Hendrawan, Nofrian Deny, Affandi, Arif Saivul ORCID: https://orcid.org/0000-0002-9478-0065 and Fadhilrifat, Rizqullah Fani (2023) Implementasi support vector machine dalam deteksi diabetes melalui indikator kesehatan. In: 3rd E-proceeding SENRIABDI 2023 Seminar Nasional Hasil Riset dan Pengabdian kepada Masyarakat, Desember 2023, Surakarta.

Preview	Text Implementasi Support Vector Machine.pdf Download (503kB) | Preview
Preview	Text HASIL CEK PLAGIASI Implementasi Support Vector Machine..pdf Download (1MB) | Preview

Abstract

Diabetes, as a global health issue, requires early detection for effective management. This study developed a diabetes detection model using the Support Vector Machine (SVM) algorithm integrated with the Tkinter interface. The model involves data from the 2021 "Behavioral Risk Factor Surveillance System" survey, including indicators such as BMI, high blood pressure, high cholesterol, and age. The SVM model, trained and tested with this data, demonstrates accuracy in predicting diabetes risk. The development process includes data preprocessing, feature selection, and normalization. SVM with a linear kernel was chosen based on data characteristics. The model's performance was evaluated using a data subset, and its accuracy indicates its effectiveness in diabetes detection. After validation, the model was integrated into the Tkinter interface, allowing users to enter health data and receive real-time diabetes risk predictions. Results show the potential of SVM as an early detection tool for diabetes. This research suggests the application of SVM in health data analysis as an effective approach for early diabetes detection, with recommendations for further research using broader datasets and additional variables to enhance model accuracy. The implementation of this technology has the potential to advance in diabetes prevention and management.

Actions (login required)

View Item