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

Comparative deep learning CNN architectures for breast cancer detection from thermal imaging

10.11591/ijeecs.v42.i2.pp369-379
Md. Sumon Hosen , Mustafizur Rahman , Zaid Bin Sajid , Md Naeem Hossan , Apu Biswas , Md. Mijanur Rahman
It has been observed that breast cancer is a severe disease among women globally. Mammography is the most effective screening method for detecting this severe illness. Over the last thirty years, mammography has been widely recognized as a preventive measure against breast cancer. In recent years, convolutional neural networks (CNN) and artificial intelligence (AI) have become more common in digital mammography for automated breast cancer detection. For classifying breast cancer, this study examines the five CNN models: LeNet-5, AlexNet, VGG-16, ResNet-50, and Inception-v3, using the database for mastology research with infrared images (DMR-IR) dataset's thermal image. These models were trained and validated using accuracy, recall, F1-score, specificity, and AUC as evaluation criteria after the dataset was preprocessed using normalization and data augmentation. Among the experimental models, Inception-v3 achieved 99.44% accuracy, outperforming other CNNs by 1–2%, while other models performed with accuracy levels above 97%. These results show the tremendous efficacy of CNN-based deep learning methods for breast thermogram analysis. The research points out thermography as a useful support for traditional imaging and InceptionV3 as a potential option for correctly detecting clinical breast cancer.
Volume: 42
Issue: 2
Page: 369-379
Publish at: 2026-05-10

An enhanced deep learning model with context-aware attention for diabetes prediction

10.11591/ijeecs.v42.i2.pp509-517
J. Jannathul Firthous , G. Murugeswari
A plethora of people worldwide suffer from diabetes, a chronic, potentially fatal illness that resulted serious risks and complications if left untreated. Effective management requires early prediction and intervention. Despite their advantages, traditional machine learning techniques frequently find it difficultly in grasping the intricate temporal as well as geographical correlations included with in medical stats. For the purpose of effectively forecast diabetes mellitus, the proposed work suggests a unique deep learning model called multilayer diabetes deep learning attention with context mechanism (MLDDAM). This model incorporates a hybrid architecture that integrates an Attention with Context Mechanism to enhance the model’s efficiency will be conversant with emphasizing on key aspects, convolutional neural networks (CNN) are utilized to extract traits, and bidirectional long short-term memory (BiLSTM) captures sequential dependencies. This innovative design enables the model to perform better by utilizing the input data’s temporal and geographical properties. Experiments using benchmark datasets show that the suggested MLDDAM model is efficient and robust, with outstanding 99.43% prediction accuracy for diabetes. These outcomes demonstrate the MLDDAM model’s effectiveness as a precise and dependable tool to assist clinical decision-making in the management of diabetes.
Volume: 42
Issue: 2
Page: 509-517
Publish at: 2026-05-10

Cost-effective sentiment analysis with chain-of-thought: a cross-lingual evaluation

10.11591/ijeecs.v42.i2.pp454-468
Shen Haijie , Madhavi Devaraj
Sentiment analysis is a core task in natural language processing with broad ap plications in social media monitoring, customer feedback mining, and market research. Although pre-trained language models (e.g., BERT) achieve strong performance, they typically rely on task-specific fine-tuning and substantial la beled data. Recent large language models (LLMs) enable a different paradigm via in-context learning. This paper presents a systematic empirical study investi gating chain-of-thought sentiment (CoT-Sent), a prompting framework that uses structured CoT reasoning to improve classification accuracy. We evaluate CoT Sent on four benchmark datasets in English and Chinese, comparing multiple representative LLMs (GPT-4, Claude-3, Gemini, Qwen-2.5) under zero-shot set tings. Across datasets, CoT-Sent improves average accuracy by 2.5% over zero shot baselines. Crucially, unlike prior work which provides a broad performance overview without analyzing deployment costs or multi-language generalization, we focus on the cost-latency-accuracy trade-offs, and demonstrate CoT-Sent’s superior cross-lingual transfer (English-to-Chinese) with detailed cost analysis. We provide a comprehensive three-dimensional analysis of accuracy, cost, and latency, offering actionable deployment strategies for resource-constrained environments.
Volume: 42
Issue: 2
Page: 454-468
Publish at: 2026-05-10

Pomelo maturity classification from field-acquired images using oil-gland morphology and a rule-based image-processing pipeline

10.11591/ijeecs.v42.i2.pp572-583
Sopapun Suwansawang , Harutai Dinsakul , Wirot Buangam , Jiraroj Tosasukul
Pomelo maturity assessment in commercial orchards relies predominantly on vi sual inspection and harvest age records, which introduce inconsistency in post harvest grading. Non-destructive alternatives such as near-infrared spectroscopy and acoustic sensing have been reported, but typically require specialised instruments and controlled acquisition conditions. This study investigates the feasibility of oil-gland morphology as an interpretable maturity indicator, implemented as a rule-based image-processing pipeline executable on standard CPU hardware without model training. A hierarchical rule-based framework was developed to classify pomelo maturity from gland count features extracted under natural outdoor illumination. Thirty-three Citrus maxima samples (Khao Yai cultivar) representing three maturity stages were analysed in this proof-of-concept study (n = 11 per stage). The pipeline integrates adaptive thresholding, subregion segmentation, multi-scale morphological detection, and threshold-based classification. Detection reliability was verified on synthetic dot-pattern images prior to real-sample evaluation. On the collected dataset, the framework achieved an overall accuracy of 78.8% with a macro-averaged F1-score of 0.784. No mis classification occurred between the immature and mature groups; errors arose exclusively between adjacent stages. Mean processing time was 57 seconds per image on a consumer-grade laptop. Given the limited sample size and single cultivar scope, these results represent methodological feasibility rather than validated generalisation, and establish a baseline for morphology-based maturity assessment in pomelo.
Volume: 42
Issue: 2
Page: 572-583
Publish at: 2026-05-10

Fairness dynamics in graph neural networks: a comparative study of graph-structured neural models with and without gradient-based training

10.11591/ijeecs.v42.i2.pp403-413
Ananda Chatterjee , K A Venkatesh
Graph neural networks (GNNs) are gaining more and more popularity in high stakes domain due to their ability to learn both from features and relationships. Nevertheless, there are concerns regarding how this accuracy centric optimization used by these models will impact fairness when deployed in socially sensitive areas. This work explores the interplay between predictive accuracy and fairness in GNNs when applied in judicial risk assessment system. A comparative study was performed among three canonical architectures such as graph convolutional networks (GCN), graph sample and aggregate (GraphSAGE) and graph attention networks (GAT) under trained and untrained settings on judicial risk assessment dataset. Fairness was evaluated through metrices like demographic parity (DP), equalized opportunity (Eopp), and equalized odds (Eodds) along with predictive performance metrices. Sensitivity analysis was conducted to investigate the effect of graph construction choices and neighborhood sizes in determing fairness and predictive accuracy. Experimental evidences proved that backpropagation improved predictive performance but in tandem fairness degradation happened. Untrained models exhibited lower fairness gap but that is superficial as weak predictive outcome of those models made group differences suppressed. Among the three trained models GAT was able to strike a good balance between accuracy and fairness while increase in neighborhood size caused little bit improvement in fairness via graph smoothing. The novelty of this work lies with its empericial characterization of GNNs under realistic settings. This study emphasizes the fact that how learning methodology, architectural designs, graph formation influence fairness outcomes. This work enlightens how graph-based models can be applied to decision making scenario and encourages embedding of fairness aware training strategies to it.
Volume: 42
Issue: 2
Page: 403-413
Publish at: 2026-05-10

Beef spoilage assessment using e-nose and machine learning on unbalanced dataset

10.11591/ijeecs.v42.i2.pp552-560
Noreddine Kazitani , Miloud Chikr-El-Mezouar , Elhocine Boutellaa
Food quality and freshness especially meat which have short shelf life like beef meat is a real problem in nowadays. This kind of food should be stored at suitable temperature and humidity conditions. For this purpose, a system is created to detect different states of freshness through an open unbalanced dataset. Machine learning models' performance is affected by unbalanced classes, which leads to biased outcomes and poor performance on minority classes, to address this issue this study uses synthetic minority oversampling technique (SMOTE). For this purpose, an open dataset containing 10800 samples, where four classes are distinguished (excellent, good, acceptable and spoiled). In this study, the proposed e-nose is composed of 10 sensors. For classification 6 machine learning methods are used. The best results are obtained from k-nearest neighbors (KNN) model with 99.83% of accuracy, 99.86% of precision, 99.80% of recall and 99.83% of F1-score.
Volume: 42
Issue: 2
Page: 552-560
Publish at: 2026-05-10

Trustworthy intelligence, sustainable systems, and resilient digital infrastructure for an AI-driven future

10.11591/ijeecs.v42.i2.pp283-288
Tole Sutikno
This editorial introduces Volume 42, Number 2, May 2026 of the Indonesian Journal of Electrical Engineering and Computer Science (IJEECS), which presents a broad collection of peer-reviewed research contributions spanning electrical engineering, electronics, computer science, artificial intelligence, cybersecurity, and information and communication technologies. The issue highlights the growing convergence of intelligent systems, sustainable engineering, trusted digital infrastructures, and data-centric innovation in addressing contemporary global challenges. The published articles demonstrate advances in renewable energy technologies, intelligent control systems, AI-enabled healthcare, cybersecurity, graph-based learning, Internet of Things (IoT) architectures, smart agriculture, educational technologies, and uncertainty-aware data management. Collectively, these contributions emphasize the importance of integrating intelligence, resilience, sustainability, and ethical considerations into next-generation engineering solutions. The issue further reflects emerging research directions focused on trustworthy artificial intelligence, secure cyber-physical systems, resource-efficient computing, and human-centered digital transformation. Through interdisciplinary innovation and practical implementation, the published works contribute to advancing technological systems capable of supporting sustainable development, economic growth, and societal well-being in an increasingly connected world.
Volume: 42
Issue: 2
Page: 283-288
Publish at: 2026-05-10

An extended relational database model and algebra with interval probability valued attributes and tuples

10.11591/ijeecs.v42.i2.pp426-441
Hoa Nguyen , Thi Nhi Tran
This paper introduces an extended relational database model and algebra, named EPRDB, where both the attribute and tuple of a relation may take values associated with interval probabilities for modelling and computing uncertain and imprecise information. To build EPRDB, three key methods are employed: i) probabilistic values and intervals are used for representing uncertain and imprecise valued attributes and tuple membership degrees; ii) the probabilistic interpretations of binary relations on sets and operators on probability intervals are proposed for computing and querying the uncertain degree of relations on value domains of attributes; and iii) the combination strategies of probabilistic intervals and values are defined for manipulating probabilistic relational tuples. Then, the EPRDB data model including fundamental concepts and components such as the schema, probabilistic relation, functional dependency, and key is extended with interval probability valued attributes and tuples such that it is coherent and consistent with the classical relational data model. The EPRDB algebra including the set of basic probabilistic relational algebraic operations is developed corresponding to the EPRDB data model. A set of the properties of the algebraic operations is also formulated and proven. The new proposed EPRDB model and algebra can represent and deal effectively with uncertain and imprecise information in practical applications.
Volume: 42
Issue: 2
Page: 426-441
Publish at: 2026-05-10

Topic modeling in tourism research: a bibliometric study

10.11591/ijeecs.v42.i2.pp485-497
Valentinus Roby Hananto , Vivine Nurcahyawati , Tutut Wurijanto , Titik Lusiani , Mate Kovacs
The application of topic modeling in the tourism domain has become a popular research topic in the last decade. This study aims to provide a comprehensive bibliometric analysis of topic modeling research in tourism over the period 2010 to 2023. The data for this study were sourced from the Scopus database, a widely recognized repository of peer-reviewed literature. The search was restricted to publications published from January 1, 2010, to December 31, 2023, to capture the evolution and current state of this rapidly growing field. Using VOSviewer and SciMAT software to analyze articles in the Scopus database, the study identified key trends, influential authors, and future research directions. This study indicates the growth and development in topic modeling for tourism research, with more than 100 Scopus-indexed papers published annually in 2023 alone. The results of this study show that topic modeling has a wide range of applications in tourism, demonstrating its utility in various contexts to understand tourist behavior and enhance smart tourism initiatives.
Volume: 42
Issue: 2
Page: 485-497
Publish at: 2026-05-10

A multi-class classification approach for feminist sentiment analysis in Bangla social media using TF-IDF and ensemble learning

10.11591/ijeecs.v42.i2.pp584-595
Zaid Bin Sajid , Md. Mijanur Rahman , Md. Sumon Hosen , Sarara Jaman Riya , Yeamin Akon , S. M. Fahad Bin Jim , Ornab Biswass
Social media has emerged as an important part of societal discourse on feminism and gender equality, especially in Bangladesh. Nevertheless, any feminist debate on social media in Bengali polarizes reactions, highlighting the need for automated sentiment analysis. This paper introduces one of the earliest multi-class feminist sentiment classification schemes of the Bengali social media with a manually annotated dataset of 6,830 comments categorized as positive, neutral, or negative. The framework uses term frequency-inverse document frequency (TF-IDF) based n-gram feature representations utilizing traditional machine learning algorithms, with a majority voting ensemble to determine optimal robust models. The data was divided into 80% and 20% for training and testing, respectively. Models were evaluated on the basis of accuracy, precision, recall, and macro-F1 to correct on imbalance of classes. Multinomial naive bayes (MNB) has the best accuracy of 84.74% and macro-F1 of 84.66, which is 4-7 times higher than other models. The ensemble method improved feature strength. Such results indicate that lightweight machine learning models based on TF-IDF features and ensemble models can be useful to detect feminist sentiment in Bangla social media and serve as a guideline in the field of domain-specific sentiment analysis in low-resource languages and help monitor online feminist discourse.
Volume: 42
Issue: 2
Page: 584-595
Publish at: 2026-05-10

E-APPS: a digital platform for application processing and records management in private educational institutions with data visualization

10.11591/ijeecs.v42.i2.pp414-425
Eusebio Laureta Mique Jr. , Alvin Reyes Malicdem , Liezl Padilla Mique , Marylen De Guia Rodriguez , Marydel Carrera Estira
Online application and processing systems are digital platforms that allow applications to be submitted, reviewed, and processed electronically. These systems enhance efficiency by streamlining workflows, reducing paperwork, and enabling faster and more accurate decision-making for both applicants and administrators. This paper presents the development, implementation, and evaluation of E-APPS: an electronic application processing system for private schools and educational institutions, and records management (E-APPS). Specifically, it determined the process and forms involved in private school applications for approval, developed an E-APPS for private schools and records management using the extreme programming model, assessed the software quality of the E-APPS, and evaluated its technical performance. Based on the result, the existing application process includes submission, validation of documents, inspection, endorsement to the regional Office, approval, and issuance of permits. The E-APPS was developed and evaluated to ensure it meets quality requirements. The developed system was also tested and proven to work reliably even when many users use it simultaneously. It can accommodate hundreds of users without delays or system errors.
Volume: 42
Issue: 2
Page: 414-425
Publish at: 2026-05-10

A structured process model to optimize detection capabilities in security operations centers (SOCs)

10.11591/ijeecs.v42.i2.pp518-530
Adi Nugroho , Charles Lim , Heru Purnomo Ipung
The security operations center (SOC) is essential for protecting organizational assets and maintaining operational continuity against rapidly changing cyber threats. Despite its significance, numerous SOCs establish detection capabilities lacking of a systematic framework, frequently culminating in inefficiencies and constrained efficacy. This paper presents a process model aimed at improving SOC detection capabilities by aligning them with business objectives, pertinent risks, and the evolving character of contemporary threats. The study includes an evaluation of current detection methodologies, utilizing the MITRE ATT&CK architecture and threat intelligence data to pinpoint relevant risks and detection deficiencies. A case study was performed at the XYZ Organization to evaluate current detection capabilities and implement the recommended process model. The model was validated through interviews with experts in the SOC field, verifying the findings' credibility. The findings demonstrate that the model efficiently helps SOC in synchronizing detection methods with organizational objectives, prioritizing pertinent threats, and promoting the enhancement of more targeted and adaptable detection capabilities. This research provides theoretical insights into SOC detection modeling and practical assistance for enterprises aiming to enhance their cybersecurity operations.
Volume: 42
Issue: 2
Page: 518-530
Publish at: 2026-05-10

Design of a cost-effective online experimental platform for electrical experiments using a Raspberry Pi-based system

10.11591/ijeecs.v42.i2.pp337-348
Abdelkrim Benali , Somia Benali , Benameur Hemidi
Following the COVID-19 pandemic, online learning platforms have become vital for supporting distance education. This work presents LABTEC, an online Experimental Platform for electronics education that enables students to manipulate real hardware through a learning management system (LMS). The platform allows remote execution of experiments with electronic circuits and instruments, such as oscilloscopes, providing hands-on practice over the Internet in real time. The main contributions of this work are threefold: (i) a hybrid Flask–Django server architecture, where flask manages instrument-level control and Django provides secure and scalable web services; (ii) the use of a Raspberry Pi gateway as a cost-efficient and versatile hardware interface; and (iii) an open-source remote laboratory framework experimentally validated to support real-time interaction with average end-to-end latency below 50 ms, stable multi-user access, and low resource utilization. Experimental results demonstrate reliable operation under concurrent user scenarios, achieving consistent measurement visualization and control with reduced deployment cost compared to proprietary and institution-centric remote laboratory platforms. Performance evaluation shows a control latency below 50 ms for closed-loop tasks, a success rate above 98% under multi-user access, and average CPU and RAM usage of 35% and 420 MB on Raspberry Pi 4B during peak load. These results demonstrate that the system is responsive, reliable, and suitable for concurrent experiments. Although validated with a single instrument type, the proposed approach offers a scalable and replicable solution that can significantly enhance electronics education and lower laboratory infrastructure costs.
Volume: 42
Issue: 2
Page: 337-348
Publish at: 2026-05-10

Achievement motivation as a predictor of historical empathy: a study of social studies university students

10.11591/ijere.v15i2.37119
Mohamed Ali Nemt-allah , Hamed Samy Ghareib , Elsayed Atef El-Hashimi , Mashael Nasser Al-Dosari , Mohamed Sayed Abdellatif , Tawfik Mahmoud Soliman , Ashraf Ragab Ibrahim Ibrahim
This study investigated the predictive relationship between achievement motivation and historical empathy among social studies university students. Using the achievement motives scale-revised (AMS-R) and the historical empathy scale-adult form (HES-AF), data were collected from 428 Egyptian university students aged 18-24 from education faculties at Al-Azhar University. Correlation analyses revealed significant positive relationships between achievement motivation dimensions (hope of success and fear of failure) and all historical empathy components (cognitive, affective, and behavioral). Multiple regression analysis demonstrated that achievement motivation significantly predicted historical empathy, F(2, 425)=86.035, p<.001, explaining 28.8% of the variance. Hope of success emerged as the primary predictor (β=.478, p<.001), with approximately four times the predictive strength of fear of failure (β=.109, p=.018). These findings suggest that approach-oriented achievement motivation, particularly hope of success, is crucial in fostering empathetic understanding of historical content. The results provide theoretical insights into the psychological mechanisms underlying historical empathy and offer practical guidance for educators seeking to enhance empathetic engagement in social studies education through motivation-focused pedagogical approaches.
Volume: 15
Issue: 2
Page: 1435-1445
Publish at: 2026-04-23

Enhancing students’ intercultural communication competence: evidence from an Indonesia–Malaysia partnership program

10.11591/ijere.v15i2.38605
Athok Fu’adi , Afif Syaiful Mahmudin , Esti Yuli Widayanti , Beta Pujangga Mukti
International community service (ICS) is increasingly recognized as an effective approach for strengthening students’ global and intercultural competence. This study examined the impact of an ICS program conducted between State Islamic University of Kiai Ageng Muhammad Besari Ponorogo and Madrasah Utsmaniyah ABIM Penang, Malaysia, on students’ intercultural communication competence (ICC) and soft skills. Employing a mixed-methods convergent design, the study involved 12 participating students, faculty supervisors, ABIM coordinators, and local community leaders. Quantitative data were obtained through pre–post assessments using validated ICC and soft-skill scales, while qualitative data were collected through interviews, participant observation, and reflective journals. The findings indicate significant improvement across all ICC dimensions, including cultural awareness, sensitivity, communication skills, and reflective competence. Students also demonstrated notable enhancement in soft skills such as leadership, teamwork, adaptability, and empathy, supported by qualitative evidence of increased confidence, communicative flexibility, and ethical awareness during community engagement. Perspectives from supervisors and community stakeholders further corroborated the program’s effectiveness. Overall, the study highlights the value of culturally proximate international service-learning in fostering global competence within Islamic higher education and offers implications for developing sustainable cross-border community service initiatives in the ASEAN context.
Volume: 15
Issue: 2
Page: 1488-1495
Publish at: 2026-04-23
1 2 3
...
2062 2063
Show 64 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