Publication Search

Chronic kidney disease is an increasingly prevalent health issue that requires more precise clinical data-based early detection methods to enable timely and appropriate treatment. This study focuses on developing a predictive model for chronic kidney disease using the Light Gradient Boosting Machine (LightGBM) algorithm and enhancing its performance through hyperparameter optimization with the Grey Wolf Optimizer (GWO). The dataset used originates from public sources and undergoes several preprocessing steps, including missing value imputation, categorical feature encoding, outlier handling, initial feature selection, and stratified data splitting to maintain model quality. Three modeling approaches were evaluated: LightGBM with default parameters, LightGBM enhanced using Random Search, and LightGBM optimized with GWO. The experimental results indicate that the baseline model already performs well, Random Search improves accuracy and F1-score, and GWO achieves the highest AUC-ROC value despite requiring longer computation time. Significance testing through cross-validation shows that the performance differences among the three models are not statistically significant, suggesting that the observed improvements are not strong enough to determine a definitively superior optimization method. The feature importance analysis highlights that clinical indicators such as creatinine levels, glomerular filtration rate, blood pressure, and urine protein contribute most prominently to the prediction. Overall, the study demonstrates that LightGBM is a reliable model for early detection of chronic kidney disease, and hyperparameter optimization still offers added value that can support the development of AI-based clinical decision-support systems

Accurate wind turbine power curve modeling plays a crucial role in performance evaluation, energy yield estimation, and data-driven control strategies. However, actual power curves often exhibit non-linear behavior influenced by atmospheric variability, measurement noise, and SCADA anomalies, making conventional modeling approaches less effective. This study proposes an optimized logistic power curve model whose parameters are tuned using Particle Swarm Optimization (PSO) to improve predictive accuracy. The analysis uses the Wind Turbine SCADA Dataset from Kaggle, which undergoes extensive preprocessing including physical rule filtering, outlier detection with the Interquartile Range (IQR) method, anomaly removal, and smoothing of the power signal. A three-parameter logistic model is selected due to its ability to capture the typical S-shaped relationship between wind speed and power output. PSO is applied to identify optimal model parameters by minimizing the Mean Squared Error (MSE), utilizing 40 particles over 200 iterations. The optimized model achieves strong predictive performance with RMSE of 404.09, MAE of 179.96, and R² of 0.904 on the test set, indicating that more than 90% of the variability in actual power can be explained by wind speed. Residual analysis reveals heteroscedastic patterns and slight overestimation in mid-range wind speeds, yet overall model consistency remains high. Comparative evaluation against Linear Regression, Random Forest, and logistic modeling using curve_fit shows that the Logistic–PSO approach provides the most accurate and stable predictions. These findings demonstrate that combining logistic modeling with PSO offers an effective and robust method for data-driven wind turbine power curve optimization.

This study aims to analyze the influence of consumer trust and product price, mediated by e-WOM (electronic word-of-mouth), on purchase decisions on the Shopee platform. A quantitative approach was used, with a sample of 75 undergraduate students living in boarding houses in the Special Region of Yogyakarta who shop on Shopee. Data were collected via questionnaires and analyzed using Structural Equation Modeling (SEM) based on Partial Least Square (PLS) with SmartPLS version 4. The results show that consumer trust and product price have a significant positive influence on purchase decisions, both directly and indirectly through e-WOM. This confirms the vital role of user reviews and recommendations in the decision-making process. The study provides strategic implications for e-commerce platforms and guidance for consumers. In addition, this study also provides guidance for consumers in considering factors that influence purchasing decisions on online platforms and educate them to be more careful in assessing available information before making a purchase. Overall, the results of this study underscore the important role of consumer trust, product price, and e-WOM in shaping purchasing decisions on e-commerce platforms.

This study aims to outline how aqeedah and moral values are applied in the learning process of fourth-grade students at MI Ridogalih, examine the strategies teachers use to internalize these values, and identify factors that support or hinder the process. Using a descriptive qualitative method, the research gathered data from the Aqeedah–Akhlaq teacher, instructional documents, and records of the school’s religious activities. Data collection was conducted through guided interviews and document review, and the analysis followed the Miles and Huberman interactive model. The results show that the incorporation of aqeedah and moral education is implemented through consistent religious habituation, exemplary behavior demonstrated by teachers, and the integration of Islamic principles into classroom instruction. Contributing factors include the strong religious environment of the school and active parental engagement, while obstacles stem from the influence of digital media and the varied backgrounds of students’ families. The study concludes that combining habituation practices, teacher role modeling, and value integration plays a significant role in reinforcing students’ Islamic character development.

This study aims to examine customer segmentation through K-Means clustering from a customer data management perspective, emphasizing the interpretive value of analytical results rather than solely their computational outcomes. The research addresses a critical issue in contemporary data-driven organizations, where customer analytics is often reduced to technical modeling without sufficient translation into managerial insights. To respond to this gap, the study adopts a qualitative interpretive approach embedded within a quantitative clustering process, positioning clustering as part of a broader information management cycle. The empirical analysis is based on the Mall Customers Dataset obtained from Kaggle, consisting of 200 customer records with numerical attributes representing age, annual income, and spending score. Quantitative processing using K-Means clustering was employed to identify customer segments, while qualitative interpretation was applied to analyze the managerial meaning of each cluster. Data interpretation was supported by analytical documentation, visualization outputs, and reflective analysis of cluster characteristics. The findings reveal four distinct customer segments with different behavioral and economic profiles, each carrying specific strategic implications for customer relationship management and marketing decision-making. The study demonstrates that the primary value of clustering lies not merely in segment formation, but in its ability to transform raw customer data into actionable managerial knowledge. In conclusion, this research contributes to customer analytics literature by integrating data mining techniques with qualitative interpretation, offering a more human-centered and decision-oriented framework for customer data management. Future research is encouraged to extend this approach using organizational case studies or participatory decision-making contexts.

The implementation of patient safety culture in hospitals remains a significant challenge, often leading to adverse events. Establishing a strong patient safety culture requires effective interprofessional collaboration among healthcare professionals to deliver patient-centered care. However, factors such as organizational distrust and job dissatisfaction continue to hinder collaborative efforts and negatively affect the quality of care and patient safety outcomes.This study aims to examine the influence of organizational trust and job satisfaction on patient safety culture, with interprofessional collaboration serving as an intervening variable at MP hospital.  This quantitative associative research used a causal approach involving 93 inpatient nurses as respondents. Primary data were obtained through questionnaires using an ordinal scale based on a 4–1 Likert scale. Data processing employed the three-box method, and data analysis was conducted using Structural Equation Modeling (SEM).The results revealed that organizational trust, job satisfaction, and interprofessional collaboration simultaneously and partially influence patient safety culture. Moreover, interprofessional collaboration was found to mediate the relationship between organizational trust, job satisfaction, and patient safety culture.The study concludes that enhancing patient safety culture can be achieved by strengthening organizational trust and job satisfaction through effective interprofessional collaboration. Hospitals should develop supportive systems that foster care and concern among staff, enhance conflict management, improve performance appraisal mechanisms, and promote open, effective communication across all professional groups involved in patient care. These strategies can create a safer, more collaborative, and high-quality healthcare environment

Objectives: This study aims to analyze the direct and indirect effects of Servant Leadership on lecturers’ Job Performance through the mediating variables of Job Satisfaction, Employee Engagement, and Organizational Citizenship Behavior (Organizational Citizenship Behavior). The study also seeks to identify which mediating variable has the strongest influence in explaining the relationship between leadership and performance among lecturers in private universities. Methodology: This study applies a causal quantitative approach using a survey method with a sample of 155 lecturers from Information Technology study programs at private universities in West Java. Data were collected through questionnaires and analyzed using Structural Equation Modeling–Partial Least Squares (SEM-PLS) to test ten research hypotheses and evaluate the mediating effects among variables. Findings: The results show that Servant Leadership has a positive influence on Job Satisfaction, Employee Engagement, and Organizational Citizenship Behavior, but does not directly affect Job Performance. Among the mediators, only Organizational Citizenship Behavior significantly mediates the relationship between Servant Leadership and Job Performance, indicating that lecturers’ voluntary behavior plays a key role in improving performance. In contrast, Job Satisfaction and Employee Engagement do not act as significant mediators. Conclusion: The findings highlight that leadership effectiveness in higher education depends on fostering Organizational Citizenship Behavior rather than relying solely on satisfaction or engagement. The study introduces the concept of Emphatic Leadership, which emphasizes empathy, accountability, and humility as essential values for leaders in academic environments. This approach offers practical insights for developing participative and humanistic leadership models to enhance lecturers’ academic performance.

The Family Welfare Empowerment (PKK) is a vital community organization with a significant role in addressing social issues. One such issue is the increasing number of juvenile delinquency cases in schools, which has become a major concern for both educational institutions and parents. Schools must be proactive in monitoring their students to address this problem effectively. However, traditional manual monitoring processes are inefficient and time-consuming. To overcome this, there is a need for an efficient, user-friendly, and multi-user monitoring system that enables both schools and parents to access information about their children's behavioral violations. This student violation monitoring system is designed to be web-based, utilizing UML (Unified Modeling Language) for system design and employing the Waterfall development method. The goal of this system is to provide an effective solution for managing and tracking student violations, allowing for better control and prevention of delinquent behavior within the school environment. By implementing this system, both school authorities and parents will be able to collaborate more effectively in monitoring and addressing student behavior.

This research explores the impact of stock returns, financial literacy, and risk perception on investment decisions among Generation Z investors who use the Ajaib application in Indonesia. The study is driven by the increasing involvement of young digital investors and the growing importance of financial knowledge, risk awareness, and return expectations in shaping their behavior. A total of 250 respondents were surveyed, and the data were processed using Partial Least Squares Structural Equation Modeling (PLS-SEM). The findings reveal that stock returns (β = 0.436, p < 0.001), financial literacy (β = 0.429, p < 0.001), and risk perception (β = 0.209, p = 0.002) each exert a positive and significant influence on investment decisions. The model explains 68% of the variance in investment decisions (R² = 0.626), confirming the robustness of the proposed framework. These results suggest that Gen Z investors with higher financial literacy, stronger risk awareness, and favorable return expectations are more likely to make confident and deliberate investment choices. The study contributes theoretically to behavioral finance literature and provides practical insights for improving financial literacy programs, enhancing investor education, and designing fintech features that foster trust. The findings can also inform policymakers in creating targeted initiatives to encourage responsible investment behavior among younger generations in Indonesia.

The rapid growth of online paylater services has raised concerns about their impact on students’ financial behavior, particularly given the increasing prevalence of consumptive lifestyles and limited financial literacy. This study investigates the influence of Lifestyle (X1) and Financial Literacy (X2) on the use of online paylater systems (Z) and their implications for Spending Behavior (Y) among students of the Faculty of Economics and Business at Dian Nuswantoro University. The study population consisted of 2,100 students from the 2021 and 2022 cohorts, with a sample of 117 respondents determined using the Slovin formula. The sample was selected purposively based on the criteria of being 18–24 years old and active users of paylater services. Primary data were collected through an online questionnaire employing a 5-point Likert scale and analyzed using SmartPLS 3.2 with the Partial Least Squares Structural Equation Modeling (PLS-SEM) technique. The results reveal that Lifestyle has a significant positive effect on both Spending Behavior and Paylater use, while Paylater use itself also positively influences Spending Behavior. In contrast, Financial Literacy shows no significant effect and does not mediate the relationships. The novelty of this study lies in integrating Lifestyle, Financial Literacy, Paylater adoption, and Spending Behavior into a single explanatory model, thereby offering new insights into the financial decision-making patterns of Generation Z students in the context of digital financial services.

The rapid development of financial technology has transformed transactional behavior, particularly among Generation Z. Easy access through mobile banking, particularly BCA Mobile, has made financial activities more practical but also poses risks of consumptive behavior due to low financial literacy and self-control. This study aims to analyze the influence of Financial Literacy, Lifestyle, and Locus of control on Financial Behavior, with Financial technology as a moderating variable. The research population consists of Generation Z users of BCA Mobile in Surabaya. A total of 147 respondents were selected using purposive sampling based on specific criteria. Data were collected through questionnaires and analyzed using the Partial Least Squares–Structural Equation Modeling (PLS-SEM) approach. The findings show that Financial Literacy and Locus of control have a significant positive effect on Financial Behavior, while Lifestyle has a significant negative effect. Furthermore, Financial technology is proven to moderate the influence of Financial Literacy and Locus of control on Financial Behavior, but not the relationship between Lifestyle and Financial Behavior.  

This study aims to examine Ibn Khaldun’s concept of character education and its relevance in shaping the personality of Generation Z in the digital era. The background of this research stems from the growing moral and social challenges faced by young people due to rapid technological advancement and the influence of globalization. This research employs a qualitative method using a library research approach by analyzing Ibn Khaldun’s works and related literature on Islamic character education. The findings reveal that Ibn Khaldun’s perspective on character education emphasizes the balance between ‘ilm (knowledge), adab (morality and ethics), and ‘ashabiyyah (social solidarity) as the foundation for forming a civilized individual. These values are highly relevant to be applied in modern education through teacher role modeling, habituation of positive behavior, and the integration of moral values into the curriculum. The implication of this study highlights that internalizing Ibn Khaldun’s principles of character education can serve as an effective strategy to develop a knowledgeable, ethical, and resilient generation capable of facing contemporary challenges.

The phenomenon of fashion FOMO (fear of missing out) exerts a significant influence on fashion consumption behavior, particularly among the demographic from late adolescence to young adulthood. The fear of missing trends can lead individuals to make impulsive purchases. In contrast, the Minimalist Wardrobe concept promotes a conscious lifestyle that emphasizes functional and sustainable clothing choices. The objective of this study is to examine the influence of Fashion FoMO on purchasing decisions and to assess the role of a Minimalist Wardrobe as a moderating variable. A quantitative approach was employed, utilizing purposive sampling to collect data through surveys administered to respondents residing in Semarang City. The data were analyzed using the Structural Equation Modeling (SEM) method with SmartPLS software. The results show that Fashion FoMO has a significant and positive influence on purchasing decisions for UNIQLO products. Meanwhile, the Minimalist Wardrobe shows an insignificant effect. These findings suggest that purchasing decisions are more strongly driven by emotional pressure from FoMO than by minimalist lifestyle considerations.

Research aims to explore the influence of robo-advisor usage, trust in artificial intelligence (AI), financial literacy, and risk tolerance on investment behavior and its impact on the portfolio performance of retail investors in Indonesia. This study applies a quantitative approach, collecting data from 100 respondents who use investment applications such as Bibit, Ajaib, and Bareksa through the distribution of structured questionnaires with a 5-point Likert scale. Data analysis was carried out using the Structural Equation Modeling (SEM) technique. The results indicate that the four independent variables robo-advisor usage, trust in AI, financial literacy, and risk tolerance significantly affect investment behavior, which in turn has a positive effect on portfolio performance. High trust in AI combined with strong financial literacy fosters more disciplined and rational investment behavior. These findings highlight the importance of effective AI technology integration, improving financial literacy, and managing risk preferences to enhance investment decision-making quality and financial well-being. The study contributes to behavioral finance literature and offers practical implications for fintech developers and policymakers in emerging markets.

The blue economy is widely promoted as a pathway to sustainable development, yet women’s enterprises remain marginalized by structural barriers. This study investigates whether support systems directly influence the sustainability of coastal women’s businesses in Bulukumba South Sulawesi, Indonesia, while applying the Quintuple Bottom Line (QBL) and Theory of Change (Toc) frameworks. A quantitative design using survey data from women-led micro, small, and medium enterprises (MSMEs) was analyzed through structural equation modeling (SEM). The model assessed the reliability of constructs and tested the hypothesized effect of support systems including access to finance, social support, and public policy on sustainability outcomes. Findings reveal that although the measurement model demonstrated reliability and validity, support systems showed no significant direct effect on sustainability. This result contrasts with much of the existing literature but aligns with recent studies emphasizing mediation through financial literacy, managerial capacity, and institutional scaffolding. The study thus adds nuance by demonstrating that external interventions, in isolation, are insufficient for sustaining women’s enterprises in coastal contexts. The research contributes theoretically by extending QBL and Toc to gendered coastal entrepreneurship and practically by highlighting the need for integrated, gender-sensitive policies. Future research should examine mediating and moderating mechanisms that translate support into long term sustainability.

This study aims to analyze the influence of employer branding and digital capability on turnover intention, with employee engagement serving as a mediating variable, in Small and Medium Enterprises (SMEs) in Central Java Province. The research design uses a quantitative approach with an explanatory research method. The research sample consists of 205 SMEs employees selected using purposive sampling techniques with criteria of a minimum of six months of service and active use of digital technology in their work. Data were collected through a Likert-scale questionnaire and analyzed using Structural Equation Modeling based on Partial Least Squares (SEM-PLS). The results indicate that employer branding has a positive effect on employee engagement and a negative effect on turnover intention. Digital capability has a positive effect on employee engagement, but its direct effect on turnover intention is not significant. Employee engagement was found to mediate the relationship between employer branding and turnover intention, as well as between digital capability and turnover intention. These findings reinforce the relevance of Social Exchange Theory and the Resource-Based View in the context of human resource management in the SME sector, while also providing practical implications that strengthening employer branding and enhancing employees' digital competencies can reduce turnover intention.

This study aims to determine self-efficacy as an intervening variable in influencing the relationship between servant leadership and organizational citizenship behavior among employees of the Muaro Jambi District Environment Agency. The analysis method used is quantitative analysis. The population and sample consisted of 56 employees. Data collection was conducted by distributing questionnaires using a Likert scale. The statistical analysis used Structural Equation Modeling (SEM) techniques, with Partial Least Squares (PLS) as the tool for managing it using SmartPLS 4.1.1. The results of this study indicate that servant leadership has a positive and significant effect on organizational citizenship behavior, servant leadership has a positive and significant effect on self-efficacy, self-efficacy has a positive and significant effect on organizational citizenship behavior, and servant leadership has a positive and significant effect on organizational citizenship behavior and is mediated by self-efficacy.

An organization's inability to build employee loyalty amidst competitive business pressures can have a direct impact on productivity, operational efficiency, and the retention of key talent. This study aims to analyze the role of job satisfaction as a key mediator in increasing employee loyalty at PT. Dua Kelinci. This study used a quantitative approach with a survey method by distributing questionnaires to a total of 190 active employees of PT. Dua Kelinci. Data were analyzed using Structural Equation Modeling based on Partial Least Squares (SEM-PLS). The results showed that Motivation, job stress, and job satisfaction were proven to have a significant effect on employee loyalty, while the work environment, workload, and work rewards did not have a significant direct effect. However, the job satisfaction variable was able to significantly mediate the relationship between Motivation, job stress, work environment, and workload on employee loyalty, but did not significantly influence employee loyalty through job satisfaction. These findings confirm that job satisfaction is not only the result of good working conditions, but also a key factor in building and strengthening employee loyalty indirectly. Practically, this study provides an important contribution to companies in designing strategies to increase employee loyalty. Theoretically, this study enriches the literature on mediation mechanisms in employee behavior models, particularly in the context of the manufacturing industry.

Background: Patient safety culture forms the cornerstone of safe and high-quality healthcare delivery. However, its implementation often encounters barriers, particularly the persistence of a blaming culture that discourages staff from reporting patient safety incidents. Clinical leadership and the intensity of incident reporting are believed to play a pivotal role in shaping and sustaining a positive patient safety culture.Objective: This study aims to examine the influence of clinical leadership and patient safety incident reporting intensity on patient safety culture, with blaming culture serving as an intervening variable at Sentra Medika Cikarang Hospital.Methods: A quantitative research approach with an explanatory design was applied. The study involved 147 nurses selected through stratified random sampling. Data were collected using structured questionnaires and analyzed using Structural Equation Modeling (SEM) with the Partial Least Squares (PLS) method to test the direct and indirect relationships among variables. Results: The findings revealed that both clinical leadership and incident reporting intensity significantly influence patient safety culture, both directly and indirectly, through the mediation of blaming culture. Strong clinical leadership and a high level of incident reporting were associated with a more positive patient safety culture, while a high blaming culture weakened this relationship. Conclusion: The study underscores the importance of fostering supportive clinical leadership and cultivating a non-punitive reporting environment to strengthen patient safety culture. Hospital management should focus on leadership development and the creation of open, blame-free communication systems to enhance safety outcomes.

The rapid growth of open-source software (OSS) in machine learning (ML) has intensified the need for reliable, automated methods to assess project quality, particularly as OSS increasingly underpins critical applications in science, industry, and public infrastructure. This study evaluates the effectiveness of a diverse set of machine learning and deep learning (ML/DL) algorithms for classifying GitHub OSS ML projects as engineered or non-engineered using a SMOTE-enhanced and explainable modeling pipeline. The dataset used in this research includes both numerical and categorical attributes representing documentation, testing, architecture, community engagement, popularity, and repository activity. After handling missing values, standardizing numerical features, encoding categorical variables, and addressing the inherent class imbalance using the Synthetic Minority Oversampling Technique (SMOTE), seven different classifiers—K-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF), XGBoost (XGB), Logistic Regression (LR), Support Vector Machine (SVM), and a Deep Neural Network (DNN)—were trained and evaluated. Results show that LR (84%) and DNN (85%) outperform all other models, indicating that both linear and moderately deep non-linear architectures can effectively capture key quality indicators in OSS ML projects. Additional explainability analysis using SHAP reveals consistent feature importance across models, with documentation quality, unit testing practices, architectural clarity, and repository dynamics emerging as the strongest predictors. These findings demonstrate that automated, explainable ML/DL-based quality assessment is both feasible and effective, offering a practical pathway for improving OSS sustainability, guiding contributor decisions, and enhancing trust in ML-based systems that depend on open-source components.