Article Per Year (5 Year)
p-Index From 2021 - 2026
2.218
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering IAES International Journal of Artificial Intelligence (IJ-AI) Sistemasi: Jurnal Sistem Informasi JOIV : International Journal on Informatics Visualization JOURNAL OF APPLIED INFORMATICS AND COMPUTING Communications in Science and Technology Building of Informatics, Technology and Science Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) JURNAL PAI: Jurnal Kajian Pendidikan Agama Islam Intechno Journal : Information Technology Journal
Agastya, I Made Artha
Unknown Affiliation
Religion Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Languange, Linguistic, Communication & Media Other

Published : 15 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 15 Documents
Search

 1   2 
Optimizing rice leaf disease classification through convolutional neural network architectural modification and augmentation techniques Firdaus, Mohamad; Kusrini, Kusrini; Agastya, I Made Artha; Martínez-Béjar, Rodrigo
International Journal of Electrical and Computer Engineering (IJECE) Vol 15, No 3: June 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v15i3.pp3429-3438

Abstract

This research focuses on advancing the accuracy of rice leaf disease classification through the integration of convolutional neural network (CNN) and deep learning models. With Indonesia ranking third in global rice production, effective crop management is crucial for sustaining agricultural output. This study employs innovative data augmentation techniques, including random zoom and others, to enhance model training robustness. The experimentation involves eight scenarios with varied architectural configurations applied to a residual network-50 (ResNet50) layers model, aiming to optimize disease classification performance. Featuring random zoom without the multilayer perceptron (MLP) component, emerges as the most effective, demonstrating superior accuracy and performance metrics. A grid search is conducted to optimize MLP layers, revealing a three-layer configuration as most effective. We found that the data augmentation and MLP layer can increase the accuracy of the disease classification task. The method proposed in this study is likely to have a much higher proportion of correct disease classification by combining MLP and zoom augmentation. Specifically, the model with three MLP layers and zoom augmentation demonstrated significantly higher accuracy, achieving a test accuracy, precision, recall, and F1-score of 0.92, 0.94, 0.92, and 0.92, respectively.
Analisis Laporan Beban Kerja Dosen Pendidikan Agama Islam (PAI) pada Bidang Penelitian dengan menggunakan Metode Clustering Pratama, Muhammad Egy; Kusrini, Kusrini; Agastya, I Made Artha
JURNAL PAI: Jurnal Kajian Pendidikan Agama Islam Vol 4 No 1 (2025)
Publisher : Prodi Pendidikan Agama Islam IAINU Kebumen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33507/pai.v4i1.3150

Abstract

This study aims to classify research activities of Islamic Education lecturers based on Lecturer Workload Reports using the K-Means clustering method. The dataset includes research activities of PAI lecturers at UIN Sultan Aji Muhammad Idris Samarinda over the past three academic years. Classification was conducted by identifying publication types based on keywords and summarizing each lecturer’s activity. The results show variations in productivity, with many activities falling into the “others” category due to the lack of explicit publication descriptions. The K-Means method grouped lecturers into three clusters: Active, Moderately Active, and Less Active, based on the number of activities and total SKS. These findings can assist faculty leaders in formulating human resource development strategies and enhancing lecturers’ performance in supporting key performance indicators (KPI) and accreditation standards.
Sentiment Analysis of Banking Application Reviews on Google Play Store using Support Vector Machine Algorithm Prasetyo, Martinus Juan; Agastya, I Made Artha
Sistemasi: Jurnal Sistem Informasi Vol 13, No 6 (2024): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v13i6.4536

Abstract

Banking applications are increasingly important in facilitating daily financial transactions. However, to ensure service quality, developers need to understand user feedback. Reviews on the Google Play Store provide important insights related to satisfaction, complaints, and suggestions. Therefore, this study aims to develop the Sentiment Analysis Model for Banking Application Reviews Using Support Vector Machine (SVM). Data collected from three popular banks in Indonesia is used to train and test models. This research also contributes to providing multi -bank dataset which can be a benchmark. Various scenarios of the distribution of training and test data are explored, and repeated tests are carried out with different random state values to get stable results. The results showed that the SVM model was able to achieve good accuracy, with BRI Mobile dataset reaching the highest accuracy of 92.97%, followed by a combined dataset of 90.05%, BCA Mobile 89.73%, and Livin Mandiri 87.46%. Negative reviews are dominated by technical complaints, while positive reviews highlight the ease and reliability of the application. This study shows that the approach used has succeeded in producing competitive performance, and application developers are advised to focus on improving technical aspects, such as fixing login, verification, and transaction problems, in order to increase user satisfaction.
Peramalan Multivariat Saham Bank Indonesia dengan Model ARIMA dan LSTM Ramadhan, Akhdan Ferdiansyah; Agastya, I Made Artha
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7352

Abstract

Stock price forecasting is a crucial aspect of financial market analysis, particularly in supporting more accurate and informed investment decision-making. This study compares the performance of the statistical Autoregressive Integrated Moving Average (ARIMA) model with three variants of the Long Short-Term Memory (LSTM) architecture, namely Vanilla LSTM, Bidirectional LSTM, and Stacked LSTM, in predicting closing prices and trading volumes of Indonesian bank stocks—specifically BBCA.JK, BBRI.JK, and BMRI.JK. The data were obtained from Kaggle and processed through normalization, transformation, and model training stages using Google Colab and TensorFlow. Evaluation was conducted using RMSE, MAE, and MAPE metrics. The results indicate that ARIMA performs better in forecasting closing prices, achieving an average MAPE of 1.9%, while Bidirectional LSTM yielded the best results in forecasting trading volumes, particularly for BBRI and BMRI stocks. However, the prediction error for volume data remains relatively high (average MAPE of 36.4%) due to its volatile nature. These findings suggest that data characteristics significantly influence model effectiveness. LSTM-based models demonstrate superior capabilities in capturing complex non-linear patterns and exhibit advantages in multivariate forecasting compared to the ARIMA model. This study is expected to serve as a reference for selecting appropriate forecasting models in the context of Indonesian banking stock markets. The results highlight a trade-off between ARIMA, which excels in modeling linear patterns such as closing prices, and LSTM, which is more adaptive to non-linear patterns like trading volumes.
Evaluation of SMOTE Technique in the Comparison of XGBoost and Random Forest Algorithms for Liver Disease Prediction Rohman, Wahyutri Nur; Agastya, I Made Artha
Journal of Applied Informatics and Computing Vol. 9 No. 6 (2025): December 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i6.10239

Abstract

In many countries, including Indonesia, liver disease remains a major cause of morbidity and mortality. Early detection plays a crucial role in improving treatment outcomes. This study evaluates the performance of two widely used machine learning models Random Forest and XGBoost for predicting liver disease, employing the SMOTE balancing technique to address class imbalance. The primary objectives are to enhance model fairness, reduce overfitting, and improve sensitivity toward the minority class. Model performance is assessed using accuracy, precision, recall, and F1-score metrics. The XGBoost model achieved an average accuracy of 99.74%, precision of 99.77%, recall of 99.75%, and F1-score of 99.72%, while the Random Forest model attained an average accuracy of 99.82%, precision of 99.89%, recall of 99.75%, and F1-score of 99.75%. Both models demonstrated excellent predictive capability, with Random Forest slightly outperforming XGBoost. These results highlight the importance of data balancing and robust model validation in developing reliable machine learning models for healthcare decision-making.
Co-Authors Adhani, Muhammad Azmi Afrig Aminuddin Arief Setyanto Dini Oktarina Dwi Handayani Kusrini, K Kusrini, Kusrini López, Alba Puelles Martínez-Béjar, Rodrigo Mohamad Firdaus, Mohamad Mohammad Haris Muzakki, Mohammad Haris Noor Akhmad Setiawan Nugroho, Agung Prasetyo, Martinus Juan Pratama, Muhammad Egy Ramadhan, Akhdan Ferdiansyah Robert Marco, Robert Rohman, Wahyutri Nur Saputra, Gilang Ardhi Sukaria, Petra Nugra Teguh Bharata Adji Wicaksono, Dika Wiryawan Sujana, Rajendra Artanto