Model Optimasi KNN-PSORF dalam Menangani High Dimensional Data Banjir Kota Samarinda
DOI:
https://doi.org/10.32493/jtsi.v7i3.41587Kata Kunci:
Klasifikasi ; K-Nearest Neighbor; Seleksi fitur; Banjir; OptimasiAbstrak
Banjir adalah fenomena alam yang sering terjadi di Indonesia, termasuk di Kota Samarinda yang mengalami masalah banjir dalam tiga tahun terakhir dengan dampak ribuan rumah sebanyak 27.000 jiwa terkena banjir. Untuk memprediksi bencana banjir dibutuhkan teknologi machine learning menggunakan metode klasifikasi data mining. Namun, pada proses klasifikasi seringkali terjadi permasalahan yang berkaitan dengan data berdimensi tinggi ini dapat menyebabkan overfitting dan ketidakseimbangan kelas yang menyebabkan bias pada kelas yang dominan dengan mengabaikan kelas minoritas. Penelitian ini bertujuan untuk meningkatkan nilai akurasi klasifiikasi pada data banjir Kota Samarinda menggunakan algoritma K-Nearest Neighbor (KNN) yang dikombinasikan seleksi fitur Relief dan optimasi Particle Swarm Optimization (PSO). Metode validasi yang digunakan adalah 10-fold cross-validation, sementara evaluasi kinerja model dilakukan menggunakan confusion matrix. Data yang digunakan diperoleh dari BPBD dan BMKG Kota Samarinda pada rentang tahun 2021-2023, dengan 19 fitur dan total 1095 record. Hasil seleksi fitur Relief didapatkan empat fitur penting, yaitu arah angin maksimum, kecepatan angin, kecepatan angin rata-rata, dan arah angin maksimum. Evaluasi rata-rata dengan nilai k=3, k=5, k=7, k=11, k=13, dan k=15 menunjukkan penerapan seleksi fitur Relief dan optimasi PSO, efektif dalam meningkatkan akurasi pada algoritma k-Nearest Neighbor pada data banjir dengan hasil akurasi KNN dan PSO memberikan peningkatan sebesar 2-5%, KNN dengan seleksi fitur Relief memberikan peningkatan sebesar 1-2% dan KNN dengan kombinasi Relief dan PSO memberikan peningkatan sebesar 2-5%. Kombinasi model KNN, Relief, PSO diharapkan dapat memberikan peforma yang optimal dalam klasifikasi data banjir Kota Samarinda.
Referensi
Abdulrazaq, M. B., Mahmood, M. R., Zeebaree, S. R. M., Abdulwahab, M. H., Zebari, R. R., & Sallow, A. B. (2021). An Analytical Appraisal for Supervised Classifiers’ Performance on Facial Expression Recognition Based on Relief-F Feature Selection. Journal of Physics: Conference Series, 1804(1). https://doi.org/10.1088/1742-6596/1804/1/012055
Ariyoga, D. (2022). Perbandingan Metode Seleksi Fitur Filter, Wrapper, Dan Embedded Pada Klasifikasi Data Nirs Mangga Menggunakan Random Forest Dan Support Vector Machine .https://dspace.uii.ac.id/handle/123456789/38955
Arora, A., Arabameri, A., Pandey, M., Siddiqui, M. A., Shukla, U. K., Bui, D. T., Mishra, V. N., & Bhardwaj, A. (2021). Optimization of state-of-the-art fuzzy-metaheuristic ANFIS-based machine learning models for flood susceptibility prediction mapping in the Middle Ganga Plain, India. Science of the Total Environment, 750(August). https://doi.org/10.1016/j.scitotenv.2020.141565
Cumel, David Zamri, Rahmaddeni, S. (2022). Perbandingan Metode Data Mining untuk Prediksi Banjir Dengan Algoritma Naïve Bayes dan KNN. SENTIMAS: Seminar Nasional Penelitian Dan, 40–48. https://journal.irpi.or.id/index.php/sentimas/article/view/353%0Ahttps://journal.irpi.or.id/index.php/sentimas/article/download/353/132
Daniel, I., Hartono, H., & Situmorang, Z. (2023). Analysis of Machine Learning Algorithms in Predicting the Flood Status of Jakarta City. International Conference on Information Science and Technology Innovation (ICoSTEC), 2(1), 82–87. https://doi.org/10.35842/icostec.v2i1.42
Databoks. (2023). BNPB: Tren Banjir di Indonesia Cenderung Menurun dalam Tiga Tahun Terakhir. https://databoks.katadata.co.id/datapublish/2023/02/20/bnpb-tren-banjir-di-indonesia-cenderung-menurun-dalam-tiga-tahun-terakhir
Dwiasnati, S., & Yudo Devianto. (2022). Optimization of Flood Prediction using SVM Algorithm to determine Flood Prone Areas. Journal of Systems Engineering and Information Technology (JOSEIT), 1(2), 40–46. https://doi.org/10.29207/joseit.v1i2.1995
Ernawati, R., Dirdjo, M. M., & Wahyuni, M. (2021). Peningkatan Pengetahuan Siswa Terhadap Mitigasi Bencana di SD Muhammadiyah 4 Samarinda. Journal of Community Engagement in 4(2), 393–399. https://jceh.org/index.php/JCEH/article/view/258
Evitasari, Y. D., Pranoto, W. J., & Verdikha, N. A. (2023). Evaluasi Support Vector Machine Dengan Optimasi Metode Genetic Algorithm Pada Klasifikasi Banjir Kota Samarinda. Jurnal Sains Komputer Dan Teknologi Informasi, 6(1), 49–53. https://doi.org/10.33084/jsakti.v6i1.5462
Faldi, F., NurHalisha, T., Pranoto, W. J., & ... (2023). The application of particle swarm optimization (PSO) to improve the accuracy of the naive bayes algorithm in predicting floods in the city of Samarinda. Journal of Intelligent …, 6(3), 138–146. http://idss.iocspublisher.org/index.php/jidss/article/view/148%0Ahttps://idss.iocspublisher.org/index.php/jidss/article/download/148/99
Gauhar, N., Das, S., & Moury, K. S. (2021). Prediction of Flood in Bangladesh using k-Nearest Neighbors Algorithm. International Conference on Robotics, Electrical and Signal Processing Techniques, 357–361. https://doi.org/10.1109/ICREST51555.2021.9331199
Hossain, M. S., & Zeyad, M. (2023). Prediction of Flood in Bangladesh Using Different Classifier Model. AIUB Journal of Science and Engineering, 22(1), 45–52. https://doi.org/10.53799/ajse.v22i1.365
Intan, S., & Sari, P. (2023). Analisis Pengaruh Gain Ratio Untuk Algoritma K-Nearest Neighbor Pada Klasifikasi Data Banjir Di Kota Samarinda Analysis Of The Effect Of Gain Ratio For Algorithms K-Nearest Neighbor On Classsification Flood Data In Samarinda City. Jurnal Sains Komputer Dan, 6(1), 54–59. https://journal.umpr.ac.id/index.php/jsakti/article/view/5472%0Ahttps://journal.umpr.ac.id/index.php/jsakti/article/download/5472/3664
Kemal Musthafa Rajabi, Witanti, W., & Rezki Yuniarti. (2023). Penerapan Algoritma K-Nearest Neighbor (KNN) Dengan Fitur Relief-F Dalam Penentuan Status Stunting. INNOVATIVE: Journal Of Social Science Research, 3, 3555–3568.
Nabila, S. P., Ulinnuha, N., Yusuf, A., Informasi, S., Wonosari, J., & Timur, J. (2021). Model Prediksi Kelulusan Tepat Waktu Dengan Metode Fuzzy C-Means Dan K-Nearest Neighbors. 6(1), 39–47.
Nawi, N. M., Makhtar, M., Salikon, M. Z., & Afip, Z. A. (2020). A comparative analysis of classification techniques on predicting flood risk. Indonesian Journal of Electrical Engineering and Computer Science, 18(3), 1342–1350. https://doi.org/10.11591/ijeecs.v18.i3.pp1342-1350
Nursyahfitri, R., Rozikin, C., & Adam, R. I. (2022). Penerapan Metode SMOTE dalam Klasifikasi Daerah Rawan Banjir di Karawang Menggunakan Algoritma Naive Bayes. Jurnal Sistem Dan Teknologi Informasi (JustIN), 10(4), 339. https://doi.org/10.26418/justin.v10i4.46935
Priscillia, S., Schillaci, C., & Lipani, A. (2022). Arti fi cial Intelligence in Geosciences Flood susceptibility assessment using arti fi cial neural networks in Indonesia. Artificial Intelligence in Geosciences, 2(April), 215–222.
Purwanto, P. (2020). Analisis Sistem Pengendalian Banjir Sungai Pampang Daerah Aliran Hulu Sungai Karangmumus. Jurnal Kacapuri : Jurnal Keilmuan Teknik Sipil, 3(2), 44. https://doi.org/10.31602/jk.v3i2.4066
Razali, N., Ismail, S., & Mustapha, A. (2020). Machine learning approach for flood risks prediction. IAES International Journal of Artificial Intelligence, 9(1), 73–80. https://doi.org/10.11591/ijai.v9.i1.pp73-80
Tarasova, L., Merz, R., Kiss, A., Basso, S., Blöschl, G., Merz, B., Viglione, A., Plötner, S., Guse, B., Schumann, A., Fischer, S., Ahrens, B., Anwar, F., Bárdossy, A., Bühler, P., Haberlandt, U., Kreibich, H., Krug, A., Lun, D., Wietzke, L. (2019). Causative classification of river flood events. Wiley Interdisciplinary Reviews: Water, 6(4), 1–23. https://doi.org/10.1002/wat2.1353
Tarigan, P. M. S., Hardinata, J. T., Qurniawan, H., Safii, M., & Winanjaya, R. (2022). Implementasi Data Mining Menggunakan Algoritma Apriori Dalam Menentukan Persediaan Barang. Jurnal Janitra Informatika Dan Sistem Informasi, 2(1), 9–19. https://doi.org/10.25008/janitra.v2i1.142
Vafakhah, M., Mohammad Hasani Loor, S., Pourghasemi, H., & Katebikord, A. (2020). Comparing performance of random forest and adaptive neuro-fuzzy inference system data mining models for flood susceptibility mapping. Arabian Journal of Geosciences, 13(11), 1–16. https://doi.org/10.1007/s12517-020-05363-1
Yahdin, S., Desiani, A., Gofar, N., & Agustin, K. (2021). Application of the Relief-f Algorithm for Feature Selection in the Prediction of the Relevance Education Background with the Graduate Employment of the Universitas Sriwijaya. Computer Engineering and Applications Journal, 10(2), 71–80. https://doi.org/10.18495/comengapp.v10i2.369
Yoga Siswa, T. A. (2023). Data Mining: Mengupas Tuntas Analisis Data Dengan Metode Klasifikasi Hingga Deployment Aplikasi Menggunakan Python (T. A. Yoga Siswa (ed.)). UMKT PRESS.
Yusra, R. N., Sitompul, O. S., & Sawaluddin. (2021). Kombinasi K-Nearest Neighbor (KNN) dan Relief-F Untuk Meningkatkan Akurasi Pada Klasifikasi Data. InfoTekJar: Jurnal Nasional Informatika Dan Teknologi Jaringan, 1, 0–5.
Unduhan
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2024 Anggiq Karisma Aji Restu, Taghfirul Azhima Yoga Siswa, Wawan Joko Pranoto
Artikel ini berlisensi Creative Commons Attribution-NonCommercial 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
Jurnal Teknologi Sistem Informasi dan Aplikasi have CC BY-NC or an equivalent license as the optimal license for the publication, distribution, use, and reuse of scholarly work.
In developing strategy and setting priorities, Jurnal Teknologi Sistem Informasi dan Aplikasi recognize that free access is better than priced access, libre access is better than free access, and libre under CC BY-NC or the equivalent is better than libre under more restrictive open licenses. We should achieve what we can when we can. We should not delay achieving free in order to achieve libre, and we should not stop with free when we can achieve libre.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) License
YOU ARE FREE TO:
- Share - copy and redistribute the material in any medium or format
- Adapt - remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms
_2020_-_7(2)_2024_-_Thumbnail.png)
