Article Per Year (5 Year)
p-Index From 2021 - 2026
0.659
P-Index
This Author published in this journals
All Journal Jurnal Eksplora Informatika Saber: Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi
Silvana Samaray
Unknown Affiliation
Computer Science & IT

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

Found 3 Documents
Search

 1 
Implementasi Algoritma Rough Set dengan Software Rosetta untuk Prediksi Hasil Belajar Silvana Samaray
Jurnal Eksplora Informatika Vol 11 No 1 (2021): Jurnal Eksplora Informatika
Publisher : Bagian Perpustakaan dan Publikasi Ilmiah - Institut Teknologi dan Bisnis STIKOM Bali

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30864/eksplora.v11i1.498

Abstract

Hasil belajar mahasiswa merupakan capaian belajar yang diperoleh mahasiswa selama perkuliahan dalam bentuk angka, huruf atau simbol. Perolehan hasil belajar mahasiswa ditentukan oleh beberapa unsur, di antaranya jumlah kehadiran, nilai tugas, nilai ujian tengah semester (UTS) dan nilai ujian akhir semester (UAS). Tiap unsur memiliki persentase yang berbeda-beda dalam penentuan hasil belajar. Hasil belajar terkadang tidak sesuai dengan target yang diinginkan. Mahasiswa cenderung mengabaikan unsur dengan persentase kecil (contoh: nilai tugas) dan hanya fokus pada unsur dengan persentase yang besar (contoh: nilai UAS). Penelitian ini bertujuan untuk memprediksi hasil belajar mahasiswa berdasarkan kehadiran, nilai tugas, nilai UTS dan nilai UAS. Penelitian ini dapat dijadikan informasi awal bagi mahasiswa agar memiliki komitmen yang tinggi terhadap semua unsur penentu hasil belajar. Metode pengambilan data menggunakan metode dokumentasi. Metode pengolahan data menggunakan algoritma Rough Set, dimulai dari pemilihan atribut kondisi dan atribut keputusan, dilanjutkan dengan proses menghilangkan data ganda, hingga memperoleh reduct dan menghasilkan rules. Pengolahan data menggunakan software Rosetta. Penelitian menghasilkan 14 buah rules berupa pola aturan sebagai acuan untuk memprediksi hasil belajar lulus, cukup dan tidak lulus. Berdasarkan rules yang dihasilkan, disimpulkan bahwa atribut kondisi yang paling berpengaruh dalam penentuan hasil belajar adalah nilai UAS dilanjutkan dengan nilai tugas dan jumlah kehadiran.
Analisis Hasil Penyelesaian Soal Integrasi Numerik Berbasis ChatGPT Silvana Samaray
SABER : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 2 No. 3 (2024): Juli : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi
Publisher : STIKes Ibnu Sina Ajibarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59841/saber.v2i3.1522

Abstract

The use of artificial intelligence technology in education continues to evolve, one of which is through the application of ChatGPT. This study aims to analyze the results of solving numerical integration problems with the help of ChatGPT compared to manual methods. Numerical integration is an important method in mathematics and various disciplines for calculating the integral values of complex functions. However, manual methods require a deep understanding and high mathematical skills, with a considerable amount of time and repetitive processes that often result in inaccurate solutions. This research attempts to explore the potential of ChatGPT as an educational tool, which has not been extensively discussed in previous literature, especially in solving complex mathematical problems. In this study, a number of numerical integration problems were solved using manual methods, such as the Trapezoidl and Simpson's methods, as well as with the help of ChatGPT. The results were then compared in terms of solution accuracy. The research findings indicate that ChatGPT is capable of providing accurate solutions, with results comparable to manual methods in many cases. The analysis shows that ChatGPT can be used as an aid in solving numerical integration problems because it can provide accurate results comparable to manual methods. However, manual methods are still necessary to maintain a balance between understanding basic concepts and utilizing technology in learning.
Penerapan Artificial Intelligence-ChatGPT dalam Pembelajaran Matematika Diskrit Silvana Samaray
SABER : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 3 No. 1 (2025): Januari : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi
Publisher : STIKes Ibnu Sina Ajibarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59841/saber.v3i1.2283

Abstract

Learning discrete mathematics, particularly on the topic of equivalence in propositional logic using propositional algebra laws, often presents challenges for students due to its abstract nature and the logical thinking skills required. This study aims to analyze the effectiveness of using ChatGPT as a learning aid to enhance students' understanding of this topic. The research employed a quantitative method with a post-test only control group design, involving two groups of students: an experimental group using ChatGPT and a control group utilizing conventional learning methods. Data were collected through a post-learning achievement test. The results showed that the average score of the experimental group (85.47) was significantly higher than that of the control group (66.78). The independent t-test results yielded a significance value of < 0.05, indicating a significant difference in learning outcomes between the two groups. Furthermore, the calculation of Cohen's d showed a value of 0.959, categorized as a large effect size. These findings indicate that the use of ChatGPT as a learning aid has a significant impact on students' learning outcomes. With its interactive and responsive features, ChatGPT helps students grasp complex propositional logic material more easily. This study recommends utilizing AI-based technologies like ChatGPT as an innovative learning strategy, particularly for abstract topics in discrete mathematics.
Co-Authors