Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Journal of Information Systems and Informatics
Annisa
IPB University
Computer Science & IT Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Classification of Pestalotiopsis sp. Leaf Fall Disease Severity in Rubber Plants using UAV Multispectral Vegetation Indices and 1-D Convolutional Neural Networks Solikin; Yeni Herdiyeni; Annisa; Lilik Budi Prasetyo; Tri Rapani Febbiyanti; Imas Sukaesih Sitanggang; Sri Nurdiati
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 3 (2026): June 2026
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i3.7601

Abstract

Leaf-fall disease caused by Pestalotiopsis sp. is a major threat to rubber (Hevea brasiliensis) plantations because it suppresses photosynthetic activity, accelerates defoliation, and reduces latex productivity. In operational practice, severity assessment is still dominated by visual field inspection, which is subjective, time-consuming, costly, and difficult to standardize across large plantation areas. This study develops a disease severity classification model for Pestalotiopsis sp. using a Convolutional Neural Network (CNN) based on vegetation-index features derived from UAV multispectral imagery. The model classifies disease severity into four levels: L1 (Light Infection), L2 (Moderate Infection), L3 (Severe Infection), and L4 (Very Severe Infection). To represent temporal and biological variability in disease expression, multispectral data were collected from multiple rubber clones over two observation periods. Feature construction focused on NDRE, LCI, CI, NDVI_NDRE_Interaction, and GCI_Ratio, which capture chlorophyll-related and canopy condition responses to infection. Because severity classes were imbalanced, the Synthetic Minority Over-sampling Technique (SMOTE) was applied before model training. A one-dimensional CNN was then trained to learn nonlinear patterns among index-based predictors for multilevel severity classification. Hyperparameter tuning improved overall accuracy from 85.30% to 90.00%. Class-wise F1-scores changed from 0.91 to 0.94 (L1), 0.83 to 0.84 (L2), 0.75 to 0.88 (L3), and 0.97 to 0.84 (L4), with the largest improvement in L3 recall (0.67 to 0.94). These results indicate that the selected vegetation indices and interaction terms are informative predictors for objective and scalable disease severity classification under heterogeneous plantation conditions.
Comparative Analysis of Similarity-Based Edge Construction Methods for Village Welfare Index Networks Abdullah Alhayad Arafah; Annisa; Sofyan Sjaf
Journal of Information System and Informatics Vol 8 No 4 (2026): August
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i4.1769

Abstract

This study compares three similarity-based edge construction methods for village welfare networks from household welfare attributes in Data Desa Presisi. Households are represented as nodes, while edges denote computational similarity between household welfare profiles rather than social relationships. Five Village Welfare Index dimensions were discretized and transformed into binary one-hot representations. Pairwise similarities were calculated using Cosine Similarity, Jaccard Index, and Pearson Correlation, followed by automatic thresholding to retain strong relationships. Network evaluation focused on the Largest Connected Component, while community structure was assessed using Louvain modularity across 14 villages. All methods produced analyzable networks, achieving a 100% success rate and 97.17% average node coverage. Jaccard achieved the highest mean modularity (0.5074) and win rate (71.43%; 10 of 14 villages). A Friedman test confirmed differences among methods (χ² = 8.71, p = 0.013). Holm-corrected Wilcoxon tests showed that Jaccard significantly outperformed Cosine and Pearson, whereas Cosine and Pearson did not differ significantly. These findings indicate that attribute-overlap-based edge construction provides most consistent representation of household welfare-profile proximity under the tested binary representation and automatic-thresholding scheme, while emphasizing that this advantage is context-dependent rather than universal.
Co-Authors Abdullah Alhayad Arafah LILIK BUDIPRASETYO Sitanggang, Imas S. Sofyan Sjaf Solikin Sri Nurdiati Tri Rapani Febbiyanti