WSNs入侵检测中实值否定选择算法研究

针对无线传感器网络免疫入侵检测中否定选择算法采用r-连续位二进制串匹配度作为亲和力,检测率低且无法反映WSNs在一段时间内的动态特性这一现象,提出采用RNS-WSNs算法,该算法用一段时间内属性值的变化率构成向量作为抗原和抗体,通过计算向量间的曼哈顿距离作为亲和力。在NS3上模拟WSNs进行实验,结果显示在能量消耗相当且误报率相同的情况下,RNS-WSNs算法具有更高的检测率。     

改进人工蜂群算法优化RBF神经网络的短时交通流预测

为了提高径向基函数RBF神经网络预测模型对短时交通流的预测准确性,提出了一种基于改进人工蜂群算法优化RBF神经网络的短时交通流预测模型。利用改进人工蜂群算法确定RBF网络隐含层的中心值以及隐含层单元数,然后训练改进的人工蜂群算法RBF神经网络预测模型,并将其应用到某城市4天的短时交通流量数据的验证。将实验结果与传统RBF神经网络预测模型、BP神经网络预测模型和小波神经网络预测模型进行了比较。对比结果表明,该方法对短时交通流具有更高的预测准确性。     

Optimal design of a 3D-printed scaffold using intelligent evolutionary algorithms

Fabrication of three-dimensional structures has gained increasing importance in the bone tissue engineering (BTE) field. Mechanical properties and permeability are two important requirement for BTE scaffolds. The mechanical properties of the scaffolds are highly dependent on the processing parameters. Layer thickness, delay time between spreading each powder layer, and printing orientation are the major factors that determine the porosity and compression strength of the 3D printed scaffold.In this study, the aggregated artificial neural network (AANN) was used to investigate the simultaneous effects of layer thickness, delay time between spreading each layer, and print orientation of porous structures on the compressive strength and porosity of scaffolds. Two optimization methods were applied to obtain the optimal 3D parameter settings for printing tiny porous structures as a real BTE problem. First, particle swarm optimization algorithm was implemented to obtain the optimum topology of the AANN. Then, Pareto front optimization was used to determine the optimal setting parameters for the fabrication of the scaffolds with required compressive strength and porosity. The results indicate the acceptable potential of the evolutionary strategies for the controlling and optimization of the 3DP process as a complicated engineering problem.     

基于改进的无量纲指标信息融合故障诊断方法

针对无量纲指标信息的不确定会产生冲突证据的问题,提出一种基于改进证据理论的无量纲指标信息融合故障诊断方法.采用人工免疫算法构建原始证据;通过计算无量纲免疫检测器证据之间的相似度找出相似证据和冲突证据.保留相似证据,并利用可信度修正冲突证据,从而降低冲突证据对证据理论合成结果的影响.组合式旋转机械故障诊断试验验证本文方法有效.该方法能够明显提高故障诊断准确率.     

数据挖掘常用分类算法研究

数据库、数据仓库以及其他存储信息库中潜藏着很多与商业、科学研究等活动的决策有关的数据和知识。对于数据挖掘中的数据分析,通常有两种常见的方法,即分类和预测,首先对数据库中的数据进行分类归纳,然后根据分类规则可以得到比较有价值的数据,然后我们可以根据这个数据来预测得到一些包含未来趋势的信息。在常见的分类算法中,决策树算法是一个有着很好扩展性的算法,可以应用到大型数据库中,可以对多种数据类型进行处理,分类模式容易转化为分类规则,结果也十分的浅显易懂易于理解。该文主要先介绍了几种常用的分类算法,然后具体介绍决策树算法的过程以及在分类算法实际应用中的优缺点。     

IT时代的第三种文化产业机遇

人类社会一直存在着并行不悖的科技与人文的两种文化与文化产业。如今,出现了第三种文化与第三种文化产业。第三种文化产业的思想基础是图灵的可计算原理;其物质基础是微处理器智力内核。第三种文化产业将打破两种文化产业界线,用人工智能与智能化工具等现代科技手段,实现人文文化领域中的艺术创作,这是人类文化领域中已经开始的没有硝烟的产业战争。     

A Proposal for Implementing Multi-User Data Base (MUD) Technology in and Academic Library

Multi-user Data base (MUD) technology, and its object-oriented descendant (MOO), is one of the most exciting tools to surface on the Internet, and offers libraries and librarians a unique opportunity to participate in creating user-friendly standardized interfaces to many of our most frequently used resources. These resources include those we access through the Internet already, using gopher, telnet, WWW, and FTP, and also those proprietary databases that we currently access through leased lines such as OCLC First Search, Prism, DIALOG, and many others. MOO technology is already being used successfully to create user-extensible collaborative professional environments for educators, astronomers, and computer network systems administrators. With the growing relevance of the Internet for libraries and other information professionals, it behooves the library community to engage those emerging technologies which will aloow us to interface most effectively with the Internet and its many resources, with the proprietary databases which we depend on, and with one another.     

Study on Robot Path Planning Based on an Improved Artificial Potential Field Method

The method of artificial potential field has obvious advantages among the robot path planning methods including simple structure, small amount of calculation and relatively mature in theory. This paper puts forward the ＂Integral method＂ focusing on solving the problem of local minimization. The method analyses the distribution of obstructions in a given environment and regards adjacent obstacles as a whole, By changing the parameters of the repulsive force field, robots can quickly get out of the minimum point and move to the target point. This paper uses the Simurosot platform to carry on the simulation experiment on the improved artificial potential field method, which projects a feasible path successfully and verifies this method.     

人工代谢算法在故障诊断中的应用

从生物体新陈代谢的生理机能出发,建立了基于酶催化的人工代谢算法模型．通过对代谢算子功能的 分析提出了模式定理的概念,并证明了算法的收敛性．利用酶与底物相匹配的原理,通过代谢操作找出酶与底物的 最优匹配,从而找出对应故障现象的原因．在寻优过程中,不断地通过凋亡算子将不可能成立的原因筛除,降低了 故障诊断的成本．实例分析表明,该算法能有效地进行故障定位,尽可能地缩小了不必要的搜索空间．     

基于分布式智能代理的反网络洗钱技术研究

本文针对当前洗钱犯罪活动迅速发展并呈现网络化的问题,提出了基于分布式智能代理框架的反网络洗钱技术,并结合关系图熵矩阵的数据挖掘技术,开发了反网络洗钱的仿真实验原型系统进行仿真验证。