Operators of mutation and crossover in a genetic algorithm for construction of axiomatic systems

被引：0
作者：
Vasin E.A. [1 ]
机构：
[1] Department of Automation of the Systems of Computational Complexes, Faculty of Computational Mathematics and Cybernetics, Moscow State University, Leninskie Gory
来源：
Moscow University Computational Mathematics and Cybernetics | 2007年 / 31卷 / 2期
关键词：
Genetic Algorithm; Elementary Condition; Algebraic Approach; Reference Trajectory; Axiomatic System;
D O I：
10.3103/S0278641907020057
中图分类号：
学科分类号：
摘要：
In this paper, the problem of automated recognition of anomalies in the behavior of complicated dynamical systems is solved by means of analyzing trajectories obtained from sensors surrounding the system. A specific feature of the problem consists in the fact that, depending on the individual properties of the system and conditions of its operation, trajectories that contain anomalies may significantly differ from each other in amplitude and length. The algorithm employed here for solving the problem of recognition of anomalies in the behavior of the system under investigation is based on the idea of applying the algebraic approach to the labeling of time series. This algorithm can be adjusted to peculiarities of a particular dynamical system; such adjustment can be performed with the help of an algorithm belonging to the class of genetic algorithms. © 2007 Allerton Press, Inc.
引用
收藏
页码：66 / 70
页数：4
相关论文
共 4 条
[1]  
Vasin E.A., Investigation of Efficiency of a Recognition Algorithm for Distorted Patterns on Time Series by Sets of Neuron Networks, Proc. Of a Conf. On Methods and Tools for Information Processing, pp. 553-559, (2005)
[2]  
Rudakov K.V., Chekhovich Y.V., On the Problem of Syntesis of Learning Algorithms for Trend Selection (Algebraic Approach), Applied Mathematics and Computer Science, pp. 97-113, (2001)
[3]  
Kovalenko D.S., Kostenko V.A., Vasin E.A., Investigation of Applicability of Algebraic Approach to Analysis of Time Series, Proc. Of a Conf. On Methods and Tools for Information Processing, pp. 553-559, (2005)
[4]  
Trekin A.G., Candidate's Dissertation in Mathematics and Physics
1