• Title/Summary/Keyword: 회귀식 개선

Search Result 184, Processing Time 0.031 seconds

Improved Function Point Model for Software Size Estmation (소프트웨어 규모예측을 위한 기능점수모형의 개선)

  • An, Yeon-Sik
    • The Transactions of the Korea Information Processing Society
    • /
    • v.4 no.4
    • /
    • pp.993-1003
    • /
    • 1997
  • In this paper an improvement is made on the function point moedl,one of sortware size dstimation model,for better fesibility with increased accuracy as my proposed moedl.For better feasibility seven function typcs are proposed in this model and technical complexity factors are used to assecss the diffculties of considering technical and distributed enviroment attributes.To assess the creditability of the proposed model,24-software develop-ment cases were cinsidered in the regression model with the actual require efforts as the total function points. As seen in the statistical results,the proposed model is at least as superior to the known function point models.

  • PDF

Development of Rainfall-Flood Damage Estimation Function using Nonlinear Regression Equation (비선형 회귀식을 이용한 강우-홍수피해액 추정함수 개발)

  • Lee, Jongso;Eo, Gyu;Choi, Changhyun;Jung, Jaewon;Kim, Hungsoo
    • Journal of the Society of Disaster Information
    • /
    • v.12 no.1
    • /
    • pp.74-88
    • /
    • 2016
  • Predicting and estimating the disaster characteristics are very important for disaster planning such as prevention, preparedness, response, and recovery. Especially, if we can predict the flood damage before flooding, the predicted or estimated damage will be a very good information to the decision maker for the response and recovery. However, most of the researches, have been performed for calculating disaster damages only after disasters had already happened and there are few studies that are related to the prediction of the damages before disaster. Therefore, the objective of this study was to predict and estimate the flood damages rapidly considering the damage scale and effect before the flood disaster, For this the relationship of rainfall and damage had been suggested using nonlinear regression equation so that it is able to predict the damages according to rainfall. We compared the estimated damages and the actual ones. As a result, the damages were underestimated in 14.16% for Suwon-city and 15.81% for Yangpyeong-town but the damage was overestimated in 37.33% for Icheon-city. The underestimated and overestimated results could be occurred due to the uncertainties involved in natural phenomenon and no considerations of the 4 disaster steps such as prevention, preparedness, response, and recovery which were already performed.. Therefore, we may need the continuous study in this area for reducing various uncertainties and considering various factors related to disasters.

Improvement of Prediction Technique of the Ship′s Manoeuvrability at Initial Design Stage (초기 설계단계에서 선박조종성능 추정에 대한 정도향상 연구)

  • Ho-Young Lee;Sang-Sung Shin;Deuk-Joon Yum
    • Journal of the Society of Naval Architects of Korea
    • /
    • v.35 no.1
    • /
    • pp.46-53
    • /
    • 1998
  • In this paper, we studied to improve Inoue's[1] and Kijima's[2] model used to predict ship's manoeuvrability at initial design state. To perform this work, we carried out PMM(Planar motion Mechanism) test and rudder open water test for 12 models of low-speed blunt-ship which have horn type rudders and bulbs in afterbody. As we adopted MMG(Mathematical Modelling Group) model, we could analyze hydrodynamic and MMG experimental coefficients. The regression analyses by principle parameters were carried out for hydrodynamic and MMG experimental coefficients. The regression analyses by principle parameters were carried out for hydrodynamic and MMG experimental coefficients and the equations by regression analysis wee used to search sensitivities and to estimate ship's manoeuvrability. We had simulated ship's manoeuvrability to check revised MMG.

  • PDF

Estimation of Discharge Using Mean Velocity Equations (평균유속공식을 활용한 하천 유량 산정)

  • Choo, Tai-Ho;Koh, Deuk-Koo;Lee, Sang-Jin
    • Journal of Korea Water Resources Association
    • /
    • v.43 no.3
    • /
    • pp.265-273
    • /
    • 2010
  • This study proposed the method that can calculate discharge using hydraulic characteristics that can acquire easily-comparatively such as hydraulic radius, bed slope, depth to improve the stage-discharge curve equation considering only stage. Roughness coefficient n value and C value that hydraulic characteristics of rivers is reflected from Manning's equation and Chezy's equation using the measured data of the natural open channel in the report of Albert University estimated and calculated discharge on the basis of this. The method proposed in this study was calculated stunningly to measured discharge. And that compared with discharge by existent stage-discharge curve.

Development of suspended solid concentration measurement technique based on multi-spectral satellite imagery in Nakdong River using machine learning model (기계학습모형을 이용한 다분광 위성 영상 기반 낙동강 부유 물질 농도 계측 기법 개발)

  • Kwon, Siyoon;Seo, Il Won;Beak, Donghae
    • Journal of Korea Water Resources Association
    • /
    • v.54 no.2
    • /
    • pp.121-133
    • /
    • 2021
  • Suspended Solids (SS) generated in rivers are mainly introduced from non-point pollutants or appear naturally in the water body, and are an important water quality factor that may cause long-term water pollution by being deposited. However, the conventional method of measuring the concentration of suspended solids is labor-intensive, and it is difficult to obtain a vast amount of data via point measurement. Therefore, in this study, a model for measuring the concentration of suspended solids based on remote sensing in the Nakdong River was developed using Sentinel-2 data that provides high-resolution multi-spectral satellite images. The proposed model considers the spectral bands and band ratios of various wavelength bands using a machine learning model, Support Vector Regression (SVR), to overcome the limitation of the existing remote sensing-based regression equations. The optimal combination of variables was derived using the Recursive Feature Elimination (RFE) and weight coefficients for each variable of SVR. The results show that the 705nm band belonging to the red-edge wavelength band was estimated as the most important spectral band, and the proposed SVR model produced the most accurate measurement compared with the previous regression equations. By using the RFE, the SVR model developed in this study reduces the variable dependence compared to the existing regression equations based on the single spectral band or band ratio and provides more accurate prediction of spatial distribution of suspended solids concentration.

Trip Generation Model based on Geographically Weighted Regression (공간가중회귀분석을 이용한 통행발생모형)

  • Kim, Jin-Hui;Park, Il-Seop;Jeong, Jin-Hyeok
    • Journal of Korean Society of Transportation
    • /
    • v.29 no.2
    • /
    • pp.101-109
    • /
    • 2011
  • In most of the urbanized cities, socio-economic attributes tend to cluster as patterns of similarity in space, namely spatial autocorrelation, by agglomeration forces. The classical linear regression model, the most frequently adopted in the trip generation step, cannot sufficiently represent this effect. In order to take into account the effect properly, we need a model which adequately deals with the spatial dependence patterns. In this study, the Geographically Weighted Regression (GWR) model is adopted as an alternative method for the local analysis of relationships in multivariate data sets; that is GWR extends this traditional regression framework by estimating local rather than global parameters. This study shows the existence of spatial effects in the production and attraction of home base/non-home based trips through the GWR model using travel data collected in Daegu metropolitan area. Furthermore, LISA is employed to verify the fact that the local spatial autocorrelation exists.

Estimation of maximum measurable depth using hyperspectral image (초분광 영상을 활용한 최대추정가능수심 산정 기법 개발)

  • Seo, Youngcheol;Kim, Dongsu;You, Hojun;Kwon, Yeonghwa
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • 2022.05a
    • /
    • pp.444-444
    • /
    • 2022
  • 하천 수심 계측은 수심을 사람이 직접 계측하거나 초음파 기반 유속계 (ADCP) 등 최신 계측기기를 이용하여 간접적으로 계측을 실시하고 있다. 하지만 사람이 직접 하천에서 수심을 측정하는 것은 위험이 동반되고, 수심자료의 측정오차가 크게 발생한다. 따라서 수심측정에서 직접 측정 방식의 한계를 극복하기 위해, 초분광 영상의 반사도와 수심이 높은 상관관계를 보이는 것을 활용하여, 초분광 영상 기반 수심 산정 기법을 개발하였다. 초분광 영상 기반 수심 산정 기법은 복수의 파장이 존재하는 초분광영상으로부터 두 개의 파장대의 밴드를 추출하여 모든 경우의 수에 대해 밴드비를 산정한 후, 실측수심과 밴드비 간의 회귀분석을 실시하여 상관계수가 가장 높은 회귀식을 찾아내는 방식이 최적 밴드비 분석법에 기반한다. 최적 밴드비 분석법을 통해 획득된 높은 상관성의 밴드비-수심 관계식을 이용하여 수심을 추정할 수 있다. 이러한 방법은 직접 수심 측정 방식에 비해, 높은 해상도와 밀도, 양질의 데이터를 수집할 수 있는 장점이 있다. 과거 연구에 따르면 저수심부에서의 높은 정확도의 수심추정 결과를 보였지만, 고수심부에서는 실측수심과의 오차도 높아지는 등 정확성이 떨어지는 경향을 보인다. 따라서 본 연구에서는 보다 효율적인 수심계측을 할 수 있도록 최적 밴드비 분석법을 활용한 수심추정에서 신뢰성 있는 수심의 범위를 파악할 수 있는 방법을 제시하고자 한다. 본 연구에서는 대상지역으로 낙동강 본류와 황강 지류 합류부로 선정하였고, 초음파 기반 유속계(ADCP)와 드론을 활용하여 실측수심과 초분광 영상을 취득하였다. 민감도 분석을 위한 수심자료를 0.5m 단위로 분할하였으며, 구간별로 최적 밴드비 분석을 실시하였다. 그 결과, 구간별로 산정된 상관계수와 평균제곱근오차 (RMSE)를 통해 정확도가 높은 구간을 구별할 수 있었다. 또한 해당 구간을 초과하는 수심은 초분광 영상을 통해 추정이 어려운 것으로 판단되며, 분석한 구간까지를 최대 추정 가능 수심으로 정의하였다. 마지막으로 검증을 위해 최대추정가능수심으로 판단된 구간까지의 데이터만 활용하여 최적 밴드비 분석법을 적용하여 상관계수나 평균제곱근오차 결과의 개선여부 확인을 통해, 본 연구에서 제시한 방법이 정확한 최대추정가능수심 구간을 산정할 수 있는지 확인하였다.

  • PDF

An improved method of NDVI correction through pattern-response low-peak detection on time series (시계열 패턴 반응형 Low-peak 탐지 기법을 통한 NDVI 보정방법 개선)

  • Lee, Kyeong-Sang;Han, Kyung-Soo
    • Korean Journal of Remote Sensing
    • /
    • v.30 no.4
    • /
    • pp.505-510
    • /
    • 2014
  • Normalized Difference Vegetation Index (NDVI) is a major indicator for monitoring climate change and detecting vegetation coverage. In order to retrieve NDVI, it is preprocessed using cloud masking and atmospheric correction. However, the preprocessed NDVI still has abnormally low values known as noise which appears in the long-term time series due to rainfall, snow and incomplete cloud masking. An existing method of using polynomial regression has some problems such as overestimation and noise detectability. Thereby, this study suggests a simple method using amoving average approach for correcting NDVI noises using SPOT/VEGETATION S10 Product. The results of the moving average method were compared with those of the polynomial regression. The results showed that the moving average method is better than the former approach in correcting NDVI noise.

Study on the Prediction of short-term Algal Bloom in Juksan weir Using the Model Tree (모델트리를 활용한 죽산보 단기조류예측에 관한 연구)

  • Lee, Bo-Mi;Yi, Hye-Suk;Chong, Sun-A;Joo, Yong-Eun;Kim, Ho-Joon;Choi, Kwang-Soon
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • 2018.05a
    • /
    • pp.450-450
    • /
    • 2018
  • 최근 기후변화와 수온상승으로 인한 녹조발생이 빈번하게 나타나며, 녹조발생에 관한 관심은 꾸준히 증가하고 있는 추세이다. 본 연구는 효율적인 녹조관리를 위하여 모델트리를 활용하여 클로로필-a 단기조류예측 기법을 개발하였다. 대상지역으로 영산강수계의 죽산보를 선정하였으며, 2013년 1월부터 2016년 12월까지 나주 수질자동측정망의 일 단위자료와 동일기간 광주 기상청의 일별 기상자료를 이용하였다. 상관 분석을 통해 T-N, T-P, N/Pratio와 클로로필-a, 수온, 일사량, 강수량을 독립변수로, 단기(t+1일, t+3일, t+5일, t+7일) 클로로필-a를 종속변수로 선정하여 단기조류예측기법을 개발하였다. 수집한 자료의 데이터세트는 격일 간격으로 Training, Testing 기간으로 구분하여 적용한 결과, 상관계수는 1일 예측 시, Training 기간에 0.89, Testing 기간에 0.91, 3일 예측 시, Training 기간에 0.74, Testing 기간에 0.68, 5일 예측 시, Training 기간에 0.70, Testing 기간에 0.66, 7일 예측 시, Training 기간에 0.63, Testing 기간에 0.62로 나타났다. RMSE(Root Mean Square Error)는 1일 예측 시, Training 기간에 13.96, Testing 기간에 12.22, 3일 예측 시, Training 기간에 20.03, Testing 기간에 22.14, 5일 예측 시, Training 기간에 21.32, Testing 기간에 22.57, 7일 예측 시, Training 기간에 23.52, Testing 기간에 23.45로 나타났다. 예측주기에 따라 모델트리와 회귀식에서 활용한 독립변수는 1일 예측 시, 모델트리는 N/Pratio, 클로로필-a, 회귀식은 클로로필-a로 다르게 나타났다. 반면, 3일, 5일, 7일 예측 시, 모델트리와 회귀식에 활용된 변수는 같게 나타났다. 클로로필-a, 수온, 일사량은 5일 예측 시 활용된 변수로, 3일 예측 시에는 기상항목인 강수량이, 7일 예측 시에는 수질항목인 T-N, N/Pratio가 추가되었다. 특히 1일 예측 시 일 때, 높은 예측정도와 활용된 변수의 수가 적게 나타나는 것을 확인하였으며, 예측기간이 길어질수록 예측의 정확성이 낮아지고, 활용된 변수의 수가 많아지는 것을 확인하였다. 향후 적정한 예측기간을 판단하고 예측가능성을 높이기 위해서는 지속적인 자료취득 및 개선이 필요하며, 이를 바탕으로 적절한 단기조류예측이 가능할 것으로 판단된다.

  • PDF

Estimation of Nondestructive Strength Equations Based on the Results of In-situ Concrete Strength for Existing Bridges (국내 교량의 현장 코어강도를 활용한 개선된 비파괴강도 추정식 제안)

  • Kim, Hun-Kyom
    • Journal of the Korea institute for structural maintenance and inspection
    • /
    • v.22 no.2
    • /
    • pp.98-104
    • /
    • 2018
  • Nondestructive strength Equations are commonly used to determine the strength of concrete. However, the application of the existing equations may include many errors because this method is proposed on the basis of limited experimental parameters while actual bridges have various parameters such as conditions of concrete mixtures, properties of concrete strength, etc. Also, the error among the existing equations causes the confusion when engineers select the proper estimation equation for the concerned bridge. In this study, a series of the field inspection and the test have been performed on 297 existing bridges, in order to evaluate the bridges, based on the test results of the in-depth inspection, and the estimated strengths by means of the nondestructive strength equations are analyzed and compared with results of the core specimen strengths. According to results of analyses, the nondestructive strength equation proposed by CNDT Committee of Architectural Institute of Japan had high relationship with core strength. However, the strengths predicted by this equation, are underestimated when concrete's strengths are over 30 MPa, otherwise, they are overestimated. Also in this paper, based on the relationship between the estimated nondestructive concrete strengths and the core specimen strengths the modified strength equation through simple correlation analysis is proposed.