Matrix decomposition model for robust based on M estimate and its application

• Published in: Cluster computing Vol. 22; no. Suppl 2; pp. 4315 - 4322
• Main Author: Zhang, Zhengyang
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.03.2019; Springer Nature B.V
• Subjects: Agriculture; Algorithms; Binary system; Computer Communication Networks; Computer Science; Decomposition; Econometrics; Empirical analysis; Expected values; Leisure; Mathematical analysis; Operating Systems; Processor Architectures; Qualitative research; Regression analysis; Regression models; Robustness (mathematics); Rural areas; Sustainable development; Tourism development; China; Robustness; Matrix decomposition; Linear regression; Leisure agriculture; M estimate
• ISSN: 1386-7857; 1573-7543
• DOI: 10.1007/s10586-018-1871-2

In order to improve algorithm accuracy for empirical analysis of development of leisure agriculture, a method for empirical analysis for development of leisure development based on M estimate robust matrix decomposition was proposed. Firstly, on the basis of studying on related theories and a large quantity of literatures, development for leisure agriculture is mainly subject to influence of the following 5 aspects concluded herein, and linear regression model was set; secondly, matrix decomposition algorithm for robust based on M estimate of Turkey test was proposed, and characteristic matrix of leisure agriculture and characteristic matrix of program was constructed. Through adjusting similarities between leisure agriculture, influence of interference configuration program to robust estimate of characteristic matrix was reduced; finally, through empirical analysis, effectiveness of algorithm proposed was provided with verification.