http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
DNN과 2차 데이터를 이용한 PM10 예보 성능 개선
유숙현,전영태 한국멀티미디어학회 2019 멀티미디어학회논문지 Vol.22 No.10
In this study, we propose a new PM10 forecasting model for Seoul region using DNN(Deep Neural Network) and secondary data. The previous numerical and Julian forecast model have been developed using primary data such as weather and air quality measurements. These models give excellent results for accuracy and false alarms, but POD is not good for the daily life usage. To solve this problem, we develop four secondary factors composed with primary data, which reflect the correlations between primary factors and high PM10 concentrations. The proposed 4 models are A(Anomaly), BT(Back trajectory), CB(Contribution), CS(Cosine similarity), and ALL(model using all 4 secondary data). Among them, model ALL shows the best performance in all indicators, especially the PODs are improved.
PM<sub>10</sub> 예보 향상을 위한 민감도 분석에 의한 역모델 파라메터 추정
유숙현,구윤서,권희용,Yu, Suk Hyun,Koo, Youn Seo,Kwon, Hee Yong 한국멀티미디어학회 2015 멀티미디어학회논문지 Vol.18 No.7
In this paper, we conduct sensitivity analysis of parameters used for inverse modeling in order to estimate the PM<sub>10</sub> emissions from the 16 areas in East Asia accurately. Parameters used in sensitivity analysis are R, the observational error covariance matrix, and B, a priori (background) error covariance matrix. In previous studies, it was used with the predetermined parameter empirically. Such a method, however, has difficulties in estimating an accurate emissions. Therefore, an automatically determining method for the most suitable value of R and B with an error measurement criteria and posteriori emissions accuracy is required. We determined the parameters through a sensitivity analysis, and improved the accuracy of posteriori emissions estimation. Inverse modeling methods used in the emissions estimation are pseudo inverse, NNLS (Nonnegative Least Square), and BA(Bayesian Approach). Pseudo inverse has a small error, but has negative values of emissions. In order to resolve the problem, NNLS is used. It has a unrealistic emissions, too. The problems are resolved with BA(Bayesian Approach). We showed the effectiveness and the accuracy of three methods through case studies.
Air Pollutants Tracing Model using Perceptron Neural Network and Non-negative Least Square
유숙현,권희용 한국멀티미디어학회 2013 멀티미디어학회논문지 Vol.16 No.12
In this paper, air pollutant tracing models using perceptron neural network(PNN) and non-negative least square(NNLS) are proposed. When the measured values of the air pollution and the contribution concentration of each source by chemical transport modeling are given, they estimate and trace the amount of the air pollutants emission from each source. Two kinds of emissions data are used in the experiments : CH4 and N2O of Geumgo-dong landfill greenhouse gas, and PM10 of 17 areas in Northeast Asia and eight regions of the Korean Peninsula. Emission values were calculated using pseudo inverse method, PNN and NNLS. Pseudo inverse method could be used for the model, but it may have negative emission values. In order to deal with the problem, we used the PNN and NNLS methods. As a result, the estimation using the NNLS is closer to the measured values than that using PNN. The proposed tracing models have better utilization and generalization than those of conventional pseudo inverse model. It could be used more efficiently for air quality management and air pollution reduction.
K-mean 군집화 알고리즘과 Non-negative Least Square를 이용한 악취분류와 악취원분석
유숙현 한국냄새환경학회 2013 실내환경 및 냄새 학회지 Vol.12 No.4
효율적인 악취관리를 위해서는 민원지역에서 발생한 악취를 분류하고, 그 악취원을 분 석해야 한다. 이를 위해서는 민원지역에서 발생한 악취를 나타낼 수 있는 악취대표패턴과 악취원의 냄새가 필요하다. 이에 본 논문에서는 민원지역의 악취분류를 위해 k-mean 알고리즘을 이용하여 악취데이 터에 대한 군집화를 수행하였다. 그 결과 생성된 악취대표패턴과 미리 측정된 악취원별 냄새와의 유사도를 비교하여 악취에 대한 분류를 수행하였다. 또한, 대기 중에서 여러 악 취가 섞였을 경우를 고려하여 non-negative least square를 이용하여 해당 악취에 대해 책임 이 있는 하나 이상의 악취원과 기여도를 추적하였다. 이러한 본 연구의 성과는 악취 관련 민원해결에 기여할 것으로 사료된다. For effective odor management, the odor in complaint area should be classified and analyzed according to the source. It is thus necessary to generate representative patterns for the odors and to identify odor sources. K-mean clustering algorithm in this study was applied to the odor data in order that classify characteristic of odor. Classification has been performed with similarities which have relationship between odor representative patterns as a result of k-mean and odor sources that are measured previously. By, considering the mixed atmospheric various odors, more than one odor sources causing the complaints and their contribution were also, traced using non-negative least square. The results will be useful for settling the civil complaint related with an odor.