuning becomes increasingly challenging as ontologies become massive and complex. Studies in related fields have developed automatic tuning frameworks using optimization… Read full abstract & cite →

Automatic tuning parallel semantic reasoning performance optimization ontology high performance computing

Abstract doi.org/10.14569/IJACSA.2025.01601125 PDF

126

Imbalance Datasets in Malware Detection: A Review of Current Solutions and Future Directions

Author 1: Hussain Almajed Author 2: Abdulrahman Alsaqer Author 3: Mounir Frikha

Imbalanced datasets are a significant challenge in the field of malware detection. The uneven distribution of malware and benign samples is a challenge for modern machine learning based detection systems, as it creates biased models and poor detection rates for malicious software. This paper provides a systematic review of existing… Read full abstract & cite →

Malware detection machine learning imbalance datasets oversampling SMOTE

Abstract doi.org/10.14569/IJACSA.2025.01601126 PDF

127

Artificial Intelligence in Financial Risk Early Warning Systems: A Bibliometric and Thematic Analysis of Emerging Trends and Insights

Author 1: Muhammad Ali Chohan Author 2: Teng Li Author 3: Suresh Ramakrishnan Author 4: Muhammad Sheraz

With the continuous development of financial markets worldwide, there has been increasing recognition of the importance of financial risk management. To mitigate financial risk, financial risk early warning serves as a risk uncovering mechanism enabling companies to anticipate and counter potential disruptions. The present review paper aims to identify the… Read full abstract & cite →

Artificial intelligence deep learning financial risk management early warning systems bibliometrics analysis

Abstract doi.org/10.14569/IJACSA.2025.01601127 PDF

128

DBFN-J: A Lightweight and Efficient Model for Hate Speech Detection on Social Media Platforms

Author 1: Nourah Fahad Janbi Author 2: Abdulwahab Ali Almazroi Author 3: Nasir Ayub

Hate speech on social media platforms like YouTube, Facebook, and Twitter threatens online safety and societal harmony. Addressing this global challenge requires innovative and efficient solutions. We propose DBFN-J (DistillBERT-Feedforward Neural Network with Jaya optimization), a lightweight and effective algorithm for detecting hate speech. This method combines DistillBERT, a distilled… Read full abstract & cite →

Hate speech detection social media analysis deep learning hybrid models artificial intelligence optimization sentiment analysis

Abstract doi.org/10.14569/IJACSA.2025.01601128 PDF

129

Exploring the Best Machine Learning Models for Breast Cancer Prediction in Wisconsin

Author 1: Abdullah Al Mamun Author 2: Touhid Bhuiyan Author 3: Md Maruf Hassan Author 4: Shahedul Islam Anik

This research focuses on predicting Wisconsin Breast Cancer Disease using machine learning algorithm, employs a dataset offered by UCI repository (WBCD) dataset. The under- gone substantial preparation, includes managing missing values, normalization, outlier elimination, increase data quality. The Synthetic Minority Oversampling Technique (SMOTE) is used to alleviate class imbalance and… Read full abstract & cite →

Wisconsin breast cancer disease prediction ML SVM KNN AUC-ROC Naive Bayes

Abstract doi.org/10.14569/IJACSA.2025.01601129 PDF

130

A Machine Learning-Based Analysis of Tourism Recommendation Systems: Holistic Parameter Discovery and Insights

Author 1: Raniah Alsahafi Author 2: Rashid Mehmood Author 3: Saad Alqahtany

Tourism is a cornerstone of the global economy, fostering cultural exchange and economic growth. As travelers increasingly seek personalized experiences, recommendation systems have become vital in guiding decision-making and enhancing satisfaction. These systems leverage advanced technologies such as IoT and machine learning to provide tailored suggestions for destinations, accommodations, and… Read full abstract & cite →

Recommendation Systems (RS) Tourism Recommendation Systems (TRS) big data analytics machine learning unsupervised learning social economic and environmental sustainability Bidirectional Encoder Representations from Transformers (BERT) SDGs literature review

Abstract doi.org/10.14569/IJACSA.2025.01601130 PDF