Analisis Performa Gradient Boosting dalam Klasifikasi Kepadatan Gulma Berbasis Fitur Citra
Abstract
Klasifikasi kepadatan gulma merupakan aspek penting dalam mendukung pengelolaan pertanian presisi, namun variasi visual citra seperti pencahayaan, tekstur, dan tumpang tindih vegetasi sering menyebabkan ketidakstabilan hasil klasifikasi. Penelitian ini bertujuan untuk membandingkan kinerja beberapa algoritma machine learning dengan pendekatan Gradient Boosting pada klasifikasi kepadatan gulma berbasis citra. Metodologi penelitian meliputi preprocessing citra, ekstraksi fitur warna (HSV), tekstur (GLCM), dan bentuk (Hu Moments), serta seleksi fitur menggunakan Information Gain hingga diperoleh fitur optimal. Dataset yang digunakan berjumlah 2.097 citra yang terbagi dalam tiga kelas, yaitu renggang, sedang, dan padat. Model yang diuji meliputi Logistic Regression, Support Vector Machine, Decision Tree, dan Random Forest, baik sebagai model dasar maupun dalam kombinasi dengan Gradient Boosting. Hasil pengujian menunjukkan bahwa model dasar menghasilkan akurasi pada rentang 0,77–0,98, sedangkan integrasi Gradient Boosting mampu meningkatkan performa hingga mencapai akurasi tertinggi sebesar 0,9905. Peningkatan paling signifikan terjadi pada model dengan performa awal rendah, menunjukkan bahwa pendekatan boosting efektif dalam mengurangi bias dan meningkatkan kemampuan generalisasi model. Dengan demikian, Gradient Boosting terbukti mampu meningkatkan akurasi dan stabilitas klasifikasi kepadatan gulma pada data citra dengan kompleksitas tinggi. Kata kunci— citra gulma, Gradient Boosting, klasifikasi kepadatan gulma, machine learning, ekstraksi fitur
Downloads
References
[1] N. Y. Murad, T. Mahmood, A. R. M. Forkan, A. Morshed, P. P. Jayaraman, and M. S. Siddiqui, “Weed Detection Using Deep Learning: A Systematic Literature Review,” Apr. 01, 2023, MDPI. doi: 10.3390/s23073670.
[2] F. D. Adhinata, Wahyono, and R. Sumiharto, “A Comprehensive Survey on Weed And Crop Classification Using Machine learning And Deep Learning,” Artificial Intelligence in Agriculture, vol. 13, pp. 45–63, Sep. 2024, doi: 10.1016/j.aiia.2024.06.005.
[3] A. M. Mishra, M. P. Singh, P. Singh, M. Diwakar, I. Gupta, and A. Bijalwan, “Hybrid Deep Learning Model For Density And Growth Rate Estimation on Weed Image Dataset,” Sci. Rep., vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-86357-5.
[4] S. Dan et al., Pengembangan Pertanian Presisi. 2024. [Online]. Available: https://epublikasi.pertanian.go.id/pertanianpress
[5] G. F. Fitriana, Paradise, D. P. Rakhmadani, P. Widyasunu, Kholifahdina, and F. D. Adhinata, “Visual Feature Combination Based on Feature Selection for Weed Density Classification,” International Journal of Computing and Digital Systems, vol. 18, no. 1, 2025, doi: 10.12785/ijcds/1571111277.
[6] S. M. Jensen, M. J. Akhter, S. Azim, and J. Rasmussen, “The Predictive Power of Regression Models to Determine Grass Weed Infestations in Cereals Based on Drone Imagery—Statistical and Practical Aspects,” Agronomy, vol. 11, no. 11, Nov. 2021, doi: 10.3390/agronomy11112277.
[7] S. G C, C. Koparan, M. R. Ahmed, Y. Zhang, K. Howatt, and X. Sun, “A Study on Deep Learning Algorithm Performance on Weed And Crop Species Identification Under Different Image Background,” Artificial Intelligence in Agriculture, vol. 6, pp. 242–256, Jan. 2022, doi: 10.1016/j.aiia.2022.11.001.
[8] Z. Wu, Y. Chen, B. Zhao, X. Kang, and Y. Ding, “Review of Weed Detection Methods Based on Computer Vision,” Sensors, vol. 21, no. 11, Jun. 2021, doi: 10.3390/s21113647.
[9] F. Marpaung, F. Aulia, N. Suryani SKom, and R. Cyra Nabila SKom, Computer Vision dan Pengolahan Citra Digital. Pustaka Askara, 2022. [Online]. Available: www.pustakaaksara.co.id
[10] P. Hu et al., “Comparison of Conventional Logistic Regression and Machine learning Methods for Predicting Delayed Cerebral Ischemia After Aneurysmal Subarachnoid Hemorrhage: A Multicentric Observational Cohort Study,” Front. Aging Neurosci., vol. 14, Jun. 2022, doi: 10.3389/fnagi.2022.857521.
[11] Q. Li and J. Zhou, “A Comparative Analysis of Extreme Gradient Boosting, Decision Tree, Support Vector Machines, and Random Forest Algorithm in Data Analysis of College Students’ Psychological Health,” Informatica (Slovenia), vol. 49, no. 15, pp. 127–134, 2025, doi: 10.31449/inf.v49i15.7004.
[12] Z. Shao, M. N. Ahmad, and A. Javed, “Comparison of Random Forest and XGBoost Classifiers Using Integrated Optical and SAR Features for Mapping Urban Impervious Surface,” Remote Sens. (Basel)., vol. 16, no. 4, Feb. 2024, doi: 10.3390/rs16040665.
[13] T. Huang et al., “Comparing Algorithms for Estimation of Aboveground Biomass in Pinus yunnanensis,” Forests, vol. 14, no. 9, Sep. 2023, doi: 10.3390/f14091742.
[14] Q. T. Bui et al., “Gradient Boosting Machine and Object‐based CNN for Land Cover Classification,” Remote Sens. (Basel)., vol. 13, no. 14, Jul. 2021, doi: 10.3390/rs13142709.
[15] A. Lo Schiavo, W. Liu, A. Ramadan, K. El Khamlichi Drissi, C. Pasquier, and K. Tehrani, “An Analytical Investigation of Multi-Transmitter Dynamic Wireless Power Transfer for Electric Vehicles,” MDPI, 2025, doi: 10.3390/app152413131.
[16] X. Y. Liew, N. Hameed, and J. Clos, “An Investigation of XGBoost-based Algorithm for Breast Cancer Classification,” Machine learning with Applications, vol. 6, p. 100154, Dec. 2021, doi: 10.1016/j.mlwa.2021.100154.
[17] O. Alshboul, A. Shehadeh, G. Almasabha, and A. S. Almuflih, “Extreme Gradient Boosting-Based Machine learning Approach for Green Building Cost Prediction,” Sustainability (Switzerland), vol. 14, no. 11, Jun. 2022, doi: 10.3390/su14116651.
[18] R. Kursun and M. Koklu, Optimized Classification of Cotton Leaf Diseases Using Machine learning and Feature Selection Techniques. Çizgi Kitabevi Publishing, 2024.
[19] A. I. Adler and A. Painsky, “Feature Importance in Gradient Boosting Trees with Cross-Validation Feature Selection,” Entropy, vol. 24, no. 5, May 2022, doi: 10.3390/e24050687.
[20] B. S. Waluyo Poetro, Eny Maria, H. Zein, E. Najwaini, and D. H. Zulfikar, “Advancements in Agricultural Automation: SVM Classifier with Hu Moments for Vegetable Identification,” Indonesian Journal of Data and Science, vol. 5, no. 1, pp. 15–22, Mar. 2024, doi: 10.56705/ijodas.v5i1.123.
[21] A. Sanga and V. Zsófia, “Evaluation of Machine learning Algorithm’s Selection Criteria for Satellite Image Classification, Leveraging Accuracy and Execution times,” Egyptian Journal of Remote Sensing and Space Science, vol. 28, no. 3, pp. 534–541, Sep. 2025, doi: 10.1016/j.ejrs.2025.08.001.
