Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Jurnal Sarjana Teknik Informatika Jurnal Pendidikan Sains dan Komputer
Surya Ario Pratama
Universitas Indo Global Mandiri
Agriculture, Biological Sciences & Forestry Humanities Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Computer Science & IT Decision Sciences, Operations Research & Management Education Energy Immunology & microbiology Materials Science & Nanotechnology Mathematics Physics Other

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

Found 2 Documents
Search

 1 
Pengaruh Resize Citra terhadap Pengenalan Sidik Jari dengan Pendekatan Klasifikasi SVM: The Effect of Image Resizing on Fingerprint Recognition with the SVM Classification Approach Surya Ario Pratama; Gasim Gasim; Indah Permatasari
Jurnal Pendidikan Sains dan Komputer Vol. 6 No. 02 (2026): Artikel Riset, Juni 2026
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/jpsk.v6i02.8711

Abstract

Fingerprint recognition systems on resource-limited devices often face the challenges of aggressive image dimension compression (resizing) and natural scan tilt variations. This research does not aim to design a commercial identification system, but rather to specifically analyze the limitations of image resolution reduction (64x64, 96x96, 128x128, and 256x256 pixels) and to evaluate the effectiveness of synthetic rotation augmentation in compensating for Support Vector Machine (SVM) classification performance. The test uses a primary dataset (100 images, 20 classes) partitioned stratified (80:20) to prevent data leakage, where the augmentation process produces a total of 1,600 training images. In comparison, 20 test images are retained as pure unseen data. The stage continues with feature extraction using the Rotation Invariant Local Binary Pattern (LBP-RoR, radius 1). The experimental results show that a 64x64-pixel size is the threshold for structural failure, at which the ridge topology is fatally damaged, leading to a test accuracy of 10%. The model exhibited the highest overfitting phenomenon at 128x128 pixel resolution (training accuracy 79.17%, testing 40%). The best generalization equilibrium point was achieved at 256x256 pixels with a testing accuracy of 50%. This maximum achievement, which was stuck at 50%, demonstrates the vulnerability of the LBP and linear SVM margin methods to pixel-artifact distortion (aliasing) caused by digital rotation. This study concludes that spatial data augmentation cannot fully substitute the need for a physical finger alignment module (fingerprint alignment) in the preprocessing stage.
Klasifikasi Kelayakan Keringanan UKT Menggunakan SMOTE dan Regresi Logistik Surya Ario Pratama; Muhammad Bagas Aries Fadilla; Rendra Gustriansyah
Jurnal Sarjana Teknik Informatika Vol. 13 No. 2 (2025): Juni
Publisher : Program Studi Informatika, Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/jstie.v13i2.31084

Abstract

Keringanan Uang Kuliah Tunggal (UKT) merupakan bantuan finansial bagi mahasiswa dari keluarga berpenghasilan rendah. Namun, proses seleksi penerima sering kali menghadapi tantangan subjektivitas dan ketidakseimbangan data, yang dapat berdampak pada ketepatan keputusan. Penelitian ini bertujuan membangun model klasifikasi untuk memprediksi kelayakan mahasiswa secara objektif menggunakan algoritma Regresi Logistik dan metode penyeimbangan data Synthetic Minority Over-sampling Technique (SMOTE). Penelitian ini menggunakan pendekatan kuantitatif dengan metode supervised learning. Dataset terdiri dari 100 data, yakni 80 data latih dan 20 data uji, dengan distribusi kelas yang tidak seimbang. Evaluasi model dilakukan menggunakan confusion matrix, akurasi, presisi, recall, dan F1-score. Hasil menunjukkan bahwa model tanpa SMOTE memiliki akurasi 91,2%, presisi 95,9%, recall 90,4% dan f1-score berada 93,1%. Setelah penerapan SMOTE, model menunjukkan akurasi meningkat menjadi 92,3% dengan presisi 94,0%, recall tetap stabil di nilai yang sama dengan model latih tanpa smote, dan F1-score mencapai 92,2%. Pada data uji, model mempertahankan kinerja tinggi dengan seluruh metrik evaluasi di atas 90%, menunjukkan kemampuan generalisasi yang baik dan minim overfitting. Penerapan SMOTE terbukti efektif dalam mengatasi ketidakseimbangan kelas dan meningkatkan sensitivitas model terhadap kelas minoritas.
Co-Authors Gasim Indah Permatasari Muhammad Bagas Aries Fadilla Rendra Gustriansyah