True Gaussian mixture regression and genetic algorithm-based optimization with constraints for direct inverse analysis

This paper deals with the identification of the anisotropic parameters using an inverse strategy. In the classical inverse methods, the inverse analysis is generally coupled with a finite element code, which leads to a long computational time. In this work an inverse analysis strategy coupled with an artificial neural network (ANN) model is proposed. This method has the advantage of being faster than the classical one. To test and validate the proposed approach an experimental cylindrical cup deep drawing test is used in order to identify the orthotropic material behaviour. The ANN model is trained by finite element simulations of this experimental test. To reduce the gap between the experimental responses and the numerical ones, the proposed method is coupled with an optimization procedure based on the genetic algorithm (GA) to identify the Cazacu and Barlat’2001 material parameters of a standard mild steel DC06.

Download Full-text

Plane-extraction from depth-data using a Gaussian mixture regression model

Pattern Recognition Letters ◽

10.1016/j.patrec.2018.03.024 ◽

2018 ◽

Vol 110 ◽

pp. 44-50 ◽

Cited By ~ 2

Author(s):

Richard T. Marriott ◽

Alexander Pashevich ◽

Radu Horaud

Keyword(s):

Regression Model ◽

Gaussian Mixture ◽

Mixture Regression ◽

Depth Data ◽

Plane Extraction ◽

Mixture Regression Model

Download Full-text

Application of Gaussian mixture regression model for short-term wind speed forecasting

2017 North American Power Symposium (NAPS) ◽

10.1109/naps.2017.8107222 ◽

2017 ◽

Cited By ~ 2

Author(s):

Md Emrad Hossain

Keyword(s):

Wind Speed ◽

Regression Model ◽

Gaussian Mixture ◽

Short Term ◽

Mixture Regression ◽

Wind Speed Forecasting ◽

Mixture Regression Model

Download Full-text

A Gaussian mixture regression model based adaptive filter for non-Gaussian noise without a priori statistic

Signal Processing ◽

10.1016/j.sigpro.2021.108314 ◽

2021 ◽

pp. 108314

Author(s):

Haoran Cui ◽

Xiaoxu Wang ◽

Shuaihe Gao ◽

Tiancheng Li

Keyword(s):

Regression Model ◽

Adaptive Filter ◽

Gaussian Noise ◽

A Priori ◽

Gaussian Mixture ◽

Mixture Regression ◽

Model Based ◽

Non Gaussian ◽

Mixture Regression Model

Download Full-text

Generating realistic Arabic handwriting dataset

International Journal of Engineering & Technology ◽

10.14419/ijet.v8i4.29786 ◽

2019 ◽

Vol 8 (4) ◽

pp. 460

Author(s):

Mahmoud I. Abdalla ◽

Mohsen A. Rashwan ◽

Mohamed A. Elserafy

Keyword(s):

Word Recognition ◽

Word List ◽

Holistic Approach ◽

Gaussian Mixture ◽

Normalization Method ◽

Gaussian Component ◽

Efficient System ◽

Mixture Regression ◽

Word Generation ◽

Input Text

During the previous year's holistic approach showing satisfactory results to solve ‎the ‎problem of Arabic handwriting word recognition instead of word letters ‎‎segmentation.‎ ‎In this paper, we present an efficient system for ‎ generation realistic Arabic handwriting dataset from ASCII input ‎text. We carefully selected simple word list that contains most Arabic ‎letters normal and ligature connection cases. To improve the ‎performance of new letters reproduction we developed our ‎normalization method that adapt its clustering action according to ‎created Arabic letters families. We enhanced Gaussian Mixture ‎Model process to learn letters template by detecting the ‎number and position of Gaussian component by implementing ‎Ramer-Douglas-Peucker‎ algorithm which improve the new letters ‎shapes reproduced by using and Gaussian Mixture Regression. ‎‎We learn the translation distance between word-part to achieve ‎real handwriting word generation shape.‎ Using combination of LSTM and CTC layer as a recognizer to validate the ‎efficiency of our approach in generating new realistic Arabic handwriting words inherit user handwriting style as shown by the experimental results.‎

Download Full-text