Jurnal Politeknik Negeri Batam (PoliBatam)
Not a member yet
3001 research outputs found
Sort by
Machine Learning-Based Approach for HIV/AIDS Prediction: Feature Selection and Data Balancing Strategy
Get PDFHIV/AIDS remains a significant global health challenge, requiring accurate predictive models for early detection and improved clinical decision-making. However, developing an effective predictive model faces challenges such as data imbalance and the presence of irrelevant features, which can compromise model accuracy. This study aims to enhance the performance of AIDS infection prediction models by integrating feature selection, data balancing, and machine learning classification techniques. Feature selection is conducted using Pearson Correlation, Mutual Information, and Chi-Square tests to retain only the most relevant features. Random Oversampling, SMOTE, and ADASYN are employed to address data imbalance and improve model robustness. Nine machine learning algorithms, including Decision Tree, Random Forest, XGBoost, LightGBM, Gradient Boosting, Support Vector Machine, AdaBoost, and Logistic Regression, are tested for classification. Performance evaluation using confusion matrix, precision, recall, F1-score, and AUC-ROC shows that tree-based models (Random Forest, Extra Trees, and XGBoost) achieve the best results, particularly in handling minority class predictions. The study concludes that combining feature selection, data balancing, and machine learning techniques significantly improves predictive performance, making it a valuable approach for early detection and clinical decision support in HIV/AIDS diagnosis. Future research may explore hyperparameter tuning and real-world clinical data integration to enhance practical applicability.HIV/AIDS remains a significant global health challenge, requiring accurate predictive models for early detection and improved clinical decision-making. However, developing an effective predictive model faces challenges such as data imbalance and the presence of irrelevant features, which can compromise model accuracy. This study aims to enhance the performance of AIDS infection prediction models by integrating feature selection, data balancing, and machine learning classification techniques. Feature selection is conducted using Pearson Correlation, Mutual Information, and Chi-Square tests to retain only the most relevant features. Random Oversampling, SMOTE, and ADASYN are employed to address data imbalance and improve model robustness. Nine machine learning algorithms, including Decision Tree, Random Forest, XGBoost, LightGBM, Gradient Boosting, Support Vector Machine, AdaBoost, and Logistic Regression, are tested for classification. Performance evaluation using confusion matrix, precision, recall, F1-score, and AUC-ROC shows that tree-based models (Random Forest, Extra Trees, and XGBoost) achieve the best results, particularly in handling minority class predictions. The study concludes that combining feature selection, data balancing, and machine learning techniques significantly improves predictive performance, making it a valuable approach for early detection and clinical decision support in HIV/AIDS diagnosis. Future research may explore hyperparameter tuning and real-world clinical data integration to enhance practical applicability
Implementation of Naive Bayes Algorithm for Early Detection of Stunting Risk
Get PDFThis study aimed to develop an early detection model for stunting risk in children in Kuningan Regency using the Naïve Bayes algorithm. The model used 3,155 data with a division of 50% training data and 50% testing data, utilizing five predictor variables: gender, age, weight, height, and nutritional intake. The results demonstrated an accuracy of 66.8%, precision of 62.4%, and recall of 69.5%, indicating that the model performs adequately but requires further refinement to enhance predictive quality. Improvements can be achieved by incorporating additional variables, such as environmental factors, sanitation, and maternal nutritional status, as well as optimizing data preprocessing techniques. The findings provide a scientific basis for the Kuningan Regency Health Office to design targeted intervention strategies, including regular screening programs, specific nutritional interventions, and community health education. Effective implementation of these strategies requires collaborative efforts among local government, community health centers (puskesmas), integrated health posts (posyandu), and other stakeholders to ensure a holistic and sustainable approach to stunting prevention. This study highlights the potential of data-driven models in supporting evidence-based public health policies and interventions.This study aimed to develop an early detection model for stunting risk in children in Kuningan Regency using the Naïve Bayes algorithm. The model used 3,155 data with a division of 50% training data and 50% testing data, utilizing five predictor variables: gender, age, weight, height, and nutritional intake. The results demonstrated an accuracy of 66.8%, precision of 62.4%, and recall of 69.5%, indicating that the model performs adequately but requires further refinement to enhance predictive quality. Improvements can be achieved by incorporating additional variables, such as environmental factors, sanitation, and maternal nutritional status, as well as optimizing data preprocessing techniques. The findings provide a scientific basis for the Kuningan Regency Health Office to design targeted intervention strategies, including regular screening programs, specific nutritional interventions, and community health education. Effective implementation of these strategies requires collaborative efforts among local government, community health centers (puskesmas), integrated health posts (posyandu), and other stakeholders to ensure a holistic and sustainable approach to stunting prevention. This study highlights the potential of data-driven models in supporting evidence-based public health policies and interventions
Analysis of Criteria for Supplier Selection of Soybean Raw Materials Using the Analytical Hierarchy Process (AHP) Method at Sagala Tofu and Tempeh MSMEs
Get PDFSagala Tofu and Tempeh MSMEs face challenges in selecting soybean suppliers due to inconsistencies in price, quality, and delivery reliability, which impact production and market demand fulfillment. Sagala Tofu and Tempe MSME is one of the MSMEs that requires 100–150 kg of soybeans daily. This research aims to help Sagala Tofu and Tempe MSME identify the correct standards (priority criteria/sub-criteria) for making decisions regarding soybean raw materials and to determine the best soybean supplier. The research method used is the Analytical Hierarchy Process (AHP). The results show that the priority criterion is quality (0.469), followed by price (0.230), quantity accuracy (0.159), delivery (0.102), and customer care (0.038). Based on these supplier selection criteria, supplier X was rated the best, with a score of 0.420, followed by supplier Z (0.340) and supplier Y (0.240)
Brand Credibility and Brand Reputation on Brand Performance
Get PDFWith regard to the Wardah brand, this study intends to examine how brand credibility and reputation affect brand performance. In this work, quantitative research methodologies are applied. Purposive sampling is used in the sampling method. This survey included 201 respondents in total. Respondents are Indonesian-born women between the ages of 17 and 55 who use skincare and makeup items under the Wardah brand. Through the use of Google Forms, the data source distributes questionnaires that collect primary data. In this study, closed questions with response options of strongly disagree, disagree, agree, and strongly agree were employed on a Likert scale. Version 4.1.0.0 of the SmartPLS tool is used in the partial least squares data analysis method. According to the study\u27s findings, there is a relationship between brand performance and credibility. A relationship between brand reputation and brand performance is evident from the second hypothesi
Analysis of Hotel and Restaurant Tax Revenue Before and During The Covid-19 Pandemic
Get PDFThis study aims to analyze the hotel and restaurant tax revenue before and during the Covid-19 pandemic in Karanganyar District. This research employs a descriptive method with a qualitative approach. It utilizes both primary and secondary data sources. Data collection techniques involve interviews and documentation. Data analysis techniques include data condensation, data presentation, and drawing conclusions. The study is conducted at the Karanganyar District Regional Finance Agency to gather information regarding hotel and restaurant tax revenue, and it involves several key informants from hotel and restaurant businesses selected using purposive sampling method. The results of this research indicate that: (1) the number of hotels and restaurants generally increased from the year before to during the pandemic, (2) hotel and restaurant tax revenue experienced a significant growth overall, (3) the procedures for hotel and restaurant tax collection were implemented appropriately and operated smoothly, and (4) the efforts of the local government to enhance hotel and restaurant tax revenue were fairly successful
Information Accounting System on Small and Medium Enterprises: Bibliometric Analysis
Get PDFThis research aims to investigate publication trends on the topic of accounting information systems in SMEs. This is intended to fill the research gap regarding the absence of previous research that discusses the development of publications on this topic. The method used is bibliometric analysis with the Scopus database in the publication range from 2014 to 2023. The search keywords use Bolean, namely "account* information system*" OR "information system*" AND "SMEs" OR "small and medium enterprise*", so that we get 982 publications. The research results found that the most productive publication sources were the Iberian Conference On Information Systems And Technologies Cisti and Advances In Intelligent Systems And Computing, while the publication that had the highest impact was Procedia Computer Science. The most prolific writers were Kamariotou and Kitsios. Both of them are also writers with the highest impact. Bina Nusantara University was identified as the most productive institution, and Indonesia was the most productive country, but the one most cited was France. This information can be an important basis for researchers, practitioners and policy makers in understanding the latest dynamics and developments in this field
Investigating the Effect of Green Accounting Adoption and Sustainability Disclosure in Indonesian Manufacturing Companies
Get PDFCompanies currently produce many impacts, such as air pollution and industrial waste, which also cause global warming. As part of the company\u27s responsibility for international and sustainability problems, the company carries out several things related to green things, ultimately leading to company profits. This research examines the effect of green accounting and sustainability disclosure on company profitability. The sustainability disclosure includes economic, environmental, and social indicators. The population in this study are manufacturing companies listed on the Indonesia Stock Exchange in 2019-2022. Researchers selected the sample using a purposive sampling method with three criteria, resulting in 15 eligible companies. This research uses panel data regression analysis using the Eviews 12 program. This research measures the green accounting variable using PROPER, the sustainability disclosure variable using GRI G4, and the profitability variable using ROA. The analysis results show that the green accounting and sustainability disclosure variables do not affect a company\u27s profitability. Indonesia has required the disclosure of sustainability reports for specific companies, including those used in this research. Even though there are mandatory regulations, there are still several challenges in implementing sustainability reporting in Indonesia. For example, a lack of awareness and varying reporting standards. The obligation to prepare sustainability reports is an essential step for Indonesia in realizing sustainable development. A sustainability report hopes to encourage companies to be more responsible for the environment and society while increasing global competitiveness and making a profit
Sentiment Analysis of Telegram App Reviews on Google Play Store Using the Support Vector Machine (SVM) Algorithm
Get PDFThis study aims to analyze the sentiment of Telegram application reviews on the Google Play Store using the Support Vector Machine (SVM) algorithm. From a total of 14,700,000 initial reviews, a sampling technique was carried out to obtain 400 review data, which then went through the pre-processing stage to produce 345 review data to be classified. The SVM model used showed good performance with an accuracy of 81.16%, precision in the positive class reached 93%, recall in the negative class of 94%, and an average f1-score of around 81%. However, there was a discrepancy between the high rating and the content of the review, which highlighted the existence of high-rated reviews that contained criticism or vice versa. The confusion matrix analysis also showed some misclassification, where reviews should be categorized as positive sentiment but detected as negative, and vice versa. This research is expected to provide valuable feedback for Telegram application developers to improve the quality of service, although the results of this analysis have not been fully discussed in practice. The limitation of this study is that it only tested reviews that used Indonesian, which limited the scope of the findings to the context of local users.This study aims to analyze the sentiment of Telegram application reviews on the Google Play Store using the Support Vector Machine (SVM) algorithm. From a total of 14,700,000 initial reviews, a sampling technique was carried out to obtain 400 review data, which then went through the pre-processing stage to produce 345 review data to be classified. The SVM model used showed good performance with an accuracy of 81.16%, precision in the positive class reached 93%, recall in the negative class of 94%, and an average f1-score of around 81%. However, there was a discrepancy between the high rating and the content of the review, which highlighted the existence of high-rated reviews that contained criticism or vice versa. The confusion matrix analysis also showed some misclassification, where reviews should be categorized as positive sentiment but detected as negative, and vice versa. This research is expected to provide valuable feedback for Telegram application developers to improve the quality of service, although the results of this analysis have not been fully discussed in practice. The limitation of this study is that it only tested reviews that used Indonesian, which limited the scope of the findings to the context of local users
Evaluasi Usability E-Commerce yang Terintegrasi dengan Fan Community Platform Menggunakan Metode Cognitive Walkthrough
No full textThis study aims to evaluate the usability and user experience of Weverse Shop e-commerce app after integration into Weverse app using the Cognitive Walkthrough and Post Study System Usability Questionnaire (PSSUQ) methods. Cognitive Walkthrough is used to identify usability issues from an expert perspective, while PSSUQ is used to quantitatively measure user experience through three subscales: System Usefulness, Information Quality, and Interface Quality. Participants in this study ran 7 task scenarios relevant to the application features. Based on the analysis results, the average scores for the PSSUQ subscales were 2.99 for System Usefulness, 2.98 for Information Quality, and 2.87 for Interface Quality, with an overall score of 2.95. These results indicate that the application interface still needs improvement, especially in the aspects of navigation and information delivery. This research provides recommendations for improvements to usability elements to increase user satisfaction
Analysis of Copy-move Manipulation in Digital Images using Scale Invariant Feature Transform (SIFT) and SVD-matching Methods
Get PDFIn recent years, more and more data has been created in digital form, allowing for easier control over storage and manipulation thanks to technological advancements. Unfortunately, these advancements also bring with them many risks, especially those related to the security of digital files. One of the concerns of many organisations is digital forgery, as it is increasingly easy to create fake images without leaving obvious traces of manipulation. One form of image forgery known as \u27copy-move\u27 is considered one of the most difficult problems in forgery detection. In this case, a portion of an image is copied and pasted at another location in the same image to hide unwanted objects in the scene. In this paper, we propose a method that automatically detects duplication areas within the same image. Duplication detection is performed by identifying local characteristics of the image (key points) using the Scale Invariant Feature Transform (SIFT) method and matching identical features using the Singular Value Decomposition (SVD) method. The results obtained show that our proposed hybrid method is robust to geometric transformations and is able to detect duplication areas with high performance