Klasifikasi Kebakaran Hutan Menggunakan Feature Selection dengan Algoritma K-NN, Naive Bayes dan ID3

Ichwanul Muslim Karo Karo, Sisti Nadia Amalia, Dian Septiana


Forest fires are a problem with high incidence and recurrence intensity in Indonesia. If this problem is not handled properly, it will threaten the air circulation in the world. Sources of fire could be caused by natural or artificial factors. As a precautionary measure against the widespread spread of fire, it is necessary to investigate the type of fire early so that the type of fire with the highest priority can be immediately extinguished. The process of identifying the type of fire can be conducted by Classification. This study aims to classify hotspot types with three algorithms, that is K-Nearest Neighbor (K-NN), Naïve Bayes and Iterative Dichotomicer 3 (ID3). The forest fire dataset was retrieved from the Global Forest Watch (GFW) platform. Before entering the classification stage, the dataset goes through a feature selection process, where the attributes that satisfy the threshold are selected for the classification process. The performance of the ID3 algorithm is outperform than other algorithms with 65.83 percent for accuracy, 67.4 for precision, 67.02 for recall and 67.21 for F1. In addition, the feature selection process makes a positive contribution to the classification process, which can improve model performance by 2-5 percent.


K-NN; naive bayes; ID3; feature selection

Full Text:



M. Nasir, Atthariq, and M. Arhami, “Sistem Pendeteksi Dini Kebakaran Menggunakan Colour Image Processing dan Raspberry Pi,” Proceeding Seminar Nasional Politeknik Negeri Lhokseumawe, vol. 2, no. 1, 2018.

Setiawan.Agung, “Kebijakan Penanganan Kebakaran Hutan dan Lahan di Indonesia Agung Setiawan Government Affairs and Administration Jusuf Kalla School of Government,” political Ecology, no. May, 2018.

Saruni Dwiasnati and Yudo Devianto, “Classification of forest fire areas using machine learning algorithm,” World Journal of Advanced Engineering Technology and Sciences, vol. 3, no. 1, 2021, doi: 10.30574/wjaets.2021.3.1.0048.

T. A. Pratiwi, M. Irsyad, R. Kurniawan, S. Agustian, and B. S. Negara, “Klasifikasi Kebakaran Hutan Dan Lahan Menggunakan Algoritma Naïve Bayes Di Kabupaten Pelalawan,” CESS (Journal of Computer Engineering, System and Science), vol. 6, no. 1, 2021, doi: 10.24114/cess.v6i1.22555.

M. D. Molovtsev and I. S. Sineva, “Classification Algorithms Analysis in the Forest Fire Detection Problem,” 2019. doi: 10.1109/ITQMIS.2019.8928398.

I. M. K. Karo, “Implementasi Metode XGBoost dan Feature Importance untuk Klasifikasi pada Kebakaran Hutan dan Lahan,” Journal of Software Engineering, Information and Communication Technology, vol. 1, no. 1, pp. 10–16, 2020.

E. S. Rahayu, R. Satria, and C. Supriyanto, “Penerapan Metode Average Gain, Threshold Pruning dan Cost Complexity Pruning Untuk Split Atribut Pada Algoritma C4.5,” Journal of Intelligent Systems, vol. 1, no. 2, 2015.

I. M. K. Karo, A. Tsany, R. Dzaky, and M. A. Saputra, “Comparative Analysis of K-Nearest Neighbor and Modified K-Nearest Neighbor Algorithm for Financial Well-Being Data Classification,” Indonesia Journal on Computing (Indo-JC), vol. 6, no. 3, pp. 26–34, 2021, doi: 10.34818/indojc.2021.6.3.593.

I. M. K. Karo, A. Khosuri, and R. Setiawan, “Effects of Distance Measurement Methods in K-Nearest Neighbor Algorithm to Select Indonesia Smart Card Recipient,” 2021. doi: 10.1109/ICoDSA53588.2021.9617476.

I. M. K. Karo, M. Y. Fajari, N. U. Fadhilah, and W. Y. Wardani, “Benchmarking Naïve Bayes and ID3 Algorithm for Prediction Student Scholarship,” IOP Conference Series: Materials Science and Engineering, vol. 1232, no. 1, p. 012002, Mar. 2022, doi: 10.1088/1757-899X/1232/1/012002.

S. Zhang, “Challenges in KNN Classification,” IEEE Transactions on Knowledge and Data Engineering, 2021, doi: 10.1109/TKDE.2021.3049250.

I. M. K. Karo, R. Ramdhani, A. W. Ramadhelza, and B. Z. Aufa, “A Hybrid Classification Based on Machine Learning Classifiers to Predict Smart Indonesia Program,” 2020. doi: 10.1109/ICVEE50212.2020.9243195.

DOI: https://doi.org/10.17509/seict.v3i1.47537


  • There are currently no refbacks.

Copyright (c) 2022 Journal of Software Engineering, Information and Communication Technology (SEICT)

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Journal of Software Engineering, Information and Communicaton Technology (SEICT), 
2774-1699 | p-ISSN:2744-1656) published by Program Studi Rekayasa Perangkat Lunak, Kampus UPI di Cibiru.

 Indexed by.