실선에 의한 표류 예측모델에 관한 연구
Study of estimated model of drift through real ship
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
표류 예측모델을 제시하기 위하여 표류시험을 수행하였으며, 이상치 및 영향점을 검증한 후 회귀분석을 하였다. DFFITS, Cook’s distance 분석결과, 표류속도의 경우 데이터 index 1, 27, 28, 72, 73, 74번째, 표류방향의 경우 index 2, 8, 68, 70, 71, 73, 74번째에서 회귀모형에 영향을 미치는 것으로 나타났다. 하지만, 회귀계수에 영향을 미치는 척도를 나타내는 DFBETAS 분석 결과, 표류속도에서는 index 1번째에서만 풍향의 DFBETAS 절대값이 임계값인 1을 초과하지만, 1에 가까우며 예측값에 대한 적합도에는 크게 영향이 미치지 않을 것으로 판단되어, 81개 샘플에 대해 다중회귀분석을 하는 데 크게 문제되지 않을 것으로 분석되었다. 예측 표류속도 및 표류방향의 예측값과 잔차의 분석 결과, 선형성과 독립성을 만족하였다. 독립변수의 다중 공선성은 10이하로 나타나 공선성이 전혀 없었으며, 잔차의 왜도 및 첨도에서도 임계값 이하로 나타났으며, omnibus 및 kolmogorv-smirnov 검정통계량도 만족하는 것으로 나타나 정규분포를 따른다고 할 수 있다. 다만, 잔차의 독립성을 나타내는 Durbin-Watson 검정통계량에서는 미흡한 점이 있지만, 양의 상관관계를 이루고 1에 가까우므로 큰 문제가 없다고 볼 수 있었다. 종속변수와 독립변수들 상관계수는 표류속도에서 유속이 0.49, 표류방향에서 유향이 0.81로 가장 높게 나타났다. 독립변수가 종속변수에 미치는 비율을 나타내는 표준회귀계수에서 표류속도는 유속이 47.1%, 표류방향에는 유향이 58.1%로 영향력이 가장 큰 변수로 나타났고, 도출한 다중회귀예측모델의 는 표류속도 69.3%, 표류방향 79.3%이며, 는 67.6%, 78.3%인 것으로 나타났다. 향후, 연구결과로 나타난 독립변수에 의한 표류속도/표류방향의 다중선형회귀모델을 추가적인 실험을 통하여 확인이 필요하다. 또한, 다양한 회귀모형을 적용하여 예측 정확도가 높은 모형 도출이 필요하다.
Abstract
In order to present a predictive drift model, Jeju National University's training ship was tested for about 11 hours and 40 minutes, and 81 samples that selected one of the entire samples at ten-minute intervals were subjected to regression analysis after verifying outliers and influence points. In the outlier and influence point analysis, although there is a part where the wind direction exceeds 1 in the DFBETAS (difference in Betas) value, the CV (cumulative variable) value is 6%, close to 1. Therefore, it was judged that there would be no problem in conducting multiple regression analyses on samples. The standard regression coefficient showed how much current and wind affect the dependent variable. It showed that current speed and direction were the most important variables for drift speed and direction, with values of 47.1% and 58.1%, respectively. The analysis showed that the statistical values indicated the fit of the model at the significance level of 0.05 for multiple regression analysis. The multiple correlation coefficients indicating the degree of influence on the dependent variable were 83.2% and 89.0%, respectively. The determination of coefficients were 69.3% and 79.3%, and the adjusted determination of coefficients were 67.6% and 78.3%, respectively. In this study, a more quantitative prediction model will be presented because it is performed after identifying outliers and influence points of sample data before multiple regression analysis. Therefore, many studies will be active in the future by combining them.
참고문헌 (25)
- Ahn BJ, "Outlier detection using dynamic plots", The Korean Journal of Applied Statistics, 24, pp.979~986 (2011)[DOI]
- Ahn JY, "Estimation of drift force by real ship using multiple regression analysis", J Korean Soc Fish Ocean Technol, 57, pp.236~245 (2021)[DOI]
- Field experiments and Implementation. U.S coast guard research and development center 1082 shennecosstt road groton, "Allen AA", 1~351, pp.CT 06340-6096 (1999)
- Barrick D, "A short-term predictive system for surface currents from a rapidly deployed coastal HF radar network", Ocean Dynam, 62, pp.725~740 (2012)[DOI]
- Breivik Ø, "An operational search and rescue model for the Norwegian sea and the north sea", Journal of marine systems, 69, pp.99~113 (2008)[DOI]
- Breivik Ø, "Wind-induced drift of objects at sea : the leeway field method", Appl Ocean Res, 33, pp.100~109 (2011)[DOI]
- Breivik Ø, "Advances in search and rescue at sea", Ocean dynam, 63, pp.83~88 (2013)[DOI]
- Chang IS, "A study on the effective safety management measures for the prevention of marine accidents", Journal of the Korean Society of Marine Environment and Safety, 15, pp.33~39 (2009)
- Chapline WE, "Estimating the drift of distressed small craft", Coast Guard Alumni Association Bulletin, pp.39~42 (1960), U.S. Coast Guard Academy
- Choe CW, "Identifying risk factors of marine accidents in coastal area by marine accident types", J Korean Soc Transp, 39, pp.540~554 (2021)[DOI]
- Draper NR, "Applied regression analysis", pp.47~50 (1981), John Wiley New York
- Hoaglin DC, "The hat matrix in regression and ANOVA", American Statistician, 32, pp.17~22 (1978)
- Hocking RR, "Method and applications of linear modes : Regression and linear models", pp.182~201 (2013), John Wiley & Sons, Inc
- Hufford GL, "Determination of small craft leeway", Department of transportation United Stated coast guard, office of research and development, 1~36 (1974)
- Kang YS, "Modelling of drift prediction in search and rescue", Bull Res Inst Mar Sci & Tech, 2, pp.47~54 (1993), Korea maritime university
- Kang SY, "Field experiment and analysis of drift characteristics of small vessels in the coastal region off busan port", Journal of Korean Navigation and Port Research, 26, pp.221~226 (2002)[DOI]
- Kline RB, "Principles and practice of structural equation modelling", pp.59~63 (2011), The Guilford Press
- Kutner MH, "Applied linear statistical models", pp.214~488 (2005), McGraw-Hill companies
- Lee CH, "Estimation of leeway of jigging fishing vessels by external factors", J Korean Soc Fish Ocean Technol, 58, pp.299~309 (2022)[DOI]
- Mim SY, "Development and validation of multiple regression models for the prediction of effluent concentration in a sewage treatment process", J Korean Soc Environmental Engineers, 34, pp.312~315 (2012)[DOI]
- Ni Z, "On predicting boat drift for search and rescue", Ocean Engineering, 37, pp.1169~1179 (2010)[DOI]
- Nowy A, "Use of multiple regression model to determine the parameters of vessel traffic flow in port areas", The International Journal on Marine Navigation and Safety sea transportation, 14, pp.443~449 (2020)[DOI]
- Sakamoto Y, "On the study of a ship's motion and her drifting", Bulletin of the faculty of fisheries, 25, pp.326~331 (1975), Hokkado university
- Seo HS, "Regression diagnostics for response transformation in a partial linear model", Journal of the Korean Data and Information Science Society, 24, pp.33~39 (2013)[DOI]
- Suzuki T, "Measurement of the drifting of a fishing boat or research vessel due to wind and wave", The Journal of Japan's Institute of Navigation, 57, pp.71~76 (1977)