Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Building of Informatics, Technology and Science

Penerapan Algoritma Decision Tree Untuk Penentuan Pola Penerima Beasiswa KIP Kuliah Arfyanti, Ita; Fahmi, Muhammad; Adytia, Pitrasacha
Building of Informatics, Technology and Science (BITS) Vol 4 No 3 (2022): December 2022
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v4i3.2275

Abstract

The Indonesian Smart College Card (KIP Lecture) is a government program that has been implemented from 2020 until now. KIP Lectures are distributed by the Ministry of Education, Culture, Research and Technology through universities in each region. Where each university gets a different quota - based on the level of progress of the college. The provision of quotas for each university based on the accreditation at each university raises its own problems for these universities. The problem faced is that the number of new prospective students who register to take the KIP Lecture program exceeds the quota set for each university. The provision of KIP Lecture assistance to the wrong person will lead to misuse of assistance and also inappropriate targets. The acceptance of the selection process for new prospective students can be seen from the previous process that has been carried out. Data mining is a technique used to solve problems in large data processing. Decision Tree is an algorithm that is included in the classification technique in data mining. The process in the decision tree aims to group or classify data against their respective classes. The results of the Decision Tree algorithm are in the form of decision trees and rules, the results obtained are in the form of rules that can be used for future decision-making processes
Classification of Diabetes Diseases Based on Medical Features Using Optimized Support Vector Machine Arfyanti, Ita; Yusnita, Amelia; Adytia, Pitrasacha
Building of Informatics, Technology and Science (BITS) Vol 7 No 3 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i3.8880

Abstract

Diabetes mellitus is a chronic disease caused by impaired glucose metabolism and has become a global health threat with a steadily increasing prevalence each year. According to WHO and IDF, the number of people living with diabetes is projected to reach 783 million by 2045. This condition demands the development of an accurate and efficient early detection system to support medical decision-making. This study aims to develop an optimized Support Vector Machine (SVM)-based classification model to enhance the accuracy and interpretability of diabetes prediction. The dataset used is the Pima Indians Diabetes Dataset, which consists of eight medical features such as glucose level, blood pressure, and body mass index (BMI). The research stages include data preprocessing, class balancing using the Synthetic Minority Over-sampling Technique (SMOTE), parameter optimization with GridSearchCV, and interpretability analysis through SHapley Additive exPlanations (SHAP). The results show that the optimized SVM model with the Radial Basis Function (RBF) kernel achieved an accuracy of 82%, with a significant improvement in the diabetes class recall value from 0.564 to 0.83 after optimization. The Area Under Curve (AUC) value of 0.871 indicates the model’s effectiveness in distinguishing between positive and negative classes. The SHAP analysis reveals that Glucose, Age, BMI, and Diabetes Pedigree Function are the most influential features in prediction. These findings emphasize that the combination of normalization, balancing, hyperparameter optimization, and interpretability produces a reliable and transparent SVM model. This model has strong potential for implementation in Clinical Decision Support Systems (CDSS) for accurate and explainable early diabetes detection.