Analysis of the Regularization Parameter for EEG Inverse Problem Using Genetic Algorithm

Author(s):  
Eric F. Schmiele ◽  
Alcimar B. Soares
2014 ◽  
Vol 31 (6) ◽  
pp. 1250-1262 ◽  
Author(s):  
Xiaofeng Zhao ◽  
Sixun Huang

Abstract This paper focuses on retrieving the atmospheric duct structure from radar sea clutter returns by the adjoint approach with the regularization technique. The adjoint is derived from the split-step Fourier parabolic equation method, and the regularization term is constructed by the background refractivity field. To ensure successful implementations of the regularization, the L-curve criterion is used to find the optimal regularization parameter. The feasibility of the proposed method is validated by the numerical simulations of different noise-level clutter returns, as well as a real clutter profile measured by the S-Band Space Range Radar located in Wallops Island. In the process of inversions, the refractivity profile is first obtained by genetic algorithm, and then it is used as the background field for the adjoint method. The retrieved results indicate that, with an appropriate regularization parameter, the structure of the background refractivity profile can be improved by the proposed method.


2021 ◽  
Vol 39 (4) ◽  
pp. 1190-1197
Author(s):  
Y. Ibrahim ◽  
E. Okafor ◽  
B. Yahaya

Manual grid-search tuning of machine learning hyperparameters is very time-consuming. Hence, to curb this problem, we propose the use of a genetic algorithm (GA) for the selection of optimal radial-basis-function based support vector machine (RBF-SVM) hyperparameters; regularization parameter C and cost-factor γ. The resulting optimal parameters were used during the training of face recognition models. To train the models, we independently extracted features from the ORL face image dataset using local binary patterns (handcrafted) and deep learning architectures (pretrained variants of VGGNet). The resulting features were passed as input to either linear-SVM or optimized RBF-SVM. The results show that the models from optimized RBFSVM combined with deep learning or hand-crafted features yielded performances that surpass models obtained from Linear-SVM combined with the aforementioned features in most of the data splits. The study demonstrated that it is profitable to optimize the hyperparameters of an SVM to obtain the best classification performance. Keywords: Face Recognition, Feature Extraction, Local Binary Patterns, Transfer Learning, Genetic Algorithm and Support Vector  Machines.


2013 ◽  
Vol 14 (2) ◽  
pp. 143-154
Author(s):  
Alexander Krainyukov ◽  
Valery Kutev

Problems of the data processing improving for pavement structure evaluation with help of subsurface radar probing are discussed. Iterative procedure to solve the inverse problem in frequency domain is used on the base of the genetic algorithm. For improving of data processing effectiveness it is proposed to use a modified genetic algorithm with adaptation of search range of pavement parameters. The results of reconstruction of electro-physical characteristics for model of five-layered pavement structure are presented.


2017 ◽  
Vol 25 (3) ◽  
Author(s):  
Maxim Pisarenco ◽  
Irwan D. Setija

AbstractWe discuss and analyze the classical discrepancy principle and the recently proposed and closely related chi-squared principle for selecting the regularization parameter of an inverse problem. Some properties that deteriorate the performance of these methods for over-determined inverse problems are highlighted. We propose a so-called


Sign in / Sign up

Export Citation Format

Share Document