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

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

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

Enhancing vehicular ad hoc network security through a trust based vehicular model for attack mitigation

10.11591/ijai.v15.i1.pp247-256
Shilpa Shilpa , Thiruvenkadam Prasanth
In vehicular ad-hoc networks (VANETs), ensuring secure and reliable communication is essential due to the growing threat of cyber-attacks. As attacks can disrupt data transmission and compromise user privacy and network integrity, it is vital to develop robust security solutions. Hence, this work introduces a trust-based vehicular security (TVS) model, which leverages trust metrics to enhance VANET security. The main objective was to establish secure connections between vehicles and infrastructure nodes, effectively mitigating attacks while maintaining higher throughput. The methodology integrated a dynamic trust evaluation model to prevent malicious activities and ensure secure data transmission. The TVS model’s performance was compared to an existing VANET model, showing improved results in terms of detection rate, misclassification rate, and throughput. The findings demonstrate an average misclassification rate of 22.75%, a detection rate of 14.77%, and a throughput of 11.45%, highlighting the superior effectiveness of the TVS model in attack-prone environments when compared with existing VANET models. The TVS model provides a promising security solution for VANETs, offering enhanced protection against denial-of-service (DoS) attacks and spoofing (cyber-attacks) with better accuracy and network performance. The novelty lies in the dynamic, multi-trust-based approach for secure communication in vehicular networks.
Volume: 15
Issue: 1
Page: 247-256
Publish at: 2026-02-01

Joint angle prediction and joint-type classification in human gait analysis using explainable deep reinforcement learning

10.11591/ijeecs.v41.i2.pp564-578
Deepak N. R. , Soumya Naik P. T. , Ambika P. R. , Shaik Sayeed Ahamed
Human gait analysis is a key component of rehabilitation, prosthetics, and sports science, especially for clinical evaluation and the development of adaptive assistive technologies. Accurate joint-angle estimation and dependable joint-type classification remain difficult because of the complex temporal behavior of gait signals and the limited interpretability of many deep learning (DL) approaches. While recent techniques have enhanced predictive accuracy, their clinical applicability is often limited by insufficient transparency and adaptability in learning mechanisms. To overcome these limitations, this work proposes an integrated framework that unifies DL, reinforcement learning (RL), and explainable artificial intelligence (XAI). Stochastic depth neural networks (SDNN) are applied for joint-angle regression, whereas deep feature factorization networks (DFFN) are used for multi-class joint-type classification. Optimization is achieved using Q-learning (QL) and mutual information maximization (MIM), ensuring stable convergence and improved learning efficiency. To improve interpretability, the framework incorporates counterfactual and contrastive explanations, feature ablation studies, and prediction probability analysis. Experimental findings show that the SDNN MIM model attains an R2 score of 0.9881, with RL rewards increasing from 0.997 to 0.999 during regression training. For joint-type classification, the DFFN MIM model achieves an accuracy of 0.95, with reward values improving from 0.90 to 0.98. These results demonstrate the effectiveness of the proposed framework in delivering accurate and interpretable gait predictions, supporting its relevance to biomechanics, healthcare, personalized rehabilitation, and intelligent assistive systems.
Volume: 41
Issue: 2
Page: 564-578
Publish at: 2026-02-01

Depth estimation in handheld augmented reality: a review

10.11591/ijeecs.v41.i2.pp589-600
Muhammad Anwar Ahmad , Norhaida Mohd Suaib , Ajune Wanis Ismail
Depth estimation involves capturing the depth information of a scene in the form of depth data. This depth information can be applied in computer vision tasks to enhance perception and comprehension. In handheld augmented reality (AR), depth estimation refers to the capability of a handheld device to estimate the depth or distance of objects in the real world based on input from its camera feed. Currently, there is a lack of work that reviews on this topic. Thus, this paper reviews and discusses the technologies regarding depth estimation on handheld devices and their applications in relation to AR. We employ partially the systematic review procedure to allow more specific focus for our, broken into three main focuses. First, we discuss the methods to obtain depth data on handheld devices. Next, we discuss on the existing frameworks that enable depth estimation for handheld AR. Then, we compile and discuss the applications of depth estimation for handheld AR based on the reviewed papers. Finally, we discuss the novelties and limitations of the current research to determine the gaps in this field of research.
Volume: 41
Issue: 2
Page: 589-600
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

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

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

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

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

Examining financial management in Thai public schools: sources of funding, allocation practices, and strategies for improvement

10.11591/ijere.v15i1.34418
Jakkrit Marnnoi , Tanate Panrat , Hambalee Jehma
This study was conducted to address the critical gaps in financial management practices within Thai public schools, where inefficiencies and mismanagement persist despite available guidelines and funding. The relevance of this research lies in its potential to enhance financial governance, ensuring optimal resource allocation and accountability, which are vital for improving educational outcomes. Employing a mixed-methods approach, the study combined descriptive questionnaires administered to 396 school administrators with structured interviews involving 36 participants to evaluate funding sources, allocation processes, and adherence to financial guidelines. The findings revealed that while schools received funding from diverse sources, namely government, parents, and donors, 85% of administrators reported insufficient budgets. Notably, 82% acknowledged non-compliance with financial guidelines despite submitting utilization reports, highlighting systemic inefficiencies. The study concluded that inadequate financial management skills and inconsistent policy implementation hinder effective resource use. To address these challenges, the study proposes targeted interventions, including specialized training programs, the establishment of dedicated financial departments, and updated management guidelines. These measures aim to strengthen financial accountability and operational efficiency in public schools, offering actionable insights for policymakers and administrators. Future research should compare public and private sector practices to refine standardized financial management frameworks.
Volume: 15
Issue: 1
Page: 535-543
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

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

Tolerance on campus: the impact of religious commitment and respect among university students

10.11591/ijere.v15i1.32607
Mohammad Jaber Thalgi , Nader Al-Refai , Kadir Gömbeyaz , Hanan Bdoor , Ayse Zisan Furat
Religious commitment, particularly within Islamic contexts, is often viewed as a guiding framework for promoting values such as tolerance, respect, and social harmony; however, differing interpretations and personal expressions of religiosity can sometimes challenge these ideals, necessitating deeper exploration of how religiosity influences social interactions. The study investigates the relationship between religious commitment and respect for others regarding the levels of tolerance behavior among university students. The study employed a descriptive quantitative cross-sectional survey from June 16 to August 16, 2023, with a sample of 334 enrolled in the College of Sharia at Yarmouk University in Jordan. The survey consists of three main scales: religious commitment, respect for others, and tolerance. Students’ demographic data, including gender, nationality, age group, academic department, and the year of study, were also collected via the questionnaire. The findings highlight significant gender differences in religious commitment, with males demonstrating higher levels than females. While no significant age differences were observed in religious commitment, tolerance varied notably, particularly among the 24-26 age group. The study participants represented a diverse range of countries of origin. A country-wise analysis revealed that students from Thailand have the highest religious commitment, underscoring the influence of cultural contexts. Departmental comparisons showed no significant differences, although the findings highlight that respect for others impacts tolerance, religious commitment and demography have almost no effect as predicted. The findings emphasize the primary role of respect in fostering social harmony, suggesting that future interventions should focus on promoting respect as a fundamental value in Islamic culture to enhance tolerance.
Volume: 15
Issue: 1
Page: 181-194
Publish at: 2026-02-01
1 2 3
...
1973 1974
Show 21 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