Emerging Science Journal (ESJ)
Not a member yet
960 research outputs found
Sort by
A Comparative Analysis of Machine Learning Models for Predicting EFL Student Language Performance in Smart Learning Environments
Full text linkIntegrating smart learning environments into modern education systems opens up significant opportunities to use data analysis techniques to predict students' English language performance. This study aims to evaluate the performance of various machine learning models for predicting English as a foreign language student performance, emphasizing data preprocessing and feature selection. The dataset was gathered from 181 students in eight middle schools in Thailand. The student's data was exported from the Smart Learning Project, which includes data on 14 PISA-like English quizzes covering 27 competencies. The study compares the predictive performance of machine learning models, including Random Forest, Support Vector Regression, AdaBoost, Bayesian Ridge, K-Nearest Neighbors, ElasticNet, XGBoost, Gradient Boosting, and Stacking Ensemble, using MSE, RMSE, MAE, and R² metrics. The analysis results indicated that ensemble models, particularly XGBoost and Stacking Ensemble, performed the best in predicting students' English language performance. These models can efficiently capture complex relationships in educational data. Therefore, data preprocessing and feature selection play a significant role in improving model performance. This study highlights the potential of advanced machine learning techniques in educational data analysis. The results can contribute to developing personalized learning strategies and early intervention. It supports an efficient and adaptive education system, advancing smart learning and data-driven instruction. Doi: 10.28991/ESJ-2025-09-02-07 Full Text: PD
Application of an Integrated Workmanship Benchmarking Framework to Building Failure in Developing Countries
No full textThe construction industry is grappling with significant challenges related to measuring and assessing workmanship performance, which has led to instances of poor workmanship and even building failures. Traditional evaluation methods often fall short, underscoring the urgent need for a more integrated approach to performance assessment. Recent research focused on developing integrated performance assessment techniques and indicators for a comprehensive evaluation of building projects. Key factors contributing to poor workmanship include a lack of standardisation, inadequate assessment frameworks, and limited empirical knowledge. In response, this study proposes implementing an integrated benchmarking framework to evaluate workmanship performance more effectively, employing various data collection methods, including case studies, questionnaires, and checklist surveys, to assess workmanship performance across construction sites throughout the project lifecycle. The questionnaire targeted critical success factors, while checklist surveys identified key failure factors at various project stages. The findings reveal that this integrated benchmarking framework significantly reduces building defects and failures, enhancing overall workmanship quality within Trinidad and Tobago’s construction sector. Analysed projects demonstrated a notable decrease in defects and improvements in structural workmanship performance across all phases of the project. These results are expected to facilitate effective workmanship management in construction and promote the development of best practices in developing countries. This integrated benchmarking framework provides a comprehensive tool for evaluating workmanship performance across various building types, considering critical success and failure factors, project structures, and the organisations involved while offering continuous assessments throughout the lifecycle of building projects
Bayesian Estimation for Zero-Truncated Bivariate Poisson Regression Model
No full textBivariate count data occurs when two associated variable counts necessitate joint estimate primarily for efficiency purposes. This paper presents Bayesian estimate for the zero-truncated bivariate Poisson regression model. This bivariate model was established using marginal-conditional models. Bayes estimators were executed utilizing the random walk Metropolis-Hastings algorithm with two distinct prior distributions: Laplace and normal distributions. Moreover, estimators employing the bootstrap approach were proposed. Additionally, the credible intervals and the percentile bootstrap confidence intervals were analyzed. The performance of the Bayes estimators was compared with that of the bootstrap estimators and the maximum likelihood estimators via a Monte Carlo simulation analysis, focusing on mean square error. The performance of intervals was evaluated based on coverage probability and average length. Furthermore, the explanatory variables were produced under conditions of both multicollinearity and a lack of multicollinearity. Two empirical datasets were examined to demonstrate the practical use of the suggested model and methodology. The findings from both the simulation and application indicate that the Bayesian method with a normal prior distribution surpasses alternative methods
Early Prediction Detection of Retail and Corporate Credit Risks Using Machine Learning Algorithms
Full text linkNowadays, banks operate in a highly dynamic environment where substantial vulnerability to credit risk exposures threatens their performance by affecting the quality of bank portfolios and increasing their vulnerability to insolvency. In this context, the paper reviews the existing literature and finds no studies investigating the determinants of retail and corporate credit risk using machine learning techniques to enhance the predictive performance of bank credit risk exposures. Consequently, the paper aims to utilize machine learning algorithms, regression analysis, and classification models to identify the most effective predictive model that can improve banks' credit risk prediction capabilities. It will cover the period from 2011 to 2023 and analyze a sample of 26 banks operating in Egypt. Additionally, it classifies credit risk into retail and corporate categories to develop more robust predictive models tailored for the retail and corporate sectors of bank credit risk management, thereby underscoring the paper's novelty. The findings showed that the Random Forest and Kernel SVM can be used to improve the prediction of corporate and retail credit risk by utilizing bank-specific factors like profitability, liquidity, income diversification, capital, asset size, and operating efficiency, as well as macroeconomic factors like external debt, inflation, exchange rate, GDP, interest rate, and foreign direct investment. Doi: 10.28991/ESJ-2025-09-02-025 Full Text: PD
Enhancing Energy and Operational Efficiency of Geotechnological Complexes Using Geoinformation Technologies
No full textThe development of digitalization and information technology opens up new opportunities to improve the efficiency of solid mineral deposit development. In the mining industry, the greatest potential lies in open-pit mining, which uses high-tech mining and transport equipment, which is currently undergoing a transition from diesel engines to gas-diesel, gas and electric ones. The purpose of this article is to design and develop the scientific and methodological potential of analysis, evaluation and optimization of the functioning of geotechnological complexes at open-pit mines. Realization of the set goal is carried out on the basis of the process approach in management of geotechnological complexes with the use of methodology of the in-depth analysis of factors and interrelations of all subsystems and elements. Scientific and practical novelty of the research lies in the development of simulation models with the main mining transport equipment using electric and diesel engines, but also gas-diesel and gas engines, as well as the development of methodological aspects of complex technical and technological audits of mining enterprises. The developed direction ensures the realization of the existing potential for improving the efficiency of geotechnological complexes, including economic and environmental aspects
IMpc-PyrYOLO: Hybrid YOLO Based Feature Pyramidal Network for Pest Detection in Rice Leaves
No full textPests pose a significant threat to global food security, making early detection crucial for maintaining crop health. Traditional pest detection models suffered from inefficiencies such as long processing time and low accuracy, which hinder effective disease management. In order to overcome these existing issues, a novel improved efficient channel attention mechanism assisted feature pyramidal network-based YOLO model (IMpc-PyrYOLO) for rice leaf pest detection. The model integrates an efficient channel attention (ECA) mechanism with the feature pyramidal network (FPN) in the YOLO network to improve multi-scale feature extraction and pest classification accuracy. Additionally, an upgraded weighted Gaussian wiener filter (Up-weGaf) is employed for noise reduction, improving image clarity. The model is evaluated on two benchmark datasets such as IP_RicePests and IP102. Experimental results demonstrate that IP_RicePests attains a precision of 95.8%, recall of 96% and F1-score of 95.9%, whereas IP102 attains a higher precision of 97.8%, recall of 96%, mean Average Precision (mAP) of 95.9% and Intersection over Union (IoU) of 97% with processing time of 2.5 seconds. The proposed model significantly outperforms existing methods in accuracy and computational efficiency, which provides a robust and scalable solution for real-time pest detection in agriculture
The Cultural and Financial Dynamics of Female Entrepreneurs as Well as Their Empowering Ventures
Full text linkThis research examines how female entrepreneurs in Bangladesh navigate the cultural, social, and financial challenges of F-commerce, where informal digital platforms like Facebook and Instagram have become vital spaces for women-led businesses. In addition, despite the growth of digital entrepreneurship, existing models such as the gendered growth framework and ‘TOCOM contingency model’ often overlook how localized cultural dynamics shape women’s entrepreneurial experiences. To bridge this gap, this research explores how these dynamics influence not only the constraints female entrepreneurs face, but also the motivations and resilience strategies that drive their success. However, grounded in ‘Consumer Culture Theory’ and enriched by anthropological perspectives, this research uses a qualitative approach, featuring instrumental case studies and in-depth interviews. The analysis, conducted through NVivo coding, captures both the lived realities and the strategic digital engagements of these women. Although the outcome is a proposed conceptual framework that links culture, motivation, and F-commerce participation offering insight into how female entrepreneurs adapt, persist, and redefine their roles in the digital economy. Therefore, this research also outlines practical recommendations to enhance digital inclusion and gender equity through skills training, mentorship, as well as policy support
Enhancing Teaching and Supervisory Staff’s Creative Problem-Solving Skills
No full textThis research analyzed creative problem-solving (CPS) components and examined the perceptions of Thai educational personnel regarding their CPS abilities. The sample consisted of 534 primary school teachers and educational supervisors during the 2024 academic year, selected through multistage random sampling. Data were collected using a questionnaire assessing CPS skills, which were then analyzed using means (M), standard deviations (SD), and second-order confirmatory factor analysis (CFA). The research revealed that the second-order CFA model for CPS among educational personnel (teachers and supervisors) consists of five key components. Ranked from highest to lowest, these were educators' perceptions of their CPS abilities to solve problems (SOL) (M = 4.23, SD = 0.54), ability to identify problems (IDE) (M = 4.17, SD = 0.57), ability to create knowledge (CRE) (M = 4.17, SD = 0.59), ability to discover concepts (INS) (M = 4.12, SD = 0.58), and ability to discover methods to solve problems (MET) (M = 4.11, SD = 0.58). The model strongly aligned with empirical data, indicating that all three models exhibited positive component weights (β) that were statistically significant at the .01 level. This finding underscores the strength of the CPS framework for educational personnel. These findings provide compelling evidence for the effectiveness of the proposed model in assessing and enhancing CPS skills among educational professionals, contributing valuable insights to both practice and future research in this field. This study fills a gap in the literature by providing empirical evidence on the CPS capabilities of educational personnel
Obstacles to Finding the Ideal Workplace: A Gender-Based Analysis Across the V4 Countries
No full textThis study explores gender-specific barriers to finding an ideal workplace in the Visegrád countries (Czech Republic, Hungary, Poland, and Slovakia), where similar historical and socioeconomic contexts shape labor market inequalities. Based on the relevant literature, women are disproportionately affected by challenges related to language proficiency, professional networks, and mobility. The research applied a quantitative methodology, including chi-square tests, multiple logistic regression, and cluster analysis, using SPSS Statistics software to analyze the survey data. Findings revealed significant gender disparities. Women report greater difficulties with language and mobility, particularly in Hungary and Slovakia, whereas men benefit more from strong professional connections. The cluster analysis identified three respondent groups: those hindered by language barriers, those with weak networks, and those facing limited mobility. International experience mitigates language challenges, and robust networks ease job search difficulties. In line with the ideals of a circular society, this study also explores how circularity, inclusiveness, and collaboration can help break down gender-based barriers in the labor market. The study’s novelty lies in its comparative regional focus and the integration of statistical methods to segment job-seeker profiles. These insights highlight the need for targeted policies that enhance language skills and foster professional networking opportunities, especially for women. By addressing these barriers, policymakers can better support gender equality in labor market access across Central Europe
Ball Detection System for a Soccer on Wheeled Robot Using the MobileNetV2 SSD Method
No full textThis paper discusses the research on the use of Artificial Intelligence in autonomous robot object identification. The specific focus of this research is on a wheeled soccer playing robot. The goal is to recognize a ball as an object using the Single Shot MultiBox Detector MobileNetV2 model. This system has multi-vision inputs such as distance measurements and angle values for object detection. This methodology is based on deep learning with the TensorFlow Object Detection API with the MobileNetV2 SSD model. This model is trained with a dataset of 3707 ball images over 617 thousand steps on Google Collaboratory. It was found that the average measurement error of the ball object is 6.58% for the distance when viewed through the robot's front camera. In addition, the omnidirectional camera is able to detect the ball object and angle values from the front of the robot. What makes this research different is the use of distance and angle measurements for detection and the omnidirectional camera for system performance in dynamic environments. This research aims to address the improvement of AI-based object detection systems for autonomous robotics in the context of real-world use cases