Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Blend Sains Jurnal Teknik Hanif Journal of Information Systems
Sumita Wardani
Universitas Al-Azhar
Automotive Engineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Library & Information Science Mechanical Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Implementasi Algoritma DCT (Discrete Cosine Transform) dan K-Means Clustering untuk Kuantisasi Warna pada Konversi Citra JPG ke Format GIF Sumita Wardani; Andi Zulherry; Karina Andriani; Ichsan Firmansyah
Blend Sains Jurnal Teknik Vol. 5 No. 1 (2026): Edisi Juli
Publisher : Ilmu Bersama Center

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56211/blendsains.v5i1.1865

Abstract

Meningkatnya kebutuhan akan penyimpanan dan transmisi citra digital yang efisien mendorong penelitian di bidang kompresi citra dan teknik kuantisasi warna. Penelitian ini bertujuan untuk mengimplementasikan algoritma Discrete Cosine Transform (DCT) yang dikombinasikan dengan K-Means Clustering untuk kuantisasi warna dalam proses konversi citra JPG ke format GIF. Algoritma DCT digunakan untuk mereduksi komponen frekuensi tinggi pada citra guna meningkatkan efisiensi data, sementara algoritma K-Means Clustering diterapkan untuk menghasilkan palet warna yang optimal sesuai dengan batasan format GIF, yaitu maksimal 256 warna. Penelitian ini menggunakan pendekatan eksperimen kuantitatif dan mengimplementasikan sistem menggunakan bahasa pemrograman Python pada platform Google Colab. Parameter evaluasi yang digunakan meliputi Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), dan ukuran file. Hasil penelitian menunjukkan bahwa proses DCT berhasil mengurangi ukuran file dari 1347,83 KB menjadi 1198,46 KB, dengan nilai MSE sebesar 42,3175 dan nilai PSNR sebesar 31,8692 dB. Proses kuantisasi K-Means dengan 256 klaster menghasilkan nilai MSE sebesar 47,6381 dan nilai PSNR sebesar 31,3504 dB, dengan ukuran file sebesar 5124,70 KB. Eksperimen lanjutan dengan jumlah klaster yang berbeda menunjukkan bahwa pengurangan jumlah klaster menurunkan ukuran file namun juga menurunkan kualitas citra; GIF dengan 8 klaster menghasilkan ukuran file terkecil, yaitu 684,35 KB, dengan nilai PSNR sebesar 25,9143 dB. Temuan ini mengindikasikan bahwa kombinasi algoritma DCT dan K-Means dapat secara efektif mengkonversi citra JPG ke format GIF, meskipun terdapat pertukaran (trade-off) antara efisiensi ukuran file dan kualitas visual citra.
Predicting Student Dropout Risk Using XGBoost and Explainable AI Sumita Wardani; Sartika Mandasari; Meisarah Riandini
Hanif Journal of Information Systems Vol. 3 No. 2 (2026): February Edition
Publisher : Ilmu Bersama Center

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Student dropout is one of the major challenges faced by higher education institutions, as it negatively affects academic performance, institutional accreditation, and educational quality. Early identification of students at risk of dropping out is essential to support timely intervention and improve student retention rates. This study proposes a student dropout risk prediction model using the Extreme Gradient Boosting (XGBoost) algorithm combined with Explainable Artificial Intelligence (XAI) through SHapley Additive exPlanations (SHAP). The dataset consists of student academic records, including Grade Point Average (GPA), semester performance, attendance, completed credit units, and academic engagement indicators. The research methodology involves data preprocessing, feature selection, dataset partitioning, model training, and performance evaluation using Accuracy, Precision, Recall, F1-Score, and Area Under the Curve (AUC). Furthermore, SHAP is employed to provide transparent interpretations of the model's predictions and identify the most influential factors contributing to dropout risk. Experimental results demonstrate that the XGBoost model achieves high predictive performance with an accuracy of 95.2%, precision of 94.1%, recall of 93.7%, and F1-score of 93.9%. The SHAP analysis reveals that cumulative GPA, attendance rate, completed credit units, and the number of failed courses are the most significant predictors of student dropout. The integration of XGBoost and Explainable AI not only improves prediction accuracy but also enhances the interpretability of the model, enabling academic stakeholders to make informed decisions and implement effective intervention strategies. The proposed framework can serve as a decision-support tool for universities in reducing dropout rates and improving student success.
Co-Authors Andi Zulherry Ichsan Firmansyah Karina Andriani Meisarah Riandini Sartika Mandasari