Article Per Year (5 Year)
p-Index From 2020 - 2025
0.562
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah Rekayasa dan Manajemen Sistem Informasi Bulletin of Computer Science Research Bulletin of Information Technology (BIT)
Siska Kurnia Gusti
Unknown Affiliation
Computer Science & IT Engineering Other

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Bulletin of Computer Science Research

 1 
Penerapan Metode ADASYN Dalam Mengatasi Imbalanced Data Untuk Klasifikasi Penyakit Stroke Menggunakan Support Vector Machine Alwaliyanto; Siska Kurnia Gusti; Iis Afrianty; Fadhilah Syafria
Bulletin of Computer Science Research Vol. 5 No. 4 (2025): June 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i4.612

Abstract

Stroke is one of the leading causes of death and disability worldwide, making it essential to develop classification models that can assist in early and accurate diagnosis. This study aims to implement the Support Vector Machine (SVM) algorithm with three types of kernels linear, polynomial, and Radial Basis Function (RBF) to classify stroke disease data. The Adaptive Synthetic Sampling (ADASYN) method is employed to address the class imbalance problem, while model training and evaluation are carried out using 5-Fold Cross-Validation to ensure stable and reliable results. The findings indicate that ADASYN successfully improves the model’s sensitivity to stroke cases (the minority class), as reflected by an increase in recall and F1-score, despite a slight decrease in overall accuracy a common trade-off in handling imbalanced data. The linear kernel (after ADASYN) achieved the best performance after imbalance handling, with an average AUC-ROC of 0.8333, recall of 0.7827, and F1-score of 0.2181 for the stroke class. Although the F1-score remains relatively low, it improved compared to the pre-ADASYN results, indicating better detection of stroke cases. The implementation was conducted using Google Colab, which also contributed to efficient data processing and visualization. Overall, the results demonstrate that the combination of SVM and ADASYN is effective in enhancing the model’s sensitivity to minority classes and is well-suited for medical data classification tasks, particularly in the early diagnosis of stroke using machine learning approaches.
Perbandingan Teknik Penyeimbang Kelas Pada Multi-Layer Perceptron (MLP) Berbasis Backpropagation Untuk Klasifikasi Diabetes Mellitus Robby Azhar; Siska Kurnia Gusti; Iis Afrianty; Elvia Budianita
Bulletin of Computer Science Research Vol. 5 No. 6 (2025): October 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i6.804

Abstract

Diabetes Mellitus (DM) is a chronic disease that can lead to serious complications if not detected early; therefore, early diagnosis is highly important. One of the methods that can be applied for early diagnosis is the classification technique in data mining. However, the classification process often faces challenges due to class imbalance, which can reduce model performance. This study aims to analyze the effect of class balancing techniques on the performance of the Backpropagation Neural Network (BPNN) in classifying DM cases. BPNN is a form of Multi-Layer Perceptron (MLP) with a simple structure and the ability to solve complex problems with good accuracy. The dataset used in this study is the Pima Indians Diabetes Dataset, consisting of 768 instances, including 500 non-diabetic and 268 diabetic cases. The research was conducted using three scenarios: without balancing, Synthetic Minority Over-sampling Technique (SMOTE), and Random Under Sampling (RUS). The BPNN model was designed with two architectural variations (one hidden layer and two hidden layers), three learning rate values (0.1, 0.01, and 0.001), and a varying number of neurons. The dataset was divided using the 10-Fold Cross Validation technique. The results show that applying SMOTE achieved the best performance, with an average accuracy of 90.89%, precision of 91.22%, recall of 90.89%, and F1-score of 90.89% on the BPNN architecture with one hidden layer. Furthermore, the single hidden layer architecture proved more stable than the two hidden layers, especially when the dataset size decreased due to RUS. Therefore, the combination of SMOTE and BPNN with one hidden layer provides better performance in classifying Diabetes Mellitus cases.
Co-Authors Alwaliyanto Elvia Budianita Fadhilah Syafria Febi Yanto Iis Afrianty Kurniansyah, Juliandi Muhammad Affandes Robby Azhar