Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal JISKa (Jurnal Informatika Sunan Kalijaga) Jurnal Sistem Informasi Triguna Dharma (JURSI TGD) Marsipature Hutanabe: Jurnal Pengabdian Kepada Masyarakat
Yasir Hasan
STMIK Mulia Darma
Humanities Computer Science & IT Economics, Econometrics & Finance Electrical & Electronics Engineering Languange, Linguistic, Communication & Media Library & Information Science

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Sistem Prediksi Dini Keberhasilan Akademik Mahasiswa Berbasis Random Forest dengan Algoritma CART Yasir Hasan
Jurnal Sistem Informasi Triguna Dharma (JURSI TGD) Vol. 5 No. 4 (2026): EDISI JULI 2026
Publisher : STMIK Triguna Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53513/jursi.v5i4.13247

Abstract

Tingginya angka mahasiswa yang tidak lulus atau tidak menyelesaikan studi tepat waktu menjadi permasalahan utama di perguruan tinggi. Penelitian ini bertujuan mengimplementasikan algoritma CART sebagai base estimator dalam Random Forest untuk memprediksi status keberhasilan akademik mahasiswa berdasarkan data historis akademik. Model dibangun menggunakan 8 variabel akademik yaitu IPS1-IPS4, tingkat kehadiran, SKS diambil, SKS lulus, dan jumlah mata kuliah mengulang, dengan tiga kelas status keberhasilan Tidak Lulus, Lulus Tidak Tepat Waktu, dan Lulus Tepat Waktu. Hasil pengujian pada 10 data uji menunjukkan bahwa Random Forest dengan 100 pohon menghasilkan akurasi 90%, dengan satu perbedaan prediksi pada data yang berada di batas ambang jika dibandingkan dengan satu pohon CART pertama. Berdasarkan validasi silang 5-fold, Random Forest menunjukkan rata-rata akurasi 89% yang lebih stabil dan konsisten. Analisis feature importance mengungkap bahwa Jumlah MK Mengulang merupakan faktor paling dominan (0.28), diikuti oleh SKS Lulus (0.21) dan SKS Diambil (0.16). Sistem prediksi dini yang dikembangkan dengan antarmuka PySimpleGUI dapat digunakan oleh dosen pembimbing akademik dan pengelola program studi sebagai alat bantu pengambilan keputusan dan intervensi akademik secara proaktif.
Uji Efektifitas Kompresi Golomb-Rice dan Huffman untuk Metadata EXIF dalam File JPEG Yasir Hasan
JISKA (Jurnal Informatika Sunan Kalijaga) Vol. 11 No. 1 (2026): January 2026
Publisher : UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/jiska.5060

Abstract

Compression algorithms are now called modern compression algorithms. This improvement is characterized by the combination of various classical techniques and is even based on machine learning and AI. However, the important part of compression is not only the algorithm, but also knowledge of the internal structure and metadata of the file is required. Like JPEG has a file structure that can be changed, cannot be changed, every marker (header), and EXIF metadata. Lack of knowledge of the file structure can cause data damage and file corruption. This study evaluates the compression of EXIF metadata of JPEG files using the Golomb-Rice and Huffman algorithms. Golomb-Rice can produce compression that affects the k parameter, while Huffman is optimal based on symbol frequency, but requires a code table. This study measures the effectiveness of both algorithms based on the compression ratio (CR). The test results of Golomb-Rice are more effective than those of Huffman. So, it can be concluded that the Golomb-Rice algorithm is superior in the context of compressing EXIF JPEG metadata, while Huffman shows lower efficiency in the tested scenarios.
Workshop Interaktif Kriptografi dan Steganografi untuk Meningkatkan Literasi Keamanan Informasi Siswa SMK Yasir Hasan
Marsipature Hutanabe: Jurnal Pengabdian Kepada Masyarakat Vol. 3 No. 02 (2026): Marsipature Hutanabe: Jurnal Pengabdian Kepada Masyarakat
Publisher : CV. Devi Tara Innovations

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

Abstract

The rapid advancement of digital technology has increased the importance of information security literacy, particularly among vocational high school (SMK) students who are prospective professionals in the field of information technology. However, knowledge of cryptography and steganography remains limited and has not been systematically integrated into vocational education. This community service activity aimed to improve students' understanding and practical skills in implementing basic cryptographic and steganographic techniques through an interactive workshop. The activity was conducted face-to-face using a practice-based learning approach (learning by doing), which consisted of four stages: pre-workshop, workshop implementation, post-workshop evaluation, and follow-up activities. Learning methods included lectures, demonstrations, hands-on practice, collaborative discussions, and evaluation through pre-test and post-test. The workshop involved 12 vocational high school students participating in industrial internships at Universitas Budi Darma. The evaluation results showed a significant improvement in participants' learning outcomes, with the average score increasing from 43.00 on the pre-test to 80.50 on the post-test, resulting in an average gain score of 37.50 points. In addition, all participants successfully completed practical exercises involving encryption, decryption, message embedding, and message extraction. These findings indicate that an interactive workshop based on direct practice effectively enhances students' information security literacy and fundamental technical competencies in cryptography and steganography. This program can serve as an alternative model for strengthening cybersecurity literacy in vocational education through sustainable practice-oriented training.
Co-Authors