Informatics and Software Engineering

Improving Survival Prediction For Heart Failure Patients Using Random Forest And Grid Search CV

Sari Susanti — 2026-06-28

Heart failure remains a major cause of mortality worldwide, and predicting patient survival has become a key area where machine learning can support clinical decision-making. This study aims to improve the accuracy of survival prediction for heart failure patients by applying hyperparameter tuning to the Random Forest algorithm. Using a publicly available dataset from the UCI Machine Learning Repository, a structured machine learning pipeline was developed. This includes data preprocessing, outlier treatment using the capping method, stratified data splitting, and model training. The Random Forest model was first trained using default parameters to establish a baseline, and then optimized using Grid Search Cross Validation to identify the best hyperparameter configuration. Results show that the optimized model achieved improved accuracy (80.83%), recall (66.00%), and F1-score (0.7416) compared to the baseline. These improvements demonstrate that systematic tuning of machine learning models can significantly enhance their predictive capability in clinical settings. The model showed greater sensitivity in identifying high-risk patients, which is essential for early intervention strategies. Although limited by the dataset size, this study offers a replicable framework for predictive modeling in healthcare and underscores the potential of machine learning as a tool for mortality risk stratification.

Application of the SAW Method in a Decision Support System for Determining Non-Academic Achievement Students at XYZ High School

Muhaqiqin Muhaqiqin — 2026-06-29

The Simple Additive Weighting (SAW) method was applied in a Decision Support System (DSS) to identify non-academic high-achieving students at SMA XYZ, Central Lampung. The assessment includes four main criteria: competition achievements, organizational involvement, discipline and attendance and ethics and social behavior. This method used weighting, data normalization, and a final score calculation to rank the students objectively. The results showed that SAW effectively reduced subjectivity and produced fair and structured rankings. Among the ten students evaluated, Student 2 achieved the highest score of 9.4. The implementation of SAW in this DSS provided a more accountable basis for decision-making. It can serve as a data-driven evaluation model for non-academic performance in educational institutions.

Design and Construction of a Web-Based Business Incubator Selection and Evaluation System for Yarsi University

Suhaeri — 2026-07-08

The research problem, namely the challenges faced by startups and business incubators in developing entrepreneurial activities within universities, is relevant and supports the motivation for developing the proposed system. The research method, including the use of development research, observation, literature review, and the prototyping approach, is also briefly explained. However, although the abstract covers the main components of the study, the description of the research results is still presented in a general manner. It does not sufficiently explain the specific achievements of the developed system. The author is advised to provide more detailed information on the system's evaluation results, particularly the outcomes from usability or user experience testing. For example, the abstract could specify which UEQ (User Experience Questionnaire) dimensions achieved the highest evaluation scores and explain their implications for the usability, effectiveness, or acceptance of the proposed system. Presenting more specific quantitative results would strengthen the evidence of the system's performance and make the research contribution clearer to readers. Furthermore, several statements in the abstract, such as improvements in innovation and creativity and the development of successful startups, remain broad and appear to be assumptions rather than conclusions directly supported by the research findings. Since the study primarily focuses on the design, development, and evaluation of a web-based business incubator selection and evaluation system, the abstract should emphasize the outcomes achieved through the system's implementation and testing. The conclusion should be more closely connected to the evaluation results to ensure consistency between the research objectives, methodology, findings, and final claims.

Web-Based COT Monitoring Application for Operating Room Service Optimization

Muhammad Iqbal Aditya — 2026-07-11

This study aims to develop a web-based COT Monitoring application that supports real-time operating room status monitoring at Universitas Indonesia Hospital. The problem addressed is the use of manual and spreadsheet-based monitoring, which caused information delays, input errors, and limited operational reporting. The study used a qualitative case study approach through observation, interview, documentation study, and literature review. The application was developed with the Waterfall model, covering requirements analysis, system design, coding, and Black Box Testing. The system provides login, real-time dashboard, user management, operation status management, operating room master data, and sequential status update features. Testing shows that the main functions met the expected outputs. The system currently runs on an internal hospital network and is not integrated with external hospital information systems. The article contributes a practical web-based monitoring design for improving information flow and transparency in operating room operations.

Development of a Web-Based Service System for the Empowerment of Mandalamekar Village

Aan Kardiana — 2026-07-17

Efficient and effective public services are key indicators of successful village governance. Mandalamekar Village, Bandung Regency, faces significant challenges in its manual population administration services. These issues reduce service efficiency, data accuracy, and transparency in village administration management. This community service activity developed an integrated web-based village service system and increased the capacity of village officials through technology training. We used a Research and Development (R&D) approach with a Software Development Life Cycle (SDLC) cycle, including needs analysis, design, development, implementation, field trials, training, mentoring, and system evaluation and improvement. The implementation results showed increased service efficiency (60% reduction in time), data recording accuracy, and community satisfaction (85% of respondents were satisfied). This activity had a positive impact in terms of improving the quality of administrative services, the digital skills of village officials, and public trust in village governance.