데이터 수준 접근방식을 이용한 제주국제공항의 강한 저층 윈드시어 분류
Classification of Severe Low Level Wind Shear of Jeju International Airport using Data-Level Approach
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Low Level Wind Shear (LLWS) is a sudden change in wind speed and wind direction below 2,000 feet above the ground, which can cause economic and personal damages. In Korea, wind shear occurs most frequently at Jeju International Airport due to the favorable topographical influences, such as the coast and Mt. Hallasan. In this study, we deal with the severe LLWS binary classification based on the LLWS data occurred in winter 2016-18 near Jeju International Airport, derived from a Limited area ENsemble prediction System (LENS). Severe LLWS is a rare event and creates a data imbalance issue and class overlap, resulting in a high misclassification rate of classification models. To solve this problem, we used sampling techniques as follows: SMOTE (Synthetic Minority Oversampling Technique), ENN (Edited Nearest Neighbor), NCR (Neighborhood Cleaning Rule). In addition, we applied a hybrid technique that combines modified ENN and STMOE, and compared the performances by learning classification models. As a result, ENN, NCR and hybrid sampling provided improved classification performance compared to the raw ensembles in terms of recall and F1-score.
Abstract
Low Level Wind Shear (LLWS) is a sudden change in wind speed and wind direction below 2,000 feet above the ground, which can cause economic and personal damages. In Korea, wind shear occurs most frequently at Jeju International Airport due to the favorable topographical influences, such as the coast and Mt. Hallasan. In this study, we deal with the severe LLWS binary classification based on the LLWS data occurred in winter 2016-18 near Jeju International Airport, derived from a Limited area ENsemble prediction System (LENS). Severe LLWS is a rare event and creates a data imbalance issue and class overlap, resulting in a high misclassification rate of classification models. To solve this problem, we used sampling techniques as follows: SMOTE (Synthetic Minority Oversampling Technique), ENN (Edited Nearest Neighbor), NCR (Neighborhood Cleaning Rule). In addition, we applied a hybrid technique that combines modified ENN and STMOE, and compared the performances by learning classification models. As a result, ENN, NCR and hybrid sampling provided improved classification performance compared to the raw ensembles in terms of recall and F1-score.
참고문헌 (14)
- Borsos, Z, "Dealing with overlap and imbalance: a new metric and approach", Pattern Analysis and Applications, 21(2), pp.381~395 (2018)
- Chawla, N. V, "SMOTE: synthetic minority over-sampling technique", Journal of artificial intelligence research, 16, pp.321~357 (2002)
- 조진호, "항공기 복행사례를 통한 제주국제공항 저층 윈드시어의 특징 연구", 한국항공운항학회지, 29(1), pp.1~8 (2021), 한국항공운항학회[DOI]
- Choi, H. W, "Probabilistic forecast of Low Level Wind Shear of Gimpo, Gimhae, Incheon and Jeju International Airports using ensemble model output statistics", Atmosphere, 12(12), pp.1643~ (2021)
- Chujai, P, "Ensemble learning for imbalanced data classification problem", Proceedings of the 3rd International Conference on Industrial Application Engineering (2015)
- Hong, K. D, "A Study on the Low Level Wind Shear around Jeju International Airport", Master, Department of Marine Production, pp.2006
- 정미애, "불균형데이터의 비용민감학습을 통한 국방분야 이미지 분류 성능 향상에 관한 연구", 한국군사과학기술학회지, 24(3), pp.281~292 (2021), 한국군사과학기술학회
- Laurikkala, J, "Improving identification of difficult small classes by balancing class distribution", Conference on artificial intelligence in medicine in Europe, pp.63~66 (2001)
- Lee, Y. G, "Probabilistic forecast of Low-Level Wind Shear over Jeju International Airport using non-homogeneous regression model", The International Journal of Electrical Engineering & Education (2021)
- Lee, Y. G, "Inter-comparison of ensemble forecasts for Low Level Wind Shear against local analyses data over Jeju area", Atmosphere, 11(2), pp.198~ (2020)
- 민병훈, "고해상도 KMAPP 자료를 활용한 제주국제공항에서 저층 윈드시어 예측", 대기, 30(3), pp.277~291 (2020), 한국기상학회[DOI]
- Song, J, "An improved adaboost algorithm for unbalanced classification data", Sixth International Conference on Fuzzy Systems and Knowledge Discovery (2009)
- Vuttipittayamongkol, P, "On the class overlap problem in imbalanced data classification", Knowledge-Based Systems, 212, pp.106631~ (2021)
- Wilson, D. L, "Asymptotic properties of nearest neighbor rules using edited data", IEEE Transactions on Systems, Man, and Cybernetics, 2(3), pp.408~421 (1972)