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

30,938 Article Results

Hybrid deep learning model for enhanced short-term gold price forecasting

10.11591/ijai.v15.i4.pp3228-3239
Hoang Ha Nguyen , Minh Duc Nguyen , Cuong H. Nguyen-Dinh
Accurate short-term gold price forecasting is crucial for the financial decision-making. This paper introduces a short-term gold prediction network (STGP-Net), a novel hybrid deep learning model designed to enhance prediction accuracy by integrating one-dimensional convolutional neural network (1D-CNN) and long short-term memory (LSTM). STGP-Net leverages the 1D-CNN's ability to extract local temporal features and the LSTM capacity to model long-range dependencies within gold price time series. Various sliding window configurations are employed to generate input sequences for multi-step ahead prediction. Comprehensive experiments were conducted comparing STGP-Net against 1D-CNN + recurrent neural network (RNN) and 1D-CNN + bidirectional long short-term memory (BiLSTM) baseline models across three configurations using metrics like mean absolute error (MAE), root mean square error (RMSE), and determination (R²). The results demonstrated that STGP-Net consistently provided better performance and robustness, proving more effective for short-term gold price forecasting than the alternative hybrid models tested.
Volume: 15
Issue: 4
Page: 3228-3239
Publish at: 2026-08-01

AI-driven hybrid neural network for electrocardiogram-based authentication and predictive health monitoring

10.11591/ijai.v15.i4.pp3309-3317
Swati Lakshmi Boppana , Velicheti Anantha Lakshmi , Padala SriKavitha , Venkata Ashok Kalaga , Venkateswara Rao Naramala , Suneetha Thalluru , Gunturi S. Raghavendra
The increasing adoption of digital healthcare systems demands secure and reliable patient authentication mechanisms. Traditional methods such as passwords and PINs are vulnerable to security breaches, motivating the use of biometric-based solutions. Among various biometrics, the electrocardiogram (ECG) signal is distinctive, stable, and non-invasive, making it suitable for secure authentication. This paper proposes CardioGuard, an artificial intelligence (AI)–based authentication framework that employs a hybrid deep learning model combining convolutional neural networks (CNNs) and long short-term memory (LSTM) networks to extract discriminative features from ECG signals and classify users as genuine or impostors. In addition to access control, the system analyzes ECG patterns to support early detection of potential cardiovascular abnormalities. Experimental results demonstrate that CardioGuard achieves improved authentication accuracy and enhanced predictive health insights compared to conventional approaches, highlighting its effectiveness for secure and intelligent healthcare monitoring.
Volume: 15
Issue: 4
Page: 3309-3317
Publish at: 2026-08-01

A model for enhancing teacher training by integrating internet of things, cloud computing, and robotics in a blended learning

10.11591/ijere.v15i4.39473
Meiramgul Mukhambetova , Salamat Idrissov , Nurgul Baitemirova
Despite educational digitalization, a divide persists in integrating robotics and the internet of things (IoT) into classroom practice. Both pre-service and in-service teachers struggle to translate theory into application due to the lack of unified methodological frameworks. This gap demonstrably undermines student academic performance. The present study introduces the teachers-oriented, learning content, methodological approaches, digital support, expected outcomes (T-LMDE) model to bridge this divide through the synergistic integration of key dimensions. The model integrates robotics and IoT with cloud computing, utilizing the Arduino IoT cloud for data analytics and remote control. Delivered via a blended-learning portal, the curriculum provides didactic materials and feedback mechanisms, enabling educators to master complex engineering solutions. The model’s efficacy was empirically validated with 31 participants across two modalities: a 15-week course for pre-service teachers and an 80-hour intensive program for in-service educators. Using a quasi-experimental, mixed-methods design, data were analyzed via paired t-tests and qualitative thematic scrutiny. Findings confirm the model’s positive impact on professional transformation and competency advancement, shifting educators from content consumers to “teachers-as-designers”.
Volume: 15
Issue: 4
Page: 3322-3333
Publish at: 2026-08-01

Blended-language instructional-approach as a determinant of science learning in rural classrooms

10.11591/ijere.v15i4.39263
Atomatofa Rachel Ovuezirie , Sekegor Crescentia Ojenikoh , Avbenagha Andrew , Ewesor Stella
Scientific concepts such as gravity continue to pose challenges for students in rural and under-resourced classrooms, where reliance on a single language of instruction often restricts access to meaning and limits conceptual understanding. This study investigated the impact of a blended English and Urhobo (BEAU) instructional approach on junior secondary one students’ learning and retention of gravity concepts in rural Nigeria. A quasi-experimental pre-test–post-test non-equivalent control group design was employed with 243 students assigned to English-only, Urhobo-only, or BEAU instructional conditions. A validated 30-item multiple-choice gravity test was administered, and analysis of covariance (ANCOVA) was used to examine differences while controlling for pre-test scores. The findings show that students taught using the BEAU language approach achieved better significantly in both post-test and retention tests compared to those taught using English-only or Urhobo-only instructional approaches. The findings provide empirical evidence that the blended language instructional approach enhances science learning outcomes in rural Nigerian contexts. Linguistically responsive instructional approach improves conceptual understanding and supports long-term retention of abstract scientific ideas, underscoring the importance of leveraging students’ linguistic resources to strengthen science education in rural and under-resourced classrooms.
Volume: 15
Issue: 4
Page: 3636-3645
Publish at: 2026-08-01

Evaluating the methodological admissibility of generative AI tools for linear regression in graduate-level research

10.11591/ijere.v15i4.38496
Valery Okulich-Kazarin , Kanat Kozhakhmet
With the growing use of generative artificial intelligence (AI) in academia, a key methodological question concerns the statistical correctness of AI-assisted quantitative analysis. This study empirically evaluates the use of generative AI tools for linear regression in graduate-level research. The authors used a methodological approach in which estimates from four AI systems (ChatGPT 4.0, DeepSeek v3.2, Gemini 3 Pro, and Grok 4.1) were compared with estimates obtained using Microsoft Excel (Windows 10). The analysis was performed on five time series using a fixed prompt structure. Comparability was assessed using thresholds for regression coefficients, the coefficient of determination (R²), and predicted results for 2030. The results show that under controlled conditions and within the ordinary least squares (OLS) method, the AI tools generate statistical results with varying degrees of accuracy. However, deviations in coefficients and predictions highlight the need for systematic validation. The study concludes that AI tools can serve as auxiliary methodological support, provided transparency, reproducibility, and threshold-based verification are ensured in graduate research practice.
Volume: 15
Issue: 4
Page: 2874-2882
Publish at: 2026-08-01

Artificial intelligence technologies in teaching Russian as a foreign language

10.11591/ijere.v15i4.38077
Larissa Krymova , Navruz Khasanov , Zhamiila Arstanbekova , Ariya Azamatova , Nuraisha Bekeyeva
The present study aims to investigate the impact of integrating artificial intelligence (AI) technologies into teaching Russian as a foreign language (RFL) from the perspective of educators. Employing a mixed-methods research design, the study utilized several methodologies, including a teacher survey, an analytical-descriptive approach to data interpretation, and the development and evaluation of AI-based interventions. The study sample comprised 120 RFL instructors from three public universities in Kazakhstan. Preliminary findings revealed a considerable awareness among teachers regarding various AI technologies, such as chatbots, voice assistants, the ChatGPT neural network, educational platforms, gaming applications, and task design tools. Nonetheless, the practical utilization of these technologies varied significantly, with only a subset of teachers incorporating them into their regular teaching practices. The study culminated in the development of a conceptual framework for AI-driven educational interventions, incorporating platforms such as Coursera, Moodle, Open EdX, and eFront; game-based applications including Duolingo, Talk2Russia, and Russian Verbs Pro; and task creation tools such as Kahoot! and Quizlet. Following the integration of these interventions into the curriculum, post-implementation evaluations indicated that teachers generally perceived the tools as effective, with the average effectiveness rating surpassing 4.0 out of 5.0 across all assessed categories. The findings of this study have practical applicability; they can be used to enhance professional development programs for teachers of the Russian language and to formulate strategies for the integration of AI technologies into language education within the Central Asian region.
Volume: 15
Issue: 4
Page: 3422-3438
Publish at: 2026-08-01

Procrastination trap: how personality traits fuel generative artificial intelligence over-reliance and erode academic performance

10.11591/ijere.v15i4.39382
Mohamad Rizal Abdul Hamid , Chen Jung Ku , Anath Rau Krishnan , Imran Mehboob Shaikh , Yoke Lian Lau , Mohd Zulkifli Muhammad , Saiful Bahri
This study investigates how long-term personality traits contribute to generative artificial intelligence (GenAI) use and whether these traits have an impact on academic procrastination and performance. The Big five personality model was used for this investigation, and a quantitative methodology was employed to analyze data from 200 undergraduate students in East Malaysia via partial least squares structural equation modeling (PLS-SEM). Findings indicated that while neuroticism and openness were associated with increased levels of GenAI use, conscientiousness was found to be a protective factor against GenAI dependency. In addition, results showed that when students excessively utilize GenAI, they experience increased levels of procrastination which leads to longer procrastination periods and decreased levels of deep learning engagement. Finally, procrastination was identified as a partial mediator between GenAI use and poor academic performance. Thus, GenAI dependency produces a ‘competence illusion’, causing a decline in students’ academic abilities over time. Ultimately, this study supports the need for interventions designed to help students learn self-regulation and develop critical AI literacy skills to enable technology to serve as a cognitive scaffold as opposed to a replacement for students’ own cognitive efforts.
Volume: 15
Issue: 4
Page: 3362-3374
Publish at: 2026-08-01

Learning across ages: the role of intergenerational engagement in elderly education

10.11591/ijere.v15i4.40178
Rita Wong Mee Mee , Muhammad Fairuz Abd Rauf , Rasithra Ravichandran , Mohd Fahmi Mohamad Amran , Khairul Annuar Abdullah , Zuraidy Adnan , Muhammad Farhan Nordin
Intergenerational learning (IGL) has gained increasing attention as a strategy to address the limited effectiveness of elderly education, particularly in the context of digital literacy and lifelong learning. Despite growing research, the field remains fragmented, with limited synthesis translating evidence into actionable educational strategies. This study aims to systematically examine how IGL enhances elderly learning ability and to identify strategic directions for its implementation. A bibliometric-driven analytical approach was employed using Scopus-indexed publications from 2021 to 2025. The top ten most-cited articles were identified through performance analysis and subsequently analyzed using a strengths, weaknesses, opportunities, and threats (SWOT) framework. The findings reveal that IGL significantly improves digital literacy, cognitive engagement, and social well-being among elderly learners. However, challenges such as internalized ageism, low learning confidence, and the absence of structured and scalable frameworks remain critical barriers. The study also highlights opportunities for integrating IGL into formal education and community-based programs, while identifying threats related to technological change and policy limitations. This study contributes a bibliometric-informed strategic synthesis that advances understanding of IGL and provides actionable insights for educators, program designers, and policymakers in elderly education.
Volume: 15
Issue: 4
Page: 3086-3098
Publish at: 2026-08-01

Genetic algorithm-optimized BERTopic with SHAP explainability for institutional research trend analysis

10.11591/ijai.v15.i4.pp3818-3826
Muhammad Dedi Irawan , Yustria Handika Siregar , Hewa Majeed Zangana , Ali Ikhwan
Institutional research grant titles constitute short-text grey literature characterized by heterogeneous semantic structures, making topic identification and research trend analysis challenging. This study proposes an integrated bidirectional encoder representation from transformers-based topic modeling (BERTopic) framework combining genetic algorithm (GA)-based hyperparameter optimization and Shapley additive explanations (SHAP)-based interpretability to improve semantic topic quality and model transparency. GA was applied to optimize dimensionality-reduction and density-based clustering parameters, while SHAP was used to estimate the contribution of bigram features to the surrogate classifier’s predictions of BERTopic-generated topic labels. Experimental results demonstrated that the proposed framework improved topic coherence from 0.367 to 0.543 while reducing the outlier ratio from 21.12% to 13.55%. In addition, the number of topics decreased from 46 to 10, resulting in a more compact and less fragmented topic structure. The resulting topic structure revealed dominant themes related to higher education, religious moderation, Islamic counseling, halal tourism, and sharia banking. Overall, the proposed framework contributes to the development of more coherent, interpretable, and semantically robust topic modeling for institutional short-text grey literature analysis.
Volume: 15
Issue: 4
Page: 3818-3826
Publish at: 2026-08-01

Leveraging artificial intelligence in education a comprehensive review of the Arab literature

10.11591/ijai.v15.i4.pp2985-2998
Mohamed Abdelraouf Elsayed , Taleb Saleh Alattas
This descriptive analytical study relied on the systematic literature review (SLR) addressing the role of artificial intelligence (AI) in improving education management and delivery, empowering teaching and teachers, learner learning, and learning assessment. The SLR sample was determined in 125 articles from Almandumah and Scopus databases. The analysis results revealed: 39.2% of articles were related to the Saudi Arabia context, 34.4% were published in 2024, and 68.8% were quantitative. The most prominent AI applications used were: ChatGPT, Alexa, Grammarly, Duolingo, Chatbot, and Coursera. The results also showed that the most areas of the educational process in which AI applications can be implemented were: empowering teaching and teachers (62.4%), and improving learner learning (48.8%). The SLR also came up with some practices that can be applied to enhance the AI use in improving the educational process. An opinion poll was applied on 37 academic experts to identify their agreement on the potential of implementing these developed practices in the areas of the educational process. The results showed that the experts' agreement on the potential of implementing these practices in the areas of the educational process was very high. The study recommended some useful mechanisms for implementing these practices.
Volume: 15
Issue: 4
Page: 2985-2998
Publish at: 2026-08-01

Context-aware AgriBot using dual intent and entity transformer and hybrid deep learning model

10.11591/ijai.v15.i4.pp3637-3645
Binod Deka , Ridip Dev Choudhury , Utpal Barman
The agriculture sector has gone through vast technological improvement, leading to increased productivity and sustainability. This research introduces AgriBot, a context-aware virtual assistant (VA) that helps farmers in rice cultivation and identifies diseases while providing instant suggestions for subsequent task. Using the RASA framework, AgriBot has been designed to understand the farmer's queries. Dual intent and entity transformer (DIET) classifier has been used for entity classification, achieving training and testing accuracy of up to 98% and 97%, respectively. Additionally, the system incorporates machine learning (ML) models for rice disease detection, utilizing a dataset of 4,624 images covering three major rice diseases: bacterial blight, brown spot, and blast. Among the tested models—neural network (NN), random forest (RF), support vector machine (SVM) and naive Bayes (NB) achieved an accuracy of up to 99.9%, demonstrating excellent classification performance. Using text-based query handling with image-based disease identification and instant suggestion makes it a more robust support system for the farmers.
Volume: 15
Issue: 4
Page: 3637-3645
Publish at: 2026-08-01

Deep learning for categorizing microsatellite stability in colorectal cancer

10.11591/ijai.v15.i4.pp3761-3769
Sofyan El Idrissi , Yassine Drider , Ikram Ben Abdel Ouahab , Mohammed Bouhorma , Fatiha El Ouaai
Cancer remains a significant global health challenge, with its incidence rising steadily in recent decades. In colorectal cancer (CRC), microsatellite instability (MSI), and microsatellite stability (MSS) are important biomarkers that influence treatment decisions and patient outcomes. Accurate MSI classification is critical but traditional methods can be costly and time-consuming. This study explores the potential of deep learning to classify MSI and MSS in CRC. A large dataset of CRC patients with confirmed MSI and MSS status was utilized, obtained through standard testing images. Deep learning models were applied to histopathological images, analyzing tissue features from digital slides. Convolutional neural network (CNN) and residual network (ResNet)-18 models demonstrated high accuracy in distinguishing between MSI and MSS CRCs. The best-performing model, which integrated genomic and histopathological data, achieved an area under the curve (AUC) receiver operating characteristic (ROC) of 0.85, indicating strong discrimination capability. The findings suggest that deep learning could be a valuable tool for clinical decision-making and personalized medicine in CRC.
Volume: 15
Issue: 4
Page: 3761-3769
Publish at: 2026-08-01

Exploring cognitive patterns in children with autism spectrum disorder using correlation and cluster analysis

10.11591/ijai.v15.i4.pp3164-3175
Hana Bezzih , Muna Darweesh , Amjad Gawanmeh
This paper investigates the relationships between age and five cognitive abilities in children diagnosed with autism spectrum disorder (ASD). Data from 210 children aged 6 to 12 years who completed measures of visual motor precision (VM), facial memory (FM), spatial vision (SV), drawing memory (DM), and orientation (OR) were analyzed. Data preparation, descriptive statistical analysis, correlation analysis, cluster analysis, and factor analysis were conducted. The results showed that age was not significantly associated with the cognitive measures. The clearest association was a moderate positive correlation between VM and FM (0.34). Cluster analysis identified three groups. However, the low silhouette score (0.1368) indicated weak separation and substantial overlap between cognitive profiles. Factor analysis suggested three latent dimensions: factor 1 was strongly associated with VM and FM; factor 2 was negatively related to DM and moderately positively related to OR; and factor 3 was primarily driven by SV. These findings suggest that cognitive abilities in children with ASD operate relatively independently, with some shared mechanisms between certain skills. It can be concluded that individualized approaches in assessment and intervention strategies are warranted.
Volume: 15
Issue: 4
Page: 3164-3175
Publish at: 2026-08-01

Hybrid quantum-classical neural networks for brain computed tomography scan diagnosis

10.11591/ijai.v15.i4.pp3342-3351
Bilal R. Altamer , Muhamad Azhar Abdilatef Alobaidy , Aws Hazim Saber Anaz , Zahraa Tarik AlAli
Medical image classification is considered as very important field of diagnosis and treatment of neurological disorders, which include stroke, tumors, and hemorrhages, it can used to facilitate timely medical intervention. A hybrid quantum-classical convolutional neural network (QCNN) is presented by combining quantum information processing with classical deep learning techniques for improved feature extraction and classification accuracy. The model combines convolutional neural network (CNN), which handles initial feature extraction with a PennyLane and TensorFlow based layer that employs quantum entanglement and superposition principles to enhance classification performance. The model is trained and tested over a computed tomography (CT) scan image dataset which has four classes (normal, stroke, tumor, and hemorrhage). Various learning rates are tested and employed a hybrid backpropagation method to improve efficiency. Confusion matrices, region of conversion receiver operating characteristic (ROC) curves, and plots for the training convergence that all pointed to promising classification accuracy were derived with a detailed analysis accordingly. Overall, the results indicate that combining quantum computing with deep learning architectures could improve classification performance at a lowest computational cost. The results suggest the viability of hybrid quantum-classical models for medical imaging applications and indicate that quantum computing is a promising direction for enhancing diagnostic accuracy in the area of radiology.
Volume: 15
Issue: 4
Page: 3342-3351
Publish at: 2026-08-01

Energy loss prediction using least absolute shrinkage and selection operator regression and SHAP explainability

10.11591/ijai.v15.i4.pp3103-3119
Nur Diana Izzani Masdzarif , Siti Azirah Asmai , Yogan Jaya Kumar , Muhammad Hafidz Fazli Md Fauadi
Technical energy loss estimation in power distribution systems is essential for improving operational efficiency and cost-effectiveness. However, distribution-level datasets are often failed to cope with the nonlinear behavior and sparse, low-resolution data typical in modern grid environments. This study proposes an interpretable artificial intelligence (AI) framework based on least absolute shrinkage and selection operator (LASSO) regression integrated with Shapley additive explanations (SHAP) to estimate and explain technical energy losses at the feeder level. An exploratory multicollinearity assessment using correlation analysis and variance inflation factor (VIF) revealed severe redundancy among operational variables, justifying the adoption of L1-regularized regression. Hyperparameter tuning via LassoCV identified an optimal regularization parameter, resulting in strong predictive performance. Comparative evaluation with nonlinear models, including random forest and gradient boosting, demonstrated that LASSO achieves competitive or superior generalization performance while preserving interpretability. Feature importance analysis and SHAP-based explanations confirmed that operational loading variables particularly infeed energy, load factor, and maximum demand are the dominant drivers of technical losses. SHAP dependence and interaction analyses further revealed context-dependent behavior among correlated predictors, enriching interpretability beyond coefficient-based rankings. The results demonstrate that regularized linear modeling, when combined with explainable AI techniques, provides a robust, transparent, and practically deployable solution for technical loss estimation in distribution networks.
Volume: 15
Issue: 4
Page: 3103-3119
Publish at: 2026-08-01
1 2 3
...
2062 2063
Show 18 of 2063

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