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

Assessing Saudi learners’ engagement with social media in English classrooms

10.11591/ijere.v14i3.28509
Mohammad Jamshed , Iftikhar Alam , Abduh Almashy , Wahaj Unnisa Warda
The study assessed Saudi English as a foreign language (EFL) learners’ perspectives on utilizing social media for educational and instructional activities, their experience with learning and teaching on social media, and how frequently they utilize these platforms to improve their language skills. The researcher randomly selected 288 EFL students from male and female campuses of College of Science and College of Business Administration, Prince Sattam bin Abdulaziz University. Respondents answered a questionnaire containing modified items from earlier studies. The data collected was examined using quantitative methods. The findings of the study revealed that tech-savvy Saudi EFL learners held exceptionally positive attitudes toward social media utilization as an effective language learning tool. It was also revealed that both learners and instructors had a very positive experiences utilizing social media for educational purposes, commonly employing it for different academic and educational activities in EFL classes. The study has implications for students and instructors because social networking sites and social media may be tailored to meet the demands of tech-savvy Saudi learners when conventional instruction no longer conforms to the taste of modern learners.
Volume: 14
Issue: 3
Page: 2450-2460
Publish at: 2025-06-01

Validation of principal’s innovation leadership scale using factor analysis in Malaysian school context

10.11591/ijere.v14i3.30397
Dayang Rafidah Syariff M. Fuad , Khalip Musa , Mat Rahimi Yusof , Bernard Swart , Ting Pick Dew , Goh Kok Ming , Amrina Rosyada Abdullah
This study addresses the need for a standardized tool to assess innovation leadership in secondary education. Despite its importance, no established instrument exists for evaluating and developing innovation leadership among school administrators. The principal innovation leadership scale (PILS) was developed and validated to bridge this gap. The process involved a literature review, expert consultations, and an initial 58-item pool. Exploratory and confirmatory factor analysis (CFA) refined the scale to 18 items across five dimensions, demonstrating strong model fit (comparative fit index (CFI)=0.957, root mean square error of approximation (RMSEA)=0.080, incremental fit index (IFI)=0.958, normed fit index (NFI)=0.947, Tucker-Lewis’s index (TLI)=0.90). The fitted model indicated a satisfactory fit, confirming that the five latent constructs effectively measure the observed variables in the questionnaire. The PILS offers a standardized tool for assessing innovative leadership among school leaders, enabling targeted improvement strategies and informing professional development programs. This study significantly contributes to the discourse on innovation leadership in education by providing a valuable instrument for evaluating and enhancing school leadership practices.
Volume: 14
Issue: 3
Page: 1790-1803
Publish at: 2025-06-01

Designing a computational thinking module for STEM teachers: a design and development approach

10.11591/ijere.v14i3.32540
Sanura Jaya , Rozniza Zaharudin , Parvinder Singh s/o Amar Singh
This study investigates the necessity of computational thinking (CT) skills integration among science, technology, engineering, and mathematics (STEM) secondary school teachers, focusing on the development of the McodE pedagogical module for the topic of heat in solar still projects. Utilizing a design and development research (DDR) approach, the research aimed to design and develop a CT module tailored to enhance teachers’ pedagogical strategies in solar still project. The case study was employed with 32 STEM secondary school teachers, through purposive sampling participated in the study based on their experience in integrating technology into pedagogy. A pre-test and post-test design was employed during a two-day workshop to assess the participants’ CT skills before and after the intervention. An additional open-ended interview was conducted among three teachers to support the quantitative data. The results revealed significant improvements in various aspects of CT application. The findings demonstrated substantial increases in teachers’ abilities to integrate CT into their teaching practices. The mean for pre-test score was 43.25, which significantly increased to 67.37 in the post-test, indicating a marked enhancement in CT skills. The t-test statistics for the pre-test (t=31.04, df=31, p<.001) and post-test (t=49.94, df=31, p<.001) confirmed a highly significant differences between the pre-test and post-test scores. The open-ended interview also showed the strong interest and necessity of the CT module among the respondents. The study concludes that there is a critical need for CT module among STEM teachers to better prepare students for the demands of modern STEM education.
Volume: 14
Issue: 3
Page: 2197-2206
Publish at: 2025-06-01

Co-training pseudo-labeling for text classification with support vector machine and long short-term memory

10.11591/ijai.v14.i3.pp2158-2168
Sri Handayani , Rizal Isnanto , Budi Warsito
The scarcity of labeled data may hamper training text-processing models. In response to this issue, a novel and intriguing strategy that combines the co-training method and pseudo-labeling design is applied to enhance the model's performance. This method, a component of an efficient semi-supervised learning paradigm for processing and comprehending text, is a fresh perspective in the field. The model, which combines a support vector machine (SVM) for classification and long short-term memory (LSTM) for text sequence interpretation, is a unique approach. By introducing samples that may be marginalized in the labeled data, the co-training approach could help solve the class imbalance problem by using a small amount of labeled data and the rest unlabeled. This study assesses the model's performance using a student dataset from higher education institutions to establish a threshold for each model's degree of confidence and ascertain how much the model can be generalized depending on the threshold. The SVM threshold was calculated as >=0.88, and the LSTM threshold was calculated as >=0.5 using a mixture of confidence metrics.
Volume: 14
Issue: 3
Page: 2158-2168
Publish at: 2025-06-01

Active online learning with remote sensing data in higher education

10.11591/ijere.v14i3.30096
Khuralay Moldamurat , Sabyrzhan Atanov , Karakat Nagymzhanova , Luigi La Spada , Dinara Kalmanova , Sapiya Tazhikenova , Syrym Zhanzhigitov , Altynbek Zhakupov , Assylkhan Yessilov , Makhabbat Bakyt
The increasing popularity of online learning has created a need for effective methods to enhance educational quality. This study addresses this need by developing and evaluating an active online learning model incorporating remote sensing data (RSD). The study included a pedagogical experiment with 181 students divided into control and experimental groups. The model included an interactive database, a web portal with tools for processing and visualizing RSD, and the implementation of active learning methods. Data were collected through testing, analysis of completed projects, and questionnaires. Quantitative and qualitative analysis methods were used to process the data. The pedagogical experiment showed that the model improved students’ average scores, increased the number of students with high levels of knowledge acquisition, and enhanced motivation. Thus, the use of RSD and active learning methods in online education is a promising approach to improve the quality of the educational process and foster students’ digital competence.
Volume: 14
Issue: 3
Page: 2346-2357
Publish at: 2025-06-01

Examining the research and academic writing needs of preservice elementary teachers: a mixed-methods study

10.11591/ijere.v14i3.29888
Bonjovi Hassan Hajan , Abubakar Jaddal Radjuni , Alhisan Utoh-asim Jemsy
In teacher education, research plays a central role in the preparation and professional development of preservice teachers. Preservice teachers’ knowledge of research and their academic writing skills serve as a pathway for successfully completing a research project. This sequential-explanatory mixed methods study was conducted to provide an in-depth understanding of the preservice elementary teachers’ needs on research and academic writing. A total of 80 preservice elementary teachers participated in the study. Data were collected online using a structured questionnaire and an interview guide. Drawing from both the quantitative and qualitative analyses, a multitude of the participants’ research and academic writing needs were uncovered. On the research component, the participants’ needs encompassed a wide range of areas, including knowledge of research methodology, access to quality data, expert support, among others. As for the academic writing, the participants’ needs varied from language use, structure and mechanics to the writing process. Based on the findings, the study outlines practical implications useful for teaching research writing within the context of teacher education.
Volume: 14
Issue: 3
Page: 2070-2078
Publish at: 2025-06-01

Review on class imbalance techniques to strengthen model prediction

10.11591/ijai.v14.i3.pp1727-1742
Hemalatha Putta , Geetha Mary Amalanathan
Data is a fundamental component in various fields, including science, business, health care, and technology. It is often processed, stored, and analyzed using computer systems and software applications. The importance of data lies in its ability to provide valuable insights, drive innovation, and improve decision-making processes. However, it’s essential to handle and manage data responsibly to address privacy and ethical considerations. Data mining (DM) involves discovering patterns, trends, correlations, or useful information from large datasets. Data dredging or DM and machine learning (ML) are closely related fields that both involve the analysis of data to discover patterns and make predictions. DM focuses on extracting knowledge from data; ML emphasizes the development of algorithms that can do analysis. The two fields are interconnected, and the techniques from one state of art integrated into the processes of the other. In ML the class imbalance problem occurs due to the class distribution in the training data is not equal. Imbalanced classification refers to a condition where a particular class (minority class) is under represented parallelled to another class (majority class) in a dataset. This paper furthermore emphasizes on the synthetic minority oversampling technique (SMOTE) variants employed by the researchers, and highlights the limitations the work.
Volume: 14
Issue: 3
Page: 1727-1742
Publish at: 2025-06-01

Deep neural network for maximizing output power estimation of dual-axis solar tracker

10.11591/ijai.v14.i3.pp2229-2235
Humairoh Ratu Ayu , Rifki Mohamad Kurniawansyah , Aqua Risma Diansari
The abundance of solar energy sources has encouraged many researchers to maximize solar photovoltaic (PV) output power using dual-axis solar tracking. However, environmental conditions, time of day, and the angle of movement of the solar tracker can affect the resulting power output. This study aims to predict the power output of dual-axis solar tracking in order to maintain the power’s stability and quality. Deep neural networks (DNN) with variations of 5 and 6 hidden layers have been proposed. The dataset used in this study was obtained from observation results and then divided into 80% training data and 20% testing data. A series of algorithms are used to recognize relationship patterns between input and hidden layers, between hidden layers, as well as hidden layers and output. Statistical results show that DNN with a variation of 6 hidden layers is better at estimating solar tracking power output with a mean absolute percentage error (MAPE) value of 12.328%, mean square error (MSE) of 0.332, and mean absolute error (MAE) of 0.425. This study can be used as a reference in utilizing artificial intelligence to predict the output power of solar panels as a renewable energy source.
Volume: 14
Issue: 3
Page: 2229-2235
Publish at: 2025-06-01

TPACK-universal design for learning for Malaysian intellectual disability education: low-high tech integration

10.11591/ijere.v14i3.31801
Rosnani Saini , Zaimuariffudin Shukri Nordin , Mohd Hafizan Hashim , Mohamad Taha Abol
The integration of technological pedagogical content knowledge (TPACK) and universal design for learning (UDL) in special education remains challenging, particularly for intellectual disabilities (ID) learners in East Malaysia. This study investigated how special education teachers utilize technology tools and integrate UDL principles with TPACK frameworks to support ID learners, addressing the need for inclusive education aligned with sustainable development goal 4 (SDG 4). Using a qualitative approach, data were collected through semi-structured interviews, classroom observations, and document analysis from four purposively selected special education teachers in two East Malaysian secondary schools offering special education integration programs (SEIP). Thematic analysis revealed three key findings: i) low technology supports for accessibility and engagement; ii) high technology integration for personalization and empowerment; and iii) integrating of TPACK and UDL principles challenges due to limited understanding and resource constraints. The study concluded that while teachers show commitment to technology use, there is a pressing need for targeted professional development to enhance TPACK and UDL competencies. These findings align with SDG 4’s focus on quality education for all, emphasizing how enhanced teacher training and effective technology integration can significantly improve the quality and inclusivity of education for ID learners.
Volume: 14
Issue: 3
Page: 2099-2106
Publish at: 2025-06-01

CGDE-YOLOv5n: a real-time safety helmet-wearing detection algorithm

10.11591/ijeecs.v38.i3.pp1765-1781
Wanbo Luo , Ahmad Ihsan Mohd Yassin , Khairul Khaizi Mohd Shariff , Rajeswari Raju
Due to numerous parameters and calculations, existing safety helmetwearing detection models are challenging to deploy on embedded devices. Therefore, this paper proposed a you only look once (YOLO) v5n-based lightweight detection algorithm called CGDE-YOLOv5n to address the shortcomings in the following areas: (i) the YOLOv5n algorithm was selected to minimize the model’s parameters and calculations, reducing the hardware cost. (ii) The convolutional block attention module (CBAM) was integrated into the backbone to enhance the network’s feature extraction capability. (iii) The neck was improved using the efficient re-parameterized generalized feature pyramid network (efficient RepGFPN) to enhance the multi-scale object detection capability. (iv) The C3 module was improved using the deformable ConvNets v2 (DCNv2) module to enhance the network’s adaptability to geometric changes of objects. (v) The complete intersection over union (CIoU) loss was replaced with focal-efficient IoU (focal-EIoU) loss to reduce the missed detection rate. Experimental results demonstrated that the customized gradient descent estimation (CGDE)- YOLOv5n achieved a mean average precision (mAP) 50 of 89.5% and recall of 84%, which is 1% and 0.8% higher than the YOLOv5n. In particular, the recall of workers not wearing safety helmets increased by 1.7%. Furthermore, the improved model achieved a detection speed of 68.5 frames per second (FPS), meeting the real-time requirements.
Volume: 38
Issue: 3
Page: 1765-1781
Publish at: 2025-06-01

A modified learning by design approach to support preservice teachers’ technology integration into teaching

10.11591/ijere.v14i3.32507
Tang Junhong , Jia Wei Lim , Meng Yew Tee
Integrating technology into instructional practices continues to pose a substantial challenge for preservice teachers, a challenge that has not been sufficiently addressed by existing teacher education programs. This study seeks to bridge this gap by implementing, evaluating, and refining a modified learning by design (mLBD) approach through a two-cycle design-based research (DBR) methodology. The research was conducted with 27 preservice teachers in the first cycle and 29 in the second cycle. Data were collected through semi-structured interviews, group lesson plans, micro-teaching sessions, peer feedback, and group discussions. The content analysis and constant comparative analysis identified two key impediments to effective technology integration: i) a superficial understanding of teaching methods and approaches and ii) a lack of targeted instructional guidance. Conversely, three facilitating factors were found to support preservice teachers’ technology integration: i) a deep understanding of teaching methods and approaches; ii) targeted guidance from the instructor; and iii) authentic experiences in collaborative curriculum design and redesign. These findings suggest that the mLBD approach offers valuable insights for enhancing teacher education programs’ capacity to support preservice teachers in effectively integrating technology into their instructional practices.
Volume: 14
Issue: 3
Page: 2079-2087
Publish at: 2025-06-01

Factors affecting high school students’ academic performance: a case study in Vietnam

10.11591/ijere.v14i3.32912
Le Thai Hung , Dang Thi Thanh Thuy , Tran Van Thien
This study investigates the factors that influence academic achievement among Vietnamese high school students, with an emphasis on a case study conducted at a specific school. To identify key determinants of students’ academic success, a quantitative survey comprising questionnaires was distributed to 438 high school students. Exploratory factor analysis (EFA) was utilized, followed by Pearson correlation coefficient and regression analysis to assess the relationships between independent variables (school-related and student-related factors) and the dependent variable (student performance). The data show that teacher competency has the greatest influence on students’ academic success, closely followed by students’ learning techniques. In addition, student motivation has a significant impact on their success. The results underscore the importance of a supportive home and school environment in fostering student achievement. The results highlight the need for enhanced teacher training to improve educational quality. It is also essential to promote students’ effective learning techniques, and ensure consistency in their study. This research contributes to a deeper understanding of the complex interplay of factors impacting academic performance and offers insights for educators and policymakers aiming to enhance educational outcomes in Vietnam. Recommendations for future research and practical interventions are discussed.
Volume: 14
Issue: 3
Page: 2236-2248
Publish at: 2025-06-01

Comparison of deep learning models: CNN and VGG-16 in identifying pornographic content

10.11591/ijai.v14.i3.pp1884-1899
Reza Chandra , Adang Suhendra , Lintang Yuniar Banowosari , Prihandoko Prihandoko
In 2020, a total of 59,741 websites were blocked by the Indonesian government due to containing negative content, including pornography, with 14,266 websites falling into this category. However, these blocked websites could still be accessed by the public using virtual private networks (VPNs). This prompted the research idea to quickly identify pornographic content. This study aims to develop a system capable of identifying websites suspected of containing pornographic image content, using a deep learning approach with convolutional neural network (CNN) and visual geometry group 16 (VGG-16) model. The two models were then explored comprehensively and holistically to determine which model was most effective in detecting pornographic content quickly. Based on the findings of the comparison between testing the CNN and VGG-16 models, research results showed that the best test results were obtained in the eighth experiment using the CNN model at an epoch value level of 50 and a learning rate of 0.001 of 0.9487 or 94.87%. This can be interpreted that the CNN model is more effective in detecting pornographic content quickly and accurately compared to using the VGG-16 model.
Volume: 14
Issue: 3
Page: 1884-1899
Publish at: 2025-06-01

The main weaknesses of using Manhattan distance for solving sliding tile puzzles

10.11591/ijai.v14.i3.pp2423-2432
Mohammed Nayef Al Refai , Zeyad Mohammed Jamhawi , Ahmed Ali Otoom , Adai Al-Momani , Hayel Khafajeh , Issa Atoum
Heuristics are a big improvement over blind searching in pathfinding. The node's test, run, and finish time are reasonable. Artificial intelligence (AI) uses Manhattan distance (MD), a good and simple heuristic, in various subjects to reduce the number of exploring nodes while requiring fewer calculations. The MD heuristics examined approximately 25 times fewer states than the blind search. Unfortunately, can’t reach the goal of pathfinding when the domain size increases, as it becomes similar to brute force or blind search algorithm results. Previous studies have concentrated on MD's weakness, specifically its low bound value for calculation results, and attempted to improve this value in various ways. Unfortunately, to our knowledge, none of the presented research has been able to find the optimal path for all slide tile puzzle sizes. This work discusses the detailed reasons for the low bound value and other related factors that contribute to its weakness. This paper discovered that the distribution of MD values within the domain, not lowbound values, is the critical issue that complicates the search. The MD's summation method for all tiles has an impact on the calculated duplication values. The total number of nodes in the optimal path also affects the search performance.
Volume: 14
Issue: 3
Page: 2423-2432
Publish at: 2025-06-01

Comprehensive survey of automated plant leaf disease identification techniques: advancements, challenges, and future directions

10.11591/ijai.v14.i3.pp1719-1726
Shilpa Patil , Ashokkumar P. Sundramma
This survey paper extensively researches into the domain of timely plant disease detection, crucial for alleviating agricultural losses and ensuring food security. It accentuates the significance of early identification in efficient disease management and informed agricultural decisions. Conventional manual methods, constrained by labor intensity and subjectivity, pave the way for investigating automated disease detection avenues, prominently leveraging image processing and deep learning techniques. In the subsequent exploration of related work, a panoramic view encompasses an array of methodologies, encompassing neural networks and convolutional neural networks (CNNs), paramount in automated disease detection. The synthesis of image processing intricacies, pre-processing strategies, and feature extraction paradigms alongside deep learning models is meticulously expounded. As the field advances, the paper accentuates lingering challenges in early-stage detection, alongside insightful solutions like data augmentation and sophisticated deep learning models. This survey paper culminates by underlining the dynamic trajectory of automated plant disease identification, accentuating its paramount role in upholding global food security.
Volume: 14
Issue: 3
Page: 1719-1726
Publish at: 2025-06-01
1 2 3
...
2097 2098
Show 296 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