Emerging Science Journal (ESJ)
Not a member yet
960 research outputs found
Sort by
Artificial Intelligence for Lean Systems: Systematic Review, Antecedents, Conceptual Mapping, and Future Opportunities
Full text linkLean systems thrive on eliminating waste by minimizing all non-value-adding activities. Therefore, significant technological developments such as artificial intelligence (AI) are expected to be swiftly adopted to elevate their performance. While several recent studies have investigated the integration of generic Industry 4.0 tools into lean systems, there is no comprehensive study of the integration of AI in lean systems. Therefore, this study investigates the evolution of the research integrating AI into lean systems from 1993 to 2024 using a thorough bibliometric analysis of 186 peer-reviewed articles retrieved from the Scopus and Web of Science databases. In addition to identifying the body of research's prevalent intellectual and social structures, thematic clusters and thematic maps are constructed to describe the relevance and development of various research themes. The results reveal no comprehensive and integrative framework with unified terminology and distinct research clusters. Furthermore, the findings indicate a concentration of the research contributions in a small set of developed countries, necessitating the deliberate channeling of funds to enhance this research focus in less developed countries. This work is the first study that explicitly tracks the integration of AI in lean systems and creates a convergent realm of analysis and application by identifying the key research foci and corresponding future trends. Doi: 10.28991/ESJ-2025-09-02-030 Full Text: PD
E-Banking Service Quality and Customer Satisfaction with Moderator Factor
Full text linkThis study explores the dimensions of e-banking service quality influencing customer satisfaction in commercial banks in Vietnam, with a focus on the moderating role of word of mouth (WOM). Using a mixed-methods approach, combining qualitative insights with quantitative analysis through Partial Least Squares Structural Equation Modeling (PLS-SEM), the study identifies five key dimensions: transaction speed, efficiency, reliability, responsiveness, and confidentiality. The findings reveal that these dimensions significantly impact customer satisfaction, with a statistical significance of 1%. Additionally, WOM is found to strengthen the positive relationship between e-banking service quality and customer satisfaction, highlighting its role as a critical moderator. By integrating service quality and customer behavior perspectives, the research provides insights into how WOM amplifies the effects of high-quality e-banking services. Doi: 10.28991/ESJ-2025-09-02-012 Full Text: PD
Students Proactive Decision-Making Scale (SPDMS-18)
No full textThis study uses the analysis, development, implementation, and evaluation research design to innovate the student proactive decision-making scale. Considering the needs analysis, the researcher constructed 18 items validated by five raters and tested on 849 students from various universities in Indonesia. The content validity test used Aiken’s formula, and the inter-rater reliability test used Pearson’s ICC. While the construct validity and reliability test used CB-SEM analysis, and the concurrent validity test used Spearman’s correlation between SPDMS-18 and Melbourne DMQ. The results of content validity proved that 18 items met Aiken’s parameters (0.80-1.00), Pearson’s ICC value = 0.524, and Cronbach alpha value = 0.846. Construct validity testing proves that the SPDMS-18 loading factor values range from 0.709-0.835, Cronbach alpha values range from 0.752-0.835, composite reliability values range from 0.751-0.839, AVE values range from 0.502-0.634, and discriminant validity values range from 0.709-0.797. The GoF test model proves that the Chi-Square/df value = 3.002, RMSEA value = 0.049, SRMR value = 0.027, NFI value = 0.958, TLI value = 0.963, and CFI value = 0.971. The concurrent validity results using Spearman’s correlation confirmed the sig. value = <0.001. Thus, SPDMS-18 has a significant psychometric function with the actual situation. It becomes one of the references lecturers can use to measure, assess, and evaluate students’ proactive decision-making in lectures
Enhancing Trajectory Tracking in Humanoid Robots Using Neural Network-Based Dynamic Gain Control
Full text linkThis paper presents the development and evaluation of a dynamic gain controller utilizing neural networks to enhance trajectory tracking performance in the NAO humanoid robot. The proposed controller employs a differential kinematic model and dynamically adjusts its gains using a backpropagation algorithm, eliminating the need for manual gain tuning and simplifying the robot's setup process. Experimental validation was conducted in a simulated environment using CoppeliaSim, with the NAOqi library facilitating integration. The analysis results demonstrate that the dynamic controller using a neural network provides better trajectory tracking accuracy than the traditional kinematic controller. Adaptability of the dynamic controller, which adjusts gain parameters in real-time, contributes to improved robustness and precision across various trajectory types. These findings demonstrate the potential of dynamic, self-tuning controllers in enhancing the performance, efficiency, and versatility of humanoid robots in complex navigation tasks. Doi: 10.28991/ESJ-2025-09-02-02 Full Text: PD
Machine Learning and Parameter Optimization for Banking Stability Prediction and Determinants Identification in ASEAN
Full text linkThis study leverages machine learning and advanced variable selection techniques to enhance the prediction of the Bank Financial Stability Index (Z-score) in emerging ASEAN markets. Utilizing a comprehensive secondary dataset comprising macroeconomic and bank-specific indicators from 61 commercial banks across Indonesia, Malaysia, the Philippines, Singapore, Thailand, and Vietnam (2010–2023), we systematically evaluate the predictive power of multiple machine learning models. A rigorous cross-validation framework is employed to optimize forecasting accuracy, integrating Linear Regression, Random Forest, K-Neighbors, Decision Tree, Gradient Boosting, AdaBoost, Support Vector Regression, and XGBoost with Lasso, Ridge, and Elastic Net regularization. Empirical results reveal that key drivers of financial stability include equity capital, financial leverage, return on equity, GDP growth, inflation, technological advancements, and systemic shocks like the COVID-19 pandemic. Notably, the Ridge-optimized XGBRegressor model achieves the highest predictive accuracy (~89%), demonstrating the efficacy of hybrid machine learning approaches in financial stability forecasting. These findings offer crucial insights for policymakers and regulators, facilitating data-driven strategies to strengthen banking resilience and mitigate systemic risks in volatile economic environments.
Jel Classifier: C45, C52, C55, G21, G32
Human Resource Quality at Commercial Banks in the Context of Digital Transformation
Full text linkThe Fourth Industrial Revolution has significantly impacted various sectors, including the economy, politics, and education. In particular, it has transformed the way businesses operate. To succeed in the digital transformation era, one of the most critical strategies is to focus on enhancing the quality of human resources in the banking sector, ensuring sustainable development and aligning the growth of the banking industry with broader economic trends in the digital age. This study aims to analyze how commercial banks can improve the quality of their human resources in the face of the digital revolution. The research employs both qualitative and quantitative methods. The findings reveal that, in the context of digital transformation, the quality of human resources in commercial banks is perceived to be lower than that of managerial staff in previous settings, despite meeting stated job requirements. Factors such as "recruitment," "employee placement," "salary and benefits," "performance appraisal," and "training and development" were found to have a positive influence on human resource quality. In contrast, the "workplace environment" factor showed no statistically significant effect. Based on these findings, the research team proposed six strategic recommendations to enhance human resource quality in the banking sector. Doi: 10.28991/ESJ-2025-09-02-015 Full Text: PD
Gradient Descent Decision Tree Algorithm and Nonlinear Programming for Credit Risk Assessment and Credit Strategy
Full text linkThis research aimed to develop a scientific and accurate credit risk assessment model for small and medium-sized enterprises (SMEs) to support banks in credit decision-making. An improved decision tree model is proposed by integrating regularization to control complexity and employing an ensemble learning approach to enhance prediction accuracy. Multiple weak classifiers are iteratively refined using gradient descent optimization to form a robust, strong classifier. The model is trained through supervised learning, with the default probability of SMEs as the objective function, enabling a quantitative assessment of credit risk. The findings show that the proposed gradient descent decision tree algorithm achieves an AUC of 0.99 under 70% and 80% training set ratios, outperforming Adaptive Boosting (AUC = 0.97), Random Forest (AUC = 0.91), and traditional decision trees (AUC = 0.82). To further optimize bank loan strategies, this paper constructs a nonlinear multi-objective programming model that maximizes expected loan returns while considering risk constraints. The proposed approach not only improves credit risk prediction but also assists banks in formulating optimal lending strategies. This study advances credit risk modelling by integrating regularization and ensemble learning, offering a novel and practical solution for SME credit assessment
Ultrasound-Assisted Extraction of Bioactive Compounds from Tanacetum vulgare L.: Antibacterial and Cytotoxic Evaluation
No full textThis study investigates ultrasound-assisted extraction (UAE) of bioactive compounds from Tanacetum vulgare L. collected in Central Kazakhstan’s Akmola region, focusing on optimizing extraction parameters, analyzing chemical composition, and evaluating biological activity. The novelty lies in the first comprehensive analysis of T. vulgare populations under the region’s extreme continental climate, known to affect metabolite accumulation. Using 70% ethanol, UAE at 20 minutes provided the highest extraction efficiency, as evidenced by a substantial recovery of phenolic compounds. High-performance liquid chromatography (HPLC) identified key bioactive components – luteolin (6.9 µg/mL), quercetin (5.0 µg/mL), apigenin (1.45 µg/mL), cynaroside (2.7 µg/mL), rutin (1.28 µg/mL), chlorogenic acid (1.1–1.14 µg/mL), and ferulic acid (2.46–2.69 µg/mL) – with extraction time significantly influencing their yield. The antibacterial assessment revealed strong inhibition against Staphylococcus aureus, with a 30-minute flower extract producing an inhibition zone of 34±1.1 mm, surpassing benzylpenicillin (30±1.1 mm). By contrast, weak or no activity was observed against Escherichia coli, Bacillus subtilis, Pseudomonas aeruginosa, and Candida albicans. In cytotoxicity tests using Artemia salina, all extracts – regardless of concentration or duration – resulted in 100% lethality, suggesting potential toxic effects. These findings underscore the impact of Kazakhstan’s harsh ecological conditions on the phytochemical profile of T. vulgare and point to both the plant’s promising pharmacological applications and the need for caution in its use
Leveraging External Networks and Internal Capabilities: A Pathway to Innovation in an Export Economy
No full textObjectives: This study examines the role of business network ties, financial resource accessibility, and export market-oriented capability in influencing product innovation intensity in Myanmar’s transitional economy. Grounded in social network theory and resource-advantage theory, it explores how firms leverage external networks and internal capabilities to foster innovation despite economic and institutional constraints. Methods/Analysis: Survey data were collected from 161 Myanmar exporters representing various industries. Structural equation modeling (SEM) was employed to test the hypothesized relationships. Findings: The results confirm that business network ties significantly enhance financial resource accessibility, with quantity, proximity, and frequency all playing critical roles. Financial resource accessibility exerts a greater influence on innovation than market-oriented capability, highlighting their instrumental role. Exporters should prioritize strategic network development to enhance financial resource access. Policymakers should facilitate business networking, financial accessibility, and export support programs to promote sustainable innovation-driven growth. Novelty/Improvement: This study fills a critical literature gap by empirically linking business network ties, financial resource acquisition, market-orientation, and innovation in a transitional economy, offering rare insights for exporters striving in resource-constrained environments. Future research should explore network dynamics, resource access, market orientation, and innovation in various transitional economies to improve generalizability
A Socio-Legal Analysis of University Students’ Perspectives on Challenges in Online Education and Protocols: Post-Covid Reflections
No full textThe COVID-19 pandemic had a profound impact on nearly all sectors, including global education systems, necessitating a rapid shift from traditional classroom teaching to online learning, despite many institutions lacking the necessary infrastructure for such a transition. The integration of interactive multimedia and flexible scheduling in e-learning has enhanced student engagement and accessibility significantly compared to traditional education methods. It is crucial to assess the post-COVID impacts on students’ learning and performance following the abrupt shift from in-person to online education. The online questionnaire used here, created using Google Forms, targeted students across Pakistan, covering their opinions, challenges, and recommendations on traditional and online learning, particularly their post-COVID perspectives. Surveys were distributed to various universities, including institutions in Punjab, Sindh, Islamabad, Khyber Pakhtunkhwa, and Balochistan. A snowball sampling method was employed to gather responses, leveraging participants’ networks to expand the sample size, and the collected data were analyzed using the Statistical Package for the Social Sciences for descriptive statistics. The demographic attributes of the involved 150 respondents showed that 59.3% had a rural background, 80% were aged 18–23, and 75% were male, with 51% living within 1–25 km from their universities. Results revealed that students showed a slight preference for online education, with a higher level of comfort expressed in using digital tools and better access to resources, though factors of engagement and peer interaction still need improvement. Universities ought to address matters involving data privacy, academic integrity, accessibility, intellectual property, and contractual duties to ensure legal obedience and equity in online education. Faculty, students, and governing bodies should work jointly to design efficient legal strategies