Article Per Year (5 Year)
p-Index From 2021 - 2026
0.751
P-Index
This Author published in this journals
All Journal Jurnal Sistem Informasi dan Informatika (SIMIKA) Journal of Applied Data Sciences Jurnal Ilmiah Betrik : Besemah Teknologi Informasi dan Komputer INOVTEK Polbeng - Seri Informatika
Wirta Agustin
Universitas Sains dan Teknologi Indonesia
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
MODEL PREDIKSI PRODUKTIVITAS PADI MENGGUNAKAN XGBOOST DAN RANDOM FOREST Yoga Safitra Anugraha; Helda Yenni; Wirta Agustin; Hadi Asnal
Jurnal Sistem Informasi dan Informatika (Simika) Vol. 9 No. 1 (2026): Jurnal Sistem Informasi dan Informatika (Simika)
Publisher : Program Studi Sistem Informasi, Universitas Banten Jaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47080/simika.v9i1.4169

Abstract

Rice is a strategic commodity in ensuring national food security in Indonesia. Predicting rice productivity is a critical issue due to the decreasing harvest area and fluctuating production. This study aims to develop and compare the performance of two machine learning algorithms, namely Extreme Gradient Boosting (XGBoost) and Random Forest, in predicting rice productivity based on harvest area and total production data. The dataset consists of rice productivity data from 38 provinces in Indonesia over the period 2018 to 2024. The models were evaluated using three data splitting ratios (70:30, 80:20, and 90:10) and four evaluation metrics: Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Coefficient of Determination (R²). The results show that both models perform well, with Random Forest achieving the highest R² value of 0.887 and the lowest RMSE of 2.939 on the 90:10 split, indicating higher accuracy. XGBoost, while slightly lower in accuracy (R² = 0.781), produced more stable predictions across varying input scales. When tested on new data, both models showed consistent performance, demonstrating generalization capabilities. These findings indicate that machine learning models are effective in modeling and forecasting agricultural productivity and can serve as decision-support tools for policymakers and agricultural stakeholders. The models can be utilized for strategic planning, resource allocation, and improving agricultural productivity in the future.
Prediksi Jumlah Titik Ruang Terbuka Hijau (RTH) Menggunakan Metode Regresi Linier dan Model Random Forest M. Azzuhri Dinata; Helda Yenni; Wirta Agustin; Aguston
BETRIK Vol. 16 No. 02 (2025): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/d81adt50

Abstract

The development and preservation of Green Open Space (GOS) is an important part of maintaining environmental balance, especially in the Sumatra Ecoregion. This study aims to predict the number of GOS points using a linear regression approach and the Random Forest algorithm. The data used include variables such as area and forest area from several provinces in Sumatra. Model performance evaluation was carried out using MAE, RMSE, and coefficient of determination (R²) metrics. The analysis results show that the Random Forest model has superior performance compared to linear regression, with an MAE value of 5.52, RMSE of 5.88, and R² of 0.74. Meanwhile, linear regression was only able to achieve an R² of 0.45. These findings indicate that Random Forest is more effective in capturing non-linear data patterns and more accurate in predicting the number of GOS points. This study contributes to the use of data science technology to support sustainable environmental planning, as well as becoming a basis for data-based spatial planning policy making
Togaf Analysis in Bengkalis State Polytechnic Laboratory Information Systems Design Khairus suhada; Wirta Agustin; Rahmaddeni; Unang Rio
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/0hz5q194

Abstract

Laboratories in educational institutions have an important role in supporting learning and research. However, effective and efficient laboratory management is still a challenge, especially in recording inventory and managing consumables (BHP). The Bengkalis State Polytechnic Informatics Engineering Laboratory already has an application system, but there are still limitations in recording monthly BHP usage, borrowing facilities, and proposing equipment procurement. This research aims to design a blueprint for an integrated laboratory information system using The Open Group Architecture Framework (TOGAF) Architecture Development Method (ADM). This approach is applied to phase F: Migration Planning, which includes requirements analysis, business architecture design, information system architecture, as well as strategy and migration implementation. The results of this research produce a blueprint for a system information laboratory that includes application design, technology recommendations, and implementation stages that can be used as a guide in system development. This blueprint is expected to increase laboratory management efficiency by optimizing inventory recording, procurement planning and maintenance of laboratory services. In addition, the TOGAF ADM approach used can be adapted for laboratories in other educational settings that have similar needs.
Improved Performance of Hybrid GRU-BiLSTM for Detection Emotion on Twitter Dataset M. Khairul Anam; Munawir Munawir; Lusiana Efrizoni; Nurul Fadillah; Wirta Agustin; Irwanda Syahputra; Tri Putri Lestari; Muhammad Bambang Firdaus; Lathifah Lathifah; Atalya Kurnia Sari
Journal of Applied Data Sciences Vol 6, No 1: JANUARY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i1.459

Abstract

This study addresses emotion detection challenges in tweets, focusing on contextual understanding and class imbalance. A novel hybrid deep learning architecture combining GRU-BiLSTM with SMOTE is proposed to enhance classification performance on an Israel-Palestine conflict dataset. The dataset contains 40,000 tweets labeled with six emotions: anger, disgust, fear, joy, sadness, and surprise. SMOTE effectively balances the dataset, improving model fairness in detecting minority classes. Experimental results show that the GRU-BiLSTM hybrid with an 80:20 data split achieves the highest accuracy of 89%, surpassing BiLSTM alone, which obtained 88%, and other state-of-the-art models. Notably, the proposed model delivers significant improvement in detecting the emotion of joy (recall: 0.87, F1-score: 0.86). In contrast, the surprise category remains challenging (recall: 0.24). Compared to existing research, this study highlights the effectiveness of combining SMOTE and hybrid GRU-BiLSTM, outperforming models such as CNN, GRU, and LSTM on similar datasets. The incorporation of GloVe embeddings enhances contextual word representations, enabling nuanced emotion detection even in sarcastic or ambiguous texts. The novelty lies in addressing class imbalance systematically with SMOTE and leveraging GRU-BiLSTM's complementary strengths, yielding superior performance metrics. This approach contributes to advancing emotion detection tasks, especially in conflict-related social media data, by offering a robust, context-sensitive, and balanced classification method.
Co-Authors Aguston Anam, M Khairul Atalya Kurnia Sari Hadi Asnal Helda Yenni Irwanda Syahputra Khairus suhada Lathifah Lathifah Lusiana Efrizoni M. Azzuhri Dinata Muhammad Bambang Firdaus Munawir Munawir Nurul Fadillah Rahmaddeni Tri Putri Lestari Unang Rio Yoga Safitra Anugraha