Article Per Year (5 Year)
p-Index From 2020 - 2025
0.751
P-Index
This Author published in this journals
All Journal JSI: Jurnal Sistem Informasi (E-Journal) Jurnal Teknologi Informasi dan Ilmu Komputer Journal of Educational Research and Evaluation
Zahnur
Unknown Affiliation
Humanities Computer Science & IT Decision Sciences, Operations Research & Management Education Engineering Library & Information Science Public Health Social Sciences Other

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

Found 3 Documents
Search

 1 
Sistem Identifikasi Pembicara Berbahasa Indonesia Menggunakan X-Vector Embedding Misbullah, Alim; Saifullah Sani, Muhammad; Husaini; Farsiah, Laina; Zahnur; Martiwi Sukiakhy, Kikye
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 11 No 2: April 2024
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.20241127866

Abstract

Penyemat pembicara adalah vektor yang terbukti efektif dalam merepresentasikan karakteristik pembicara sehingga menghasilkan akurasi yang tinggi dalam ranah pengenalan pembicara. Penelitian ini berfokus pada penerapan x-vectors sebagai penyemat pembicara pada sistem identifikasi pembicara berbahasa Indonesia yang menggunakan model speaker identification. Model dibangun dengan menggunakan dataset VoxCeleb sebagai data latih dan dataset INF19 sebagai data uji yang dikumpulkan dari suara mahasiswa dan mahasiswi Informatika Universitas Syiah Kuala angkatan 2019. Fitur-fitur yang digunakan diekstrak dari dataset audio dengan menggunakan dua jenis konfigurasi mel frequency cepstral coefficients (MFCC). Untuk membangun model, fitur-fitur diekstrak dengan menggunakan MFCC, dihitung voice activity detection (VAD), dilakukan augmentasi dan normalisasi fitur menggunakan cepstral mean and variance normalization (CMVN) serta dilakukan filtering. Sedangkan proses pengujian model hanya membutuhkan fitur-fitur yang diekstrak dengan menggunakan MFCC dan dihitung VAD. Selanjutnya, dibangun empat model dengan cara mengombinasikan dua jenis konfigurasi MFCC dan dua jenis arsitektur Deep Neural Network (DNN) yang memanfaatkan Time Delay Neural Network (TDNN). Model terbaik dipilih berdasarkan akurasi tertinggi yang dihitung menggunakan metrik equal error rate (EER) dan durasi ekstraksi x-vectors tersingkat dari keempat model. Nilai EER dari model yang terbaik untuk dataset VoxCeleb1 bagian test sebesar 3,51%, inf19_test_td sebesar 1,3%, dan inf19_test_tid sebesar 1,4%. Durasi ekstraksi x-vectors menggunakan model terbaik untuk dataset data train berdurasi 6 jam 42 menit 39 detik, VoxCeleb1 bagian test berdurasi 2 menit 24 detik, inf19_enroll berdurasi 18 detik, inf19_test_td berdurasi 25 detik, dan inf19_test_tid berdurasi 9 detik. Arsitektur DNN kedua dan konfigurasi MFCC kedua yang telah dirancang menghasilkan model yang lebih kecil, akurasi yang lebih baik terutama untuk dataset pembicara berbahasa Indonesia, dan durasi ekstraksi x-vectors yang lebih singkat.
Learning Media Visualisation of Distance in Augmented Reality-Based Three-Dimensional Space Baeha, Nadilah Hasfahani; Zahnur; Oktavia, Rini
Journal of Education Reseach and Evaluation Vol 9 No 1 (2025): February
Publisher : LPPM Undiksha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/jere.v9i1.87270

Abstract

One of the challenges encountered by students when studying distance in space is the difficulty in conceptualizing abstract mathematical concepts, such as determining perpendicular line segments in a cube represented in a two dimensional image. The visualization of abstract mathematical objects can be represented using augmented reality (AR) technology. This technology turns images of objects into virtual ones that appear in the real world. Previous studies showed that there is a need to enrich AR application with more multimedia content. Developing an AR system utilizing smartphones has become a prevalent endeavor recently. This study aims to develop augmented reality-based learning media to enhance students' comprehension of the concept of distance in three-dimensional space. This study employed a research and development (R&D) approach utilizing the ADDIE model, comprising five stages: analysis, design, development, implementation, and evaluation. The sample consisted of 36 students in the  12th-grade from a high school located in Indonesia, and the experiment employed a pretest-posttest control group design. The Mann-Whitney U test showed no statistically significant difference between the pretest scores of the experimental and control groups. However, the posttest results showed the experimental group had a higher mean rank score (22.36) than the control group (14.64), with a p-value of 0.017 and effect size of 0.42. This indicates that the learning media has a meaningful impact, which can significantly improve students' ability to understand the material on distance in a three-dimensional space.
Penerapan Metode Forward Chaining untuk Sistem Pakar Diagnosis Penyakit Ginjal Berbasis Website Husaini; At-Tharfi’in, Khairunnisa; Misbullah, Alim; Zahnur
JSI: Jurnal Sistem Informasi (E-Journal) Vol 17 No 1 (2025): Vol 17, No 1 (2025)
Publisher : Jurusan Sistem Informasi Fakultas Ilmu Komputer Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18495/jsi.v17i1.191

Abstract

An expert system is used to replicate the knowledge and reasoning of an expert to assist in decision-making, diagnosis, prediction, and problem-solving in a specific field. Expert systems have been applied across various domains, including healthcare, such as for diagnosing kidney diseases. In this case, the web-based expert system for kidney disease diagnosis is designed to help analyze symptoms and provide an initial diagnosis based on the knowledge and rules of an expert. The system is designed to be utilized by the public, allowing users to input their symptoms, after which the system will provide a diagnosis. It is expected that this expert system can help the public detect kidney disorders early by applying expert knowledge integrated within the system. Another benefit of this system is that it makes it easier for users to perform self-diagnosis and detect potential kidney issues early based on the symptoms they experience. This expert system is developed using the forward chaining method, leveraging the Laravel framework and MySQL database. Forward chaining is a reasoning technique that starts by using available facts and then progresses through relevant premises to reach a conclusion. The use of this method ensures a systematic and accurate reasoning process for generating diagnoses or decisions based on the input information. Testing of the application shows that the developed expert system has successfully met expectations in helping the public accurately and easily identify kidney diseases. Additionally, the application of forward chaining allows the system to provide precise diagnoses based on the symptoms entered by the user, improving the ease of access to health information efficiently.
Co-Authors At-Tharfi’in, Khairunnisa Baeha, Nadilah Hasfahani Farsiah, Laina Husaini Husaini Husaini Martiwi Sukiakhy, Kikye Misbullah, Alim Oktavia, Rini Saifullah Sani, Muhammad