Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Journal of Information Systems and Informatics
Ahmad Yusuf
Politeknik Negeri Banjarmasin
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
A Lightweight Classical Machine Learning Pipeline for Rice NPK Deficiency Classification Using Hand-Crafted Feature Fusion Dhiyaussalam; Kun Nursyaiful Priyo Pamungkas; Wanvy Arifha Saputra; Ahmad Yusuf
Journal of Information System and Informatics Vol 8 No 2 (2026): April
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i2.1486

Abstract

Many high-accuracy deep learning solutions for plant nutrient deficiency remain impractical in resource-limited settings due to computational cost and limited explainability. This study proposes a lightweight classical machine learning pipeline for rice leaf NPK (nitrogen, phosphorus, potassium) deficiency classification on the publicly available Kaggle Nutrient-Deficiency-Symptoms-in-Rice dataset (1,156 images); all results should be interpreted in this dataset context rather than as field-validated performance. The pipeline applies HSV-based leaf segmentation to reduce background influence. It extracts a 126-dimensional feature set combining masked color moments, HSV histograms, vegetation indices, LBP and GLCM texture descriptors, and spatial symptom ratios. Hyperparameters are tuned via RandomizedSearchCV with 5-fold StratifiedKFold and macro-F1 scoring; final evaluation uses a held-out 80/20 stratified test set kept separate throughout tuning. XGBoost achieves the best test performance (accuracy 0.9267; macro-F1 0.9233), followed by SVM-RBF (0.9224; 0.9187) and Random Forest. Feature importance analysis confirms that color moments dominate class separability, with texture and spatial features providing complementary support. The dominant remaining error is phosphorus–potassium confusion. The novelty lies in integrating leaf-focused preprocessing with a structured, low-cost feature representation suitable for mobile or edge deployment.
Co-Authors Dhiyaussalam Kun Nursyaiful Priyo Pamungkas Wanvy Arifha Saputra