Articles

Access the latest knowledge in applied science, electrical engineering, computer science and information technology, education, and health.

Advanced Search
Filter Icon

Filters article

Years

FAQ Arrow
Single Year
Range Year
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

31,128 Article Results

Automated recognition of Thai fabric patterns using transfer learning with ResNet-50

10.11591/ijeecs.v43.i3.pp847-856
Kittiya Poonsilp , Pijitra Jomsri , Dulyawit Prangchumpol , Thammarat Panityakul
Traditional Thai fabric patterns are valuable cultural heritage, but expert knowledge of these patterns is declining. This study uses a convolutional neural network (CNN) with transfer learning (ResNet-50) to classify traditional Thai fabric patterns automatically. We collected 961 images across 19 pattern categories, split into training (57%), validation (11%), and test (32%) sets. Using ImageNet pre-trained weights and progressive fine-tuning, the model achieved 99.68% test accuracy with macro-averaged F1-score of 99.35%. Ablation studies validated our approach: augmentation improved accuracy by 2.26%, fine-tuning outperformed frozen backbone by 4.84%, and backbone comparison showed ResNet-50 achieves higher F1-score than MobileNetV2 while MobileNetV2 offers 90% parameter reduction for mobile deployment. Controlled stress tests demonstrated robustness under image degradations typical of smartphone photography. Unlike previous studies using controlled conditions, our dataset includes real-world variations. These results show that transfer learning with small datasets can match expert-level pattern recognition for cultural heritage preservation.
Volume: 43
Issue: 3
Page: 847-856
Publish at: 2026-09-01

Low-cost BLDC drive with PBBO-tuned FOPID controller for enhanced speed regulation and torque ripple reduction

10.11591/ijeecs.v43.i3.pp956-964
Pandi Maharajan M. , Rohini G. , Ravindran Ramkumar , Dharani Kumar Narne
Torque ripple (TR) minimization in brushless DC (BLDC) motors has become a critical research focus due to its direct impact on drive performance, efficiency, and reliability. Conventional BLDC drives typically employ large DC-link capacitors, which increase system cost and weight and are highly sensitive to operating temperature, thereby reducing lifetime. To address these limitations, this work proposes a low-cost capacitor-based BLDC drive integrated with a torque ripple compensation (TRC) technique and optimized control using the probabilistic biogeography-based optimization (PBBO) algorithm. The PBBO method is employed to tune the parameters of a fractional-order proportional-integral-derivative (FOPID) controller, ensuring effective speed regulation and TR reduction. By probabilistically refining migration and emigration rates, PBBO enhances convergence and eliminates redundant species movements, leading to superior controller parameter optimization. Simulation studies validate the proposed PBBO-FOPID approach, demonstrating significant improvements in TR reduction and speed control compared to conventional controllers such as DGOA-FOPID and spider web-based controller (SWC). Results confirm that the PBBO-FOPID controller achieves smoother torque response, reduced ripple, and enhanced speed regulation, establishing it as a cost effective and high-performance solution for BLDC motor drives.
Volume: 43
Issue: 3
Page: 956-964
Publish at: 2026-09-01

Automated smart handbag with enhanced women's safety using cutting edge technology

10.11591/ijra.v15i3.pp669-677
Vijayaraja Loganathan , Dhanasekar Ravikumar , Ashish Ragavendra Nattamai Uthayakumar , Arulmurugan Nagarajan Renukadevi , Rishikeshwaran Balamurugan Rani , Rupa Kesavan
Women’s safety has been an area of concern, especially in public places where timely assistance cannot be provided. To mitigate this problem, this paper proposes an intelligent handbag-based women’s safety system that utilizes the concept of biometric identification, location tracking, and edge computing-based AI threat verification. The proposed system, unlike other traditional women’s safety devices that rely on GPS-GSM for emergency alerts and are more likely to send false alarms, utilizes fingerprint identification for secure and authorized use, along with YOLO v3 vision model on an ESP32-CAM for threat verification. Upon failure in the authentication process or threat detection, the system sends an SOS message with the current location via GSM with the help of GPS coordinates. The system achieves an emergency response time of 33 seconds, primarily limited by GPS acquisition delay. The results confirm the effectiveness and applicability of the proposed system in providing an intelligent emergency response system for women’s safety.
Volume: 15
Issue: 3
Page: 669-677
Publish at: 2026-09-01

URL-based phishing detection using XGBoost with engineered features

10.11591/ijeecs.v43.i3.pp908-927
Jawaher Alharbi , Manal Bayousef , Hind Almisbahi
URL-based phishing involves fake uniform resource locators (URLs) created by attackers to trick users into believing they are visiting a legitimate website and thereby steal their confidential information. While several powerful machine learning (ML) and deep learning (DL) studies exist to detect phishing, they still face limitations. Many studies rely on third-party intervention to extract features, which introduces delays that make them unsuitable for fast detection. Another limitation is that existing studies often use small datasets, and traditional features hinder models' ability to learn new phishing techniques, resulting in poor generalization. Therefore, developing new features is crucial to ensure that anti-phishing tools can keep pace with evolving phishing tactics. In addition, the existing studies do not report detection time, which is important for fast detection, and reduces methodological clarity. This paper aims to address these limitations by applying a neural network model and traditional ML classification algorithms to support browser-based phishing detection that balances high accuracy with fast detection. Our XGBoost model achieved 98% accuracy on the test set, utilizing 40 third-party-independent features. Additionally, we achieved an average response time of 0.026225 seconds and an average computation time of 1.6977×10⁻6 seconds per URL, which demonstrates competitive speed. We provided a table of features from recent studies, together with their documented sources, to support future research and analyze key URL-based features.
Volume: 43
Issue: 3
Page: 908-927
Publish at: 2026-09-01

ROVAA: Offline attendance automation using a voice–OCR-based 3-DOF robotic arm with Raspberry Pi

10.11591/ijra.v15i3.pp561-576
Rajanikanth Kashi Nagaraj , Archana Harihara Ranganatha , Surendra Hanumanthaiah Honnamachanahalli , Venu Manighatta Gopalakrishnappa
Conventional classroom attendance systems suffer from limitations in accuracy, hygiene, data privacy, and reliability in low-connectivity environments, whether they are manual, cloud-dependent, or single-modality systems. To address these gaps, this paper presents ROVAA, a low-cost, fully offline, AI-driven robotic attendance system in the classroom environment that uniquely integrates three complementary modalities: offline voice recognition, optical character recognition (OCR), and a 3- degrees of freedom (DOF) robotic arm controlled via inverse kinematics, an integration not demonstrated in prior work. The system operates on a Raspberry Pi 4 model B and employs the Vosk speech recognition model and Tesseract OCR for accurate offline processing. Audio and visual inputs are matched in real time to enable the arm to mark attendance at pre-calibrated positions on a touchscreen. Experimental validation under varied lighting and acoustic conditions yielded 96.2% speech recognition accuracy, 95.8% OCR accuracy, and 97.6% robotic arm precision, producing an overall system success rate of 92.8%, demonstrating that high reliability is achievable without cloud infrastructure. The system is designed for cost-effectiveness, data privacy, and scalability, making it suitable for resource-constrained environments such as rural schools and institutions with limited network access. It additionally serves as an educational platform for human–robot collaboration.
Volume: 15
Issue: 3
Page: 561-576
Publish at: 2026-09-01

Optimal robust control for self-balancing robot-based feedback linearization and Atom Search Optimization

10.11591/ijra.v15i3.pp519-528
Alaa Jumaah Al-Maiahy , Yahya Ghufran Khidhir , Adnan Jabbar Attiya , Hisham H. Jasim
In this paper, a robust control method is suggested for attitude control of the two-wheeled self-balancing robot by combining feedback linearization with sliding mode control techniques. The proposed method takes into account important challenges such as external disturbance and system uncertainty. Feedback linearization cancels the nonlinearities in the dynamics of the robotic system, while the sliding mode control handles the uncertainties and the external disturbance. The parameters of the proposed controller are selected by tuning the controller with the Atom Search Optimization algorithm. MATLAB is used to simulate the proposed controller. Simulation results indicate a good performance of the presented controller with high robustness compared with the proportional-integral-derivative (PID) controller. Moreover, the proposed method reduces the rise time by approximately 40% and 50% with respect to PID. These results illustrate the feasibility of the presented control method to be used for real-time implementation in autonomous robotic balancing systems.
Volume: 15
Issue: 3
Page: 519-528
Publish at: 2026-09-01

Explainable hybrid machine learning for predicting student enrollment decisions in Indonesian private universities

10.11591/ijeecs.v43.i3.pp880-897
Dybio Dompu Hot Asih , Alex Permatanta Karo-Karo , Erbin Sitorus
Student enrollment prediction is an important challenge for private universities because accurate predictions can support admission planning, marketing strategies, and institutional resource allocation. However, conventional prediction models may provide high predictive performance while offering limited insight into the factors underlying students’ enrollment decisions. This study proposes an explainable hybrid machine learning approach to predict student enrollment decisions in Indonesian private universities and to identify the factors that contribute most strongly to the prediction outcomes. The study uses student enrollment data collected from Universitas Wirahusada Medan and Universitas Audi Indonesia. The proposed approach combines feature selection and multiple machine learning algorithms to improve predictive performance, while explainable artificial intelligence (XAI) using Shapley additive explanations (SHAP) is employed to interpret the model predictions. The models are evaluated using accuracy, precision, recall, F1-score, receiver operating characteristic - area under the curve (ROC-AUC), and confusion matrix analysis. The results show that the proposed hybrid approach provides competitive predictive performance compared with individual machine learning models. The SHAP analysis further reveals the relative contribution and direction of the most influential features in determining student enrollment decisions. These findings demonstrate that combining predictive modeling with explainability can provide not only accurate enrollment predictions but also actionable insights for university decision-makers. The study contributes an integrated approach for supporting data-driven student recruitment and enrollment management in Indonesian private higher education institutions.
Volume: 43
Issue: 3
Page: 880-897
Publish at: 2026-09-01

Low-depth three-parameter quantum convolutional neural network for image classification

10.11591/ijeecs.v43.i3.pp857-870
Jing Wang , Yong Zhang , Min Zhao
Quantum convolutional neural networks (QCNNs) typically consist of quantum encoding, convolution, and pooling layers. However, existing QCNNs for image classification still face two major limitations. Most encoding layers rely on single-parameter angle encoding, which limits their ability to represent complex image features. Many circuit architectures are relatively deep, increasing cir cuit complexity and noise accumulation and thus hindering implementation on noisy intermediate-scale quantum devices. To address these issues, this paper proposes a low-depth three-parameter encoding quantum convolutional neural network (LTP-QCNN) for image classification. The model employs a three parameter angle encoding layer that maps compressed image features onto the rotation angles of single-qubit gates. A first low-depth quantum convolutional layer is employed to extract local features, followed by a quantum pooling layer for quantum-state dimensionality reduction and information fusion. The pooled quantum states are then processed by a second quantum convolutional layer to extract discriminative features. Finally, the measured quantum feature vector is input into a classical classification layer to produce the final prediction. Simulation experiments were conducted on the Fashion-MNIST, MNIST, and KMNIST benchmark datasets. On Fashion-MNIST, LTP-QCNN achieved an accuracy of 99.85% on binary classification, while the accuracies for five-class and six class tasks reached 90.98% and 89.48%, respectively. The results demonstrate that LTP-QCNN achieves effective and stable image classification under limited quantum resources.
Volume: 43
Issue: 3
Page: 857-870
Publish at: 2026-09-01

Performance index for optimization method based on PMSM drives using ABC and PSO

10.11591/ijpeds.v17.i3.pp1688-1701
Leong Hui Ee , Jurifa Mat Lazi , Mohd Ruzaini Hashim , Md Hairul Nizam Talib , Azrita Alias , Anggun Anugrah
The permanent magnet synchronous motor (PMSM) is commonly used in industrial and home appliances for its high efficiency and dynamic performance. In this research, a PMSM drive based on field-oriented control (FOC) is designed and simulated using MATLAB/Simulink. The speed controller of the drive is tuned using the trial-and-error method. However, the method requires more time for testing and adjustment of the speed controller to generate an optimal output response. Thus, particle swarm optimization (PSO) and artificial bee colony (ABC) algorithms, which require less computational effort and effectively produce good responses, are used to optimize the speed controller of the drive. PSO and ABC also offer an attractive optimization framework because of their independent, agnostic model structures, global searching capability, and low-load real-time calculation. In this study, the results obtained from different tuning methods are compared to determine the best optimization method of the speed controller in the PMSM drive under different operations. Other than that, performance measures such as integral square error (ISE), integral absolute error (IAE), and integral time absolute error (ITAE), which are commonly used to measure the effectiveness of a controller, are also discussed. The results show that the PMSM drive based on the ITAE criterion using the ABC algorithm gives better performance under different conditions.
Volume: 17
Issue: 3
Page: 1688-1701
Publish at: 2026-09-01

Association between occupational NO₂ exposure and hypertension risk: a PRISMA-based systematic review with risk-of-bias assessment

10.11591/ijphs.v15i3.27111
Ayudhia Rachmawati , Morrin Choirunnisa Thohira , Muhammad Aidil Fitrah , Vivi Filia Elvira
Nitrogen dioxide (NO₂) is a major air pollutant generated from fossil fuel combustion in transportation and industrial activities and is associated with adverse health effects. Prolonged exposure to NO₂ may induce chronic inflammation and endothelial dysfunction, which contribute to the development of hypertension. This study aimed to systematically review the association between NO₂ exposure and the incidence of hypertension among workers. The review was conducted in accordance with PRISMA guidelines, with literature searches performed in Google Scholar, PubMed, and ScienceDirect for publications from 2020 to 2025. Inclusion criteria comprised full-text articles in English or Indonesian employing observational study designs (cross-sectional, cohort, case-control, or ecological) and involving workers in both formal and informal sectors. Eligible studies examined NO₂ exposure as the independent variable and hypertension as the outcome. Of 2,051 records identified, five studies met the inclusion criteria, originating from China and Nigeria. Risk of bias was assessed using the office of health assessment and translation (OHAT) risk of bias tool. The findings demonstrated a consistent association between NO₂ exposure and an increased risk of hypertension, particularly in poorly ventilated work environments. These results underscore the importance of improving workplace air quality management, strengthening exposure monitoring, and implementing preventive occupational health strategies.
Volume: 15
Issue: 3
Page: 868-878
Publish at: 2026-09-01

Association between sociodemographic factors and mental health status among secondary school students in Cambodia: a cross-sectional study using SDQ

10.11591/ijphs.v15i3.27007
Sophealeaksmy Em , Keisuke Teramoto , Kohei Yamada , Chansean Mam
Adolescent mental health significantly influences social well-being and academic achievement, yet empirical data remains scarce in Cambodia. This study examined the association between sociodemographic characteristics and mental health status among Cambodian secondary school students using the Strengths and Difficulties Questionnaire (SDQ). A cross-sectional survey was conducted from March to April 2024 across five major provinces and Phnom Penh. Using purposive sampling, 1,528 students from urban and rural schools were recruited. Abnormal mental health was reported by 50.56% of females and 52.33% of students whose mothers had only elementary education. T-test and ANOVA analyses revealed significant associations between mental health and gender, school location, school type, and maternal education (p < 0.001), while socioeconomic status showed no significant impact. Findings emphasize that gender and maternal education are primary correlates of psychological well-being. These results necessitate gender-responsive school health programs and decentralized mental health services in rural areas. Furthermore, community initiatives should prioritize maternal health literacy to empower mothers as central caregivers, fostering supportive home environments for student resilience.
Volume: 15
Issue: 3
Page: 687-695
Publish at: 2026-09-01

Cross-modal attention fusion using vision transformers for robust student attentiveness estimation

10.11591/ijict.v15i3.pp935-943
Rajasekaran Mariswamy , Praveen Sundar
Automated student attentiveness estimation is a fundamental component of intelligent e-learning systems and adaptive classroom analytics. Traditional convolutional and recurrent architectures often struggle to model long-range temporal dependencies and complex inter-modal relationships inherent in engagement behavior. To address these limitations, this paper proposes a cross-modal attention fusion framework built upon a vision transformer (ViT) backbone for robust student attentiveness estimation. The proposed architecture leverages patch-based visual encoding through a ViT to capture global spatial dependencies, while behavioral cues such as gaze direction, head pose, and blink dynamics are embedded into a shared latent representation space. A cross-modal multi-head attention mechanism is introduced to dynamically learn interactions between visual and behavioral modalities, replacing static weighted fusion strategies. Temporal dynamics are modeled using a Transformer encoder, enabling effective long-range sequence modeling without recurrent dependencies. Experimental evaluation on a benchmark attentiveness dataset demonstrates superior performance compared to CNN–LSTM-based models, achieving improved accuracy, F1 score, and robustness under challenging lighting and occlusion conditions. Ablation studies validate the contribution of cross-modal attention and transformer-based temporal modeling. The proposed framework maintains real-time feasibility while significantly enhancing discriminative capability.
Volume: 15
Issue: 3
Page: 935-943
Publish at: 2026-09-01

Design and implementation of an AI, IoT, and blockchain-based system for circular economy transition in landfill management: a case study of Quilmaná, Peru

10.11591/ijict.v15i3.pp1254-1262
Brandon Perez Flores , Juan Villantoy Peralta , Jimmy Acosta García , Jesús Zamora Mondragon , Cesar Patricio-Peralta , Luis Segura Terrones , Héctor Odín Delgado-Enríquez , Walter Patricio Peralta , Richard Aguilar Paredes
This study presents the design and implementation of an integrated system based on artificial intelligence (AI), internet of things (IoT), and blockchain to support circular economy practices in landfill management. The system addresses the lack of integrated and validated digital solutions for environmental monitoring, resource optimization, and social inclusion in resource-constrained contexts. Developed under a design science research (DSR) approach, the system combines IoT sensors for real-time monitoring, machine learning models (LSTM for methane prediction, CNN for waste classification, and reinforcement learning (RL) for biogas optimization), and a blockchain-based platform for transparent transactions and recycler formalization. The system was implemented and evaluated over 12 months using operational data. The LSTM model achieved 95% prediction accuracy, while the CNN model demonstrated high classification performance. Results indicate a 35% reduction in landfill waste, a 40% decrease in CH₄ emissions, and a 30% increase in recycler income, with 60% of informal workers formalized. These findings demonstrate that integrating AI, IoT, and blockchain enables the transformation of landfill systems into scalable circular economy platforms for sustainable waste management.
Volume: 15
Issue: 3
Page: 1254-1262
Publish at: 2026-09-01

Classroom behavior mining in adolescents: a cognitive and data-driven approach using BEHAVE_Apriori

10.11591/ijict.v15i3.pp1058-1065
Suresh Govindarajalu , Muthukumaran Subramaniyan , Kamatchy Balakrishnan , Kalaichelvi Nagarajan , Nandhini Krishnamoorthy
Adolescence is a critical developmental stage that leads to essential changes in social, emotional, and cognitive domains that affect conduct in the classroom. Students' perceptions, processing, and reactions to their learning environment are better-understood thanks to cognitive psychology. However, contemporary data mining techniques frequently ignore the environmental, emotional, and cognitive elements influencing teenage behavior in learning environments. This research presents a comprehensive approach to analyzing teenage college students' classroom behavior by integrating cognitive psychology with data-driven methods to identify key behavioral traits shaped by both external and internal factors. A brand-new algorithm called the behavioral evaluation via hybrid attributes and valuable extraction using the Apriori (BEHAVE_Apriori) approach is presented. Also, a variety of feature selection (FS) strategies, including information gain (IG), chi-squared (CS), and tree-based approaches, are used for FS. Then, using the Apriori algorithm, association rules are found that relate behavior patterns to elements like family history, academic involvement, and peer influence. The IG-based FS combined with the Apriori algorithm delivered the best performance, generating 95 rules in 0.0241 seconds, outperforming CS (154 rules, 0.0629s) and tree-based FS (251 rules, 0.1394s), while the unfiltered dataset produced 514 rules in 0.2853 seconds.
Volume: 15
Issue: 3
Page: 1058-1065
Publish at: 2026-09-01

Development of highway vehicle detection using background subtraction and Haar cascade methods

10.11591/ijict.v15i3.pp1004-1015
Ni Gusti Ayu Dasriani , Anthony Anggrawan , Khasnur Hidjah , Christofer Satria , I Nyoman Yoga Sumadewa
Vehicle recognition is a critical component of traffic analysis and the progress of advanced transportation systems, underscoring the importance of automated, real-time methods that reduce the need for manual observation. While the field has seen notable innovations in deep learning-centric detection technologies, many of these approaches require considerable computational strength and are not well-suited for real-time application in resource-constrained environments. In response to this limitation, the present study introduces a streamlined vehicle detection framework that combines background subtraction for motion-oriented foreground extraction with a Haar cascade classifier for object identification in traffic video sequences. The system is evaluated using real-world highway traffic recordings under different illumination conditions, including both day and night scenarios. The experiment's findings show that the system achieves an overall accuracy of 82.08%, with a precision of 85.33%, a recall of 66.67%, and an F1-score of 74.86%. The system also demonstrates consistent performance across different lighting conditions. These findings indicate a trade-off between detection accuracy and computational efficiency, where the proposed approach prioritizes practical deployment feasibility. Overall, the results suggest that classical computer vision techniques remain viable alternatives for real-time traffic monitoring in environments with limited computational resources.
Volume: 15
Issue: 3
Page: 1004-1015
Publish at: 2026-09-01
1 2 3
...
2075 2076
Show 18 of 2076

Discover Our Library

Embark on a journey through our expansive collection of articles and let curiosity lead your path to innovation.

Explore Now
Library 3D Ilustration