Korean Journal of Artificial Intelligence (한국인공지능학회지)

Korea Artificial Intelligence Association (한국인공지능학회)
권호 표지
DOI QR코드

DOI QR Code

A study on Natural Disaster Prediction Using Multi-Class Decision Forest

  • Received : 2022.04.25
  • Accepted : 2022.05.15
  • Published : 2022.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, a study was conducted to predict natural disasters in Afghanistan based on machine learning. Natural disasters need to be prepared not only in Korea but also in other vulnerable countries. Every year in Afghanistan, natural disasters(snow, earthquake, drought, flood) cause property and casualties. We decided to conduct research on this phenomenon because we thought that the damage would be small if we were to prepare for it. The Azure Machine Learning Studio used in the study has the advantage of being more visible and easier to use than other Machine Learning tools. Decision Forest is a model for classifying into decision tree types. Decision forest enables intuitive analysis as a model that is easy to analyze results and presents key variables and separation criteria. Also, since it is a nonparametric model, it is free to assume (normality, independence, equal dispersion) required by the statistical model. Finally, linear/non-linear relationships can be searched considering interactions between variables. Therefore, the study used decision forest. The study found that overall accuracy was 89 percent and average accuracy was 97 percent. Although the results of the experiment showed a little high accuracy, items with low natural disaster frequency were less accurate due to lack of learning. By learning and complementing more data, overall accuracy can be improved, and damage can be reduced by predicting natural disasters.

Keywords

References

  1. Afghanistan (2022). Retrieved April 26, 2022, from https://ko.wikipedia.org/wiki/%EC%95%84%ED%94%84%EA%B0%80%EB%8B%88%EC%8A%A4%ED%83%84
  2. An, S. H., Yeo S. H., & Kang, M. S. (2021). A Study on a car Insurance purchase Prediction Using Two-Class Logistic Regression and Two-Class Boosted Decision Tree, Korea Journal of Artificial Intelligence, 9(1), 9-14. https://doi.org/10.24225/KJAI.2021.9.1.9
  3. Choi, B. J., Park, C. W., Cho, Y. H., Kim, D. S., & Lee, K. W. (2020). A Proposal of New Breaker Index Formula Using Supervised Machine Learning. Korean Society of Coastal and Ocean Engineers, 32(6), 384-395. https://doi.org/10.9765/KSCOE.2020.32.6.384
  4. Choi, E. S., Yoo, H. J., Kang, M. S., & Kim, S. A. (2019). Applying Artificial Intelligence for Diagnostic Classification of Korean Autism Spectrum Disorder. Korean Neuropsychiatric Association, 17(11), 1090-1095.
  5. Choi, S. A. (2010). Natural Disaster Damage Cost Prediction Model based on Neural Network and Genetic Algorithm, Proceedings of the Korean Information Science Society Conference, 37(1), 380-384.
  6. data world (2020). afghanistan-natural-disaster-incidents-from-january-to-september. Retrieved April 26, 2020, from https://data.humdata.org/dataset/afghanistan-natural-disaster-incidents-in-2020
  7. Han, S. H., & Yang, K. C. (2007). Investigation of Standardization for Natural Disaster Classification, The Journal of the Korea Contents Association, 7(11), 309-319. https://doi.org/10.5392/JKCA.2007.7.11.309
  8. Jeong, Y. C., Ryu, H. Y., Lee, S. J., Seo, D. J., & Park, C. G. (2021). Identification recidivism risk factors study based on machine learning: Using decision tree analysis and random forest algorithm, Korean Police Studies Association, 20(1), 323-350. https://doi.org/10.38084/2021.20.1.14
  9. Kang, M. S., Kang, H. J., Yoo, K. B., Ihm, C. H., & Choi., E. S. (2018). Getting started Machine Learning with Microsoft AZURE ML. Seoul, Korea: Hanti Media.
  10. Kim, J. Y. (2017). AlphaGo Case Study: On the Social Nature of Artificial Intelligence, Journal of Science and Technology Studies, 17(1), 5-39.
  11. Kwak, Y. S., Kang M.S. (2020). A Study on Methods to Prevent the Spread of COVID-19 Based on Machine Learning, Korea Journal of Artificial Intelligence, 8(1), 7-9. https://doi.org/10.24225/KJAI.2020.8.1.7
  12. Microsoft Azure Machine Learning (2020). Retrieved April 20, 2020, from https://docs.microsoft.com/ko-kr/azure/machinelearning/studio/what-is-ml-studio
  13. Nam, Y. J., & Shin, W. J. (2019). A Study on Comparison of Lung Cancer Prediction Using Ensemble Machine Learning, Korea Journal of Artificial Intelligence, 7(2), 19-24. https://doi.org/10.24225/KJAI.2019.7.2.19
  14. Yun, J. M., Song, Y. S., Bak, G. J., & You, S. k. (2017). Prediction of Landslide Probability around Railway using Decision Tree Model, Journal of the Korean Geosynthetics Society. 16(4), 129-137. https://doi.org/10.12814/JKGSS.2017.16.4.129