Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal bit-Tech
Trimono Trimono
University of Pembangunan Nasional “Veteran” East Java
Computer Science & IT

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

Found 3 Documents
Search

 1 
Rice Leaf Disease Classification Using EfficientNetV2 with Hyperparameter Tuning Rizal Harjo Utomo; Mohammad Idhom; Trimono Trimono
bit-Tech Vol. 8 No. 2 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i2.3194

Abstract

Rice is a strategic food commodity and a primary source of food security in many countries, including Indonesia. However, rice productivity often declines due to leaf diseases that remain difficult for farmers to identify manually with consistent accuracy. Deep learning–based artificial intelligence offers a promising solution for automatically detecting and classifying plant diseases in a more objective and reliable manner. This study implements the EfficientNetV2 model for classifying rice leaf disease images and enhances its performance through systematic hyperparameter tuning. The dataset includes rice leaf images obtained from field observations in Lamongan Regency combined with supplementary data from an open-access platform, representing several major rice diseases such as blast, bacterial leaf blight, brown spot, tungro disease, and healthy leaves. The model is trained using a transfer learning approach and evaluated using accuracy, precision, recall, and F1-score to ensure comprehensive performance assessment. The experimental results from this study demonstrate that hyperparameter tuning substantially improves model performance compared to the untuned baseline. The optimized EfficientNetV2 model achieves a final accuracy of 99%, with precision, recall, and F1-scores consistently reaching 0.97–1.00 across all classes, indicating strong robustness and generalization capability. This research contributes to the development of an automated diagnostic system capable of assisting farmers in identifying rice leaf diseases more quickly and effectively, while also supporting broader applications in smart agriculture. The findings underscore the potential of deep learning to enhance sustainable agricultural productivity through early detection and rapid decision-making support.
Forecasting Financial Sector Stock Price and Loss Risk Using the ARIMAX and Value-at-Risk Methods Amanda Aulia; Trimono Trimono; Kartika Maulida Hindrayani
bit-Tech Vol. 8 No. 2 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i2.3219

Abstract

Stock price volatility remains a persistent challenge in financial forecasting, as traditional ARIMA-based models often neglect the role of macroeconomic forces, leading to limited predictive robustness. Addressing this methodological gap, this study uniquely integrates the Autoregressive Integrated Moving Average with Exogenous Variables (ARIMAX) model and the Value-at-Risk (VaR) framework to simultaneously predict stock prices and quantify investment risk. This dual approach advances prior forecasting literature by merging predictive modeling and risk assessment within a single analytical structure. Using daily data from PT Bank Central Asia Tbk (BBCA) and the USD/IDR and SGD/IDR exchange rates from January 2019 to September 2024, model identification through ACF, PACF, and the Akaike Information Criterion (AIC) identifies ARIMAX(0,1,1) as optimal. The model achieves a Mean Absolute Percentage Error (MAPE) of 2.19%, indicating very high predictive accuracy. Although forecasted movements appear smoother than observed fluctuations, the model effectively captures short-term market trends influenced by exchange rate dynamics. Historical simulation at a 95% confidence level estimates a daily Value-at-Risk (VaR) of 1.71%, implying a potential loss of approximately Rp17,144 per Rp1,000,000 invested. These results demonstrate that integrating ARIMAX with VaR not only enhances statistical precision but also provides practical value for investors and policymakers. The combined framework enables evidence-based decision-making, portfolio optimization, and risk mitigation in volatile capital markets, offering a replicable and data-driven model for financial forecasting under macroeconomic uncertainty.
Rice Price Forecasting Using an Ensemble GRU–SVR Model with Enhanced Feature Engineering Dandi Nur Faizi; Trimono Trimono; Wahyu Syaifullah Jauharis Saputra
bit-Tech Vol. 8 No. 3 (2026): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i3.3532

Abstract

Rice price volatility significantly impacts economic stability and food security in Indonesia, particularly in East Java, where fluctuations in staple food prices affect household purchasing power and inflation management. This study addresses the limitations of existing rice price forecasting models, which often struggle to capture the complex, nonlinear dynamics of agricultural prices influenced by multiple factors such as climate variability and market conditions. Accurate and reliable price forecasting is essential to support effective policy formulation, market intervention, and food price stabilization strategies. This research develops an ensemble forecasting framework integrating Gated Recurrent Unit (GRU) and Support Vector Regression (SVR) with enhanced feature engineering to predict daily medium rice prices using historical price and weather data. The dataset comprises daily observations from 2021 to 2025, including rice prices, average temperature, relative humidity, rainfall, and sunshine duration. In this framework, GRU serves as a temporal feature extractor to learn complex temporal dependencies, while enhanced feature engineering generates complementary statistical features from sliding windows to enrich GRU's output. The combined feature set is provided to an SVR model with a Radial Basis Function kernel for final regression. Experimental results show that the proposed model achieves a high forecasting accuracy with an MAPE of 0.109%, demonstrating stable predictive behavior and making it a valuable tool for monitoring rice prices. The model's effectiveness in capturing temporal dependencies and nonlinear patterns suggests potential applicability beyond East Java, offering broader insights for agricultural price forecasting in other regions.
Co-Authors Amanda Aulia Dandi Nur Faizi Kartika Maulida Hindrayani Mohammad Idhom Rizal Harjo Utomo Wahyu Syaifullah Jauharis Saputra