Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Jurnal Ilmu Komputer JURNAL REKAYASA TEKNOLOGI INFORMASI
Maulidia, Raisa
Unknown Affiliation
Computer Science & IT Languange, Linguistic, Communication & Media Library & Information Science

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Model Prediksi Umur Kepiting Berdasarkan Data Morfometrik dan Gender: Pendekatan Model Support Vector Regression Ramadhani, Tirta Samudera; Mudaim, Syarifah; Sabitta, Valin Rizkia; Maulidia, Raisa
Jurnal Ilmu Komputer Vol 16 No 2 (2023): Jurnal Ilmu Komputer
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JIK.2023.v16.i02.p07

Abstract

Crab is one of the most important marine commodities and resources in Indonesian waters, both economically and ecologically. Crab age determination can provide a better understanding of crab growth and development, so that crab farming can be carried out effectively, efficiently, and profitably for its supporters. In addition, determining the age of the crab can also help the sustainability of the crab population. This study was conducted using support vector regression (SVR) modeling to predict crab age by establishing a predictive relationship between the dependent variable (x) and the independent variable (y). The attributes of the dependent variable (x) include length, diameter, height, and weight. While the independent variable (y) only includes crab age. SVR modeling is carried out to show predicted data with actual data, where the results of the SVR modeling will be evaluated based on the results of the RMSE value test. This study resulted in an RMSE value of 0.019814 so it can be said that the model to predict crab age is very accurate. The purpose of this research is to develop a statistical model that can predict crab age based on morphometric data and crab gender using the Support Vector Regression (SVR) model approach.
Perbandingan Algoritma Machine Learning untuk Prediksi Multi-Output Variabel Osean-Atmosfer Maulidia, Raisa; Arifin, Willdan Aprizal; Syafri, Herman
Jurnal Rekayasa Teknologi Informasi (JURTI) Vol 9, No 4 (2025): Jurnal Rekayasa Teknologi Informasi (JURTI)
Publisher : Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30872/jurti.v9i4.25976

Abstract

Prediksi variabel osean-atmosfer merupakan komponen penting dalam mendukung keselamatan dan efisiensi aktivitas maritim. Kompleksitas data osean-atmosfer yang bersifat multivariat dan dinamis memerlukan pendekatan komputasional yang mampu menangkap hubungan non-linear dan temporal secara simultan. Penelitian ini membandingkan performa tiga algoritma machine learning, yaitu Long Short-Term Memory (LSTM), Random Forest, dan XGBoost dalam memprediksi multi-output variabel osean-atmosfer menggunakan data Automatic Weather Station (AWS) periode 2022–2025. Tahapan penelitian meliputi pra-pemrosesan, normalisasi menggunakan StandardScaler, pembagian data (90% latih dan 10% uji), pelatihan model teroptimasi, serta evaluasi menggunakan RMSE dan R². Hasil penelitian menunjukkan bahwa XGBoost memiliki performa terbaik pada sebagian besar variabel dengan nilai RMSE terendah pada windspeed (0,77), waterlevel (0,12), RH (2,40), dan winddir (28,79), serta nilai R² tertinggi masing-masing sebesar 0,840; 0,940; 0,870; dan 0,730. LSTM menunjukkan performa terbaik pada variabel watertemp dengan RMSE sebesar 0,31 dan R² sebesar 0,814. Sementara itu, Random Forest memiliki performa yang relatif lebih rendah dengan nilai R² berkisar antara 0,680 hingga 0,982 tergantung variabel. Secara keseluruhan, XGBoost terbukti paling konsisten dan efektif dalam menangani prediksi multi-output variabel osean-atmosfer yang kompleks dan non-linear.
Co-Authors Mudaim, Syarifah Ramadhani, Tirta Samudera Sabitta, Valin Rizkia Syafri, Herman Willdan Aprizal Arifin