Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal CAUCHY: Jurnal Matematika Murni dan Aplikasi BAREKENG: Jurnal Ilmu Matematika dan Terapan Journal of Mathematics: Theory and Applications
Sriwahyuni, Lilis
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Energy Engineering Mathematics Mechanical Engineering Physics Transportation

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

Found 3 Documents
Search

 1 
IMPUTATION OF MISSING DAILY RAINFALL DATA USING CONVOLUTIONAL NEURAL NETWORKS (CNN) WITH SPATIAL INTERPOLATION Sriwahyuni, Lilis; Nurdiati, Sri; Nugrahani, Endar Hasafah; Sukmana, Ihwan; Najib, Mohamad Khoirun
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 19 No 4 (2025): BAREKENG: Journal of Mathematics and Its Application
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol19iss4pp2921-2936

Abstract

Accurate rainfall estimation is crucial in climate analysis and water resource planning. Observational data from weather stations play a vital role in climatological analysis as they represent actual conditions at specific locations. However, many observation stations in Indonesia need more complete data, hindering analysis and data-driven decision-making. To address this issue, this study aims to impute missing rainfall data for BMKG stations in East Java using the Convolutional Neural Network (CNN) method. Satellite data used in this study include ERA5 without interpolation and ERA5 with interpolation. The study employs a spatial interpolation approach. Data were split into training and testing datasets with various ratios: 95:5%, 90:10%, 80:20%, 70:30%, and 50:50%. The results show that the CNN method with spatially interpolated satellite data yields better results, with a Mean Absolute Error (MAE) of 7.50 on the training data and 7.05 on the testing data, indicating better generalization capability than the method without interpolation. The combination of CNN and ERA5 with interpolation was chosen for imputing missing rainfall data at BMKG stations in East Java due to its lower MAE.
Implementasi Metode Random Forest dan Support Vector Regression dalam Memprediksi Harga Cryptocurrency Ethereum Firdhasari, Azizah Aulia; Sriwahyuni, Lilis; Nurdiati, Sri; Najib, Mohamad Khoirun
Journal of Mathematics: Theory and Applications Vol. 8 No. 1 (2026): Volume 8 Nomor 1 Tahun 2026
Publisher : Program Studi Matematika Universitas Sulawesi Barat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31605/jomta.v8i1.6189

Abstract

Perkembangan cryptocurrency menjadikan Ethereum (ETH) sebagai salah satu aset digital penting, namun pergerakan harganya sangat volatil karena dipengaruhi oleh berbagai faktor fundamental dan eksternal. Kondisi tersebut menyebabkan prediksi harga close ETH menjadi permasalahan utama karena akurasi peramalan sangat menentukan analisis dan pengambilan keputusan berbasis data. Penelitian ini bertujuan membangun serta membandingkan model prediksi harga close Ethereum menggunakan Random Forest dan Support Vector Regression (SVR) untuk forecasting 30 hari ke depan. Data yang digunakan berupa harga harian Ethereum periode 1 Januari 2020 hingga 30 Desember 2024 dari Yahoo Finance, kemudian dilakukan pra-pemrosesan, standarisasi, dan pembagian data train-test 80:20 dengan menjaga urutan waktu. Feature engineering dibagun dari harga close melalui MA 7, EMA 7, dan lag return 7, serta diterapkan exponential smoothing untuk mengurangi noise. Model Random Forest dan SVR dioptimasi menggunakan Grid Search CV, kemudian dievaluasi menggunakan metrik MAPE. Hasil tuning menunjukkan konfigurasi terbaik Random Forest adalah max depth = 10 dan total estimator = 90. Konfigurasi terbaik SVR adalah kernel linear dengan C = 10, ε = 0.5, dan γ = scale. Evaluasi MAPE menunjukkan Random Forest lebih unggul dengan MAPE train 1,37% dan test 2,04%, sedangkan SVR menghasilkan MAPE train 5,83% dan test 2,22%. Secara keseluruhan, kedua model memberikan akurasi prediksi yang sangat baik, namun Random Forest menunjukkan kinerja lebih stabil dan akurat pada data pengujian. Model Random Forest kemudian digunakan untuk forecasting harga close ETH 30 hari ke depan sebagai estimasi jangka pendek yang cenderung stabil dan mengikuti tren data pengujian.
Sentiment Analysis of Indonesia’s Free Nutritious Meal Program on X Using SVM and Random Forest Hasyim, Ferdy Aliansyah; Mahenindra, Talenta Parfaibya; Sriwahyuni, Lilis; Shapira, Alika Azka; Wigawijayanti, Wigawijayanti; Ghaisani, Nadhifa Zahra; Sujana, Mirlan; Nurdiati, Sri; Najib, Mohamad Khoirun
CAUCHY: Jurnal Matematika Murni dan Aplikasi Vol 11, No 1 (2026): CAUCHY: JURNAL MATEMATIKA MURNI DAN APLIKASI
Publisher : Mathematics Department, Universitas Islam Negeri Maulana Malik Ibrahim Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18860/cauchy.v11i1.40717

Abstract

The Free Nutritious Meal (Makan Bergizi Gratis/MBG) Program was introduced to address stunting in Indonesia, yet its implementation has sparked diverse public debate. This study aims to map public perception on social media X and compare the performance of Support Vector Machine (SVM) and Random Forest algorithms in sentiment classification. Utilizing a large-scale dataset of 7,452 tweets collected via stratified random sampling from January to October 2025, this research applies TF-IDF feature extraction and SMOTE data balancing. The analysis reveals that positive sentiment dominates at 47.62%, while negative sentiment accounts for 39.8\%, and neutral for 12.57%. In model comparison, SVM without SMOTE achieved the best performance with 80.66% accuracy and an F1-Score of 79.79%, outperforming Random Forest, which only reached a maximum accuracy of 72.23% after SMOTE application. These findings provide an objective overview of MBG policy acceptance and methodological insights into the effectiveness of SVM in handling high-dimensional text data.
Co-Authors Endar Hasafah Nugrahani Firdhasari, Azizah Aulia Ghaisani, Nadhifa Zahra Hasyim, Ferdy Aliansyah Mahenindra, Talenta Parfaibya Najib, Mohamad Khoirun Shapira, Alika Azka Sri Nurdiati Sujana, Mirlan Sukmana, Ihwan Wigawijayanti, Wigawijayanti