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

25,002 Article Results

Enhanced automated Alzheimer’s disease detection from MRI images by exploring handcrafted and transfer learning feature extraction methods

10.11591/ijece.v15i2.pp1557-1571
Touati Menad , Mohamed Bentoumi , Arezki Larbi , Malika Mimi , Abdelmalik Taleb Ahmed
The rising prevalence of Alzheimer’s disease (AD) poses a significant global health challenge. Early detection of AD enables appropriate and timely treatment to slow disease progression. In this paper, we propose an enhanced procedure for automated AD detection from magnetic resonance imaging (MRI) images, focusing on two primary tasks: feature extraction and classification. For feature extraction, we have investigated two categories of methods: handcrafted techniques and those based on pre-trained convolutional neural network (CNN) models. Handcrafted methods are preceded by a preprocessing step to improve the MRI image contrast, while the pre-trained CNN models were adapted by utilizing only a part of the models as feature extractors, incorporating a global average pooling (GAP) layer to flatten the feature vector and reduce its dimensionality. For classification, we employed three different algorithms as binary classifiers to detect AD from MRI images. Our results demonstrate that the support vector machine (SVM) classifier achieves a classification accuracy of 99.92% with Gabor features and 100% with ResNet101 CNN features, competing with existing methods. This study underscores the effectiveness of feature extraction using Gabor filters, as well as those based on the adapted pre-trained CNN models, for accurate AD detection from MRI images, offering significant advancements in early diagnosis.
Volume: 15
Issue: 2
Page: 1557-1571
Publish at: 2025-04-01

Improved convolutional neural network-based bearing fault diagnosis using multi-phase motor current signals

10.11591/ijece.v15i2.pp1656-1669
Hai Dang Huu , Ngoc-My Bui , Van-Phuc Hoang , Thang Bui Quy , Yen Hoang Thi
Diagnosing bearing faults of the induction motor is crucial for the maintenance of rotating electrical machines. Numerous methods have been developed and published for monitoring and classifying these faults using sensor data such as vibration, audio, and current signals. Ideally, the current phases are balanced; however, faults disrupt this symmetry, causing each phase to reveal unique diagnostic details. Consequently, studies that rely on a single phase of the current signal may not capture all fault-related characteristics. Research on motor bearing fault diagnosis using two current phases typically extracts features from each phase separately, applying machine learning to classify the faults. Currently, no approach has been proposed to extract features from both phases simultaneously. Furthermore, the proposed solutions have only been published with noise-free data. To address these challenges, this paper introduces an enhanced solution that improves the accuracy of motor bearing fault classification based on an improved convolutional neural network that processes current signals from two phases simultaneously. Experimental results demonstrate that the proposed method significantly outperforms traditional approaches, particularly in scenarios where the sample signals are noise-adding signals. Fault classification accuracy of the proposed improved convolutional neural network (MI-CNN) about 95.12% with noise-adding signals at the signal-to- noise ratio of 20 dB.
Volume: 15
Issue: 2
Page: 1656-1669
Publish at: 2025-04-01

Enhancing accuracy in greenhouse microclimate forecasting through a hybrid long short-term memory light gradient boosting machine ensemble approach

10.11591/ijece.v15i2.pp2392-2403
Mokeddem Kamal Abdelmadjid , Seddiki Noureddine , Bourouis Amina , Benahmed Khelifa
Greenhouse cultivation is one of the main methods for improving agricultural yield and quality. With the world needing more and more production, improving greenhouses using innovative technology becomes a must. These high-tech, aka, smart greenhouses depend much on the accuracy and availability of sensor data to perform at their best. In challenging situations such as sensor malfunctions or data gaps, utilizing historical data to predict microclimate parameters within the greenhouse is essential for maintaining optimal growing conditions and effective sustainable resource management control. In this work, and by employing a synthesis technique across various time series models, we forecast internal temperature and humidity, the two main parameters for a greenhouse, by incorporating diverse characteristics as input into a customized forecasting model. The selected architecture integrates deep learning and nonlinear learning models, specifically long short-term memory (LSTM) and light gradient boosting machine (LightGBM) as an ensemble approach, providing a comprehensive framework for time-series prediction, evaluated through mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R²) metrics. With a focus on improving accuracy in anticipating environmental changes, we have achieved high precision in predicting temperature (98.45%) and humidity (99.61%).
Volume: 15
Issue: 2
Page: 2392-2403
Publish at: 2025-04-01

A comprehensive analysis of different models: skin cancer detection

10.11591/ijece.v15i2.pp2404-2415
Amruta Thorat , Chaya Jadhav
Due to fast-growing worldwide air pollution and ozone layer destruction, an alarming number of people are found to have skin cancer, more than any other kind of cancer combined. It is known to be one of the deadliest malignancies; if not identified and cured in its early stages, it is likely to spread to other body parts. Early detection is critical and helps prevent cancer from spreading. This allows for early decisions on diagnostic and treatment options. Early diagnosis and discovery, combined with the right treatment, can save lives. In this paper, we have done a detailed survey on various techniques and models developed for skin cancer detection and also discussed different security-related issues. This work thoroughly explores the several types of models utilized to identify cancer in the skin.
Volume: 15
Issue: 2
Page: 2404-2415
Publish at: 2025-04-01

Architecture of multi-agent systems for generative automatic matching among heterogeneous systems

10.11591/ijece.v15i2.pp2345-2355
Zouhair Ibn Batouta , Rachid Dehbi , Mohamed Talea
This paper presents the generative automatic matching (GAM) approach, implemented through a multi-agent system (MAS), to address the challenges of heterogeneity across meta-models. GAM integrates automatic meta-model matching with model generation, offering a comprehensive solution to complex systems involving diverse architectures. The key innovation lies in its ability to automate both the detection of correspondences and the transformation of models, improving the precision and recall of matching processes. The system's scalability and adaptability are enhanced by MAS, allowing for efficient management of diverse meta-models. The approach was evaluated through relational to big data UML meta-models (RBDU) case study. The results demonstrated high accuracy, with precision and recall metrics approaching 1, underscoring the robustness of GAM in managing heterogeneous systems. Compared to traditional methods, GAM offers significant advantages, including automated matching and generation, adaptability to various domains, and superior performance metrics. The study contributes to the field of model-driven engineering (MDE) by formalizing a method that effectively bridges the gap between heterogeneous meta-models. Future research will focus on refining matching heuristics, expanding case studies.
Volume: 15
Issue: 2
Page: 2345-2355
Publish at: 2025-04-01

Computer science and educational games to enhancing students’ Islamic content learning

10.11591/ijere.v14i2.29459
Ahmed Tlili , Salim Chikhi
Learning in all humanities content branch such as Islamic sciences is declared to be boring, tiring and very dry plain content because the educational level of learners becomes low and worrying. This statement is justified by the result of our statistical study which reveals that learning of Islamic content is not attractive and needs to be revolutionized in order to make it more attractive and interesting for the new generation called digital generation. In this paper, we have used the gamification concept with learning analytics (LA) approach to design an educational game to improve Islamic content learning. However, and due to the lake of works and the knowledge about teaching Islamic contents using education games look insufficient and at their begins. The obtained results, in this study, with proposed approach, shows that the students had remarkably higher motivation and performance to learn than before. The main objective of this investigation is, firstly, allows managers and teachers easily incorporate LA approaches to help student improves their learning; and secondly, future work benefits from these results to define an appropriate dashboard for the Islamic content learning and teaching.
Volume: 14
Issue: 2
Page: 995-1003
Publish at: 2025-04-01

Impact of external demands problems on students’ psychological well-being: systematic literature review

10.11591/ijere.v14i2.30128
Muhammad Andi Setiawan , Endang Sri Estimurti , Yuni Pantiwati , Latipun Latipun , Bulkani Bulkani , Akhsanul In'am , Atok Miftachul Hudha
Students’ well-being is often disturbed by external demands, such as academic pressure, family expectations, and social expectations. These demands can impact students’ mental and emotional well-being. This research aims to explore the problems of external demands for students’ psychological well-being. This research used the systematic literature review (SLR) method to investigate the impact of external demands on students’ psychological well-being. Data were collected from articles published between 2018 and 2023 from the Scopus database. Of the 93 articles, 26 articles were obtained after screening. Data mining and analysis were conducted with the help of Publish or Perish, Biblioshiny, and ATLAS.ti. The results show the complexity of external demands, with factors such as internal and external support, job control, social media use, and individual differences in emotion regulation playing essential roles. The long-term impacts of these demands can include increased levels of stress, anxiety, and depression in students. Therefore, it is essential to manage external demands strategically to create a learning environment that supports students’ psychological well-being. This research highlights the need for joint efforts between schools, families, and communities to address external demands on students. Effective interventions are needed to reduce the negative impact of external demands.
Volume: 14
Issue: 2
Page: 1447-1458
Publish at: 2025-04-01

Predicting students’ intentions for post-COVID-19 face-to-face classes

10.11591/ijere.v14i2.29737
Wei Boon Quah , Krishnavehni Gopal
The COVID-19 pandemic led to community college closures, with reopening being considered as a potential strategy to enhance learning outcomes. However, existing literature lacks insights into the factors that determine students’ intention to attend limited face-to-face classes. To address this gap, a study was conducted to explore the intentions of 122 English students at a Malaysian community college regarding attendance in such classes post-reopening, using the theory of planned behavior as a framework. Results indicated a moderate level of intention to attend. Perceived behavioral control (PBC) and subjective norm positively predicted students’ intentions, while attitude did not significantly contribute. These findings highlight the critical role of PBC and subjective norms in shaping students’ intentions. As many community colleges prepare for phased reopening, understanding students’ diverse perspectives is crucial for informed decision-making regarding in-person instruction. Institutions must consider these factors to gain nuanced insights into students’ inclinations towards face-to-face classes, thereby facilitating effective planning amidst ongoing uncertainties.
Volume: 14
Issue: 2
Page: 1351-1356
Publish at: 2025-04-01

The readiness of mathematics teachers as agents of change: a recent comprehensive review

10.11591/ijere.v14i2.30291
Sharida Abu Talib , Nurfaradilla Mohamad Nasri , Muhammad Sofwan Mahmud
This study scrutinizes the role of mathematics teachers as pivotal agents of change in the evolving educational landscape, focusing on their readiness to embrace pedagogical reforms. The review aims to reveal the current patterns and trends in mathematics teachers’ readiness literature discussed in recent studies. Utilizing the preferred reporting items for systematic reviews and meta-analyses (PRISMA) framework, this study analyzed 31 empirical articles from the Scopus and Web of Science databases in 2023. The review process for chosen articles is examined, encompassing aspects such as publication criteria, eligibility and exclusion standards, databases, and the progression of review stages. The most striking result from the analysis is that mathematics teachers’ readiness is closely related to teaching strategies and pedagogy. Moreover, inconsistencies in practice and constraints such as inadequate resources, insufficient institutional support, and teacher training program gaps hinder their ability to implement change effectively. The implications of this study extend to various stakeholders in the education ecosystem, including policymakers, educational institutions, teacher training programs, and practitioners. This review suggests strategies to enhance teachers’ professional development and serve as preliminary work toward developing a pedagogy model. In conclusion, this systematic review consolidates the existing knowledge on the readiness of mathematics teachers as agents of change.
Volume: 14
Issue: 2
Page: 1468-1476
Publish at: 2025-04-01

Digital learning models: experience of online learning during the pandemic

10.11591/ijere.v14i2.30032
Umi Muzayanah , Moch Lukluil Maknun , Faidus Sa'ad , Mustolehudin Mustolehudin , Mulyani Mudis Taruna
During the global pandemic of COVID-19, the learning model has been “forced” to transition from conventional to distance learning. At the beginning of its implementation, digital-based learning received many complaints from teachers, parents, and students. Gradually, they can adapt to distance learning that utilizes many digital devices. Through quantitative and qualitative research approaches, this paper aims to describe the online learning model in schools and Islamic boarding school (pesantren) based on their experience during COVID-19. From these studies, several digital-based learning models can be identified. First, social media-based learning. Social media-based learning is carried out by optimizing the use of WhatsApp as the main media in learning. Second, learning through virtual classrooms, which is face-to-face learning between teachers and students in a digital space. Third, education platform-based learning, where the learning process is conducted through internal school or government platforms. Fourth is blended learning, which is learning partly online and offline. This fourth lesson aims to accommodate the learning needs of students or teachers who have obstacles such as signal difficulties and weak economies. The findings contribute to the availability of references for digital learning models that can be applied in the future.
Volume: 14
Issue: 2
Page: 1196-1206
Publish at: 2025-04-01

Learning competencies in the electrical installations laboratory for engineering students

10.11591/ijere.v14i2.30130
Margarita F. Murillo Manrique , Jorge A. Sánchez Ayte , Antonio A. Meléndez Murillo
The research addresses the lack of practical competencies in the electrical installations-I (IE-1) course at the School of Mechanical and Electrical Engineering (EPIME) at the National Technological University of Lima Sur, where the current content is mostly theoretical. To solve this problem, the course was moved to the Electrical Installations Laboratory (LABIE) and the conceive, design, implement, and operate (CDIO) methodology was applied, combining theory with practice to develop competencies in knowledge, skills, and attitudes. The laboratory guides were aligned with the new IE-1 syllabus, including single-phase and three-phase systems of 220 V at 60 Hz, which were not previously covered. Two groups of 15 students were compared: an experimental group (EG) and a control group (CG). Both took a pre-test with similar results. The CG followed traditional classes, while the EG worked in the LABIE with CDIO. At the end, a post-test showed significant improvements in the EG, validating the effectiveness of CDIO in enhancing practical training in IE-1. It is concluded that this methodology should be implemented in the new EPIME curriculum.
Volume: 14
Issue: 2
Page: 1217-1226
Publish at: 2025-04-01

Investigation of the factors affecting students’ self-directed learning readiness in the blended learning model

10.11591/ijere.v14i2.31398
Nguyen Thi Bich , Kieu Phuong Thuy , Vu Thi Mai Huong , Pham Thi Binh
Many factors influence the level of readiness for self-directed learning. This study seeks to examine the relationship between learners’ personal characteristics (gender, major, academic year), external factors (facilities, self-study time, peer influence, teacher support), internal factors (cognitive skills, metacognitive skills, attitudes, motivation), and self-directed learning readiness in a blended learning model. The aim is to identify the decisive influencing factors to promote learners’ readiness for self-directed learning and improve blended teaching effectiveness. A survey was conducted with 1,276 students participating in the blended learning model at Hanoi National University of Education in Vietnam. The data were quantitatively analyzed using structural equation modeling with the partial least squares approach in SmartPLS 3, as well as regression analysis in SPSS 20. The findings showed that external factors accounted for 68.7% of the variation in internal factors and 41.6% of the variation in self-directed learning readiness. The study also found that factors such as major and academic year had significant impacts on self-directed learning readiness, as evidenced by statistically significant differences with p-values less than 0.05. These results suggest strategies for educators to effectively address these factors to enhance students’ self-directed learning readiness in blended learning environments.
Volume: 14
Issue: 2
Page: 1340-1350
Publish at: 2025-04-01

IT education: impact assessment of a multi-fold approach

10.11591/ijere.v14i2.30197
Moh’d A. Radaideh , Qasem Abu Al-Haija
This study addresses the benefits and challenges of implementing a multi-faceted hybrid approach to delivering an introductory information technology (IT) course at Jordan University of Science and Technology, Jordan. We conducted a questionnaire survey with 251 participants, utilizing Google Forms for data collection and Microsoft Excel 2016 for coding. Data analysis was performed using SPSS statistics 17.0. Most participants were male students aged 21-23, pursuing bachelor’s degrees across various departments, with network engineering and security (NES) being the most represented. The survey items exhibited good internal consistency (Cronbach’s alpha=0.778), and significant associations were found among variables (p-value<0.05). Strengths of the hybrid approach include flexibility, instructor responsiveness, and engaging online resources. However, areas for improvement were identified in online discussion forums, such as technology tool usability, workload management, communication clarity, and assessment transparency. Despite challenges, the study underscores the successful implementation of the hybrid approach in IT course delivery, supported by positive student perceptions and recommendations for future adoption.
Volume: 14
Issue: 2
Page: 1264-1272
Publish at: 2025-04-01

Strategies and techniques for creating educational programs for teachers of natural science subjects

10.11591/ijere.v14i2.28905
Zhanara Nurmukhamedova , Dilara Nurbayeva , Bulbul Yerzhenbek , Diana Nassirova
The relevance of the study is based on the current educational reforms in the Republic of Kazakhstan, which is implemented under the conditions of humanization and integration at different levels. This is based on the development of the informatization and technologization of current science and practice, the trend towards the interpenetration of certain fields of knowledge into others, the exploration of interdisciplinary approaches in explaining the current world view, which is itself multidimensional, persistent, impartial and integrative. The purpose of this study is to provide a theoretical framework, developing a model for the training of modern natural science teachers and investigate the main stages of curriculum development for future teachers. The objectives of the study are aimed at disseminating knowledge about the development of effective educational programs. Objective methods included theoretical analysis, analysis of future teachers’ activities, synthesis of philosophical and educational psychology literature, modelling and observation. The study investigated and systematized approaches to the methodological design of educational programs and identified all types of professional competence using the method of analysis.
Volume: 14
Issue: 2
Page: 1369-1378
Publish at: 2025-04-01

Systematic Literature Review on Developing an Integrated STEM Leadership Model for Middle Leaders in School

10.11591/ijere.v14i2.31691
Saifulbahri Abdul Rahman , Abdul Halim Busari , Mohammad Nur Azhar Mazlan , Adawati Suhaili
This systematic literature review investigates the development of anintegrated science, technology, engineering, and mathematics (STEM)leadership model tailored for middle leaders in Malaysian schools. Theintroduction highlights the global emphasis on STEM education to fosterinnovation and economic growth, while acknowledging Malaysia’scommitment to enhancing STEM capabilities within its educational system.The problem statement identifies a gap in effective STEM leadership amongmiddle leaders, which is critical for implementing STEM initiatives andimproving student outcomes. To achieve this, we conducted an extensivesearch of scholarly articles from reputable databases such as Scopus and Webof Science (WoS), focusing on studies published between 2021 and 2024. Theflow of study is based on PRISMA framework. The database found (n=34)final primary data was analyzed. The finding was divided into three themeswhich are i) STEM education policy and implementation; ii) leadership inSTEM educational; iii) professional development in STEM education. Theconclusion emphasizes the need for a specialized leadership model thatincorporates instructional leadership principles, fosters professionaldevelopment, and supports collaborative practices among middle leaders. Thisintegrated model aims to address the unique challenges faced by middleleaders in Malaysian schools, ultimately enhancing STEM education andcontributing to Malaysia’s educational and economic aspirations.
Volume: 14
Issue: 2
Page: 786-796
Publish at: 2025-04-01
1 2 3
...
1666 1667
Show 23 of 1667

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