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

28,719 Article Results

Design and performance analysis of an NSFET-based biosensor for the early detection of dengue

10.11591/ijece.v15i6.pp5183-5192
Tulasi Radhika Patnala , Madhavi Tatineni
Healthcare industry is changing due to technological breakthroughs that spur creative methods for diagnosing and treating illnesses. This study examines the development of nanowire-based stacked field-effect transistor (NSFET) biosensors for the early detection of dengue virus. Dengue fever is severe threat to public health and a flavivirus spread by mosquitoes. About half of the global population is at risk due to an endemic illness in tropical and subtropical regions, which affects approximately 100 million individuals annually in 130 countries. The virus has four antigenically distinct serotypes, and there may be a fifth. These serotypes induce variety of clinical symptoms. This can include benign infections that go away on their own or extremely serious, potentially fatal consequences like organ failure, plasma leakage, and bleeding. While many techniques are now used to diagnose dengue fever in the laboratory, no single technique satisfies the optimum standards for speed, economy, sensitivity, specificity. To close this gap in dengue diagnosis, newer detection technologies are desperately needed. This ultrasensitive label-free electrical device can detect the dengue virus (DENV) early on and prevent severe additional harm to humans. To detect various DENV concentrations in human blood and demonstrate potential for eventual point-of-care (POC) detection, NSFET constructed and simulated in this work.
Volume: 15
Issue: 6
Page: 5183-5192
Publish at: 2025-12-01

Intrusion detection based on image transformations and data augmentation

10.11591/ijece.v15i6.pp5594-5603
Nada Ali Abood , Asghar A. Asgharian Sardroud
The increasing growth of users and communication networks in different platforms has led to the emergence of various types of network attacks. intrusion detection systems (IDS) are one of the important solutions to cope with these problems. An IDS determines whether incoming traffic is intrusive or normal. IDSs often achieve high efficiency with methods based on deep neural networks. However, one of the shortcomings of these methods is the lack of sufficient attention to the spatial features in the data. This research presents an intrusion detection method based on image transformations and data augmentation is presented. In the proposed method, the intrusion detection process is performed by transforming the traffic vector into an image using a convolutional neural network (CNN). Also, we use data augmentation and dimension reduction techniques to increase accuracy and reduce complexity in the proposed method. Simulation results on network security laboratory - knowledge discovery and data mining (NSL-KDD) show that the proposed IDS can classify intrusion traffic with an accuracy of 97.58%.
Volume: 15
Issue: 6
Page: 5594-5603
Publish at: 2025-12-01

Improving time-domain winner-take-all circuit for neuromorphic computing systems

10.11591/ijece.v15i6.pp5173-5182
Son Ngoc Truong , Tu Tien Ngo
With the rapid advancements of information processing systems, winner- take-all (WTA) circuits have emerged as essential components in a wide range of cognitive functions and decision-making applications. Neuromorphic computing systems, inspired by the biological brain, utilize WTA circuits as selective mechanisms that identify and retain the strongest signal while suppressing all others. In this study, we present an effective time-domain WTA circuit with optimized multiple-input NOT AND (NAND) gate and delay circuit for neuromorphic computing applications. The circuit is evaluated using sinusoidal current inputs with varying phase delays, which successfully demonstrating precise winner selection. When applied to neuromorphic image recognition task, the enhanced time-domain WTA achieves an improvement of 0.2% in precision while significantly reducing power consumption, yielding a low figure of merit (FoM) of 0.03 µW/MHz, compared to the previous study with FoM of 0.25 µW/MHz. The optimized WTA circuit is highly promising for large-scale neuromorphic applications.
Volume: 15
Issue: 6
Page: 5173-5182
Publish at: 2025-12-01

Development and evaluation of a re-sequenced intervention module in learning chemical bonding

10.11591/ijere.v14i6.31851
Baby Eve N. Asequia , Leemarc C. Alia , Kevin Client B. Matutes
In the typical high school chemistry curriculum, chemical bonding precedes the chemical reactions. In this study, the re-sequenced effect of learning chemical bonding when chemical reactions are introduced first among grade 9 learners was investigated. A learning module with re-sequenced intervention in chemical bonding was developed using analysis, design, development, implementation, evaluation (ADDIE) model and validated by eight science education professionals rated as very satisfactory. A quasi-experimental research design was utilized in the implementation phase with 129 respondents selected through cluster random sampling. Pre- and post-tests, formative and summative assessments, and evaluation surveys were administered. Evaluation results revealed that the scores from the re-sequenced intervention group displayed a slightly higher overall satisfaction percentage (99.06%) compared to the control group (94.74%). In addition, the experimental group achieved significantly higher competency levels (M=49.3, SD=19.4) compared to the control group (M=41.4, SD=15.3), with p=0.016 and d=0.37. Furthermore, students reported positive perceptions despite initial misconceptions. These findings highlight that re-sequencing topic order enhances chemistry learning outcomes and student engagement. Hence, the re-sequenced learning module became a valuable tool for enhancing understanding of chemical bonding, independent of baseline competency or attitudes toward the material.
Volume: 14
Issue: 6
Page: 4864-4873
Publish at: 2025-12-01

Prediction of peripheral arterial disease through non-invasive diagnostic approach

10.11591/ijece.v15i6.pp5782-5791
Sobhana Mummaneni , Lalitha Devi Katakam , Pali Ramya Sri , Mounika Lingamallu , Smitha Chowdary Ch , D.N.V.S.L.S Indira
Peripheral arterial disease (PAD) is a cardiovascular condition caused by arterial blockages and poor blood circulation, increasing the risk of severe complications such as stroke, heart attack, and limb ischemia. Early and accurate detection is essential to prevent disease progression and improve patient outcomes. This study introduces a non-invasive diagnostic method using laser doppler flowmetry (LDF), electrocardiography (ECG), and photoplethysmography (PPG) to assess vascular health. LDF measures microvascular blood flow, ECG evaluates heart rate variability, and PPG captures pulse waveform characteristics. Key physiological features such as blood flow variability, pulse transit time, and hemodynamic responses are extracted and analyzed using machine learning. Random forest and XGBoost models are employed and combined using ensemble learning to classify individuals into non-PAD, moderate PAD, and severe PAD categories. A comparative evaluation shows that the ensemble model delivers superior classification accuracy. This integrated system offers a fast, reliable screening tool that supports early PAD detection and intervention. By combining multimodal signal analysis with machine learning, the approach enhances diagnostic precision and provides a scalable solution for preventive cardiovascular care.
Volume: 15
Issue: 6
Page: 5782-5791
Publish at: 2025-12-01

Impact of outlier detection techniques on time-series forecasting accuracy for multi-country energy demand prediction

10.11591/ijece.v15i6.pp5067-5079
Shreyas Karnick , Sanjay Lakshminarayanan , Madhu Palati , Prakash R
Accurate energy demand prediction is crucial for efficient grid management and resource optimization, particularly across multiple countries with varying consumption patterns. However, real-world energy demand data often contains outliers that can distort forecasting accuracy. This study evaluates the impact of five outlier detection techniques—Z-Score, density- based spatial clustering of applications with noise (DBSCAN), isolation forest (IF), local outlier factor (LOF), and one-class support vector machine (SVM)—on the performance of three time-series forecasting models: long short-term memory (LSTM) networks, convolutional neural network (CNN) Autoencoders, and LSTM with attention mechanisms. The models are tested using energy demand data from four European countries— Germany, France, Spain, and Italy—derived from real-time consumption records. A comparative analysis based on root mean squared error (RMSE) demonstrates that incorporating outlier detection significantly enhances model robustness, reducing forecasting errors caused by anomalous data. The findings emphasize the importance of selecting appropriate outlier detection strategies to improve the accuracy and reliability of energy demand forecasting. This research provides valuable insights into the trade-offs involved in outlier removal, with implications for policy and operational practices in energy management.
Volume: 15
Issue: 6
Page: 5067-5079
Publish at: 2025-12-01

SGcoSim: a co-simulation framework to explore smart grid applications

10.11591/ijece.v15i6.pp5106-5118
Abdalkarim Awad , Abdallatif Abu-Issa , Peter Bazan , Reinhard German
Under the smart grid concept, new novel applications are emerging. These applications make use of information and communication technology (ICT) to help the electrical grid run more smoothly. This paper introduces SGcoSim, a co-simulation framework that integrates power system modeling and data communication to enhance smart grid applications. The framework utilizes OpenDSS for simulating power distribution components and OMNeT++ for communication modeling, enabling real-time peer-to-peer interactions via wireless sensor network (WSN) techniques. Virtual cord protocol (VCP) is deployed for efficient routing and data management within the field area network. SGcoSim’s functionality is demonstrated through two case studies: a phasor measurement unit (PMU)-based wide-area monitoring system and an integrated volt/VAR optimization with demand response (IVVO-DR) application. Results indicate significant reductions in energy consumption and power losses, highlighting the capabilities of SGcoSim.
Volume: 15
Issue: 6
Page: 5106-5118
Publish at: 2025-12-01

Enhancing teachers’ digital literacy for security: a systematic review of frameworks and analytical methods in education

10.11591/ijere.v14i6.32613
Nadirah Othman , Nor Aslily Sarkam , Norhayati Baharun , Teoh Sian Hoon , Suraya Masrom , Nor Faezah Mohamad Razi , Abdullah Sani Abd Rahman
The rising use of digital tools in education emphasizes the crucial need of teachers’ digital security, which relies on strong digital literacy. This study assesses teachers’ digital literacy on digital security literature to meet the urgent need for safe practices in schools due to increased security breaches. A total of 30 studies were reviewed using preferred reporting items for systematic reviews and meta-analyses (PRISMA) criteria to build frameworks and data analysis methodologies in this field. Five research areas were identified: teacher perspectives, security-related issues, educational impacts, pedagogical approaches, and instrument validation. The predominant framework used was the digital competence framework for citizens (DigComp), however hybrid frameworks that integrate other theoretical perspectives were highly commended for their comprehensive approach. The 30% of the studies focused on security issues, including cyberbullying and data protection, while 70% incorporated security dimensions into digital literacy frameworks. Quantitative approaches comprising 60%, including t-tests, analysis of variance (ANOVA), and regression analysis. Structural equation modeling (SEM) was used in several studies to examine complex relationships. Although current research predominantly emphasizes quantitative methods, future investigations could enhance knowledge of teachers’ digital literacy and security by integrating SEM with artificial neural networks (ANN). This review emphasizes the necessity for hybrid frameworks and sophisticated approaches to enhance research.
Volume: 14
Issue: 6
Page: 4276-4294
Publish at: 2025-12-01

Investigating Japanese EFL learners’ communication apprehension and oral presentation strategies

10.11591/ijere.v14i6.34246
Akiko Kamata , Kamisah Ariffin , Roslina Abdul Aziz , Nadhratunnaim Abas , Badli Esham Ahmad , Hiroki Okada
This study examines communication apprehension (CA) and oral presentation strategies among Japanese English as a foreign language (EFL) learner to understand their impact on verbal communication challenges. Despite educational reforms prioritizing communicative competence, Japanese learners face persistent difficulties, particularly in formal contexts like public speaking. A descriptive quantitative design was employed, and a purposive sampling method was used to select a sample of 140 EFL learners from a private Japanese university. Data was collected using the oral presentation strategies inventory (OPSI) and the personal report of communication apprehension (PRCA). Quantitative analysis via SPSS 29 assessed learners’ apprehension levels and strategy use patterns. Findings revealed moderate CA levels, with interpersonal communication inducing the most anxiety and public speaking causing the least. Learners relied heavily on message reduction and alteration (MRA) strategies, simplifying expressions to manage anxiety, while non-verbal (NV) strategies were minimally utilized. Positive correlations between strategy use and CA highlight the potential of targeted strategies to mitigate apprehension. Practical implications include the need to integrate Japanese cultural values into pedagogy to manage CA through collaborative learning, peer assistance, and structured oral activities, while also balancing accuracy with fluency and utilizing technological tools to support language development.
Volume: 14
Issue: 6
Page: 4231-4243
Publish at: 2025-12-01

Geometrical determination of the focal point of parabolic solar concentrators

10.11591/ijece.v15i6.pp5055-5066
Bekzod Maxmudov , Sherzod A. Korabayev , Nosir Yu. Sharibaev , Abror Abdulkhaev , Xulkarxon Mahmudova , Sh A. Mahsudov
Parabolic solar concentrators play a crucial role in harnessing solar energy by focusing sunlight onto a single focal point, enhancing efficiency in solar thermal applications. However, accurately determining the focal point remains a significant challenge, affecting energy efficiency, stability, and operational costs. This study presents a novel approach to determining the focal point of parabolic solar concentrators using two distinct geometric and mathematical methods. The first method applies standard parabolic equations to derive the focal point, while the second method introduces a geometric approach based on the properties of straight-line tangents and angular measurements. Experimental validation was conducted by comparing the proposed method against laser-based focal point determination. The results demonstrate that the proposed method enhances heat collection efficiency and stability, leading to improved energy output. The findings of this study contribute to optimizing solar concentrator designs, reducing energy losses, and promoting sustainable energy applications.
Volume: 15
Issue: 6
Page: 5055-5066
Publish at: 2025-12-01

Exploring feature selection method for microarray classification

10.11591/ijece.v15i6.pp5584-5593
Muhammad Zaky Hakim Akmal , Devi Fitrianah
Effectively selecting features from high-dimensional microarray data is essential for accurate cancer detection. This study explores the pivotal role of feature selection in improving the accuracy of classifying microarray data for ovarian cancer detection. Utilizing machine learning techniques and microarray technology, the research aims to identify subtle gene expression patterns that indicate ovarian cancer. The research explores the utilization of principal component analysis (PCA) for dimensionality reduction and compares the effectiveness of feature selection techniques such as artificial bee colony (ABC) and sequential forward floating selection (SFFS). The dataset used in this study comprises of 15154 genes, 253 instances, and 2 classes related to ovarian cancer. Through a comprehensive analysis, the study aims to optimize the classification process and improve the early detection of ovarian cancer. Moreover, the study presents the classification accuracy results obtained by PCA, ABC, and SFFS. While PCA achieved an accuracy of 96% and SFFS yielded a classification accuracy of 98%, ABC demonstrated the highest classification accuracy of 100%. These findings underscore the effectiveness of ABC as the preferred choice for feature selection in improving the classification accuracy of ovarian cancer detection using microarray data.
Volume: 15
Issue: 6
Page: 5584-5593
Publish at: 2025-12-01

AI-MG-LEACH: investigation of MG-LEACH in wireless sensor networks energy efficiency applied the advanced algorithm

10.11591/ijece.v15i6.pp5080-5090
Hicham Ouldzira , Alami Essaadoui , Mustapha EL Hanine , Ahmed Mouhsen , Hassane Mes-Adi
Wireless sensor networks (WSNs) play a crucial role in data collection across various fields like environmental monitoring and industrial automation. The energy efficiency of these networks, powered by limited-capacity batteries, is key to their performance. Clustering protocols such as low- energy adaptive clustering hierarchy (LEACH) are widely used to optimize energy consumption. To enhance LEACH’s performance, MG-LEACH was introduced, improving cluster head selection to extend network lifespan. This study compares MG-LEACH with AI-MG-LEACH, which incorporates artificial intelligence (AI) to further improve energy efficiency by selecting cluster heads based on factors like residual energy. Simulations show AI-MG-LEACH reduces energy consumption, extends network life, and enhances data reliability, outperforming MG-LEACH.
Volume: 15
Issue: 6
Page: 5080-5090
Publish at: 2025-12-01

Enhanced spectrum sensing in MIMO-OFDM cognitive radio networks using multi-user detection and square-law combining techniques

10.11591/ijece.v15i6.pp5401-5410
Srikantha Kandhgal Mochigar , Rohitha Ujjini Matad , Premachand Doddamagadi Ramanaik
Spectrum sensing (SS) is essential for cognitive radio (CR) networks to enable secondary users to opportunistically access unused spectrum without interfering with primary users. This article proposes a novel multi-user detection (MUD) and square-law combining (SLC) framework for SS in multiple-input multiple-output (MIMO) and orthogonal frequency division multiplexing (OFDM) CR networks. Traditional SS methods, especially energy detection (ED), often underperform in low signal-to-noise ratio (SNR) conditions, resulting in high false alarm rates due to noise uncertainty and multi-user interference. The multi-user detection-square-law combining (MUD-SLC) framework addresses these limitations by using MUD to separate user signals and SLC to combine energy from multiple antennas, significantly improving probability of detection (PD) while maintaining a low false alarm probability (Pfa). Simulation results show that the proposed approach achieves a PD of 0.81 at Pfa=0.15 and SNR=15 dB, outperforming conventional and advanced SS methods. Moreover, MUD-SLC demonstrates a considerable boost in detection performance, even in the presence of severe interference and noise uncertainty, leading to more reliable spectrum utilization in systems. The framework also maintains a lower Pfa, especially in dynamic wireless environments. This research work contributes to improving the efficiency and reliability of SS in CR networks.
Volume: 15
Issue: 6
Page: 5401-5410
Publish at: 2025-12-01

Predictive insights into student online learning adaptability: elevating e-learning landscape

10.11591/ijict.v14i3.pp892-902
Mohamed El Ghali , Issam Atouf , Kamal El Guemmat , Mohamed Talea
In Morocco’s rapidly transforming educational landscape, this study delves into students’ adaptability to online learning environments by integrating sophisticated artificial intelligence (AI) algorithms and hyperparameter optimization techniques. This research uses the comprehensive “online learning adaptivity” dataset to identify pivotal factors influencing student flexibility and effectiveness in e-learning platforms. We applied various AI models, with a particular emphasis on the CatBoost classifier, which exhibited exceptional predictive performance, achieving an accuracy rate near 98%. This high precision in predicting student adaptiveness offers essential insights into tailoring digital education systems. The results underscore the significant potential of machine learning technologies to enhance educational methodologies by catering to the diverse needs of students. Such capabilities are instrumental for educators and policymakers dedicated to refining e-learning strategies that effectively accommodate individual learning styles, ultimately improving the broader educational outcomes in Moroccan tertiary education. These findings advocate for a more nuanced understanding of the interplay between student behavior and technological solutions, providing a roadmap for developing more responsive and effective educational platforms.
Volume: 14
Issue: 3
Page: 892-902
Publish at: 2025-12-01

Chatbot for virtual medical assistance

10.11591/ijict.v14i3.pp914-922
Aravalli Sainath Chaithanya , Sampangi Lahari Vishista , Adepu MadhuSri
A healthy population is vital for societal prosperity and happiness. Amidst busy lifestyles and the challenges posed by the COVID-19 pandemic, individuals often neglect their health needs. To address this, we introduce a novel approach utilizing a chatbot for virtual medical assistance. Tailored for individuals confined indoors or hesitant to visit hospitals for minor ailments, our chatbot offers personalized medical support by diagnosing ailments based on user-reported symptoms and engaging in interactive conversations. Leveraging a robust dataset containing 132 symptoms, 41 diseases, and corresponding medications, our chatbot employs a systematic approach for symptom refinement, enhancing diagnostic precision. Upon identifying a disease, the chatbot promptly suggests basic medications tailored to the specific ailment. Furthermore, our system integrates user demographics to evaluate medication history and current state, allowing for personalized medication recommendations based on individual needs. Through extensive testing and validation, we demonstrate the effectiveness of our chatbot in accurately predicting ailments and providing timely treatment advice. Our study introduces a novel paradigm for medicine recommendation and disease prediction, with the potential to enhance healthcare accessibility and effectiveness.
Volume: 14
Issue: 3
Page: 914-922
Publish at: 2025-12-01
1 2 3
...
1914 1915
Show 13 of 1915

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