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

Markov processes in Bayesian network computation

10.11591/ijece.v15i2.pp2181-2191
Assem Shayakhmetova , Nurbolat Tasbolatuly , Ardak Akhmetova , Assel Abdildayeva , Marat Shurenov , Anar Sultangaziyeva
The article examines the influence of Markov processes on computations in Bayesian networks (BN), an important area of research within probabilistic graphical models. The concept of Bayesian Markov networks (BMN) is introduced, an extension of traditional Bayesian networks with the addition of a Markov constraint, according to which the probability in a node can only depend on the state of neighboring nodes. This constraint makes the model more realistic for many practical tasks, as most graphical models that reflect real-world processes possess the Markov property. The article also discusses that Bayesian networks, in the absence of evidence, actually exhibit the Markov property. However, when evidence (additional information) is introduced into the model, challenges arise that require more complex computational methods. In response, the article proposes algorithms adapted for working with Bayesian Markov networks in the presence of evidence. These algorithms are aimed at optimizing computations and reducing computational complexity. Additionally, a comparative analysis of calculations in Bayesian networks without Markov constraints and with them is conducted, highlighting the advantages and disadvantages of each approach. Special attention is paid to the practical applications of the proposed methods and their effectiveness in various scenarios.
Volume: 15
Issue: 2
Page: 2181-2191
Publish at: 2025-04-01

Anxiety and self-belongingness of inclusive learners: the stance, facet overcoming

10.11591/ijere.v14i2.29993
Panneerselvam G. , Bella Wiselet S.
It was inevitable that young learners at this time would have to pay special attention to both prosaic life and their schoolwork. It is also acknowledged that the majority of learners live in a multi varied situations. This study focuses on and analyses academic anxiety and self-belongingness in learners in an inclusive setup. Academic anxiety is related to distinct characteristic of learner, including gender, venue, instructional media, and family structure. The study focused on these four personal characteristics, and an experimental design technique was used to perform the analysis. This was accomplished using a convenience sampling procedure, which yielded 284 samples. The descriptive analysis is assisted to examine the collected data. However, there is a significant variance regarding their locality of residency. As a result, there is an essential geographical divide between them. The study outcomes also revealed a correlation between learners’ academic concerns and sense of belonging. Significant differences in personnel parameters, such as the residential location of learners, were observed.
Volume: 14
Issue: 2
Page: 1286-1294
Publish at: 2025-04-01

The advances in natural language processing technology and its impact on modern society

10.11591/ijece.v15i2.pp2325-2333
Nadezhda Borisova , Elena Karashtranova , Irena Atanasova
A wide range of information, such as books, news, reports, and other content, is constantly being produced, much of which is available online. Machine translation, spam detection, natural language interfaces, and question-answering applications have become increasingly popular. Natural language processing (NLP) is at the core of the automatic retrieval of information stored on computers. This article discusses NLP and its applications in daily activities. It covers the main stages of NLP and provides examples of its advances in various higher-level tasks. The objective is to highlight the significance of NLP in processing online content and in efficient interactions between humans and computers across various applications. As an essential element of artificial intelligence, NLP provides solutions for real-world problems and has the potential to transform the way companies operate.
Volume: 15
Issue: 2
Page: 2325-2333
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

Enhancing predictive modelling and interpretability in heart failure prediction: a SHAP-based analysis

10.11591/ijict.v14i1.pp11-19
Niaz Ashraf Khan , Md. Ferdous Bin Hafiz , Md. Aktaruzzaman Pramanik
Predictive modelling plays a crucial role in healthcare, particularly in forecasting mortality due to heart failure. This study focuses on enhancing predictive modelling and interpretability in heart failure prediction through advanced boosting algorithms, ensemble methods, and SHapley Additive exPlanations (SHAP) analysis. Leveraging a dataset of patients diagnosed with cardiovascular diseases (CVD), we employed techniques such as synthetic minority over-sampling technique (SMOTE) and bootstrapping to address class imbalance. Our results demonstrated exceptional predictive performance, with the gradient boosting (GBoost) model achieving the highest accuracy of 91.39%. Ensemble techniques further enhanced performance, with the voting classifier (VC), stacking classifier (SC), and Blending achieving accuracies of 91.00%. SHAP analysis uncovered key features such as time, Serum_creatinine, and Ejection_fraction, significantly impacting mortality prediction. These findings highlight the importance of transparent and interpretable machine learning models in healthcare decision-making processes, facilitating informed interventions and personalized treatment strategies for heart failure patients.
Volume: 14
Issue: 1
Page: 11-19
Publish at: 2025-04-01

Accounting education from 1960 to 2023: a bibliometric review

10.11591/ijere.v14i2.30486
Guojing Hu , Haslinah Muhamad , Hasri Mustafa , Mushtaq Yousif Alhasnawi
Since 1960, publications in accounting education have demonstrated a high level of productivity and influence. However, few studies have attempted to use bibliometric methods to map and visualize accounting education research. This study aimed to identify global issues in accounting education through bibliometric analysis, covering the period from 1960 to 2023, by exploring publication trends, top topics, and major contributors in the field. Tools such as Microsoft Excel, VOSviewer, the bibliometric R-package, and WordSift were utilized to comprehensively analyze 717 Scopus-indexed documents. The findings underscore a continuous and recently accelerated historical evolution of accounting education publications, with primary research areas clustering around “business, management, and accounting.” Noteworthy trends include a geographic concentration in the United States, the United Kingdom, and Australia, with RMIT University emerging as a key contributor. Hassell, from the United States, is recognized as the most influential author, and “accounting education” from Taylor & Francis stands out as the most productive journal. Works by Bui and Porter in 2020 emerge as the most frequently cited documents. The research results indicate that future research directions should focus on students, higher education, and the profession, emphasizing themes such as curriculum, learning, and skills.
Volume: 14
Issue: 2
Page: 849-861
Publish at: 2025-04-01

Evaluating tumor heterogeneity in oncology with genomic-imaging and cloud-based genomic algorithms

10.11591/ijece.v15i2.pp2427-2435
Gurumoorthi Gurulakshmanan , Raveendra N. Amarnath , Sivaprasad Lebaka , Munnangi Koti Reddy , Nagarajan Mohankumar , Surulivelu Muthumarilakshmi , Chelliah Srinivasan
The goal of this initiative is to rethink how oncology is traditionally practiced by integrating novel approaches to genomic imaging with cloud-based genomic algorithms. The research intends to give a thorough knowledge of cancer biology by focusing on the decoding of tumor heterogeneity as its primary objective. It is possible to get a more nuanced understanding of the intricacy of tumors via the integration of high-resolution imaging tools and sophisticated genetic analysis. It is a pioneering use of cloud computing, which enables the quick analysis of large genomic information. The major goal is to decipher the complex genetic variants that are present inside tumors in order to direct the creation of individualized treatment strategies. This discovery marks a significant step forward, since it successfully bridges the gap between genetics and imaging. Diagnostic accuracy and treatment effectiveness have both been improved. This innovative technique permits real-time analysis, which in turn enables treatment tactics to be adjusted in a timely manner. It makes a significant contribution to the continuous development of oncological research as well as its translation into better clinical outcomes for cancer patients.
Volume: 15
Issue: 2
Page: 2427-2435
Publish at: 2025-04-01

Experimental research on text CAPTCHA of fine-grained security features

10.11591/ijeecs.v38.i1.pp535-545
Qian Wang , Shafaf Ibrahim , Xing Wan , Zainura Idrus
CAPTCHA is a cybersecurity measure that distinguishes between humans and automated scripts. Researchers have employed various security features to thwart automated program identification by hackers. However, previous research on the attack resistance of CAPTCHAs has used roughly quantitative analysis instead of a fine-grain quantitative study. This study implemented comparative experiments based on CAPTCHA recognition algorithms to find the best-mixed security features. A multi-stage best parameter selection (MBPS) mechanism was proposed in this study. Experiment results indicated that mixed security features of “overlap + scale + rotate + bg (background)” were the best, with an average machine recognition accuracy of only 4.81%. The contrast experiment result illustrated that the anti-attack ability of mixed security features was better than adding adversarial noise, with machine recognition accuracy decreased by 2.2%. Moreover, by investigating the efficacy of security feature parameters, this study provides practical guidelines for designing robust CAPTCHAs. Furthermore, this study also presents valuable insights into the security of image generation technology.
Volume: 38
Issue: 1
Page: 535-545
Publish at: 2025-04-01

Enhancing mathematics learning in phase E: assessing Wordwall effectiveness

10.11591/ijere.v14i2.30051
Sri Rezeki , Sindi Amelia
The use of technology, classroom atmosphere, facilities, and learning resources can support quality learning outcomes in students. Wordwall, as a gamification tool, has been proven to be effective for elementary and junior high school students in mathematics. However, the effectiveness of Wordwall in enhancing senior high school students’ cognitive abilities in mathematics learning has not been investigated. Previous studies have only shown its effectiveness in improving affective abilities. Therefore, this study endeavors to evaluate the effects of using Wordwall on the mathematics learning outcomes of senior high school students in phase E. Through quasi-experimental research with pre- and post-test group design, 38 experimental class students and 37 control class students were selected as samples in this study. The study found a statistically significant difference (sig. 0.000<0.05) in the mean learning outcomes of students who used Wordwall compared to those who did not. Descriptively, the experimental group displayed superior average mathematics learning outcomes compared to the control group, demonstrating a moderate level of effectiveness (ES=0.57). The strong effect of Wordwall can be realized if it is used not only as an exercise tool within the classroom but also as an instrument for knowledge transformation, incorporating consideration of students’ learning styles.
Volume: 14
Issue: 2
Page: 1246-1252
Publish at: 2025-04-01

Novel features extraction: pigment epithelial detachment detection using machine learning algorithms

10.11591/ijece.v15i2.pp1572-1583
Sheeba Thankappan Mercy , Albert Antony Raj Saminathan , Anand Murugadhas , Anshy Princella Anand Sheeba
The majority of the retinal diseases have visual symptoms. Any area of the retina, a delicate layer of tissue on the interior the posterior wall of the human eye, can be impacted by retinal disorders. Optical coherence tomography (OCT) is the utmost commonly used imaging procedure for diagnosing retinal disorders such as age-related macular degeneration (ARMD), diabetic retinopathy, pigment epithelial detachment (PED), macular holes, and more. In this study, we put forth a brand-new technique for accurately extracting features from OCT images to identify PED diseases. For the preprocessing step, we examined the wiener filtering method. After that, we segmented the retinal pigment epithelium (RPE) layer used to the thresholding method, extracted the features from the RPE layer, and then gave the features to machine learning (ML) classifiers like the support vector machine (SVM), logistic regression (LR), k-nearest neighbors (KNN), decision tree (DT), random forest (RF), naive Bayes (NB), and artificial neural network (ANN). The total dataset about 200 images among 100 is normal and 100 is PED, we trained the dataset as an unbalanced and balanced group. The RF is the best outcome in comparison of other classifiers. The overall outcome of random forest is 100% accuracy.
Volume: 15
Issue: 2
Page: 1572-1583
Publish at: 2025-04-01

Data analysis and visualization on titanic and student’s performance datasets-an exploratory study

10.11591/ijict.v14i1.pp68-76
Seong-Cheol Kim , Surender Reddy Salkuti , Alka Manvayalar Suresh , Madhu Sree Sankaran
Exploratory data analysis (EDA) is all about exploring the data in order to identify any underlying pattern before you try to use it to make a predictive model. It also plays a major role in the data discovery process as it is used to analyze data and to recapitulate their different characteristics, which is displayed efficiently with the help of data visualization methods. This paper aims to identify errors in the dataset, to understand the existing hidden structure and to identify new ones, to detect points in a dataset that deviate to a greater extent from the collected data (outliers), and also to find any relationship or intersection between the variables and constants. Two datasets are used namely ‘Titanic’ and ‘student’s performance’ to perform data analysis and ‘data visualization’ to depict ‘exploratory data analysis’ which acts as an important set of tools for recognizing a qualitative understanding. The datasets were explored and hence it assisted with identifying patterns, outliers, corrupt data, and discovering the relationship between the fields in the dataset.
Volume: 14
Issue: 1
Page: 68-76
Publish at: 2025-04-01

Revolutionizing nonrigid demons registration with the whale optimization algorithm

10.11591/ijece.v15i2.pp2372-2380
Abhisek Roy , Pranab Kanti Roy , Anirban Mitra , Swarnali Daw , Dipannita Basu , Sayan Chakraborty
Image registration is one of the popular image transformation models in satellite and medical imaging currently. Image registration refers to image mapping with two or more than images. The ground-breaking fusion of the whale optimization algorithm and nonrigid demons registration (WOA-NDR) is applied in the current work to improve image registration's precision and effectiveness. NDR is an effective method for aligning images that have pliable structures. Nevertheless, it frequently runs into issues with local minima and massive deformations. To address these issues, WOA-which draws inspiration from whale hunting behavior-is integrated into the NDR architecture. The WOA-NDR approach intelligently explores the solution space, enhancing convergence and avoiding premature convergence. With the innovative WOA and NDR integration, the nonrigid image registration process is revolutionized and yields superior outcomes in terms of robustness and accuracy. The efficiency of the suggested strategy is demonstrated by experimental findings on a dataset of monomodal images. The obtained results are also compared with particle swarm optimization (PSO) based framework.
Volume: 15
Issue: 2
Page: 2372-2380
Publish at: 2025-04-01

Comparison design of dynamic voltage restorers, distribution static compensators and unified power quality conditioner series shunts on voltage sag, and voltage swell

10.11591/ijece.v15i2.pp1396-1410
Yulianta Siregar , Syahrun Mubarok , Nur Nabila Mohamed
One issue with the power system is electrical power quality, which is brought on by short circuit disruptions and growing nonlinear loads. Power systems frequently have short circuits, resulting in voltage sags that can harm delicate loads. Voltage sage and swell issues can be resolved using unified power quality conditioner series shunts (UPQC-S), distribution static compensators (DSTATCOM), and dynamic voltage restorers (DVR). Custom power devices are very useful in overcoming problems with electrical networks. In this research, due to 3-phase short circuit faults, voltage sag and swell simulations were conducted using a load equal to 70% of the total load and a fault location point of 75% of the feeder length, from the results of research conducted with the case study PT. PLN (Persero) UP3 Sibolga Feeder SB 02 shows that DVR performs better than DSTATCOM and UPQC-S in handling voltage sag and voltage swell due to 3-phase short circuit disturbances. The DVR succeeded in providing the largest voltage sag recovery in phase C, increasing the voltage from 0.2481 pu to 0.9776 pu. The DVR is also effective in overcoming voltage swell on phase A, reducing it from 1.724 pu to 0.9969 pu.
Volume: 15
Issue: 2
Page: 1396-1410
Publish at: 2025-04-01

Digital media’s role in overcoming anxiety, enhancing linguistic elements and fostering motivation for developing speaking skills

10.11591/ijere.v14i2.31931
Syamsudin Syamsudin , Langgeng Budianto , Kususanto Ditto Prihadi , Djoko Susanto , Abdul Rohman , Ahmad Kholil , Muhammad Anwar Firdousi
The qualitative study investigated the digital media impact on language learning, focusing on overcoming anxiety, enhancing linguistic elements, and fostering motivation for developing speaking skills among four English as foreign language (EFL) learners at an Islamic University in Malang, Indonesia. Through the use of observations and in-depth interviews, the study found that learners utilized various digital media such as storytelling, movies, variety shows, and song videos to aid their speaking learning process. The findings indicated that digital media played a significant role in helping learners overcome language anxiety by providing a platform for practice without direct peer interaction, thereby reducing feelings of fear and shyness. Additionally, digital media usage contributed to linguistic element enhancement, including vocabulary, pronunciation, grammar, and speaking fluency. Moreover, learners’ motivation for developing speaking skills was positively influenced by the enjoyment derived from using digital media which increased their willingness to practice speaking. The study underscores the importance of integrating digital media into EFL speaking instruction due to its potential to address language anxiety, improve linguistic elements, and foster motivation for speaking ability development. By leveraging digital media tools effectively, educators can create engaging and supportive learning milieus that provide to the diverse needs of language learners, eventually enhancing learners’ speaking skills.
Volume: 14
Issue: 2
Page: 1379-1388
Publish at: 2025-04-01

An efficient frequent itemsets finding in distributed datasets with minimum communication overhead

10.11591/ijeecs.v38.i1.pp496-507
Houda Essalmi , Anass El Affar
Finding frequent itemsets is an essential researched technique and a challenging task of data mining. Traditional approaches for distributed frequent itemsets require massive communication overhead among different distributed datasets. In this paper, we adopt a new strategy for optimizing the time of communications/synchronizations from large datasets and, we present a novel algorithm for discovering frequent itemsets in different distributed datasets on the slave sites called finding efficient distributed frequent itemsets (FEDFI). The proposed algorithm is capable of generating the important frequent itemsets by applying an efficient technique for pruning the candidate itemsets. The experimental results confirm that our algorithm FEDFI performs better than Apriori and candidate distribution (CD) algorithms in terms of communication and computation costs.
Volume: 38
Issue: 1
Page: 496-507
Publish at: 2025-04-01
1 2 3
...
2097 2098
Show 314 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