Diabetes is one of the diseases that poses a significant global health challenge, with a considerable impact on quality of life and mortality rates. This study examines the use of the Support Vector Machine (SVM) algorithm for diabetes classification through a literature review. SVM was chosen due to its ability to handle imbalanced and complex data. The aim of this study is to assess the effectiveness of SVM compared to other machine learning methods in detecting diabetes. The results of the literature review indicate that SVM achieves higher accuracy than other methods such as Naïve Bayes and Decision Tree, with some studies showing accuracy above 90%. This study is expected to provide deeper insights into the development of machine learning-based diagnostic systems for diabetes.

Puskesmas Kosambi employs Non-PNS staff whose discipline, particularly regarding attendance and work location, needs to be evaluated. The previous manual attendance system was found to be ineffective in monitoring staff discipline. This study aims to develop a mobile-based attendance system equipped with GPS radius and selfie photo features to improve the accuracy and management of attendance. The GPS radius feature ensures that staff can only clock in within the designated area, such as the Puskesmas area, while the selfie photo feature verifies the identity of the staff member clocking in. This study involved 24 Non-PNS staff members and used the K-Means Clustering algorithm to group staff based on their discipline levels. The results showed that the system was effective in improving staff discipline, with 11 employees categorized as highly disciplined, 10 as moderately disciplined, and 3 as lowly disciplined. The implications of this study suggest that the implementation of a mobile-based attendance system can improve attendance monitoring and enhance work discipline at Puskesmas Kosambi.