Simulating the Ecology of Oligopolistic Competition with Genetic Algorithms

In economics, the n-person oligopoly game and the n-person IPD game are often considered close in spirit. Our analytical framework shows that this is not the case owing to the path dependence of the pay-off matrix of the oligopoly game. By simulating the evolution of a three-person oligopoly game with genetic algorithms, we explore the significance of the path dependence property to the rich ecology of oligopoly. The emergent behavior of oligopolists in the simulations indicates how the path dependence nature may shed light on the phenotypes and genotypes coming into existence. The features shown in this research can be further exploited in more practical contexts so that nontrivial policy issues in industrial economics can be seriously tackled. Received 12 February 1999 / Revised 9 December 1999 / Accepted 3 April 2000     

遗传算法及其进化硬件设计研究

遗传算法(Genetic Algorithms，GAs)是进化计算中的重要领域．也是人工智能迅速发展的重要领域，它是一类模拟自然进化过程和达尔文“适者生存”的算法。这一算法企图通过使用诸如交叉、变异等算子从先前的候选解中生成最佳解。进化硬件(Evolvable Hardware，EHW)则是受自然进化得到灵感、设计硬件系统的新型设计方法，它是进化计算技术和电子硬件结合的产物。本文给出GAs在计算机模型中的基本概念．讨论进化再配置硬件的设计，最后给出几个进化实验的例子。     

Simulating Network Delays: Applications,Algorithms, and Tools

Organizations are rushing to establish a presence on the World Wide Web (WWW). Researchers, designers, and users all recognize the importance of network delays, with longer delays frequently being associated with more negative user experiences. Although some delay is unavoidable, design decisions do contribute to the total delay users experience. In this article, a collection of tools that allow individuals to experience realistic network delays during informal evaluations, usability studies, and controlled experiments are described. These tools allow practitioners to more effectively assess usability in the context of realistic network delays, researchers to more effectively investigate the factors that affect the usability of information and applications delivered via the WWW, and educators to more effectively convey the importance of design decisions in the context of the WWW. This article describes how these tools may be used as well as the tools themselves, including the algorithms that make them effective. 2 approaches for validating simulations with results are presented. The first validation suggests that the simulation process utilized in the wide-area network delay simulator tools (Borella & Sears, 1997) effectively reproduces the network delays observed when retrieving material via the WWW. The second validation provides even stronger support, indicating that the simulation process can be used to reproduce a specific set of network conditions more accurately than the network itself. Directions for additional research are also discussed.     

Asset Pricing Models, Specification Search, and Stability Analysis

Testing asset pricing models is closely related to specification searchanalysis in quantitative economics. Most specification search processes selectmodels based on some goodness of fit statistic (such as R² orrelated F). The effects of the sequential search on the statistical testsshould be taken into account when looking for the maximum goodness of fit. Toavoid misspecified models it is useful to study the selected models based bothon the full sample and along the sample. This paper presents a conditionalsequential procedure for the specification search process with linearregression models that minimizes data snooping or data mining. It is acombined test that first considers the search for the `best' set of regressorsand, conditional on this set, studies its significance and/or stability alongthe sample. The characteristics of the conditional tests are presented. Itsefficacy is illustrated with a model of future returns as a function of pastvolume and returns.     

Exact Schema Theory and Markov Chain Models for Genetic Programming and Variable-length Genetic Algorithms with Homologous Crossover

Genetic Programming (GP) homologous crossovers are a group of operators, including GP one-point crossover and GP uniform crossover, where the offspring are created preserving the position of the genetic material taken from the parents. In this paper we present an exact schema theory for GP and variable-length Genetic Algorithms (GAs) which is applicable to this class of operators. The theory is based on the concepts of GP crossover masks and GP recombination distributions that are generalisations of the corresponding notions used in GA theory and in population genetics, as well as the notions of hyperschema and node reference systems, which are specifically required when dealing with variable size representations.In this paper we also present a Markov chain model for GP and variable-length GAs with homologous crossover. We obtain this result by using the core of Vose's model for GAs in conjunction with the GP schema theory just described. The model is then specialised for the case of GP operating on 0/1 trees: a tree-like generalisation of the concept of binary string. For these, symmetries exist that can be exploited to obtain further simplifications.In the absence of mutation, the Markov chain model presented here generalises Vose's GA model to GP and variable-length GAs. Likewise, our schema theory generalises and refines a variety of previous results in GP and GA theory.     

Saddle Points in Random Matrices: Analysis of Knuth Search Algorithms

We present an analysis of algorithms for finding saddle points in a random matrix, presented by Donald E. Knuth as Exercise 1.3.2-12 in The Art of Computer Programming . We estimate the average computing costs of three saddle point search algorithms. Amusingly, the asymptotic results in this analysis about matrix saddle points uses the same approach that leads to the celebrated saddle point method in complex analysis. Received December 22, 1997; revised March 15, 1998.     

Tackling Real-Coded Genetic Algorithms: Operators and Tools for Behavioural Analysis

Genetic algorithms play a significant role, as search techniques forhandling complex spaces, in many fields such as artificial intelligence, engineering, robotic, etc. Genetic algorithms are based on the underlying genetic process in biological organisms and on the naturalevolution principles of populations. These algorithms process apopulation of chromosomes, which represent search space solutions,with three operations: selection, crossover and mutation.Under its initial formulation, the search space solutions are coded using the binary alphabet. However, the good properties related with these algorithms do not stem from the use of this alphabet; other coding types have been considered for the representation issue, such as real coding, which would seem particularly natural when tackling optimization problems of parameters with variables in continuous domains. In this paper we review the features of real-coded genetic algorithms. Different models of genetic operators and some mechanisms available for studying the behaviour of this type of genetic algorithms are revised and compared.     

多服务中心设置问题局部搜索算法的分析与实验

讨论了多服务中心设置问题的局部搜索近似算法及其在实际计算中表现出的新性质。首先对局部搜索算法求解多服务中心设置问题的实际近似性能比给出了一个针对性分析结果,然后编程实验对局部搜索求解算法的求解时间和求解质量进行了探讨。     

一种集成遗传算法与模糊推理的粗糙集数据分析算法

粗糙集数据分析的主要优点在于它不要求任何关于被处理数据的先验或额外的知识,文章利用其对数据库进行分析计算,自动获取数据库在各个层次上的规则集。在保证量化后的数据库具有最大一致性的前提下,利用遗传算法求取连续属性值的最优量化区间个数及各个区间分点值。同时将量化区间进行模糊化,将清晰规则集转化为模糊规则集,利用模糊推理进行决策以提高鲁棒性。通过对UCI中几个数据库的测试验证了所提出算法的有效性。     

组合优化问题中GA性能分析及多样性评价

随着生产调度、机器学习、最优规划等组合优化问题的大规模化,复杂化,传统的基于运筹学的搜索算法已显得无能为力．具有广域搜索能力的遗传算法(GA)也因“完备性”与“健全性”的不充分不能有效地对应上述问题．为此,本文提出了保证GA上述两个性质地方法,使其能有效地解决复杂组合优化问题．     

Dynamic Stability of Power Systems Using UPFC: Bat‐Inspired Search and Gravitational Search Algorithms

In this paper, the bat‐inspired algorithm and the Gravitational Search Algorithm (GSA) based optimal location and capacity of UPFC are proposed to improve the dynamic stability of power systems. The novelty of the proposed method is in improved searching ability, random reduction and reduced complexity. Here, the GSA is used to optimize the location of the UPFC if a generator fault occurs. The GSA selects the maximum power loss line as the optimum location to place UPFC as per the objective function, since the generator fault violates the system equality and inequality constraints from the secure limit. From the UPFC control parameters, the minimum voltage deviation is optimized using the bat algorithm. The minimum voltage deviation has been used to find the optimum capacity of the UPFC. Then the optimum UPFC capacity is applied in the optimum location, which enhances the dynamic stability of the system. The proposed method is implemented in the MATLAB/Simulink platform and the performance is evaluated by means of comparison with the different techniques like GSA and bat‐inspired algorithm. The comparison results demonstrate the superiority of the proposed approach and confirm its potential to solve the problem.     

自适应小生态遗传算法的理论分析和加速技术

提出了联赛选择和相似个体概率替换的自适应小生态遗传算法,建立了小生态生长的动力学模型．平衡态理论分析和仿其实验表明,概率联赛小生态技术选择能够形成和维持稳定的子种群．提出了种群聚类分割和单纯形搜索的并行局部搜索算于,定性地分析了其搜索性能．对复杂多峰问题的优化结果表明,结合概率联赛选择和并行局部搜索算子的小生态遗传算法不但能够快速可靠地收敛到全局最优解,且能并行地搜索到多个局部最优解,其收敛速度和全局收敛可靠性均显著地优于简单遗传算法和其它小生态方法．     

Dynamic Hybrid Random Fields for the Probabilistic Graphical Modeling of Sequential Data: Definitions,Algorithms, and an Application to Bioinformatics

The paper introduces a dynamic extension of the hybrid random field (HRF), called dynamic HRF (D-HRF). The D-HRF is aimed at the probabilistic graphical modeling of arbitrary-length sequences of sets of (time-dependent) discrete random variables under Markov assumptions. Suitable maximum likelihood algorithms for learning the parameters and the structure of the D-HRF are presented. The D-HRF inherits the computational efficiency and the modeling capabilities of HRFs, subsuming both dynamic Bayesian networks and Markov random fields. The behavior of the D-HRF is first evaluated empirically on synthetic data drawn from probabilistic distributions having known form. Then, D-HRFs (combined with a recurrent autoencoder) are successfully applied to the prediction of the disulfide-bonding state of cysteines from the primary structure of proteins in the Protein Data Bank.     

人工免疫系统:原理、模型、分析及展望

目前,受生物免疫系统启发而产生的人工免疫系统（Artificial ImmuneSystem,AIS)正在兴起,它作为计算智能研究的新领域,提供了一种强大的信息处理和问题求解范式,该文侧重以AIS的基本原理框架为线索,对其研究状况加以系统综述,首先从AIS的生物原型入手,归纳提炼出其仿生机理,主要包括免疫识别,免疫学习,免疫记忆,克隆选择,个体多样性,分布式和自适应等,进而对几种典型的AIS模型和算法分门别类地进行了细致讨论,随后介绍了AIS在若干具有代表性的领域中的应用情况,最后通过对AIS的特性和存在问题的分析,展望了今后的研究重点和发展趋势。     

最小风险准则和遗传算法优化神经网络

提出了一种基于最小平均风险准则的遗传算法优化设计前向神经网络的方法,遗传算法的适应度函数并不采用传统的均方误差准则,而是由平均风险则所决定,这种方法在神经网络输出与期望输出之间误差的同时,还要考虑神经网络对不同类型训练样本产生的这种误差所引起的不同的风险损失。这种方法优化得到的神经网络不仅可以准确地再现训练样本集合的期望输出,对训练样本集合外样本的正确预测能力也有明显的提高。     

基于遗传算法和BP神经网络的房价预测分析

针对BP神经网络存在易陷入局部极小值、收敛速度慢等问题,提出用遗传算法优化BP神经网络并用于房价预测。采用BP神经网络建立房价预测模型。利用遗传算法对BP神经网络的初始权值和阈值进行优化。选取1998年2011年贵阳市的房价及其主要影响因素作为实验数据,分别对传统的BP神经网络和经过遗传算法优化后的BP神经网络进行训练和仿真实验,结果表明,与传统的BP神经网络预测模型相比,经过遗传算法优化后的BP神经网络预测模型能加快网络的收敛速度,提高房价的预测精度。     

Unsupervised Learning of Word Segmentation Rules with Genetic Algorithms and Inductive Logic Programming

This article presents a combination of unsupervised and supervised learning techniques for the generation of word segmentation rules from a raw list of words. First, a language bias for word segmentation is introduced and a simple genetic algorithm is used in the search for a segmentation that corresponds to the best bias value. In the second phase, the words segmented by the genetic algorithm are used as an input for the first order decision list learner CLOG. The result is a set of first order rules which can be used for segmentation of unseen words. When applied on either the training data or unseen data, these rules produce segmentations which are linguistically meaningful, and to a large degree conforming to the annotation provided.     

Control of the System of Optimal Parallel Data Processing in Local Computer Networks: Models, Algorithms, Interface

The models, algorithms, and interface to control the system of optimal parallel data processing in local computer networks developed by the North Caucasian State Technological University were described with the aim of analyzing the efficiency of cluster resource utilization according to the targets and specific features of the tasks at hand. The majority of the described algorithms were illustrated by examples. Search of the optimal strategy is supported by a friendly interface which is intuitively understandable.     

Choice of an Optimal Set of Geotechnical Jobs at Oil Fields: Models and Algorithms

An optimal set of jobs at oil fields is chosen with an extremal multi-criteria model. An algorithm based on the universal procedure of finding a sequence of best solutions on a finite set due to one of the authors is applied to choose the set with this model.__________Translated from Avtomatika i Telemekhanika, No. 8, 2005, pp. 36–45.Original Russian Text Copyright © 2005 by Koltun, Pershin, Ponomarev.