Integer-coded Genetic Algorithm for Trimmed Estimator of Multivariate Linear Errors in Variables Model
The multivariate linear errors-in-variables (EIV) model is frequently used in computer vision for model fitting tasks. As well known, when sample data is contaminated by large numbers of awkwardly placed outliers, the least squares estimator isn’t robust. To obtain robust estimators of multivariate linear EIV model, orthogonal least trimmed square and orthogonal least trimmed absolute deviation estimators based on the subset of h cases(out of n)are proposed. However, these robust estimators possessing the exact fit property are NP-hard to compute. To tackle this problem, an integer-coded genetic algorithm that is applicable to trimmed estimators is presented. The trimmed estimators of multivariate linear EIV model on real data are provided and the results show that the integer-coded genetic algorithm is correct and effective.
integer-coded genetic algorithm linear error-in-variable model orthogonal least trimmed squares (OLTS) orthogonal least trimmed absolute deviation (OLTAD) C-Step
Huirong Cao Fuchang Wang
College of Mathematics and Information Science Langfang Teachers College, Langfang, China Department of Basic Courses Institute of Disaster Prevention of CEA, Sanhe, China
国际会议
沈阳
英文
1223-1229
2011-11-22（万方平台首次上网日期，不代表论文的发表时间）