Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)

Indonesian Crude Oil Price (ICP) Prediction Using Support Vector Regression Algorithm Des Suryani; Fadhila, Mutia
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 8 No 1 (2024): February 2024
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v8i1.5551

Abstract

Indonesian crude oil prices (ICP) experience fluctuating movements, influenced by several factors and other conditions that make ICP prices difficult to predict. ICP price prediction can be done with the Support Vector Regression (SVR) method. The information utilized originates from the Ministry of Energy and Mineral Resources' official website, specifically focusing on crude oil pricing data for six primary types of crude oil: SLC, Attaka, Duri, Belida, Banyu and SC. The data applied covers the time frame from January 2018 to August 2023. The forecast of the ICP relies on the date Brent variable and the Alpha factor through the use of support vector regression (SVR. In the case of a linear kernel, the parameters (epsilon) and C (cost) are determined using the Grid Search algorithm. In the Dated-Brent variable, the best parameter value is obtained with the value of C = 100 and  = 1 while for the Alpha variable, the best parameter value for the SLC crude oil type is C= 0.01 and  = 0.01, SC value C = 10 and  = 1, Banyu value C = 100 and  = 0.1, Banyu value C = 100 and  = 0.1, Belida value C = 0.01 and  = 0.1, Attaka value C = 0.1 and  = 0.01 and Duri value C = 1 and  = 1. The Alpha value of the main crude oil type is the Duri crude oil type with the lowest RMSE value of 0.9651. The MAPE value for SC crude oil type = 19.55% and Duri = 19.46% is in the good category. The R2 value for Banyu crude oil = 0.60610, SC = 0.42717 and Duri = 0.50421 is in the good category and the MAPE value for Dated-Brent of 49.73% is included in the fair category.
Android Application for Tomato Leaf Disease Prediction Based on MobileNet Fine-tuning Mutia Fadhilla; Des Suryani
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 7 No 6 (2023): December 2023
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v7i6.5132

Abstract

Tomato is one of the most well-known and widely cultivated plants in the world. The result of tomato production is affected by the conditions of the plants when they are grown. It may decrease due to leaf plant disease caused by climate change, pollinator decrease, microbial pets, or parasites. To prevent this, an image-based application is needed to identify tomato plant disease based on visually unique patterns or marks seen on leaves. In this paper, we proposed a CNN fine-tuned model based on MobileNet architectures to identify tomato leaf disease for mobile applications. Based on the results tested by K-fold cross-validation, the best accuracy achieved by the proposed model is 97.1%. Additionally, the best average precision, recall and F1 Score are 99.8%, 99.8%, and 99.5%, respectively. The model with the best results is also implemented into Android-based mobile applications.