DESIGN OF A DIGITAL SIGNATURE SCHEME BASED ON FACTORING AND DISCRETE LOGARITHMS

Objective Focusing on the security problem of authentication and confidentiality in the context of computer networks, a digital signature scheme was proposed based on the public key cryptosystem. Methods Firstly,the course of digital signature based on the public key cryptosystem was given. Then, RSA and ELGamal schemes were described respectively. They were the basis of the proposed scheme. Generalized ELGamal type signature schemes were listed. After comparing with each other, one scheme, whose Signature equation was (m r)x=j s modФ(p) , was adopted in the designing. Results Based on two well-known cryptographic assumptions, the factorization and the discrete logarithms, a digital signature scheme was presented. It must be required that s“ was not equal to p‘q“ in the signing procedure, because attackers could forge the signatures with high probabilities if the discrete logarithms modulo a large prime were solvable. The variable public key “e“ is used instead of the invariable parameter “3“ in Ham‘s signature scheme to enhance the security. One generalized ELGamal type scheme made the proposed scheme escape one multiplicative inverse operation in the signing procedure and one modular exponentiation in the verification procedure.Conclusion The presented scheme obtains the security that Harn‘s scheme was originally claimed. It is secure if the factorization and the discrete logarithms are simultaneously unsolvable.     

NEURAL NETWORK TRAINING WITH PARALLEL PARTICLE SWARM OPTIMIZER

Feed forward neural net works such as multi-layer perceptron,radial basis function neural net-works,have been widely applied to classification,function approxi mation and data mining.Evolu-tionary computation has been explored to train neu-ral net works as a very promising and competitive al-ternative learning method,because it has potentialto produce global mini mum in the weight space.Recently,an emerging evolutionary computationtechnique,Particle Swar m Opti mization(PSO)be-comes a hot to…     

基于计算机技术的一体化列车运行智能控制系统

针对列车运行多目标、多个互相联系的受控对象控制问题,探讨列车运行一体化控制概念和智能化控制的方法、手段。提出列车运行控制的7个约束集、7个限制集、5个指标集,并进行分析和排列,运用模糊逻辑、神经网络、遗传算法等智能控制理论和技术,构造一体化列车运行智能控制的分布式并行框架结构,分析距离差值ΔS等7个影响列车智能控制的决策因数,从移动性角度探讨目标函数的时变、非线性动态加权特性,提出了具有5层结构的模糊移动神经网络系统,介绍该系统的调节变量、输出变量、预测误差之间的关系和特性。     

支持向量机在列车自动控制中的应用

提出支持向量机-模糊预测控制方法,介绍支持向量机在列车启动控制过程中的应用。通过仿真试验,验证了该方法的有效性,解决了列车启动过程中平稳性不高的问题。     

非线性系统的智能容错控制

本文提出一种针对非线性系统问题的智能容错控制方案,该方案基于自适应模糊逻辑系统的学习方法,论述了控制器作为一个扩充的体系,集成了自适应模糊控制器、检测控制器及调节控制器三者的功能。仿真表明,所提出的控制方案能够有效的鉴别和适应非线性未知错误,且被控系统在不确定及产生错误时具有很好的稳定性和鲁棒性。     

SVM算法及其应用研究

采用将支持向量机-模糊预测控制应用于列车自动控制系统的方法,解决了目前列车自动控制中,启动控制过程平稳性不高的问题.首先给出模糊预测控制的有限样本的预测学习方法.在此基础上,设计了基于支持向量机-模糊预测控制方法,并把该方法应用于列车的启动控制过程中,通过仿真实验验证了改进的有效性.