Article Per Year (5 Year)
p-Index From 2021 - 2026
2.93
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Informasi dan Ilmu Komputer Jurnal Ilmiah Flash JurTI (JURNAL TEKNOLOGI INFORMASI) The IJICS (International Journal of Informatics and Computer Science) JATI (Jurnal Mahasiswa Teknik Informatika) Journal of Applied Data Sciences Jurnal Manajemen Informatika Jayakarta HOAQ (High Education of Organization Archive Quality) : Jurnal Teknologi Informasi Jurnal Nasional Teknik Elektro dan Teknologi Informasi Jurnal Manajemen Informatika & Teknologi Journal of Novel Engineering Science and Technology Infact: Jurnal Sains dan Komputer JuTISI (Jurnal Teknik Informatika dan Sistem Informasi) Jurnal Penelitian Sains Teknologi
Edwin Ariesto Umbu Malahina
STIKOM Uyelindo Kupang
Biochemistry, Genetics & Molecular Biology Chemistry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Electrical & Electronics Engineering Energy Engineering Environmental Science Industrial & Manufacturing Engineering Library & Information Science Materials Science & Nanotechnology Mechanical Engineering Physics Transportation

Published : 22 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 22 Documents
Search

 1   2   3 
Analisis Optimasi Klasifikasi Citra Awan Berdasarkan Nilai Hyperparameter Pada Teachable Machine untuk Pengembangan Aplikasi Web Mobile Bendi, Muhammad Indra; Malahina, Edwin Ariesto Umbu
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 12 No 6: Desember 2025
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2025126

Abstract

Pengamatan cuaca menjadi aspek penting dalam berbagai bidang seperti meteorologi, penelitian lingkungan dan penerbangan. Identifikasi jenis awan memainkan peran kunci dalam memprediksi perubahan cuaca dan mengevaluasi dampak lingkungan. Tujuan dari penelitian ini adalah untuk mengembangkan sebuah aplikasi web mobile sistem cerdas yang mampu membantu masyarakat dalam mendeteksi jenis awan secara mandiri di sekitar, memberikan edukasi tentang jenis awan dan yang paling penting adalah mencari nilai optimasi hyperparameter epoch, batch size dan learning rate dalam Teachable Machine. Penelitian ini menggunakan nilai untuk parameter-parameter yang diteliti, yaitu nilai epoch yang bervariasi antara 10, 50, 100, 250, 750 dan 1000. Kemudian nilai batch size yang bervariasi antara 16, 32, 64, 128, 256 dan 512 serta learning rate yang bervariasi antara 0,00001; 0,0001; 0,001; 0,01; 0,1 dan 1. Total dataset sebanyak 4.000 sampel data latih (400 sampel dalam 10 kelas) digunakan dalam Teachable Machine. Metode yang digunakan adalah dengan memanfaatkan framework TensorFlow pada layanan Teachable Machine untuk melatih data citra atau gambar. Framework ini menyediakan algoritma Convolutional Neural Networks (CNN) yang dapat melakukan klasifikasi citra atau gambar dengan tingkat akurasi yang tinggi. Hasil pengujian menunjukkan bahwa nilai optimal tertinggi tercapai pada nilai epoch ke-50, dengan nilai batch size 16 dan learning rate 0,00001 yang menghasilkan tingkat akurasi antara 70% hingga 98%. Aplikasi web mobile ini diharapkan dapat diimplementasikan secara luas untuk kepentingan masyarakat agar mengenali jenis awan yang menyebabkan potensi hujan.   Abstract Weather observation is becoming an increasingly important aspect in various fields, such as Meteorology, Environmental Research, and aviation. The identification of cloud types plays a key role in predicting weather changes and evaluating environmental impacts. The purpose of this study is to develop a mobile web application intelligent system that is able to help people detect the type of cloud independently around, provide education about the type of cloud, and most importantly, find the value of optimization hyperparameter epoch, batch size and learning rate in Teachable Machine. This study uses the values for the parameters studied, namely the epoch values that vary between 10, 50, 100, 250, 750, and 1000. Then the value of batch size varies between 16, 32, 64, 128, 256, and 512, and the learning rate varies between 0.00001; 0.0001; 0.001; 0.01; 0.1, and 1. A total of 4,000 training data samples (400 samples per class) were used in the Teachable Machine. The method used is to utilize the TensorFlow framework in the Teachable Machine Service to train image or image data. This Framework provides Convolutional Neural Networks (CNN) algorithms that can classify images with a high degree of accuracy. The test results showed that the highest optimal value was reached at the 50th epoch value, with a batch size value of 16 and a learning rate of 0.00001 which resulted in an accuracy rate of 70% to 98%. This application is expected to be widely implemented for the benefit of the community in order to recognize the type of cloud that causes the potential for rain.
NuminaMath 7B: Revolutionizing Math Solving with Integrated Reasoning Advanced Generative AI Tools and Python REPL Jufriansah, Adi; Akib, Irwan; Ishartono, Naufal; Khusnani, Azmi; Rahmawati, Tanti Diyah; Malahina, Edwin Ariesto Umbu; Maure, Osniman Paulina; Romadloni, Nova Tri
Jurnal Penelitian Sains Teknologi Vol. 2, No. 1, March 2026
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/saintek.v2i1.15728

Abstract

The efficacy of NuminaMath 7B, an AI model that was created to address mathematical challenges, is assessed in this investigation. We evaluated the model's accuracy and efficiency against conventional methods through experiments that produced quantitative data. Qualitative data were collected through surveys and interviews with users to gain insight into their experiences and pinpoint areas for improvement. The survey results indicated that users found NuminaMath 7B to be pertinent, effective, and user-friendly, as evidenced by the exceptionally high average scores in user experience (95), perception of features and interface (90), and additional feedback (85). NuminaMath 7B was able to offer mathematical solutions with logical and detailed explanations as a result of the model's development through two phases of adjustments, which were conducted using the Chain of Thought (CoT) methodology and inspiration from the Tool-Integrated Reasoning Agent (ToRA) framework. Testing demonstrated that the model achieved a score of 29 out of 50 in the AI Math Olympiad competition, despite encountering difficulties in resolving more intricate problems. This study underscores the significance and urgency of AI technology, particularly in the field of mathematics, as well as the significant potential of AI models to facilitate a more comprehensive comprehension of mathematical concepts.
Co-Authors Abdul Syawal Laan, Muhammad Adi Jufriansah Agustina Clarissa Huko Langoday Akib, Irwan Aulia Safirah, Nindy Ayub Djara Lulu Azmi Khusnani Bendi, Muhammad Indra Duka, Alsha Day Franki Yusuf Bisilisin Jimi, Asmara Kaesmetan, Yampi R Mardhalia Saitakela Maure, Osniman Paulina Melania Zemil Menhya Snae Muhammad Agus Muljanto Muhammad Syahrul Ramadhan A.S. Dapubeang Natzir, Sadam Muhammad Naufal Ishartono Nova Tri Romadloni Pereira, Yubita Dasilva Petrus Katemba Rudi Hariyanto Ryan Peterzon Hadjon S Sumarlin S Sumarlin Sadam Muhammad Natzir Salsa Sukma Semlinda Juszandri Bulan Tanti Diyah Rahmawati, Tanti Diyah Yohanes Suban Belutowe Yudhiakto Pramudya Zampi, Aprilia Ch