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

29,602 Article Results

RAC: a reusable adaptive convolution for CNN layer

10.11591/ijeecs.v41.i2.pp753-763
Nguyen Viet Hung , Phi Dinh Huynh , Pham Hong Thinh , Phuc Hau Nguyen , Trong-Minh Hoang
This paper proposes reusable adaptive convolution (RAC), an efficient alternative to standard 3×3 convolutions for convolutional neural networks (CNNs). The main advantage of RAC lies in its simplicity and parameter efficiency, achieved by sharing horizontal and vertical 1×k/k×1 filter banks across blocks within a stage and recombining them through a lightweight 1×1 mixing layer. By operating at the operator design level, RAC avoids post-training compression steps and preserves the conventional Conv–BN–activation structure, enabling seamless integration into existing CNN backbones. To evaluate the effectiveness of the proposed method, extensive experiments are conducted on CIFAR-10 using several architectures, including ResNet-18/50/101, DenseNet, WideResNet, and EfficientNet. Experimental results demonstrate that RAC significantly reduces parameters and memory usage while maintaining competitive accuracy. These results indicate that RAC offers a reasonable balance between accuracy and compression, and is suitable for deploying CNN networks on resource-constrained platforms.
Volume: 41
Issue: 2
Page: 753-763
Publish at: 2026-02-01

An automatic stock price movement prediction using circularly dilated convolutions with orthogonal gated recurrent unit

10.11591/ijeecs.v41.i2.pp823-832
Durga Meena Rajendran , Maharajan Kalianandi , Bhuvanesh Ananthan
Recently, stock trend analysis has played an integral role in gaining knowledge about trading policy and determining stock intrinsic patterns. Several conventional studies reported stock trend prediction analysis but failed to obtain better performance due to poor generalization capability and high gradient vanishing problems. In light of the need to forecast stock price trends using both textual and empirical price data, this research proposed a novel hybridized deep learning (DL) model. Preprocessing, feature extraction, and prediction are the three effective stages that the created research goes through in order to properly estimate the stock movements. Data cleaning, which helps improve data quality, is calculated in the preprocessing step. Next, we use the created CDConv-OGRU technique-hybridized circularly dilated convolutions with orthogonal gated recurrent units-to extract features and make predictions. Python serves as the platform for processing and analyzing the created approach. This research uses a publicly accessible StockNet database for testing and compares results using a number of performance metrics, including accuracy, recall, precision, Mathew’s correlation coefficient (MCC), and f-score. In the experimental part, the created approach obtains a total of 95.16% accuracy, 94.8% precision, 94.89% recall, 95% confidence interval, and 0.9 MCC, in that order.
Volume: 41
Issue: 2
Page: 823-832
Publish at: 2026-02-01

Stable and accurate customer churn prediction: comparative analysis of eight classification algorithms

10.11591/ijeecs.v41.i2.pp655-665
Vincent Alexander Haris , Muhammad Ilyas Arsyad , Nathanael Septhian Adi Nugraha , Yasi Dani , Maria Artanta Ginting
Predicting customer churn is a challenging problem in many subscription-based industries, though it is considered more cost-effective than acquiring new customers. In this research, customer churn is predicted using a public dataset from an internet service provider, with 72,274 instances and 55% churn rate. The main contribution is to provide a comprehensive comparison of the stability and performance of eight classification algorithms in customer churn prediction using a large-scale public dataset. The research process includes data collection, data preprocessing, feature engineering, and model evaluation. The metrics evaluation presents test accuracy, accuracy gap, precision, recall, F1-Score, and ROC AUC, with stratified K-Fold cross-validation. Since the proportion of churn and non-churn in the dataset is relatively balanced, the F1-score is considered as the primary evaluation metric, as it provides a balanced assessment of precision and recall for both classes. The results show that CatBoost and XGBoost are the most effective models that achieve high F1-scores of 94.97% and 94.92%, respectively.
Volume: 41
Issue: 2
Page: 655-665
Publish at: 2026-02-01

A hybrid edge–cloud computing framework for low-latency, energy-efficient, and sustainable smart city applications

10.11591/ijeecs.v41.i2.pp791-799
Kamal Saluja , Tanya Khaneja , Sunil Gupta , Reema Goyal , Wai Yie Leong
Smart-city applications demand ultra-low latency, high reliability, and sustainable operation, which are difficult to achieve using cloud-only or edge-only computing paradigms. This study suggests a carbon-conscious architecture for managing smart cities’ intelligent job offloading between the edge and the cloud. This is made possible by the Internet of Things and driven by reinforcement learning (RL). A deep Q-network (DQN) is used to dynamically assign tasks to cloud servers and edge nodes based on how much energy they use, how long it takes to send data over the network, and how much bandwidth they have. A lightweight permissioned blockchain layer makes sure that data is correct across all of its parts, and carbon-aware scheduling puts low-carbon resources first. EdgeCloudSim is used to test the system with real-world smart city workloads. When compared to systems that simply use the cloud, the proposed solution showed a 64.6% drop in average latency, a 24.2% drop in energy use, and a 15% drop in carbon emissions. Combining artificial intelligence (AI)-driven orchestration with scheduling that takes sustainability into account in a hybrid edge-cloud environment yields positive outcomes.
Volume: 41
Issue: 2
Page: 791-799
Publish at: 2026-02-01

Driving connectivity: a thorough review of networking protocols in electric mobility

10.11591/ijeecs.v41.i2.pp764-772
Ramandeep Sandhu , Harpreet Kaur Channi , Nimay Chandra Giri , Pulkit Kumar , Mohamed A. Elaskily , Mohamed A. Hebaishy
The rapid advancement of technology has transformed the automotive sector through intelligent systems for safety, control, and infotainment. This study reviews key networking protocols controller area network (CAN), local interconnect network (LIN), FlexRay, MOST, Ethernet, and Master-Slave used in electric vehicles (EVs) in India and worldwide, providing insights into their application trends across different regions. CAN provides reliable low-latency communication for safety-critical functions (1 Mbps), while CAN FD extends support up to 12 Mbps. LIN and Master-Slave topologies enable cost-effective low-speed operations (2–20 kbps). FlexRay ensures real-time communication (10–100 Mbps), and MOST supports 150 Mbps for multimedia applications. Ethernet offers superior bandwidth up to 10 Gbps for advanced driver assistance and autonomous systems, but it involves higher complexity and cost. The review identifies key challenges in interoperability, scalability, and cybersecurity and evaluates protocol suitability for next-generation EV architectures. It also integrates Industry 5.0 principles and SDGs 7, 9, and 13, emphasizing human-centric, sustainable, and resilient mobility.
Volume: 41
Issue: 2
Page: 764-772
Publish at: 2026-02-01

Fraud detection using TabNet* classifier: a machine learning approach

10.11591/ijeecs.v41.i2.pp601-613
G. Anish Mary , S. Sudha
Detecting fraudulent transactions is a big challenge in the digital financial world. Transaction volumes are growing quickly, and new attack methods often outstrip traditional detection systems. Current fraud-detection models usually lack clarity and do not perform reliably on unbalanced real-world datasets. This highlights the urgent need for clear and explainable deep-learning methods for tabular financial data. This paper presents an interpretable deep learning framework built on the TabNet classifier. It uses attention-driven feature selection, sparse representation learning, and sequential decision reasoning to model complex interactions among transactional, demographic, and geographical factors. The model was tested on a real-world credit card transaction dataset with 23 features. It achieved 99.69% accuracy, a 0.975 F1-score, and a 0.956 ROC-AUC. This performance outperforms benchmark models such as random forest, XGBoost, LightGBM, and logistic regression. In addition to outstanding predictive results. Furthermore, interpretability is enhanced by TabNet's attention-based feature attribution. This facilitates the clear understanding of model decisions, supporting its use in regulated financial environments where precision and responsibility are crucial.
Volume: 41
Issue: 2
Page: 601-613
Publish at: 2026-02-01

Dengue case forecasting using multi-step deep learning models with attention layers

10.11591/ijeecs.v41.i2.pp546-554
Anibal Flores , Hugo Tito Chura , Victor Yana Mamani , Charles Rosado Chavez
Dengue is a viral infection that is transmitted from mosquitoes to people. It is more common in regions with tropical and subtropical climates. Accurate dengue forecasting is important to make the right decisions on time. In this sense, in this study, deep learning models with attention mechanisms such as long short-term memory (LSTM), bidirectional LSTM (BiLSTM), gated recurrent unit (GRU), and bidirectional GRU (BiGRU) were implemented, and to improve the accuracy of model results they were linearly interpolated. According to the results, in most cases, linear interpolation improved the implemented deep learning models with attention mechanisms in terms of mean squared error (RMSE), mean absolute percentage error (MAPE) and R2. For one-step predictions, improvements occurred between 0.08% and 0.13%, for two-step predictions between 8.55% and 22.81%, for three-step predictions between 0.26% and 23.88%, for four-steps between 0.15% and 4.79%, and between 0.11% and 0.19% for five-step predictions. Based on the obtained results, it is possible to experiment with other types of interpolations such as polynomial, spline, and inverse distance weighting (IDW).
Volume: 41
Issue: 2
Page: 546-554
Publish at: 2026-02-01

The role of digital technologies in the transformation of ethical norms in the educational process

10.11591/ijere.v15i1.32497
ZuoYuan Liu , Alena Gura , Olga Pavlovskaya , Nataliya Antonova
In contemporary education, which increasingly incorporates digital technologies, the issue of adhering to ethical norms by both educators and students has gained particular relevance. This study aims to examine the impact of digital technologies on the transformation of ethical standards within the educational process. A survey was conducted among 45 educators and 345 students from three universities before and after the transition to remote learning, to assess changes in the adherence to ethical standards. The results revealed that after the implementation of remote learning, there was a significant increase in the level of adherence to ethical norms among educators (up to 98%) and students (up to 91%). Additionally, there was an improvement in academic performance, with 46% of students achieving a high level of success following the transition to remote learning. The evaluation of the impact of digital technologies on ethical transformation was found to be moderate but positive. Thus, digital technologies can serve as an effective tool for enhancing ethical standards and improving educational outcomes, particularly in the context of remote learning. These findings underscore the importance of integrating digital technologies into the educational process as a means of supporting ethical culture.
Volume: 15
Issue: 1
Page: 943-954
Publish at: 2026-02-01

Understanding student motivation towards achieving goals among college students: an exploratory research

10.11591/ijere.v15i1.33551
Nilda Wines Balsicas , Eddie Rima Cabrera , Elgien Candelaria Padohinog , Freddie Bulauan
Motivation could be the greatest currency to succeed in a student’s academic life. This study analyzed academic motivation after students were affected by the pandemic or after their two-year hiatus from active academic face-to-face activities. Moreover, this research examined whether students have influenced academic motivation in terms of gender and degree of program. Using a descriptive-sequential research design, 652 college students at St. Dominic College of Asia, Cavite, Philippines, took part in this study. A survey questionnaire adapted from the academic motivation scale (AMS-C 28) college version was used to determine the level of academic motivation of students. Open-ended questions were provided to the students relating to what motivates them to study and to which students are motivated through techniques during online learning. Findings revealed that the degree of program has a positive effect on student motivation, whereas gender does not significantly associate with motivation. Students showed appreciation for a greater convenience to study because of the technology; however, lack of interaction makes it more challenging for some. Helping students as teachers to keep track of their tasks can make them become great learners and succeed with confidence and determination through their personal and scholarly lives.
Volume: 15
Issue: 1
Page: 448-456
Publish at: 2026-02-01

Organizing students’ research activities based on STEM elements in the study process

10.11591/ijere.v15i1.35075
Shakhislam Laiskhanov , Seminar Yerkegul
Although science, technology, engineering, and mathematics (STEM) integration in higher education is advancing globally, its adoption in geography programs in Kazakhstan remains limited. This study examines the effectiveness of embedding selected STEM elements into the course “Geography of Aktobe Oblаst” as а means of strengthening students’ research competencies. A mixed-method design was employed, combining analysis of satellite-derived indicаtоrs, wоrk with geоspаtiаl plаtfоrms (аrcGIS Prо, EоSDа Crоp Mоnitоring, and Eо Brоwser), prаcticаl climаte-bаsed cаlculаtiоns, clаssrооm оbservаtiоns аnd cоmpаrаtive аssessment аnаlysis. The 24 students pаrticipаted in the interventiоn, cоmpleting а series оf inquiry-driven tаsks invоlving the Normalized Difference Vegetation Index (NDVI) interpretаtiоn, spectrаl reflectаnce аnаlysis аnd climаtоlоgicаl cоrrelаtiоns. Survey dаtа indicаted thаt mоre thаn 90% оf pаrticipаnts repоrted imprоved understаnding оf envirоnmentаl prоcesses, while mаny nоted gаins in аnаlyticаl reаsоning аnd dаtа-driven interpretаtiоn. Midterm perfоrmаnce results shоwed а mоdest but cоnsistent imprоvement fоllоwing the implementаtiоn оf STEM-оriented аssignments. The findings suggest thаt structured integrаtiоn оf geоspаtiаl аnd аnаlyticаl STEM tооls cаn meаningfully suppоrt the develоpment оf reseаrch skills in university geоgrаphy cоurses. By enаbling students tо wоrk with аuthentic envirоnmentаl dаtаsets, the аpprоаch cultivаtes higher-оrder reаsоning, interdisciplinаry thinking аnd sustained learner engаgement. The results highlight the pоtentiаl fоr brоаder аpplicаtiоn оf STEM-bаsed instructiоnаl mоdels in Kаzаkhstаni higher educаtiоn аnd underscоre the need fоr further lоngitudinаl аnd cоmpаrаtive studies tо evаluаte lоng-term impаcts.
Volume: 15
Issue: 1
Page: 705-713
Publish at: 2026-02-01

Assessing the impact of a business-oriented educational course on the development of entrepreneurial thinking in pre-service primary school teacher

10.11591/ijere.v15i1.36257
Nurzhaugan Balginbayeva , Aktoty Akzholova , Zhuldyzai Baimaganbetova , Abay Duisenbayev , Saule Yerkebayeva , Alua Smanova , Elmira Aitenova
This study aimed to assess the impact of a business-oriented educational course on the development of key components of entrepreneurial thinking among pre-service primary school teachers. The research involved 220 students from M. Dulati Taraz University. A pre-test/post-test design was used with an author-developed questionnaire. Entrepreneurial thinking was assessed both before and immediately after the course. Statistical analysis revealed a significant increase in the overall level of entrepreneurial thinking and its key components, including initiative, creativity, risk-taking, result orientation, and persistence. The course featured innovative teaching methods such as project-based learning, case studies, and business games, and was offered as an elective module on an experimental educational platform. The findings are consistent with international research, highlighting the importance of integrating entrepreneurial thinking into teacher training to enhance professional preparedness. These findings can help shape modern educational programs in Kazakhstan and the countries of the Commonwealth of Independent States, in line with global trends and the challenges of the 21st century.
Volume: 15
Issue: 1
Page: 511-523
Publish at: 2026-02-01

Determinants of AI adoption for authentic assessment in open university systems

10.11591/ijere.v15i1.36368
Kemmanat Mingsiritham , Gan Chanyawudhiwan
Artificial intelligence (AI) is transforming higher education through personalized learning and innovative assessment methods. This study explores the factors influencing AI adoption for authentic assessment in open and distance learning environments. Using a survey of 185 instructors, an integrated framework based on the theory of planned behavior (TPB) and the technology acceptance model (TAM) was tested via structural equation modeling (SEM). Key constructs included attitude toward the behavior (ATT), subjective norm (SN), perceived behavioral control (PBC), self-efficacy (SE), and barriers to AI adoption (BAA), with intention to use AI (INT) and actual adoption behavior (AAB) as outcomes. Results showed that SE, ATT, PBC, and SN positively influenced INT, which in turn strongly predicted AAB. In addition, BAA had no significant effect on INT but showed a negative impact on AAB. The model demonstrated good fit and explained substantial variance (R²=0.746 for INT; R²=0.649 for AAB). These findings highlight the importance of enhancing instructors’ confidence, control, and institutional support while reducing perceived barriers. Strategic investments in training, infrastructure, and leadership support are crucial to advancing AI-enabled authentic assessment in higher education.
Volume: 15
Issue: 1
Page: 479-488
Publish at: 2026-02-01

Integration in reading literacy: a systematic review of pedagogical, professional, and engagement approaches

10.11591/ijere.v15i1.34044
Md Zahril Nizam Md Yusoff , Wan Nur Aida Sakinah Wan Jusoh , Norfaizah Abdul Jobar , Noor Zuhidayah Muhd Zulkipli , Muhamad Fadzllah Zaini , Tajul Shuhaizam Said
This systematic literature review (SLR) following preferred reporting items for systematic reviews and meta-analyses (PRISMA) 2020 who explores integrated approaches to reading literacy across pedagogical integration, teacher development, and student engagement. From 1,108 retrieved articles, 59 article high-quality studies were selected for in-depth synthesis. Based on all studies published between 2020 and 2024, the findings reveal that multimodal instruction, inclusive pedagogy, and proposes a cohesive framework linking instructional innovation, teacher agency, and learner experience, offering actionable insights for educators and policymakers. The analysis identified three key thematic drivers of literacy improvement. First, integrated pedagogical practices such as multimodal, bilingual, and play-based instruction enhance literacy by making learning more inclusive, interactive, and context-responsive. Second, teacher professional development through targeted training in visual literacy, inclusive pedagogy, and digital tools strengthens instructional quality and prepares educators for evolving literacy demands. These approaches reflect current trends in instructional innovation and professional capacity building. Third, student engagement is significantly elevated through identity-driven learning, project-based tasks, and emotionally supportive environments that foster confidence, motivation, and deeper literacy outcomes. Together, these themes forms a new integration model that links teaching practices, teacher agency, and student experience into a cohesive literacy framework. The findings offer practical, evidence-based insights for policymakers, curriculum designers, and practitioners aiming to improve reading literacy across diverse settings.
Volume: 15
Issue: 1
Page: 771-783
Publish at: 2026-02-01

Empowering educators and students through contextualized global citizenship for sustainable development

10.11591/ijere.v15i1.35810
Erwin B. Berry , El Dixon G. Plazo , Ofelia L. Correos
This study explores how educators and students in Philippine secondary schools conceptualize global citizenship education (GCE) and understand their roles in advancing the sustainable development goals (SDGs). Despite its prominence in global education agendas, GCE remains inconsistently understood across local contexts. Using a qualitative research design, in-depth interviews were conducted with 21 teachers and students in Surigao del Sur. Thematic analysis revealed seven interconnected themes: i) holistic education: framing global citizenship beyond academics; ii) cultural sensitivity and respect for diversity; iii) active engagement and global awareness; iv) education as a channel for sustainable development; v) becoming a global citizen as a personal journey; vi) technology and global connectivity; and vii) teaching values for global responsibility. Findings indicate that while both groups support GCE, their interpretations are shaped by lived experiences, institutional conditions, and cultural environments. Teachers highlighted intentional instruction and moral formation, whereas students emphasized identity development, participation, and global awareness. However, gaps remain in critical reflection and structural understanding. In response, this study introduces the contextualized empowerment framework, a strategic model that integrates civic action, values, identity, and digital literacy to guide localized and ethical implementation of GCE. The framework offers actionable insights for curriculum development, teacher training, and educational policy reforms.
Volume: 15
Issue: 1
Page: 16-27
Publish at: 2026-02-01

Enhancing academic resilience through motivation and strategy: evidence from Malaysian boarding schools using SDT

10.11591/ijere.v15i1.35494
Mohd Sofian Omar Fauzee , Shaohua Zhang , Marni Ishak , Li Ma , Mo Hou , Wenjie Zhang , Muhammad Nazrul Hakim Abdullah , Akhmad Habibi , Daljit Singh Gurbaksh Singh , Mohd Hanafi Mohd Yasin , Wan Suraya Wan Nik
This study investigates the relationship between student motivation and self-regulated learning strategies among Malaysian boarding school students, using self-determination theory (SDT) as its theoretical foundation. A total of 328 form four students from four northern Malaysian boarding schools participated. Using a validated version of the motivated strategies for learning questionnaire (MSLQ) and analyzed through second-order partial least squares structural equation modeling (PLS-SEM), results revealed a significant positive relationship between motivational beliefs, especially self-efficacy and intrinsic value, and self-regulated learning strategies. The study’s novelty lies in validating a culturally adapted, second-order motivation model tailored to Malaysian boarding schools. Notably, the research isolates the mediating effect of intrinsic motivation on self-regulation within a high-pressure, collectivist setting, extending SDT’s applicability. However, limitations lie in the use of a cross-sectional design and dependence on self-reported data, and regional focus. Future studies should adopt longitudinal designs, consider diverse school types, and integrate perspectives from teachers or parents to strengthen validity. Including objective academic performance metrics may offer deeper insight. This research affirms the relevance of SDT in Malaysia’s education system and provides a validated framework linking motivation to strategic learning. The findings support evidence-based pedagogical strategies and align with sustainable development goal (SDG) 4 on quality education and goal 10 on reduced inequalities, promoting for fair and motivation-enhancing environments of learning.
Volume: 15
Issue: 1
Page: 238-257
Publish at: 2026-02-01
1 2 3
...
1973 1974
Show 19 of 1974

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