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

29,939 Article Results

Blockchain and internet of things synergy: transforming smart grids for the future

10.11591/ijece.v15i4.pp4239-4248
Mouad Bensalah , Abdellatif Hair , Reda Rabie
Conventional smart grid systems face challenges in security, transparency, and efficiency. This study addresses these limitations by integrating blockchain and internet of things (IoT) technologies, presenting proof-of-concept implemented on an Orange Pi 4 single-board computer. The realized prototype demonstrated secure and transparent energy transaction management with consistent throughput between 7.45 and 7.81 transactions per second, and efficient resource utilization across varying transaction volumes. However, scalability challenges, including a linear increase in processing time with larger block sizes, emphasize the need for optimized consensus mechanisms. The findings underscore the feasibility of blockchain-based smart grids in resource-constrained settings, paving the way for advancements in peer-to-peer energy trading, decentralized energy storage, and integration with artificial intelligence for dynamic energy optimization. This work contributes to developing secure, efficient, and sustainable energy systems.
Volume: 15
Issue: 4
Page: 4239-4248
Publish at: 2025-08-01

Two-step majority voting of convolutional neural networks for brain tumor classification

10.11591/ijece.v15i4.pp4087-4098
Irwan Budi Santoso , Shoffin Nahwa Utama , Supriyono Supriyono
Brain tumor type classification is essential for determining further examinations. Convolutional neural network (CNN) model with magnetic resonance imaging (MRI) image input can improve brain tumor classification performance. However, due to the highly variable shape, size, and location of brain tumors, increasing the performance of tumor classification requires consideration of the results of several different CNN models. Therefore, we proposed a two-step majority voting (MV) on the results of several CNN models for tumor classification. The CNN models included InceptionV3, Xception, DensNet201, EfficientNetB3, and ResNet50; each was customized at the classification layer. The initial step of the method is transfer-learning for each CNN model. The next step is to carry out two steps of MV, namely MV on the three CNN model classification results at different training epochs and MV on the results of the first step. The performance evaluation of the proposed method used the Nickparvar dataset, which included MRI images of glioma, pituitary, no tumor, and meningioma. The test results showed that the proposed method obtained an accuracy of 99.69% with a precision and sensitivity average of 99.67% and a specificity of 99.90%. With these results, the proposed method is better than several other methods.
Volume: 15
Issue: 4
Page: 4087-4098
Publish at: 2025-08-01

Multi-class pneumonia detection using fine-tuned vision transformer model

10.11591/ijece.v15i4.pp3996-4003
Khushboo Trivedi , Chintan B. Thacker
Distinguishing between the various forms of pneumonia (bacterial, viral, fungal, and normal) using chest X-rays is a major problem in global health. Conventional approaches to pneumonia identification frequently depend on laborious and error-prone manual interpretation. Current machine learning (ML) models, like convolutional neural networks (CNNs), have demonstrated some success, but they frequently fail on jobs requiring multi-class classification or generalization. The potential of vision transformer (ViT) models, fine-tuned to address these limitations, is explored. The approach enhances the accuracy of pneumonia classification into four distinct classes by leveraging the attention mechanism in vision transformers (ViTs). Fine-tuning with a tagged chest X-ray dataset improves the algorithm's ability to detect subtle variations in pneumonia types. The findings demonstrate the model's effectiveness in multi-class pneumonia diagnosis, achieving a significant performance improvement with 98% accuracy across the four classes. This work highlights the promise of vision transformers in medical imaging, enabling the development of improved and scalable pneumonia classification methods.
Volume: 15
Issue: 4
Page: 3996-4003
Publish at: 2025-08-01

Instance segmentation for PCB defect detection with Detectron2

10.11591/ijece.v15i4.pp4172-4180
Aravalli Sainath Chaithanya , Lavadya Nirmala Devi , Putty Srividya
Printed circuit boards (PCBs) are essential in modern electronics, where even minor defects can lead to failures. Traditional inspection methods struggle with complex PCB designs, necessitating automated deep learning techniques. Object detection models like Faster R-CNN and YOLO rely on bounding boxes for defect localization but face overlap issues, limiting precise defect isolation. This paper presents a segmentation-based PCB defect detection model using Detectron2’s Mask R-CNN. By leveraging instance segmentation, the model enables pixel-level defect localization and classification, addressing challenges such as shape variations, complex structures, and occlusions. Trained on a dataset of 690 COCO-annotated images, the model underwent rigorous experimentation and parameter tuning. Evaluation metrics, including loss functions and mean average precision (mAP), assessed performance. Results showed a steady decline in loss values and high precision for defects like mouse bites and missing holes. However, performance was lower for complex defects like spurs and spurious copper. This study highlights the effectiveness of instance segmentation in PCB defect detection, contributing to improved quality control and manufacturing automation.
Volume: 15
Issue: 4
Page: 4172-4180
Publish at: 2025-08-01

An in-depth analysis of a tutoring solution by digital technology

10.11591/ijece.v15i4.pp4058-4073
Soukaina Nai , Amal Rifai , Abdelalim Sadiq , Bahaa Eddine Elbaghazaoui
In Morocco, the dropout rate in primary and secondary education remains high due to environmental, social, familial, and educational factors. To address this issue, students rely on private tutoring or online platforms. However, socio-economic disparities make private tutoring inaccessible to many, while technical and pedagogical challenges limit the effectiveness of online platforms, deepening educational inequalities. This article proposes a nationwide participatory tutoring approach involving educational administration and teachers to ensure equitable and quality learning. We analyze existing models to identify their limitations and propose a structured tutoring system tailored to different student profiles. This system is based on a specific algorithm that defines skill assessment, remediation, and progress tracking. Unified modeling language UML is used to structure and present our approach in detail. Then, we compare current Moroccan platforms, particularly Massar, with our system, evaluating student engagement, pedagogical monitoring, curriculum alignment, and remediation effectiveness. Finally, we discuss our results, highlighting our system’s potential to reduce learning gaps, improve education, and significantly decrease the dropout rate in Morocco.
Volume: 15
Issue: 4
Page: 4058-4073
Publish at: 2025-08-01

An approach for predicting brain tumor with machine learning techniques

10.11591/ijece.v15i4.pp4332-4340
PSRB Shashank , L. Anand , R. Pitchai
The medical industry relies heavily on image processing for tumor diagnosis. Medical imaging is an ever-evolving and intricate field. Brain tumor (BT) is extremely frequent and may cause death. A BT develops when brain cells divide and grow out of control. The prognosis for people with BT can be greatly improved and the survival rate can be increased if the tumor is detected early. A single individual's brain magnetic resonance imaging (MRI) scan comprises of multiple slices through the 3D anatomical perspective. As a result, extracting tumor from MRI scans is a difficult and time-consuming laborious task. Because of the risks associated with biopsies, an MRI-based automated BT categorization is a safer alternative. The scientific profession has worked tirelessly from the beginning of the millennium to develop an automatic BT segmentation and classification system. Therefore, there is a large body of work in the field dedicated to the study of BT research through machine learning (ML) techniques. The review paper summaries the publicly accessible benchmark datasets typically used and compares various processing approaches, feature extraction (FE), segmentation, and classification algorithms for BT. The report also emphasizes the challenges of BT detection. Our hope is that this survey will provide researchers, clinicians, and other interested parties will gain an in-depth understanding of BT segmentation and classification using ML.
Volume: 15
Issue: 4
Page: 4332-4340
Publish at: 2025-08-01

Enhancing multi-class text classification in biomedical literature by integrating sequential and contextual learning with BERT and LSTM

10.11591/ijece.v15i4.pp4202-4212
Oussama Ndama , Ismail Bensassi , Safae Ndama , El Mokhtar En-Naimi
Classification of sentences in biomedical abstracts into predefined categories is essential for enhancing readability and facilitating information retrieval in scientific literature. We propose a novel hybrid model that integrates bidirectional encoder representations from transformers (BERT) for contextual learning, long short-term memory (LSTM) for sequential processing, and sentence order information to classify sentences from biomedical abstracts. Utilizing the PubMed 200k randomized controlled trial (RCT) dataset, our model achieved an overall accuracy of 88.42%, demonstrating strong performance in identifying methods and results sections while maintaining balanced precision, recall, and F1-scores across all categories. This hybrid approach effectively captures both contextual and sequential patterns of biomedical text, offering a robust solution for improving the segmentation of scientific abstracts. The model's design promotes stability and generalization, making it an effective tool for automatic text classification and information retrieval in biomedical research. These results underscore the model's efficacy in handling overlapping categories and its significant contribution to advancing biomedical text analysis.
Volume: 15
Issue: 4
Page: 4202-4212
Publish at: 2025-08-01

Review of implantable-based wireless body area network metrics issues

10.11591/ijece.v15i4.pp4004-4021
Rawan Al Majdoubah , Yousef Eljaafreh
Recent developments in wireless communications, low-power integrated circuits, and biological physiological sensors have led to a new generation of wireless sensor networks. Body area networks are an interdisciplinary field that allows for real-time updates of medical records via the internet and continuous, affordable health monitoring. Several intelligent physiological sensors can be easily integrated into a flexible wireless body area network for implanted use, supporting early disease detection or computer-assisted rehabilitation. This field relies on the feasibility of small, easily implanted biosensors that do not impede daily activities. The body's implanted sensors record various physiological changes to monitor the patient's status no matter where they are. Nonetheless, because they handle health data, these networks ought to use benchmarking criteria to ensure high levels of service quality. Network routing protocols, wireless technologies, quality of service, privacy and security, energy efficiency, and performance are among the challenges being focused on to better satisfy its expectations. This review aims to comprehensively compare implantable wireless body area network metrics issues, seeking to generate a consistent and understandable overview. This study also attempts to address the gaps and provides a current assessment of the metrics concerning a wireless body area network used in healthcare services.
Volume: 15
Issue: 4
Page: 4004-4021
Publish at: 2025-08-01

A ten-year retrospective (2014-2024): Bibliometric insights into the study of internet of things in engineering education

10.11591/ijece.v15i4.pp4213-4226
Zakiah Mohd Yusoff , Siti Aminah Nordin , Norhalida Othman , Zahari Abu Bakar , Nurlaila Ismail
This article presents a comprehensive ten-year retrospective analysis (2014-2024) of the evolving landscape of internet of things (IoT) studies within engineering education, employing bibliometric insights. The pervasive influence of IoT technologies across diverse domains, including education, underscores the significance of examining its trajectory in engineering education research over the past decade. Recognizing the dynamic nature of this intersection is crucial for educators, researchers, and policymakers to adapt educational strategies to IoT-induced technological shifts. Addressing this imperative, the study conducts a detailed bibliometric review to identify gaps, trends, and areas necessitating further exploration. Methodologically, the study follows a framework involving a comprehensive search of Scopus and Web of Science databases to identify relevant articles. Selected articles undergo bibliometric analysis using the Biblioshiny tool, supplemented by manual verification and additional analysis in Excel. This approach facilitates robust evaluation of citation patterns, co-authorship networks, keyword trends, and publication patterns over the specified timeframe. Anticipated outcomes include the identification of seminal works, key contributors, influential journals, and science mapping. The study aims to unveil emerging themes, track research trends, and provide insights into collaborative networks shaping IoT discourse in engineering education. This analysis offers a roadmap for future research directions, guiding educators and researchers toward fruitful avenues of exploration.
Volume: 15
Issue: 4
Page: 4213-4226
Publish at: 2025-08-01

To ensure public safety internet of things and convolutional neural network algorithm for a surveillance system enabled with 5G

10.11591/ijece.v15i4.pp4268-4278
Chandrasekar priya , Kesavan Kumuthapriya , Savarimuthu Sagayamary , L. M. Merlin Livingston , Marimuthu Venkatesan
Public safety and security are top priorities in the constantly urbanizing society and research develops and implements a smart surveillance system using fifth generation (5G) of wireless communication technology and internet of things (IoT) technologies to improve public safety. It developed a comprehensive and responsive monitoring solution using machine learning methods, especially convolutional neural networks (CNNs). IoT devices, including high-definition cameras, environmental sensors, and drones, are carefully deployed in urban centers, transit hubs, and essential infrastructure. These devices provide data to a central processing unit through the 5G network and CNNs analyze incoming data in real-time. The CNNs are taught to recognize objects, anomalies, faces, and license plates. These tasks help the system identify risks, odd activities, and intriguing people and warn authorities of real-time irregularities and security issues, simplifying emergency responses. Predictive analytics analyzes previous data to forecast security issues, enabling preventative steps and data are protected by strict privacy protections. According to this analysis, 5G-enabled IoT surveillance systems and machine learning may improve public safety, situational awareness, and emergency response times and approach ensures that security advancements respect privacy and integrity.
Volume: 15
Issue: 4
Page: 4268-4278
Publish at: 2025-08-01

Integration of strain gauge sensor in biceps muscle movement detection using LabView

10.11591/ijece.v15i4.pp3696-3706
Desy Kristyawati , Busono Soerowirdjo , Erma Triawati Christina , Robby Kurniawan Harahap
Muscle injuries caused by sports can have a serious impact on sportsmen, to avoid injuries during sports can be prevented by detecting the wrong movement using a strain gauge sensor attached to the muscle which in this study is devoted to the biceps muscle. The strain gauge will detect muscle movement, and the output generated at the strain gauge will be converted into the form of voltage and current which will be used to be processed using machine learning to get data patterns so that they can be grouped into data patterns of wrong movements and correct movements. The strain gauge movement pattern here is simulated using LabView by using a gauge resistance of 120 Ω, strain configuration Quarter Bridge 1, gauge factor 2.05, Vex is the excitation voltage given to the Wheatstone bridge is 5 V and the initial voltage -180.08 µV, the strain gauge output pattern is obtained in the form of Excel and with this data can be converted into voltage and current.
Volume: 15
Issue: 4
Page: 3696-3706
Publish at: 2025-08-01

Explainable artificial intelligence and feature based technique for the classification of kidney ultrasound images

10.11591/ijece.v15i4.pp4148-4159
Fizhan Kausar , Ramamurthy Bojan
Millions of people worldwide are affected by chronic kidney disease (CKD), which is one of the main causes of death. Using machine learning (ML) models, this study attempts to create a computer-aided diagnostic (CAD) system that can autonomously detect chronic kidney disease (CKD) with improved interpretability. An online medical database provided 340 ultrasound images used in this study, which included both normal and abnormal instances. 94 texture and intensity attributes were obtained from these images using Pyrandiomics. Six machine learning methods were used for classification: According to the evaluation results, support vector machine (SVM), decision tree (DT), random forest (RF), k-nearest neighbors (k-NN), XG-Boost, and naïve Bayes (NB) models were considered. Among these models, the random forest model demonstrated the highest accuracy. Explainable artificial intelligence (XAI) methods, namely Shapley additive explanation (SHAP), were utilized to improve model transparency. Clinicians could be assisted in comprehending the reasoning behind the predictions using SHAP analysis, which identifies the most important features impacting the ML model and visualizes the ranking of each individual feature.
Volume: 15
Issue: 4
Page: 4148-4159
Publish at: 2025-08-01

Enhancing mobile agent protection using a hybrid security framework combining pretty good protocol and code obfuscation

10.11591/ijece.v15i4.pp3913-3927
Jamal Zraqou , Wesam Alkhadour , Mahmoud Baklizi , Khalil Omar , Hussam Fakhouri
The security of mobile agents, which are autonomous software entities capable of migrating between computers to execute tasks, remains a critical concern in modern information technology. Cybersecurity has been a central component of this technological revolution and continues to be one of the most essential requirements for any software or platform. Despite advances in security measures, protecting mobile agents, particularly those carrying sensitive data, while they transmit over networks remains challenging. This research proposes a novel hybrid security technique, abbreviated as pretty good privacy and code obfuscation framework (PGF), which combines pretty good privacy (PGP) with code obfuscation. PGF is designed specifically to protect mobile agents, focusing on systems like Aglets. The technique aims to safeguard the integrity and confidentiality of the agent's data during transmission. Based on the mobile agent Aglets and the PGF technique, the proposed model enhances security by introducing additional protection layers during agent creation and transmission using PGP and code obfuscation. The comparative analysis demonstrated that PGF outperformed other algorithms in terms of time efficiency and security, effectively handling large data sizes through its hybrid cryptographic approach, which combines asymmetric and symmetric encryption. The model was implemented using the Aglets framework in Java development kit (JDK) and NetBeans and showed high reliability and practicality. However, its current design is tailored to Aglets, and future work could focus on adapting the model to other platforms and optimizing its resource efficiency for constrained environments.
Volume: 15
Issue: 4
Page: 3913-3927
Publish at: 2025-08-01

Sensitivity factors based computationally efficient approach for evaluation and enhancement of available transfer capability

10.11591/ijece.v15i4.pp3556-3565
Manjula S. Sureban , Shekhappa G. Ankaliki
Available transfer capability (ATC) is an indication of the capability of the transmission system to efficiently increase power transmission for further commercial trading between two areas or two points. ATC plays an important role in operating power systems economically, reliably, and securely. As the deregulation in the power system can cause overload in the transmission system, ATC evaluation and enhancement are required for secure and reliable operation. The advancements in power generation techniques and switching from centralized generation to distributed generation (DG) with more emphasis on renewable sources have resulted in various approaches to enhance ATC. In this work, a computationally efficient sensitivity-based methodology for evaluating and improving ATC with the presence of renewable generation is proposed. The developed approach is implemented on the IEEE 30 bus system and the outcome is compared with the existing methods in the literature.
Volume: 15
Issue: 4
Page: 3556-3565
Publish at: 2025-08-01

Cyber-fraud detection methodology by using machine learning algorithms

10.11591/ijece.v15i4.pp3949-3956
Ahmed Abu-Khadrah , Sahar Al-Washmi , Ali Mohd Ali , Muath Jarrah
Cybercrime covers a wide array of illegal online activities such as hacking and identity theft, while cyber fraud specifically involves deceptive practices like phishing and fraudulent financial transactions. The rise in technology and digital communication has exacerbated cyber fraud. Although prevention technologies are advancing, fraudsters continually adapt, making effective detection methods essential for identifying and addressing fraud when prevention fails. The proposed model aims to reduce online fraud through new detection algorithms. It utilizes statistical and machine learning techniques, including logistic regression, random forest, and naïve Bayes, to identify non-transactional fraud behaviors. By analyzing a meticulously collected and fine-tuned dataset, the study enhances detection capabilities beyond traditional transaction-focused approaches. The algorithms monitor user interactions and device characteristics to create profiles of normal behaviors and detect deviations indicative of fraud. The evaluation of proposed model showed 100% accuracy. A unified model incorporating all decision-making processes was used, leading to a voting phase and accuracy assessment. This approach consolidates multiple algorithms into a single framework, proving highly effective for comprehensive fraud detection. The research demonstrates the value of integrating machine learning techniques with real-world data to advance fraud detection and emphasizes the importance of continual adaptation to address evolving cyber threats.
Volume: 15
Issue: 4
Page: 3949-3956
Publish at: 2025-08-01
1 2 3
...
1995 1996
Show 152 of 1996

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