Article Per Year (5 Year)
p-Index From 2021 - 2026
0.659
P-Index
This Author published in this journals
All Journal Jurnal Informatika dan Teknik Elektro Terapan JIEET (Journal of Information Engineering and Educational Technology) bit-Tech
yisti vita via
Universitas Pembangunan Nasional "Veteran" Jawa Timur
Computer Science & IT Engineering

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

Found 2 Documents
Search
Journal : bit-Tech

 1 
Rapid Application Development Method for Web-Based Shallot Price Prediction Using Machine Learning Model Rafani Bardatus Salsabilah; Yisti Vita Via; Eva Yulia Puspaningrum
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.v8i2.3348

Abstract

Fluctuations in shallot prices in Indonesia create uncertainty within the agricultural supply chain and affect farmers, traders, and policymakers. This condition highlights the need for analytical mechanisms capable of accurately monitoring and predicting price dynamics. This study develops a web-based shallot price prediction system using the Rapid Application Development (RAD) method, with the best-performing model obtained from the training process being a combination of Long Short-Term Memory (LSTM) and CatBoost. The model is designed to process historical data along with non-sequential variables including price, production, rainfall, inflation, the Consumer Price Index (CPI), and seasonal indicators using a five-year dataset compiled from various official government sources. The trained model is integrated into a Flask-based backend to generate the next 7-day price forecasts. The system allows users to upload datasets, execute prediction processes, and analyze outputs through interactive charts and prediction tables. The evaluation shows that the model achieves strong performance, indicated by a MAPE of 6.71% and an RMSE of 0.029120, reflecting good accuracy and alignment with the seasonal patterns of shallot prices. Black-box testing confirms that all system functions operate as expected. The RAD method contributes to accelerating the development process through continuous iteration, resulting in a lightweight, responsive, and user-friendly system for non-technical users. Consequently, this system has the potential to serve as a decision-support tool for monitoring and anticipating shallot price dynamics at both regional and national levels.
Implementation of MobileNetV3-Large in Rhizome Classification M. Ryan Nurdiansyah N.A; Yisti Vita Via; Afina Lina Nurlaili
bit-Tech Vol. 8 No. 3 (2026): bit-Tech - IN PROGRESS
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i3.3365

Abstract

Rhizomes are widely used in Indonesia as cooking spices and herbal ingredients, yet their visual similarity often causes misidentification when recognition relies on manual inspection, leading to inconsistent product quality and economic losses. This study presents an automatic rhizome image classification system based on the MobileNetV3-Large architecture to distinguish eight Indonesian rhizome types (bangle, ginger, kencur, kunci, turmeric, galangal, temu ireng, and temulawak) from RGB images. The dataset is organised by class and processed with a pipeline that includes resizing to 224×224 pixels, image flipping and rotation, brightness adjustment, zoom, and normalisation, before being split into training, validation, and testing subsets with an 80:10:10 ratio. MobileNetV3-Large pretrained on ImageNet is used as a feature extractor with a three layer dense classification head and dropout regularisation, trained using the Adam optimiser with a learning rate of 0.0001 and a checkpoint mechanism to store the best validation model. The proposed model achieves 97.50% accuracy, 97.65% precision, 97.50% recall, and 97.51% f1-score on the test set, indicating stable and balanced performance across all rhizome classes despite their similarity. Compared with earlier rhizome classification approaches based on handcrafted features, which typically report lower accuracies on fewer classes, and with heavier VGG or ResNet backbones, this work provides, to the best of the authors’ knowledge, the first evaluation of MobileNetV3-Large for multi class rhizome classification and shows that it offers a practical and computationally efficient baseline for image based rhizome identification on resource constrained mobile or embedded devices.
Co-Authors Afina Lina Nurlaili Eva Yulia Puspaningrum Frisda Dita Isnaini M. Ryan Nurdiansyah N.A Mandyartha, Eka Prakarsa Rafani Bardatus Salsabilah Retno Mumpuni