Optimization of classification theory and application in stochastic functional analysis
- DOI
- 10.2991/amcce-15.2015.204How to use a DOI?
- Keywords
- stochastic functional; support vector machine; convergence; data classification
- Abstract
A class of stochastic functional differential equation boundary value convergence problem is researched, and the support vector machine (SVM) optimization classification theory is taken for the data classification, and the training sample set processing algorithm is proposed based on the stochastic functional analysis, the stability and convergence of the stochastic functional characteristics is improved, new algorithm can effectively absorb or eliminate redundant information and avoid additional data, repeatedly re calculation can be avoided, it can radically reduce the number of iterations and calculation cost. Stability properties of positive semidefinite minimum positive characteristic zonal sparse conditions is proved by mathematical deduction, the line approximation error continuous edge stability analysis is taken for stochastic functional value, singular decomposition is taken with conjugate gradient method, the boundary conditions are incorporated into the stochastic functional elliptic function, the small positive semidefinite minimum feature of the stiffness matrix is given, the asymptotic convergence condition of Stochastic Functional Differential Equations is obtained, and the boundary value is solved. KDD_CUP2012 database is used in simulation for data classification, simulation results show that, the classification model can classify all kinds of data and reorganize the data effectively. It can improve the data processing ability, guarantee the convergence of stochastic functional differential equations boundary value.
- Copyright
- © 2015, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Xiuli Yuan PY - 2015/04 DA - 2015/04 TI - Optimization of classification theory and application in stochastic functional analysis BT - Proceedings of the 2015 International Conference on Automation, Mechanical Control and Computational Engineering PB - Atlantis Press SP - 643 EP - 649 SN - 1951-6851 UR - https://doi.org/10.2991/amcce-15.2015.204 DO - 10.2991/amcce-15.2015.204 ID - Yuan2015/04 ER -