scholarly journals Regionalisation of flood frequencies based on flood type-specific mixture distributions

2021 ◽  
pp. 100107
Author(s):  
Svenja Fischer ◽  
Andreas H. Schumann
Keyword(s):  
Mixture Distributions

scholarly journals Initializing the EM Algorithm for Univariate Gaussian, Multi-Component, Heteroscedastic Mixture Models by Dynamic Programming Partitions

2018 ◽  
Vol 15 (03) ◽  
pp. 1850012 ◽  
Author(s):  
Andrzej Polanski ◽  
Michal Marczyk ◽  
Monika Pietrowska ◽  
Piotr Widlak ◽  
Joanna Polanska
Keyword(s):  
Dynamic Programming ◽  
Mixture Models ◽  
Recursive Algorithm ◽  
Dynamic Programming Method ◽  
Mixture Distributions ◽  
Gaussian Mixtures ◽  
Scoring Functions ◽  
Initial Values ◽  
The Em Algorithm

Setting initial values of parameters of mixture distributions estimated by using the EM recursive algorithm is very important to the overall quality of estimation. None of the existing methods are suitable for heteroscedastic mixtures with a large number of components. We present relevant novel methodology of estimating the initial values of parameters of univariate, heteroscedastic Gaussian mixtures, on the basis of dynamic programming partitioning of the range of observations into bins. We evaluate variants of the dynamic programming method corresponding to different scoring functions for partitioning. We demonstrate the superior efficiency of the proposed method compared to existing techniques for both simulated and real datasets.

Identifying spatial mixture distributions of PM2.5 and PM10 in Taiwan during and after a dust storm

2012 ◽  
Vol 54 ◽  
pp. 728-737 ◽  
Author(s):  
Hone-Jay Chu ◽  
Hwa-Lung Yu ◽  
Yi-Ming Kuo
Keyword(s):  
Dust Storm ◽  
Mixture Distributions ◽  
Pm2.5 And Pm10
Sign in / Sign up

Export Citation Format

Share Document