Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Informatik : Jurnal Ilmu Komputer Journal of Computing Innovations and Emerging Technologies
Dyah Listianing Tyas
Universitas Prisma
Computer Science & IT

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

Found 3 Documents
Search

 1 
Forecasting Monthly Sales Using Single Exponential Smoothing: An Evaluation and Performance Analysis Dyah Listianing Tyas; Layth Charifi
Journal of Computing Innovations and Emerging Technologies Vol. 1 No. 1 (2025): Volume 1 No 1
Publisher : novamindpress

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64472/jciet.v1i1.3

Abstract

Micro, Small, and Medium Enterprises (MSMEs) have a strategic role in Indonesia's economy, contributing more than 60% to the Gross Domestic Product (GDP) and absorbing the majority of the national workforce. One of the MSME sectors that is growing rapidly is the food and beverage industry, including home cake shops. However, many MSME actors have not utilized scientific methods in business decision-making, especially in sales forecasting. In fact, accurate sales predictions are very important in managing production, raw material procurement, and operational efficiency. This study examines the performance of the Single Exponential Smoothing (SES) method compared to Holt's Linear Trend in predicting cake shop sales over the past two years. Based on the evaluation using MAE, RMSE, and MAPE, the SES model showed higher accuracy, with a MAPE value of 2.82%, lower than Holt's which reached 3.73%. These results indicate that a simple model like SES is better suited for sales data that does not have strong trends. These findings confirm that the selection of prediction models should consider the characteristics of the data, not just the complexity of the algorithms used.
Integration of Deep Learning for Optimization of Coconut Farming in North Sulawesi through Disease Detection Based on Hybrid CNN and LSTM Approaches Dyah Listianing Tyas; Andreuw Vandy Lengkong; Frendy Rocky Rumambi; Adrian Nicholas Lumowa
Informatik : Jurnal Ilmu Komputer Vol 22 No 1 (2026): April 2026
Publisher : Fakultas Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52958/iftk.v22i1.12362

Abstract

This research aims to develop a palm leaf disease detection system based on a Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) integrated into a mobile application. The CNN model is used to extract visual features from leaf images, while the BiLSTM serves to capture sequential dependencies, thereby improving classification accuracy. The implementation was carried out by connecting the model, which is served via a Flask API, and accessed by the mobile application using Ngrok as a tunneling service for testing. Test results show that the system is capable of detecting healthy leaf conditions with an accuracy rate of up to 99.7%, and provides descriptive information about the leaf's condition and preventive treatment recommendations. The integration of the model into a mobile application enables real-time plant health monitoring, making it an innovative solution to support farmers in increasing productivity and preventing losses due to disease outbreaks.
Explainable Deep Learning for Multi-Class Plant Disease Classification Using ResNet and EfficientNet with Grad-CAM Analysis Wahyuni Zalmi; Rahmi Putri Kurnia; Dyah Listianing Tyas
Informatik : Jurnal Ilmu Komputer Vol 22 No 2 (2026): August 2026
Publisher : Fakultas Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52958/iftk.v22i2.14396

Abstract

Plant diseases can reduce crop quality and productivity, making early detection an important aspect of modern agriculture. Recent advances in deep learning, particularly Convolutional Neural Networks (CNN), have shown promising performance in image-based plant disease classification. This study proposes an explainable deep learning approach for multi-class plant disease classification using ResNet50 and EfficientNetB0 combined with Grad-CAM visualization. The experiments were conducted using the PlantVillage dataset consisting of 15 classes of healthy and diseased plant leaves.The research process included image preprocessing, data augmentation, transfer learning, model training, performance evaluation, and explainability analysis. The dataset was divided into training and validation sets with a ratio of 80:20. Model performance was evaluated using accuracy, loss, confusion matrix, precision, recall, and f1-score metrics. Experimental results showed that ResNet50 achieved the best performance with an accuracy of 92% and a validation loss of 0.19, outperforming EfficientNetB0 which obtained 76% accuracy and 0.82 validation loss. The classification report demonstrated that ResNet50 provided more stable and consistent predictions across most disease classes. Furthermore, Grad-CAM visualization successfully highlighted disease-relevant regions such as lesions, discoloration, and damaged leaf areas, improving the interpretability of the CNN model. The findings indicate that the combination of ResNet50 and Grad-CAM is effective for plant disease classification and provides better explainability for deep learning-based agricultural applications.
Co-Authors Adrian Nicholas Lumowa Andreuw Vandy Lengkong Frendy Rocky Rumambi Layth Charifi Rahmi Putri Kurnia Wahyuni Zalmi