Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Seminar Nasional Aplikasi Teknologi Informasi (SNATI) International Journal of Engineering, Science and Information Technology J-KOMA : Jurnal Ilmu Komputer dan Aplikasi
Muhammad Eka Suryana
Universitas Negeri Jakarta
Astronomy Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Education Electrical & Electronics Engineering Energy Engineering Industrial & Manufacturing Engineering Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Physics Social Sciences Transportation

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

Found 3 Documents
Search

 1 
Membandingkan Pengaruh Feature Selection Terhadap Algoritma Naïve Bayes dan Support Vector Machine Aldi Rahmansyah; Ovitasari Dewi; Puti Andini; Trisna Hastuti Puspita Ningrum; Muhammad Eka Suryana
Seminar Nasional Aplikasi Teknologi Informasi (SNATI) 2018
Publisher : Jurusan Teknik Informatika, Fakultas Teknologi Industri, Universitas Islam Indonesia

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

Abstract

Feature selection menjadi perhatian di banyak bidang penelitian yang menggunakan machine learning, karena menyediakan pengklasifikasi untuk mempercepat proses, menghemat biaya dan meningkatkan akurasi. Pada penelitian ini kami menggunakan beberapa algoritma dengan menerapkan Algoritma Machine learning. Algoritma yang kami gunakan yaitu Support Vector Machine dan Naïve Bayes dengan sebelas features. Dan untuk mempermudah penerapannya di dunia nyata kami juga melakukan feature selection dengan harapan mengurangi features yang digunakan. Hasil yang kami dapatkan adalah pengaruh feature selection terbaik ada pada algoritma Naive Bayes yang mendapat nilai presisi dan recall 0.5 dan 0.52 yang sebelumnya adalah 0.455 dan 0.434. Sebaliknya pada Support Vector Machine, hasil terbaiknya adalah ketika semua feature digunakan tanpa ada yang dikurangi.
Web-Based Math Braille Translator Using Indonesian Braille Symbols Ari Hendarno; Andira Azzahra; Muhammad Eka Suryana
International Journal of Engineering, Science and Information Technology Vol 4, No 2 (2024)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v4i2.506

Abstract

According to estimates from the Indonesian Ministry of Health in 2017, at least 3,750,000 people in Indonesia have visual impairments. This significant number highlights the need for special attention to their educational needs, especially in mathematics. Educational media is essential to facilitate learning for visually impaired students and educators, as they often struggle with understanding math due to limited access to visual content. One solution is to use Mathematical Braille symbols, yet technology that translates these symbols into mathematical text is still limited. To address this, the author has developed a web-based Math Braille Translator application aimed at assisting visually impaired individuals and educators. This website translates mathematical Braille into notation by inputting Braille using the keys s, d, f, j, k, and l on the keyboard. The application is developed using the waterfall methodology and is based on the Indonesian Mathematical Braille Symbol Reference NOMOR 056/U/2000.
Prediksi Risiko Putus Sekolah Menggunakan Long Short-Term Memory Berdasarkan Data Prestasi Akademik Ria Arafiyah; Vera Maya Santi; Muhammad Eka Suryana; Salwa Tsabitah; Rahma Wati Malawat
J-KOMA : Jurnal Ilmu Komputer dan Aplikasi Vol 8 No 02 (2025): J-KOMA : Jurnal Ilmu Komputer dan Aplikasi
Publisher : Universitas Negeri Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21009/JKOMA.082.06

Abstract

Student dropout is a critical issue affecting academic quality and institutional performance in higher education. Dropout behavior usually emerges gradually through declining academic performance across semesters. Therefore, time-series modeling is essential to capture such temporal patterns. This study proposes a Long Short-Term Memory (LSTM) model to predict student dropout risk based on semester-wise academic data. The dataset consists of 385 undergraduate students from the Computer Science program, FMIPA, represented by Grade Point Average (GPA) and credit load (SKS) over eight semesters. Student status is converted into a binary label: dropout and non-dropout. To address class imbalance, Synthetic Minority Over-sampling Technique (SMOTE) is applied. Experimental results show that the proposed LSTM model achieves a recall of 1.00 for the dropout class, indicating that all dropout cases are successfully detected. Although the precision remains relatively low due to false positives, the model demonstrates strong potential as a basis for academic monitoring and early intervention systems.
Co-Authors Aldi Rahmansyah Andira Azzahra Arafiyah, Ria Ari Hendarno Ovitasari Dewi Puti Andini Rahma Wati Malawat Salwa Tsabitah Trisna Hastuti Puspita Ningrum Vera Maya Santi