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

31,456 Article Results

Efficient deep learning models for Telugu handwritten text recognition

10.11591/ijeecs.v36.i3.pp1564-1572
Buddaraju Revathi , B. N. V. Narasimha Raju , Boddu L. V. Siva Rama Krishna , Ajay Dilip Kumar Marapatla , S. Suryanarayanaraju
Optical character recognition (OCR) technology is indispensable for converting and analyzing text from various sources into a format that is editable and searchable. Telugu handwriting presents notable challenges due to the resemblance of characters, the extensive character set, and the need to segment overlapping characters. To segment the overlapping characters, we assess the width of small characters within a word and segment the overlapping characters accordingly. This method is well suited for the segmentation of overlapping compound characters. To address the recognition of similar characters with less training periods we have used ResNet 18 and SqueezeNet models which have achieved character recognition rates of 95% and 94% respectively.
Volume: 36
Issue: 3
Page: 1564-1572
Publish at: 2024-12-01

Utilizing minimum spanning trees for effective mobile sink routing in wireless sensor networks

10.11591/ijeecs.v36.i3.pp1938-1949
Anas Abu Taleb , Ammar Odeh
With many practical applications, wireless sensor networks (WSNs) represent an important field of study. Real-world applications of WSNs include smart home automation, healthcare, agriculture, industrial automation, and environmental monitoring. WSNs present countless chances for creative solutions across various industries as they develop and become more sophisticated. But because they are unattended, we must devise ways to make them work better without using the sensor nodes’ most important resource—battery power. A unique sink mobility model from a deployed WSN is proposed in this paper, based on constructing a minimal Spanning tree. The proposed approach derives a controlled movement model for the mobile sink based on minimal spanning tree (MST) features. Consequently, fixed nodes will be scheduled and visited to save routing overhead and improve network efficiency. Using the properties of the minimal spanning tree, the moving sink node can visit immobile sensor nodes, which is the most effective approach to gather data and send it to the base station. The effectiveness of WSNs was examined when implementing this mobility model, and we used the NS-2 simulator to run simulations to assess how efficiently the suggested strategy performed. Our findings demonstrate that WSN performance can be significantly enhanced by implementing the proposed method.
Volume: 36
Issue: 3
Page: 1938-1949
Publish at: 2024-12-01

Enhancing pre-service teachers’ TPACK through the integrating of community of practice and lesson study

10.11591/ijere.v13i6.29240
Kanyarat Cojorn , Chaweewan Seesom
This study explores the impact of a combined community of practice (CoP) and lesson study (LS) approach on fostering technology pedagogical content knowledge (TPACK) in student teachers. TPACK encompasses various knowledge areas, including technological knowledge (TK), content knowledge (CK), pedagogical knowledge (PK), pedagogical content knowledge (PCK), technology content knowledge (TCK), and technology pedagogical knowledge (TPK). The study employs combined CoP-LS practices in two distinct CoPs: CoP A characterized by varied experiences, and CoP B comprising members with comparable experiences. Data gathered through questionnaires and group discussions. The findings reveal that the CoP-LS activities effectively enhance TPACK among student teachers, leading to improved confidence in designing learning activities. Both CoP A and CoP B show overall enhancements in TPACK, with CoP A exhibiting superior development across all dimensions. Further analysis demonstrates that CoP A exhibits greater advancements in PK and PCK, transitioning from the adapting level to the advancing level. Moreover, TCK and TPK demonstrate progress from the exploring level to the advancing level within CoP A. In contrast, CoP B showcases advancements in TK from the exploring level to the advancing level, while no notable changes are observed in CK, PK, PCK, TCK, and TPK.
Volume: 13
Issue: 6
Page: 4237-4246
Publish at: 2024-12-01

Influence of the use of ground enhancement materials on the reduction of electrical resistivity in grounding systems: a review

10.11591/ijeecs.v36.i3.pp1365-1378
Martínez Ángeles Hugo , Ríos Moreno José Gabriel , Velázquez Castillo Rodrigo Rafael , Trejo Perea Mario
A grounding system (GS) is an indispensable component in an electrical system network, as it is responsible for conducting electrical discharges to the ground due to faults caused by lightning strikes or transient system failures. Globally, it is estimated that 40 lightning strikes occur per second on the planet, amounting to around 1.2 billion per year, resulting in daily losses of various electrical equipment and human fatalities ranging from 6,000 to 24,000. Additionally, soil resistivity, which impedes the flow of electricity from electrical discharges into the ground, leads to inadequate mitigation of electrical overload effects, resulting in poor GS performance. Consequently, the implementation of ground enhancement materials (GEMs) to reduce impedance to optimal levels becomes necessary. The objective of this review is to broadly examine the current status of GEMs reported in the literature for use in GS, focusing on their composition and their effectiveness in improving soil conductivity and dissipating electrical currents as well as to identify emerging trends and current challenges in the development and application of these materials, in order to provide information to guide future research in the design and implementation of efficient and safe GS.
Volume: 36
Issue: 3
Page: 1365-1378
Publish at: 2024-12-01

Accuracy based-stacked ensemble learning model for the prediction of coronary heart disease

10.11591/ijai.v13.i4.pp4516-4525
Santosini Bhutia , Bichitrananda Patra , Mitrabinda Ray
Coronary heart disease (CHD) is the primary cause of silent and noncommunicable deaths. Early detection is essential for slowing the progression of death and saving lives. Medical researchers use machine learning techniques to predict CHD. This article proposes an accuracy based-stacked ensemble learning (AB-SEL) model to predict CHD while minimizing computational time (CT). The dataset undergoes the logistic regression recursive feature elimination (LR-RFE) method to identify the important features. The three strong classifiers, logistic regression (LR), random forest (RF), and AdaBoost, are chosen to build ensemble machine-learning models, including techniques like bagging, majority voting, and stacking, for the Cleveland dataset accessible from Kaggle. Data scaling was done using the normal scalar method, and hyperparameter optimization was done using random search and grid search. Effectiveness is measured by accuracy, precision, recall, F1 score, and CT is validated through 5-fold cross-validation. The suggested approach achieved a 90.16% accuracy rate, required only 0.2 seconds of CT, and yielded an area under the curve (AUC) of 0.892.
Volume: 13
Issue: 4
Page: 4516-4525
Publish at: 2024-12-01

Android malware detection using the random forest algorithm

10.11591/ijeecs.v36.i3.pp1876-1883
Anas El Attaoui , Norelislam El Hami , Younes Koulou
The rapid growth in Android device usage has resulted in a significant increase in malware targeting this platform, posing serious threats to user security and privacy. This research tackles the challenge of Android malware detection by leveraging advanced machine learning techniques, with a particular emphasis on the random forest (RF) algorithm. Our primary objective is to accurately identify and classify malicious applications to enhance the security of Android devices. In this study, we employed the RF algorithm to analyze a comprehensive dataset of Android applications, where the classification of each application as either malware or benign is known. The method was rigorously tested, yielding impressive results: an average accuracy of 98.47%, a sensitivity of 98.60%, and an F-score of 98.60%. These metrics underscore the effectiveness of our approach. Moreover, we conducted a comparative analysis of the RF algorithm against other malware detection methods. The results demonstrate that the RF algorithm outperforms these alternative methods, offering superior detection capabilities and contributing to more robust Android security measures.
Volume: 36
Issue: 3
Page: 1876-1883
Publish at: 2024-12-01

Stacking-based ensemble learning for identifying artist signatures on paintings

10.11591/ijeecs.v36.i3.pp1683-1693
Shintami Chusnul Hidayati , Agustinus Aldi Irawan Rahardja , Nanik Suciati
Identifying artist signatures on paintings is essential for authenticating artworks and advancing digital humanities. An artist’s signature is a consistent element included in each painting that the artist creates, providing a unique identifier for their work. Traditional methods that rely on expert analysis and manual comparison are time-consuming and are prone to human error. Although convolutional neural networks (CNNs) have shown promise in automating this process, existing single-model approaches struggle with the diversity and complexity of artistic styles, leading to limitations in their performance and generalizability. Therefore, this study proposes an ensemble learning approach that integrates the predictive power of multiple CNN-based models. The proposed framework leverages the strengths of three state-of-the-art CNNs: EfficientNetB4, ResNet-50, and Xception. These models were independently trained, and the predictions were combined using a meta-learning strategy. To address class imbalance, data augmentation techniques and weighted loss functions were employed. The experimental results obtained on a dataset of more than 8,000 paintings from 50 artists demonstrate significant improvements over individual CNN architectures and other ensemble methods, thereby effectively capturing complex features and improving generalizability.
Volume: 36
Issue: 3
Page: 1683-1693
Publish at: 2024-12-01

Proactive cervical cancer risk assessment using data-driven analytics

10.11591/ijai.v13.i4.pp4301-4311
Sreelatha Sreelatha , Vrinda Shivashetty
This study introduces a sophisticated predictive model integrating clinical and lifestyle data addressing the critical public health challenge of cervical cancer, particularly in regions lacking routine screenings. Leveraging data driven analytics, the proposed model undergoes comprehensive preprocessing, including exploratory data analysis, missing value imputation, and feature extraction. Feature selection is carried out using the XGBoost classifier to ensure model efficacy. Data normalization and class balance via oversampling techniques are applied, with model validation conducted through stratified cross-validation. The optimized feature vector is then employed to train a LightGBM model. Utilizing a retrospective dataset of 858 patients from the Hospital Universitario de Caracas, Venezuela, comprising demographic, lifestyle, and medical history data, the LightGBM model achieves an impressive accuracy of 98%, outperforming similar existing approaches. The study outcome demonstrates the effectiveness of the proposed data modelling framework and feature selection, along with the choice of LightGBM as a suitable classifier. The proposed predictive framework can efficiently aid healthcare professionals in prioritizing high-risk patients for further evaluation and intervention.
Volume: 13
Issue: 4
Page: 4301-4311
Publish at: 2024-12-01

Character N-gram model for toxicity prediction

10.11591/ijai.v13.i4.pp4380-4387
Eman Shehab , Hamada Nayel , Mohamed Taha
Molecular toxicity prediction is a crucial step in the drug discovery process. It has a direct relationship with human health and medical destiny. Accurately assessing a molecule’s toxicity can aid in the weeding out of low-quality compounds early in the drug discovery phase, avoiding depletion later in the drug development process. Computational models have been used automatically for molecular toxicity prediction. In this paper, a machine learning-based model has been proposed. TF/IDF representation scheme has been used for N-gram and integrated with simplified molecular-input line-entry system (SMILES). Multiple machine learning classifiers such as logistic regression (LR), support vector machine (SVM), random forest (RF), decision tree (DT), k-nearest neighbors (KNN), AdaBoost, multi-layer perceptron (MLP), and stochastic gradient descent (SGD) classifiers have been implemented. A wide range of N-gram models have been implemented and trigram reported the best results. RF and SVM achieved 85% and 84% accuracy respectively. Comparable to state-of-the-art models, our results are acceptable as we used minimum available resources.
Volume: 13
Issue: 4
Page: 4380-4387
Publish at: 2024-12-01

Guided imitation optimizer: a metaheuristic combining guided search and imitation search

10.11591/ijai.v13.i4.pp4217-4228
Purba Daru Kusuma , Meta Kallista
This paper proposes a novel metaphor-free metaheuristic, namely the guided imitation optimizer (GIO). This metaheuristic combines the guided search and imitation-based search. There are five guided searches and three imitation based searches. Meanwhile, there are three references used in this metaheuristic: global finest, a randomly picked solution among the swarm, and a randomized solution within the search space. GIO is then evaluated by using 23 classic functions that consist of seven high dimension unimodal functions (HDUF), six high dimension multimodal functions (HDMF), and ten fixed dimension multimodal functions (FDMF). Through simulation, GIO is superior to golden search optimizer (GSO), grey wolf optimizer (GWO), puzzle optimization algorithm (POA), and coati optimization algorithm (COA) in handling most of these functions. GIO is the first finest in tackling seventeen functions and second finest in tackling six functions. Tight competition occurs between GIO and COA due to the performance of COA which becomes the second finest in handling most of these functions.
Volume: 13
Issue: 4
Page: 4217-4228
Publish at: 2024-12-01

Factors of susceptibility to online romance scam in Malaysia: unraveling the complex pathways

10.11591/ijphs.v13i4.23669
Evi Kurniasari Purwaningrum , Yi Ming Ho , Diana Imawati , Kususanto Ditto Prihadi , Mansor Abu Talib
In this cross-sectional study, we delve into the multifaceted realm of online scam victimization by investigating a diverse array of individual factors that may predispose adults to fall prey to online scams. The central objective of this research is to ascertain the strongest predictor among the following variables: loneliness and the sense of mattering and to elucidate the moderating effect of social media engagement (SME) on the relationship between these predictors and online romantic scam (ORS) susceptibility (OSS). A sample of 380 adults aged 18 to 65 years (M=33.4) participated in this study to respond to demographic questionnaires and scales of the respective variable. The results suggested that the direct effect of relationship satisfaction on ORS susceptibility is not significant without the serial mediation roles of loneliness and mattering at a high level of SME. Further implications, limitations, and suggestions are discussed.
Volume: 13
Issue: 4
Page: 2053-2060
Publish at: 2024-12-01

Nice couple, funny couple, happy couple: emotional intelligence, humor style, and relationship satisfaction

10.11591/ijphs.v13i4.24030
Niya Treza Sunil , Anasuya Jegathevi Jegathesan , Kususanto Ditto Prihadi
This study explores the interplay of emotional intelligence (EI), beneficial humor styles (BHS), and relationship satisfaction (RS) within romantic relationships. Drawing on the social exchange theory, it examines whether BHS mediate the relationship between EI and RS. Data was collected from individuals aged 18 to 65 in romantic relationships, and analyses were conducted using bootstrapping methods. Results reveal a significant positive direct effect of EI on RS. However, the mediation analysis suggests that BHS do not mediate the relationship between EI and RS, indicating that EI's impact on RS remains independent of humor styles. These findings underscore the distinct and substantial roles of EI and BHS in predicting RS. While both factors contribute to RS, they do so independently. This study enhances our understanding of the multifaceted factors influencing romantic relationship dynamics and highlights the importance of emotional intelligence and humor styles in fostering relationship satisfaction. Limitations include self-report measures and a limited age range, suggesting the need for further research to explore these dynamics across diverse populations.
Volume: 13
Issue: 4
Page: 1769-1774
Publish at: 2024-12-01

A new hybrid LED driver

10.11591/ijpeds.v15.i4.pp2367-2375
Orazbayev Sagi , Dzhunusbekov Erlan
The ongoing challenge in light-emitting diode (LED) lighting is to integrate power and control circuits into a single chip to reduce the number and cost of components, minimize size, and enhance reliability. This integration requires a reduction in power dissipation on the chip, improved efficiency, and smaller magnetic components. Recently, hybrid LED drivers have been proposed to address this integration challenge. Unlike traditional transformerless single-stage LED drivers, which implement boost or buck topologies, hybrid drivers reduce pulsed voltage on power semiconductors. The proposed hybrid LED driver aims to prevent power switches from hard switching, which in turn reduces metal–oxide semiconductor field-effect transistor or MOSFETs' overheating in the integrated circuit body, increases the reliability of the chip, and alleviates electromagnetic interference or EMI issues. The proposed improvement to the hybrid driver is analyzed. The control method was suggested. Computer modelling was provided to confirm the feasibility, controllability and resulting advantages of the proposal. The proposed hybrid LED driver is attractive for circuit integration to reduce size and cost compared to the achievements of previous art.
Volume: 15
Issue: 4
Page: 2367-2375
Publish at: 2024-12-01

Non-contact power system fault diagnosis: a machine learning approach with electromagnetic current sensing

10.11591/ijeecs.v36.i3.pp1356-1364
Amit L. Nehete , Deepak S. Bankar , Ritika Asati , Chetan Khadse
Modern power system protection schemes incorporate artificial intelligence (AI) techniques. However, in a conventional way, most of these schemes rely on the data of current and voltage collected from current transformer (CT) and potential transformer (PT) respectively. CTs suffer from the drawback of core saturation and impact the accuracy and effectiveness of intelligent methods. Also, it has the constraints of size, safety, and economy. The research here explores the effectiveness of magnetic sensors in advanced power system protection schemes as an alternative to traditional current sensing. In the presented work, a novel dataset is prepared by transforming transmission line currents into magnetic field components. Several supervised as well as unsupervised machine learning algorithms have been applied to this data instead of traditional currents and voltage for fault prediction. The paper discusses the comparative evaluation of these algorithms based on various performance metrices which reveals that Gaussian Naïve Bayes (GNB), K-nearest neighbor (KNN), random forest (RF), and extreme gradient boost (XGB) algorithms excel in fault detection, while multilayer perceptron (MLP) and KNN performs better fault classification. The findings promise the potential for developing compact, safe, and cost-effective protection schemes utilizing magnetic field sensors.
Volume: 36
Issue: 3
Page: 1356-1364
Publish at: 2024-12-01

A systematic literature review on the impact of participation in sport and physical activities on psychological resilience

10.11591/ijphs.v13i4.24345
Haslinda Husain , Shamsulariffin Samsudin , Ahmad Fauzi Mohd Ayub , Mohamad Firdaus Ahmad , Nur Syazwani Zulaikha S afwan
Participation in sports and physical activity (PA) is often considered a potential contributor to psychological resilience due to its physical, cognitive, and social benefits. This review aims to synthesize an extensive overview of the existing knowledge landscape, shedding light on the mechanisms through which sport and PA may contribute to psychological resilience among students. Guided by the preferred reporting items for systematic reviews and meta-analyses (PRISMA) statement review method, we comprehensively searched key databases, including EBSCOhost and Scopus. Note that a total of 353 publications were initially determined. The final finding data concludes that 15 met the selection criteria. The findings were synthesized based on three themes: enhancing positive mental health, reducing negative emotions, and mitigating depression and anxiety. These outcomes highlight the transformative potential of sports and PAs in nurturing a robust psychological foundation among student populations. However, it calls for more robust and standardized research approaches. This is with implications suggesting the integration of sports and PA into comprehensive mental health programs, emphasizing their multifaceted benefits beyond psychological resilience. Tailoring interventions, recognizing the social aspects, and emphasizing the personalized approach can contribute to more effective mental health promotion strategies for students.
Volume: 13
Issue: 4
Page: 1727-1737
Publish at: 2024-12-01
1 2 3
...
2097 2098
Show 416 of 2098

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