遗传算法综述

遗传算法来源于进化论和群体遗传学，是计算智能的重要组成部分，正受到众多学科的高度重视。本文系统综述了遗传算法的发展历程，理论研究和应用研究，并进行了分析和评价。  

一种基于学习机制的并行遗传算法

基于生物学群落的概念，提出了一个群落一种群一个体的三层模型，并在该模型上发展了一种基于学习机制的并行遗传算法(PGABL)。算法引入黑板模型作为控制和交互的数据结构，采用群内、群间、群落三个学习算子，将遗传进化和遗传学习相结合，有效地改善了遗传算法的性能。实验结果表明，该算法具有良好的适应性和稳定性。  

A genetic fuzzy agent using ontology model for meeting scheduling system

A Genetic Fuzzy Agent (GFA) using the ontology model for Meeting Scheduling System (MSS) is presented in this paper. The ontology model includes the Fuzzy Meeting Scheduling Ontology (FMSO) and the Fuzzy Personal Ontology (FPO) that can support to construct the knowledge base of the GFA. The FMSO is utilized to record and describe the meeting scheduling domain knowledge for the GFA. In addition, we implement a FMSO editor for generating the Web Ontology Language, OWL, that will be utilized by the GFA. Furthermore, the GFA will infer the suitable meeting time slots based on the ontology model. Moreover, it also adjusts the FMSO and FPO based on the results of the genetic learning mechanism for the next meeting. The experimental results show that our approach can effectively work for MSS.  

一种基于组织学习的自适应Agent系统体系结构

在复杂适应系统和组织学习理论的基础上，探讨了一种基于组织学习的自适应Agent系统体系结构。在这种体系结构中，通过Agent交互中的适应性行为获取对系统复杂性的认知，而Agent的适应能力则依靠增强学习和动态自组织与重构来实现。文中给出了一个基于组织增长模型的分类器系统算法以及相应的软件实现技术途径。  

RTCS: a Reactive with Tags Classifier System

In this work, a new Classifier System is proposed (CS). The system, a Reactive with Tags Classifier System (RTCS), is able to take into account environmental situations in intermediate decisions. CSs are special production systems, where conditions and actions are codified in order to learn new rules by means of Genetic Algorithms (GA). The RTCS has been designed to generate sequences of actions like the traditional classifier systems, but RTCS also has the capability of chaining rules among different time instants and reacting to new environmental situations, considering the last environmental situation to take a decision. In addition to the capability to react and generate sequences of actions, the design of a new rule codification allows the evolution of groups of specialized rules. This new codification is based on the inclusion of several bits, named tags, in conditions and actions, which evolve by means of GA. RTCS has been tested in robotic navigation. Results show the suitability of this approximation to the navigation problem and the coherence of tag values in rules classification.  

Predicting Aflatoxin Contamination in Peanuts: A Genetic Algorithm/Neural Network Approach

Aflatoxin contamination in peanut crops is a problem of significant health and financial importance. Predicting aflatoxin levels prior to crop harvest is useful for minimizing the impact of a contaminated crop and is the goal of our research. Backpropagation neural networks have been used to model problems of this type, however development of networks poses the complex problem of setting values for architectural features and backpropagation parameters. Genetic algorithms have been used in other studies to determine parameters for backpropagation neural networks. This paper describes the development of a genetic algorithm/backpropagation neural network hybrid (GA/BPN) in which a genetic algorithm is used to find architectures and backpropagation parameter values simultaneously for a backpropagation neural network that predicts aflatoxin contamination levels in peanuts based on environmental data. Learning rate, momentum, and number of hidden nodes are the parameters that are set by the genetic algorithm. A three-layer feed-forward network with logistic activation functions is used. Inputs to the network are soil temperature, drought duration, crop age, and accumulated heat units. The project showed that the GA/BPN approach automatically finds highly fit parameter sets for backpropagation neural networks for the aflatoxin problem.  

Neural network design with genetic learning for control of a single link flexible manipulator

The application of neural networks for active control of lightly damped systems is considered in this article. The training process of the neural-network controller is based on the genetic learning algorithm. The schemes imitates nature's cleansing phenomena of natural selection and survival of the fittest to generate individual controllers withe best fitness values. It essentially incorporates an exhaustive search in the weight-space governed by the rituals of crossover and mutation to seek the optimum neural-network weights to satisfy certain performance criteria. Several appropriate modifications of the classical genetic algorithm for neural-network control purposes are discussed. The genetic-trained neural-network controller is applied for tip position tracking and vibration suppression of a single-link flexible arm. Simulation studies are presented to validate the effectiveness of the advocated algorithms.