Publication Search

This study explores the application of machine learning to predict students' GPA based on behavioral and time-related factors, including study hours, extracurricular activities, sleep, social interactions, and physical activity. Seven regression algorithms were employed to evaluate predictive accuracy using metrics such as MAE, RMSE, and R2 Among these, Regularized Linear Regression demonstrated the highest accuracy and interpretability, highlighting its suitability for this dataset. The findings emphasize the potential of machine learning in identifying key predictors of academic performance and offer practical applications for personalized academic advising and time management. This research provides a data-driven framework to support students and educators in optimizing learning outcomes.

Pakistan is a developing country. Its transportation infrastructure mainly consists of road network. About 95% passengers and fright is transported using the road network. This high demand on road network is because of the unreliable railway system between the cities. Due to such high demand on road network the accident involvement risk of an individual is much high as compared to developed countries. This study uses a new modeling approach to estimate road safety risk for WTP.  A correlated random parameters Tobit model (heterogeneity-in-mean) is integrated with machine learning (Decision tree).  The decision tree categorizes higher-order interactions, while the model captures unobserved correlations and heterogeneity. The framework examines WTP determinants using a representative sample of 3178 road users from Pakistan. The model estimates WTP for different (fatal and severe injury) risk reductions to monetize road traffic crash costs. Results show maximum respondents are willing to support safety improvement policies. The model reveals significant WTP heterogeneity linked to perceptions of road safety and accident risk. Systematic preference heterogeneity emerges through higher-order interactions, offering insights into WTP relationships. Marginal effects highlight varying sensitivities to explanatory variables, quantifying their impact on WTP probability and magnitude. The framework provides two key contributions. It identifies public WTP determinants, emphasizing heterogeneous effects. It also helps in prioritization safety policies by understanding public sensitivity to WTP. The insights further emphasizing on the importance of road safety interventions to the specific socio-economic profiles of road users. This study offers a significant contribution to road safety improvement by providing valuable recommendations for policy makers. By integrating detailed socio-economic factors, it also addresses the urgent need for targeted traffic safety interventions in Pakistan. These findings are expected to aid policymakers and stakeholders in developing effective strategies to enhance road safety and reduce the accident involvement risk effectively.

This study aims to analyze the quality of Grade XI SMA/MA chemistry textbooks, aligning with the standards set by the National Standards Agency for Education (BSNP). This research employs the Research and Development (R&D) method, specifically the ADDIE model (Analysis, Design, Development, Implementation, and Evaluation), with both qualitative and quantitative approaches. The results indicate that the textbooks scored: 3.37 for content validity, 3.87 for language, 3.85 for presentation, and 3.69 for graphics, categorizing them as highly valid.

The integration of Artificial Intelligence (AI) in personalized and adaptive learning environments has revolutionized the education sector by offering customized learning experiences tailored to individual student needs. This study explores the role of AI in enhancing adaptive learning through data-driven insights, intelligent tutoring systems, and real-time feedback mechanisms. By employing machine learning algorithms and natural language processing, AI-driven platforms can analyze student performance, predict learning patterns, and deliver personalized content. The study highlights the effectiveness of AI in addressing diverse learning styles, improving engagement, and optimizing educational outcomes. Furthermore, it discusses the implications of AI in fostering inclusive education and lifelong learning. The findings suggest that AI-powered learning environments significantly enhance student-centered education, promoting efficiency and accessibility.

Road infrastructure is a vital element in supporting economic, social, and transportation activities in a region. Labuhan Batu Utara Regency faces challenges in managing and maintaining road conditions, especially in hard-to-reach areas. This article presents a recent literature review from the past five years on the application of Geographic Information Systems (GIS) for mapping and managing road conditions. The discussion covers technological innovations such as drone usage, machine learning, and crowdsourcing integration within GIS. Additionally, several international and national case studies are referenced to provide insights into the challenges and opportunities of GIS implementation. This article recommends strategies such as open-source GIS implementation, integration with mobile applications, and regular data updates to support efficient road condition management in Labuhan Batu Utara Regency. 

Hydroponic plant cultivation is booming, but stock and sales are hard to predict. Poor prediction can cause farmers to overstock and lose money. This study suggests a framework that uses several machine learning models, including Linear Regression (LR), Random Forest (RF), Decision Tree (DT), and Extreme Gradient Boosting. "Ensemble Learning," which combines these models, should yield more accurate and generalizable results than a single model. This framework is assessed using historical hydroponic plant sales data and related factors like price, weather, and market trends. The model's performance is measured by the difference between predictions and actual values using RMSE and MAE metrics. This framework should improve hydroponic plant stock and sales predictions. Farmers can make better production, inventory, and harvest distribution decisions. Besides reducing financial losses, this reduces food waste and improves food security.

Technological advancements have brought significant transformations across various fields, including the application of machine learning in recommendation and classification systems. Machine learning leverages data processing, utilizes algorithms, and efficiently identifies patterns to produce accurate recommendations and predictions. This study aims to review machine learning-based recommendation system approaches, analyze model performance, and compare the algorithms used. A literature review was conducted by examining journals published in the past five years, focusing on algorithm implementation. The findings indicate that the Naïve Bayes algorithm delivers the best performance, achieving an accuracy of up to 97%. This algorithm is particularly well-suited for processing small to medium-sized datasets with high efficiency. The research provides comprehensive insights into the performance and limitations of various algorithms, serving as a valuable guide for future developments in the field.

Cardiovascular disease is a leading cause of death globally, necessitating effective predictive systems. This research aims to analyze the effectiveness of various machine learning (ML) models—Logistic Regression (LR), Random Forest (RF), Naive Bayes (NB), Support Vector Classifier (SVC), and K-Nearest Neighbors (KNN)—in predicting heart disease using publicly available health data. The study involved pre-processing data, training models, and evaluating them using accuracy, precision, recall, F1-score, and G-Mean metrics. The results show that KNN is the most reliable model, with the highest accuracy of 92%. Significant health features were identified, such as chest pain type and maximum heart rate. The study contributes to improving clinical decision support systems by identifying optimal ML models for heart disease prediction.

This study aims to develop an automated pipeline for data cleaning using Pandas and Scikit-learn. The data cleaning process is often performed manually, requiring a long time and prone to errors. This study uses a quantitative experimental method with a dataset of 100,000 rows of e-commerce transaction data. The results show that the automated pipeline reduces missing values by 95.7% and outliers by 91.7%, and accelerates processing time by 35% compared to manual methods. The distribution of data after cleaning becomes more stable, allowing for more accurate analysis. This study contributes to the development of a more efficient and accurate automated data cleaning approach.Keywords: Systematic Literature Review, Artificial Intelligence and Marketing Strategy.

The growth of e-commerce in Indonesia has led to the emergence of various online shopping platforms, with Shopee being one of the most popular in Semarang City. User reviews on the Shopee application serve as a valuable data source for analyzing customer satisfaction levels; however, the large volume of data requires a systematic and accurate analytical approach. This study aims to analyze user review sentiments of the Shopee application using three machine learning algorithms: Random Forest, Naïve Bayes, and Support Vector Machine (SVM), as well as comparing the accuracy of these three algorithms. This research utilized 1000 reviews collected through web scraping from the Play Store, which were categorized into three classifications: positive, neutral, and negative sentiments. The analysis process encompassed pre-processing stages, feature extraction using TF-IDF, and classification using Random Forest, Naïve Bayes, and Support Vector Machine algorithms. The results demonstrated that the Random Forest algorithm achieved the highest accuracy at 96.19%, followed by Support Vector Machine with 95.71% accuracy, and Naïve Bayes with 84.76% accuracy. This research highlights the effectiveness of Random Forest and SVM in classifying user review sentiments towards the Shopee application.

Research on Artificial Intelligence (AI) in finance has been growing significantly alongside its increasing implementation in the financial sector. This development raises questions about the specific financial areas and AI technology applications that are most frequently explored as research topics within AI in finance. This study aims to address these questions by employing a systematic literature review (SLR) method, analyzing journal articles indexed in Scopus (Q1–Q4) and published between 2020 and 2024. A search conducted using Publish or Perish on the Scopus database identified 496 records, which were subsequently filtered to 94 articles using the PRISMA protocol. The selected articles were examined through bibliometric analysis using VOSviewer, followed by content analysis. The findings reveal that fintech and risk management are the most frequently discussed financial areas in AI in finance research. Moreover, machine learning emerges as the most commonly addressed AI technology application in this domain. Notably, the combination of machine learning and risk management stands out as the most prominent research topic.    

This work explores the potential of PennyLane and variational quantum-classical algorithms (VQCA) to forecast lung cancer using a structured dataset. The VQCA model performs exceptionally well, with flawless training, validation, and test accuracies of 1.0, demonstrating its capacity to identify patterns in the dataset and provide reliable predictions successfully. Contrarily, the accuracy of the quantum neural network (QNN) and classical neural network (NN) models is lower, demonstrating the benefits of utilizing quantum computing methods for enhanced predictive modeling. We provide a complete examination of the data, stressing the better performance of the VQCA model and its promise in correctly predicting lung cancer. The results highlight the importance of quantum-classical algorithms and help us understand the benefits and drawbacks of various strategies for predicting lung cancer. The study highlights the potential applications of quantum computing techniques in advancing the field of healthcare analytics. It shows the capability of the VQCA model to predict lung cancer using a tabular dataset accurately. Further research in this area is needed to explore scalability and practical implementation aspects. In summary, this study showcases the potential of VQCA and PennyLane in predicting lung cancer and underscores the benefits of quantum computing techniques in healthcare analytics.

The purpose of integrating artificial intelligence (AI) technology into campus smart parking management systems is to improve user comfort, safety, and efficiency. To control car traffic in real-time, the system combines technologies including computer vision, machine learning, and the Internet of Things (IoT). Automatic vehicle detection, license plate recognition, parking lot availability prediction, and ideal vehicle flow regulation are some of the key characteristics. The system can effectively recommend parking to users through a mobile app by using pattern analysis and historical data. The implementation results showed a 25% reduction in traffic in the university's parking area and a 30% increase in parking time efficiency. According to the findings of the study, applying AI technology in parking management can be a creative way to overcome the difficulties associated with facility management in higher education environments.

The increasingly dynamic global financial landscape demands effective risk management strategies to ensure financial stability and institutional sustainability. Two critical approaches, risk financing transfers and risk retention, offer complementary solutions. Risk financing transfers allow institutions to redistribute financial risks to third parties through mechanisms such as securitization and Credit Risk Transfers (CRTs), improving market efficiency. In contrast, risk retention emphasizes accountability by require institutions to retain a portion of the risks, fostering market discipline and investor confidence.This study employs a Semantic Literature Review (SLR) to analyze the interaction between these approaches, focusing on mechanisms like securitization, contract design, and macroprudential policies. By reviewing ten peer reviewed articles published between 2015 and 2024, key themes and challenges related to systemic risks, moral hazards, and regulatory gaps are identified. Thematic analysis, supported by tools like NVivo, reveals the potential of these mechanisms to enhance financial stability when implemented within a robust regulatory framework.The results highlights that while risk financing transfers increase flexibility and market efficiency, they May exacerbate moral hazards without sufficient risk retention. Macroprudential policies and accurate risk pricing is crucial in addressing systemic risks, particularly in sectors like shadow banking and climate vulnerable regions. The study also underscore the importance of transparent contract design and the integration of innovative tools, such as geospatial data and machine learning, to support fair and efficient risk distribution.In conclusion, balancing market efficiency and systemic risk mitigation is imperative.While​ risk retention strengths accountability and oversight, effective integration with risk financing transfers is necessary to create a sustainable and resilient financial system.This​ review provides valuable insights for policy makers and practitioners in addressing emerging financial challenges.

This research investigates school scope classification using Deep Neural Networks (DNN), focusing on students living environments and educational opportunities. By addressing the interplay of socioeconomic and educational factors, the study aims to develop an analytical framework for understanding how environmental contexts shape academic trajectories. The research provides a nuanced understanding of the importance of features in educational classification by developing DNN models based on Spearman's Rank Correlation Coefficient (SRCC). The methodology employs machine learning techniques, integrating data wrangling, exploratory analysis, and multiple DNN models with K-fold cross-validation. The study analyzes 677 student records from two schools. The research examined multiple model configurations. Results show that the 'All Data' model achieved 83.08% accuracy, the 'Top 5' model 81.54%, and the 'Non-Top 5' model 79.23%. The SRCC-based approach revealed that while top correlated features are important, additional variables significantly contribute to model performance. The study highlights the profound impact of family background, social environment, and educational contexts on school selection. Furthermore, it demonstrates DNN's capability to uncover intricate, non-linear relationships, offering actionable insights for policymakers to leverage machine learning's potential in developing targeted educational strategies.

Computer vision technology has advanced rapidly and made significant contributions across various fields, including object identification in images. This study aims to develop a computer vision-based system to identify fruit types from images. A machine learning model is applied using a dataset of fruit images to train the system for accurate fruit recognition. The primary processes include data acquisition, image preprocessing, feature extraction, model training, and performance evaluation. The results demonstrate a high level of accuracy in identifying specific fruit types, showcasing the potential of this technology in agricultural and commercial applications.

The integration of IT Governance and expert system design offers transformative benefits for enhancing library user services. This research employs the COBIT 5.0 framework to align IT strategies with library objectives while developing an expert system tailored for personalized recommendations. The findings indicate that the expert system significantly improves operational efficiency, service accuracy, and user satisfaction by using user profiles to recommend relevant materials and streamline the borrowing process. Testing revealed high user satisfaction levels, with 96.6% finding the system effective and 100% confirming its efficiency. Additionally, IT Governance ensures strategic integration between technological infrastructure and service quality objectives, enabling data-driven decision-making. The study also highlights challenges, such as the need for robust data management and user training, suggesting areas for future improvement. Recommendations include incorporating machine learning to enhance system intelligence, conducting regular evaluations to maintain system relevance, and testing the scalability of this approach across various types of libraries. By integrating IT Governance with an expert system, this research sets a strong foundation for modernizing library services to better meet user expectations in the digital era.

The Water Quality Index (WQI) shows the condition of water quality in an area based on the status of water quality resulting from the measurement of physical, chemical and bacteriological parameters of a water body both rivers and lakes. Several machine learning techniques can be used to predict water quality in an area, one of which is through the prophet model approach which is able to provide fairly accurate predictions for the water quality index in Indonesia. The main objective of this research is to obtain a WQI prediction value as a baseline in the formulation of future environmental control activity policies using the prophet model. The result is that the predicted value of IKA for 2021-2023 generated through machine learning with the prophet model approach shows that the Mean Absolute Error (MAE) value: 7.01, Root Mean Square Error (RMSE): 8.61 and Mean Absolute Percentage Error (MAPE): 13.06%, which means that IKA prediction with the prophet model is effective in capturing annual patterns between historical data and future predictions.    

Credit approval prediction is one of the critical challenges in the financial industry, where the accuracy and efficiency of credit decision-making can significantly affect business risk. This study proposes an outlier detection method using the Gaussian Mixture Model (GMM) combined with Extreme Gradient Boosting (XGBoost) to improve prediction accuracy. GMM is used to detect outliers with a probabilistic approach, allowing for finer-grained anomaly identification compared to distance- or density-based methods. Furthermore, the data cleaned through GMM is processed using XGBoost, a decision tree-based boosting algorithm that efficiently handles complex datasets. This study compares the performance of XGBoost with various outlier detection methods, such as LOF, CBLOF, DBSCAN, IF, and K-Means, as well as various other classification algorithms based on machine learning and deep learning. Experimental results show that the combination of GMM and XGBoost provides the best performance with an accuracy of 95.493%, a recall of 91.650%, and an AUC of 95.145%, outperforming other models in the context of credit approval prediction on an imbalanced dataset. The proposed method has been proven to reduce prediction errors and improve the model's reliability in detecting eligible credit applications.

Diabetic wounds have quite serious impacts on sufferers, so a comprehensive wound assessment must be carried out. However, currently there are still many nurses who carry out wound assessments only relying on the nurse's experience in assessing wound characteristics. The use of a digital application (Dicafoler) is a solution to be used as a tool to comprehensively assess diabetes wounds so that it can minimize the impact of the risk of infection and amputation. The aim of this research is to describe the use of the dicafoler application as a tool to assess diabetes wounds among nurses at RSUD Dr. Dradjat Prawiranegara Serang. The research design used in this research is Quantitative Description. Sampling technique with a total sampling of 24 respondents. The results of this research were that the age of the executive nurses was young adults (25-35 years), the dominant sex was that the executive nurses were female, the educational level of the executive nurses was at most D3 nursing, the length of service of the executive nurses was >5 years. Bivariate results show that the use of Dicafoler is effective in assessing wounds more accurately.  The conclusion of this research is that the Dicafoler application can be easily used to assist in the process of assessing diabetic wounds, but it requires further development through further research to add incomplete features so that a comprehensive assessment can be carried out.