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

31,456 Article Results

Unraveling the predictors of research utilization among Thai educators: evidence from PLS-SEM analysis

10.11591/ijere.v14i3.31468
Phuchit Laowang , Suntonrapot Damrongpanit
This groundbreaking study unveils critical factors driving research utilization (RU) among Thai educators, offering vital insights for educational policymakers and administrators. Employing an advanced partial least squares structural equation modeling (PLS-SEM) approach, we examined data from 688 teachers under the office of the basic education commission. Our findings reveal a complex interplay of factors influencing RU, with organizational support (SUPP) emerging as the most potent driver (beta=0.570), followed by knowledge and research skills (KNOWS) (beta=0.539), organizational leadership (LEAD) (beta=0.472), and attributes of research (ATTR) (beta=0.391). Interestingly, ATTR showed the highest direct effect (DE) (beta=0.391), while LEAD had the strongest indirect impact (beta=0.429). Surprisingly, organizational climate (ORGA) showed no significant effect, challenging conventional wisdom. The study explains 52.5% of the variance in RU, providing a robust foundation for evidence-based educational reforms. Delve into our analysis to discover how these relationships between knowledge, leadership, and organizational dynamics shape educational RU in Thailand, and explore our recommendations for enhancing research integration in educational practices.
Volume: 14
Issue: 3
Page: 1684-1694
Publish at: 2025-06-01

Optimized design and development of a vehicle-mounted vertical axis wind turbine for defense cut-off locations and its performance analysis

10.11591/ijpeds.v16.i2.pp1124-1136
M. Priyadharsini , Sunil Kumar Gupta , Manoj Gupta
This paper presents a vehicle-mounted vertical-axis wind turbine (VAWT) designed to generate power in motion and at cut-off locations. Particularly, its application to military vehicles is explored to provide uninterrupted electrical power for radio communication equipment and lighting needs in remote areas. The design uses a helical wind turbine for its compactness, lightweight, and suitability for vehicle mounting without heavy support structures. These turbines have low starting wind speeds, minimal vibration, portability, affordability, and low maintenance requirements. Utilizing fiberglass blades, the turbine unit measures 103 mm in height and 27.5 mm in diameter, achieving optimal rpm and torque for given wind speeds. Operating within the wind speed range of 10 km/h to 40 km/h, the VAWT produces an output voltage ranging from 5 V to 55 V, with a maximum wind turbine power output of 1120 watts at a wind speed of 12 m/s. The final generator output power obtained with the above wind turbine output of 1120 watts is 352 watts. A prototype unit has been tested and mounted on an all-terrain vehicle for evaluation. The paper provides detailed design steps, calculations, and insights for optimizing performance and facilitating large-scale implementation in the future.
Volume: 16
Issue: 2
Page: 1124-1136
Publish at: 2025-06-01

Perceptions of the generative AI-enabled cognitive offload instruction in English writing

10.11591/ijere.v14i3.33138
Hui Hong , Poonsri Vate-U-Lan , Chantana Viriyavejakul
This study examines the students’ perceptions of the generative artificial intelligence (AI)-enabled cognitive offload instruction and its effectiveness in improving their critical thinking skills in writing English essays. This qualitative research collects data from 120 students through focus group discussions and is analyzed by Word Clouds to generate a visual representation of the word frequencies. The findings reveal that generative AI-enabled cognitive offload instruction had: i) an impact on critical thinking and writing skills; ii) effective features of Skywork, ability to generate relevant prompts and provide constructive feedback; iii) use of Skywork in developing stronger arguments; iv) promoting critical examination of different perspectives; v) interactive nature and motivation; vi) enhanced analytical skills; vii) impact on essay structuring and organization; viii) feedback and revision process; and ix) transferability of critical thinking skills. This study concludes that the highest frequency was Skywork, ability, writing, feedback, evidence, skills, thinking, arguments, essays, and peers. Students recommend in-depth explanations for complex topics, advanced tutorials, regular updates, collaboration features, advanced modules, and personalized learning paces to enhance Skyworks’s integration into instruction.
Volume: 14
Issue: 3
Page: 1761-1769
Publish at: 2025-06-01

Empowering SDN with DDoS attack detection: leveraging hybrid machine learning based IDPS controller for robust security

10.11591/ijai.v14.i3.pp2479-2489
Florance G. , R. J. Anandhi
Software-defined network (SDN) is an innovative networking framework where a centralized controller manages networking administration and sorts out network traffic issues. It becomes difficult for the controller to identify the malicious user who is sending a large number of spoofed packets, such as in a distributed denial of service (DDoS) attack. To prevent DDoS attacks from damaging legitimate users, it is important to take steps to prevent them. The issue of preventing DDoS attacks in SDN remains unresolved despite many algorithms proposed. Methods presented in this paper employ bandwidth threshold estimation, which triggers the intrusion detection and prevention system (IDPS) controller if the threshold is exceeded. Whenever the threshold is exceeded due to network congestion, transferred packets are filtered at the server level by identifying the utilization of bandwidth in OpenDaylight (ODL) and POX. K-nearest neighbor (K-NN) and support vector machine (SVM) are used by the IDPS controller to detect and thwart DDoS attacks. Using Mininet, two SDN centralized controllers are simulated to improve performance significantly. Based on SVM in the ODL controller, this work has provided mitigation techniques for preventing DDoS attacks with an accuracy of 96.75% compared to previously published accuracy.
Volume: 14
Issue: 3
Page: 2479-2489
Publish at: 2025-06-01

Enhancing preservice teachers’ collaborative problem solving through STEM project-based learning

10.11591/ijere.v14i3.27725
Rita Fitriani , Hadi Suwono , Ibrohim Ibrohim , Betty Lukiati
This study aimed to determine the effect of science, technology, engineering, and mathematics project-based learning (STEM-PjBL) on the collaborative problem solving (CPS) of preservice teachers (PSTs). The pretest-posttest non-equivalent control group design was employed. A total of 72 PSTs enrolled in plant physiology course participated in this study. Self-assessment and project were used to evaluate PSTs’ CPS skills. Self-assessment scores were analyzed by analysis of covariance (ANCOVA), while project scores were analyzed by the Mann-Whitney U test. The results of self-assessment indicated that STEM-PjBL enhances CPS skills, particularly in social regulation, task regulation, and knowledge building. The results of the team’s problem-solving skills in completing the project did not differ between the two groups. But the result of integrated STEM skills showed that the STEM-PjBL group was better at integrating STEM disciplines into their project. This study highlights the importance of interdisciplinary projects in a PjBL environment that can be adopted by teacher preparation programs for enhancing PSTs’ CPS skills as well as gaining knowledge of STEM integration.
Volume: 14
Issue: 3
Page: 2278-2289
Publish at: 2025-06-01

A single-stage constant-power and optimal-efficiency double-sided LCC wireless battery charger

10.11591/ijpeds.v16.i2.pp1409-1416
Jiabo Yan , Mohd Junaidi Bin Abdul Aziz , Nik Rumzi Nik Idris , Tole Sutikno
This article proposes a novel single-stage double-sided LCC (DS-LCC) constant power (CP) wireless battery charger. The proposed CP charger uses a closedloop control in the secondary side with the active rectifier to make the DS-LCC charger achieve CP charging and optimal efficiency. Compared to previous work, the proposed CP wireless power transfer system does not involve any switch-controlled capacitor (SCC), does not require wireless communication, and can achieve optimal efficiency throughout the charging process. The proposed charger reduces cost and system complexity while improving efficiency. The proposed wireless charger is validated by simulation, and the efficiency remains between 94.44% and 94.52%, surpassing the previous work.
Volume: 16
Issue: 2
Page: 1409-1416
Publish at: 2025-06-01

Early detection and classification of bone marrow changes in lumbar vertebrae using machine learning techniques

10.11591/ijai.v14.i3.pp2132-2145
Yasir Hussein Shakir , Tiong Sieh Kiong , Chai Phing Chen
Bone marrow changes in lumbar vertebrae (BMCLVB) have emerged as a significant correlation of chronic low back pain (CLBP) severity, especially in patients with comorbid conditions like HIV, osteoporosis, and cancer. Identifying these correlations not only aids governments and health insurance providers but also facilitates early treatment for those at risk. However, challenges lurk due to the unavailability and quality of healthcare data. The collaboration between data science and artificial intelligence, particularly machine learning (ML), has propelled biomedical research forward. So far, accessing and processing hospital and clinical data remains a hurdle. In doing so it aims to provide an opportunity for early intervention and treatment. In addition, the goal of the current study was to overcome data shortcomings using advanced ML techniques to unlock complex magnetic resonance imaging (MRI) features. We believe that extending the dataset with that obtained from an Iraqi hospital will not only assist in diagnosing BMCLVB but also fill the gap between data science and healthcare. Above all, the upgrade is intended to empower biomedical research and increase the chances of successful patient treatment.
Volume: 14
Issue: 3
Page: 2132-2145
Publish at: 2025-06-01

Customer segmentation using association rule mining on retail transaction data

10.11591/ijai.v14.i3.pp1919-1929
Siriwan Kajornkasirat , Pattarawan Gunglin , Kritsada Puangsuwan , Nawapon Kaewsuwan
This research aimed to investigate a suitable algorithm for customer segmentation using as customer behavior indicators the recency, frequency, and monetary (RFM) values of the customers. The clustering algorithms K-means, fuzzy C-means, and self-organizing neural network (SONN) were compared for finding the most appropriate algorithm. The customer segmentation was analyzed using association rule mining with the frequent pattern algorithm (FP-Growth). Data on retail transactions during January 2021 - May 2023 were obtained from Tuenjai Company, Thailand, with a total of 202,469 records. The results from the three algorithms were compared by the silhouette coefficient (SC), Calinski-Harabasz (CH) index, Davies-Bouldin (DB) index, iteration count, and execution time. The results showed that the K-means algorithm was the most suitable algorithm for customer segmentation in this study. K-means clustering grouped the customers into three groups here labeled as “important value”, “general development”, and “lost”, based on the RFM values. There were 38 rules for the important value segment, and two rules each for the general development and the lost groups. These results could be useful to the business organization for improving the customer experiences, increasing sales, preparing or promoting products, and stock management efficiency.
Volume: 14
Issue: 3
Page: 1919-1929
Publish at: 2025-06-01

A symptom-driven medical diagnosis support model based on machine learning techniques

10.11591/ijai.v14.i3.pp2072-2082
Adil Laabidi , Mohammed Aissaoui
Medicine is a human science that is constantly evolving, and this evolution generates a large mass of data that needs to be exploited with the multitude of IT resources available to guarantee and maintain this scientific progress. Some diseases share most symptoms, whereas others could have a low probability of being identified in an early stage. Thus, when facing a such situation, an inexperienced doctor may have difficulty making the right diagnosis or may test different cases, which will be a big waste of time. In this paper, we are going to make this embarrassing situation less complex by giving practitioners every probable disease, and even the least probable ones according to the given symptoms. Indeed, this work will push the diagnosis deeper to reveal hidden symptoms and pathogenesis, to help practitioners make the right decisions. To develop such a solution, the data is organized by matching each disease with its known symptoms, then we used naive Bayes as a classification model, and different metrics to evaluate the performance of this experiment. This work proves that machine learning has become very effective in the medical sector, especially when we notice that the accuracy exceeds 90% in the detection of diseases.
Volume: 14
Issue: 3
Page: 2072-2082
Publish at: 2025-06-01

A novel light-weight convolutional neural network for rice leaf disease classification

10.11591/ijai.v14.i3.pp2547-2558
Parthasarathi Jayaraman , Muthulakshmi Palaniyandi
Rice is one of the primary sources of staple meals. It may turn out to be a disaster as the production of agricultural products is declined due to diseases and therefore it is required to straighten up the situation by taking precautionary measures. Generally, deep learning (DL) architectures are employed for the identification of plant leaf diseases and it is observed that there is a trade-off between the accuracy and parameters. This study introduces a light-weight architecture called rice leaf disease classification convolutional neural network (RLDC-CNN). The objective of the proposed architecture is to improve the accuracy and reduce the loss by using a combination of convolutional layers, maxpooling layers, and fully connected layers. These layers use activation function for non-linearity, dropout for regularization and implements hyperparameter tuning with various optimizers that include Adam, RMSprop, stochastic gradient descent (SGD) and adaptive gradient (AdaGrad). Experiments are conducted on the dataset of 7,096 images with batch size of 32 under various learning rates. The behavior is analyzed by comparing the existing models and the count of parameters (in millions) equipped by RLDC-CNN, DenseNet121, VGG-16, and ResNet50 is 0.65, 8.49, 15.44, 26.49 with accuracy of 99.15%, 98.94%, 97.82%, 96.48% respectively.
Volume: 14
Issue: 3
Page: 2547-2558
Publish at: 2025-06-01

Blockchain and machine learning driven agricultural transformation framework to enhance efficiency, transparency, and sustainability

10.11591/ijai.v14.i3.pp1976-1988
Shivashankar Shivashankar , Krishna Prasad Karani , Manjunath Rajgopal , Sarala Totad , Erappa Giddappa , Shivakumar Swamy
The agricultural sector is undergoing a transformative journey empowered by technological innovations. In this context, this research work endeavors to revolutionize the agricultural supply chain (ASC) by developing a comprehensive online platform that connects sellers, farmers, and customers. Through meticulous planning, design, and implementation, the system aims to streamline the process of buying and selling agricultural products, thereby fostering efficiency, transparency and accessibility. The key features include user registration, product management, order tracking, and blockchain-machine learning (ML) based transaction security. The proposed research work's success hinges on thorough testing and validation, ensuring its reliability and usability. By leveraging technology to bridge gaps in the agricultural ecosystem, this proposed work seeks to empower stakeholders and contribute to the sustainable growth of the agricultural industry. In the current agricultural landscape in India, traceability has been a significant challenge. The industry lacks a comprehensive system that provides visibility into the source and quality of produce. Our proposed system aims to address the shortcomings of the existing agricultural ecosystem by introducing a comprehensive solution powered by blockchain technology and advanced data processing techniques.
Volume: 14
Issue: 3
Page: 1976-1988
Publish at: 2025-06-01

Enhanced Arabic-language cyberbullying detection: deep embedding and transformer (BERT) approaches

10.11591/ijai.v14.i3.pp2258-2269
Ebtesam Jaber Aljohani , Wael M. S. Yafooz
Recent technological advances in smartphones and communications, including the growth of such online platforms as massive social media networks such as X (formerly known as Twitter) endangers young people and their emotional well-being by exposing them to cyberbullying, taunting, and bullying content. Most proposed approaches for automatically detecting cyberbullying have been developed around the English language, and methods for detecting Arabic-language cyberbullying are scarce. Methods for detecting Arabic-language cyberbullying are especially scarce. This paper aims to enhance the effectiveness of methods for detecting cyberbullying in Arabic-language content. We assembled a dataset of 10,662 X posts, pre-processed the data, and used the kappa tool to verify and enhance the quality of our annotations. We conducted four experiments to test numerous deep learning models for automatically detecting Arabic-language cyberbullying. We first tested a long short-term memory (LSTM) model and a bidirectional long short-term memory (Bi-LSTM) model with several experimental word embeddings. We also tested the LSTM and Bi-LSTM models with a novel pre-trained bidirectional encoder from representations (BERT) and then tested them on a different experimental models BERT again. LSTM-BERT and Bi-LSTM-BERT demonstrated a 97% accuracy. Bi-LSTM with FastText embedding word performed even better, achieving 98% accuracy. As a result, the outcomes are generalized.
Volume: 14
Issue: 3
Page: 2258-2269
Publish at: 2025-06-01

Intravenous drug administration application for pediatric patients via augmented reality

10.11591/ijai.v14.i3.pp2412-2422
Kritsada Puangsuwan , Siriwan Kajornkasirat , Jaruphat Wongpanich , Chulalak Kaewsuk , Simaporn Puangsuwan
This research presents the development of the intravenous drug administration application for pediatric patients using augmented reality (AR) technology, with a primary focus on aiding nursing students in administering medications accurately to reduce the risk of errors. The system architecture encompasses two core components: the creation of medication preparation videos and detailed drug information, and the design of a mobile application featuring medication list display, drug dosage calculation, user satisfaction assessment, and intravenous drug information addition. The system classifies users into administrators and nursing students, allowing administrators to manage user information in the member database. the application seamlessly integrates Visual Studio Code, flutter, dart programming language, firebase database, and AR.js Studio for QR code-linked videos. Operating in four main parts, namely users, mobile application, member database, and results display, the IDA application enables users to log in, access detailed drug information, calculate dosages, and view AR-based medication preparation videos. Tested with 111 nursing students, the system demonstrated functionality, completeness, and accuracy. The Likert scale-based evaluation revealed high satisfaction levels in content, design, functionality, and benefits received, affirming the intravenous drug administration application's effectiveness in pediatric intravenous drug management through AR, offering an innovative solution for nursing education and error reduction.
Volume: 14
Issue: 3
Page: 2412-2422
Publish at: 2025-06-01

MedicalBERT: enhancing biomedical natural language processing using pretrained BERT-based model

10.11591/ijai.v14.i3.pp2367-2378
K. Sahit Reddy , N. Ragavenderan , Vasanth K. , Ganesh N. Naik , Vishalakshi Prabhu H , Nagaraja G. S.
Recent advances in natural language processing (NLP) have been driven by pretrained language models like BERT, RoBERTa, T5, and GPT. These models excel at understanding complex texts, but biomedical literature, with its domain-specific terminology, poses challenges that models like Word2Vec and bidirectional long short-term memory (Bi-LSTM) can't fully address. GPT and T5, despite capturing context, fall short in tasks needing bidirectional understanding, unlike BERT. Addressing this, we proposed MedicalBERT, a pretrained BERT model trained on a large biomedical dataset and equipped with domain-specific vocabulary that enhances the comprehension of biomedical terminology. MedicalBERT model is further optimized and fine-tuned to address diverse tasks, including named entity recognition, relation extraction, question answering, sentence similarity, and document classification. Performance metrics such as the F1-score, accuracy, and Pearson correlation are employed to showcase the efficiency of our model in comparison to other BERT-based models such as BioBERT, SciBERT, and ClinicalBERT. MedicalBERT outperforms these models on most of the benchmarks, and surpasses the general-purpose BERT model by 5.67% on average across all the tasks evaluated respectively. This work also underscores the potential of leveraging pretrained BERT models for medical NLP tasks, demonstrating the effectiveness of transfer learning techniques in capturing domain-specific information.
Volume: 14
Issue: 3
Page: 2367-2378
Publish at: 2025-06-01

System-on-chip design for improved switching angle driven 35-level LUO progression-based multi-level inverter

10.11591/ijpeds.v16.i2.pp974-981
Joseph Anthony Prathap , J. Kanti Prasad , Vivekananda Reddy , Chinthapalli Suheil
This article concentrates on the development of the IC layout for the driving switches of the inverter with improved switching control. This work uses the improved non-carrier switching pattern algorithms to have precise control of inverter switches with twin objectives of i) reducing the total harmonic distortion (THD)% and ii) developing a dedicated system on chip for the improved switching control of the 35-level switched ladder multi-level inverter. The DC voltage of the inputs to the inverter is designated based on the LUO progression, which consists of an improved mathematical formula for deriving its values. Conventionally, the multi-level inverter circuits are driven by the pulse width modulation signals by overlapping the modulating sine wave with different levels of triangle waves, such as phase disposition, phase opposite disposition, and alternate phase opposite disposition, utilized to drive various voltage source inverter topologies. Although the MLI design concentrates on minimal THD%, factors like accuracy, minimum number of switches, and cost demands for advanced switching strategy algorithms. This paper compares the improved switching angle method to the existing algorithm by considering VPEAK, VRMS, and %THD for the 35-level LUO progression-based switched ladder inverter. The IC layout for the improved switching control is developed using the hardware description language code in the Cadence tool and validated by cross-compiling in Simulink MATLAB.
Volume: 16
Issue: 2
Page: 974-981
Publish at: 2025-06-01
1 2 3
...
2097 2098
Show 297 of 2098

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