基于区间适应值灰度的交互式遗传算法

针对交互式遗传算法缺乏衡量评价的不确定性问题,采用区间数评价进化个体适应值,利用灰度衡量评价的不确定性。通过区间适应值的灰度分析,提取反映种群进化分布的信息,给出进化个体的自适应交叉和变异概率。应用于服装进化设计系统的分析结果表明,该算法可有效缓解人的疲劳,提高优化效率。     

基于个体适应值灰模型的交互式遗传算法

为将交互式遗传算法应用于复杂的优化问题中,提出一种基于进化个体适应值灰模型预测的交互式遗传算法,为每代适应值序列建立灰模型,以衡量个体适应值评价的不确定性,通过对灰模型的灰预测,提取进化个体评价的可信度,在此基础上,给出进化个体适应值修正公式,将该算法应用于服装进化设计系统中。实验结果表明,该算法在每代都能获取更多的满意解。     

基于区间适应值交互式遗传算法的加权多输出高斯过程代理模型

融合了用户认知和智能评价的交互式遗传算法（Interactive genetic algorithm,IGA）是解决一类定性性能指标优化问题的有效方法,但是,评价不确定性和易疲劳性极大地限制了该算法解决实际问题的能力. 基于用户已评价信息,采用合适的机器学习方法,构建用户认知代理模型是解决上述问题的常用方法之一. 但是,现有研究成果均没有考虑用户评价不确定性对学习样本、代理模型的影响,以及模型拟合不确定性对基于适应值的进化操作有效性的影响. 针对上述问题,本文提出基于加权多输出高斯过程（Gaussian process,GP）代理模型的交互式遗传算法. 首先,在区间适应值评价模式下,提取学习样本的噪声特性,以确定相应学习样本对代理模型的影响度权重系数,构建两输出高斯过程代理模型;然后,利用代理模型提供的预测值及预测置信水平,给出一种新的个体适应值估计方法和个体选择方法;基于模型预测信息,实现模型更新管理. 将所提算法分别应用于含噪函数和服装设计问题中,所得结果表明本文算法可更好地拟合和跟踪用户认知,减小对进化搜索的误导,更快找到用户满意解.     

区间适应值交互式遗传算法神经网络代理模型

为了解决交互式遗传算法的用户疲劳问题,提出区间适应值交互式遗传算法神经网络代理模型．首先,对用户已评价个体的基因型及其适应值进行采样以训练神经网络,使其逼近区间适应值的上下限;然后,利用神经网络代理模型,评价后续的部分进化个体,并不断更新训练数据和代理模型,以保证逼近精度;最后,对算法性能进行了定量分析,并将其应用于服装进化设计系统．分析结果表明,所提算法在减轻用户疲劳的前提下,具有更多找到满意解的机会．

     

基于半监督学习的变种群规模区间适应值交互式遗传算法

为了减轻用户疲劳并增强算法的搜索性能,本文在变种群规模交互式遗传算法的基础上引入协同训练半监督学习方法,提出基于半监督学习的变种群规模区间适应值交互式遗传算法.根据对大规模种群的聚类结果,给出标记样本和未标记样本的获取方法;结合半监督协同学习器逼近误差的改变,提出高可信度未标记样本的选择策略;采用半监督协同学习机制训练两个径向基函数(RBF)神经网络,构造精度高泛化能力强的代理模型;在进化过程中,利用代理模型估计大种群规模进化个体适应值,并根据估计偏差更新代理模型.算法的理论分析及其在服装进化设计系统中的应用结果说明了算法的有效性.     

改进的区间值模糊集交互式遗传算法

区间值模糊集的交互式遗传算法,能有效缓解用户的疲劳,同时避免用户因一时无法给出确定值而浪费掉的时间,大大加快了收敛速度。首先采用区间值模糊集的方法表示对个体进行评价的适应度值,即为区间适应度值,然后对其进行排序,按照排序结果采用交互式遗传算法进行全局搜索。整个过程符合人的思维过程,能有效搜索到用户满意的个体。将该方法应用于图像检索系统中,结果表明该方法有效地提高了检索速度,并且取得了较好的检索结果。     

基于BP神经网络代理模型的交互式遗传算法

针对交互式遗传算法存在用户评价噪声和审美疲劳的问题,提出一种基于误差反向传播神经网络用户认知代理模型的交互式遗传算法。通过构建用户评价噪声模型,形成进化个体动态模糊区间适应值,以刻画用户认知随机不确定性;在用户认知确定阶段历史评价信息基础上,构建误差反向传播神经网络代理模型,给出一种新的适应值估计策略;通过度量均方误差,实现代理模型的管理与更新。将所提方法应用于蜡染风格图案设计,并与其他典型算法对比。结果表明,该方法能够有效优化进化个体适应值质量、降低用户审美疲劳。     

基于进化个体模糊适应值估计的交互式遗传算法

采用大规模种群进化优化策略,根据用户评价时间和单一数值适应值估计个体模糊适应值;根据个体表现型属性和参照个体模糊适应值宽度计算个体表现型相似度;利用个体表现型相似度对种群聚类并估计未评价个体的模糊适应值;基于个体模糊适应值和表现型相似性构造个体选择适应值,实现个体相似性选择.将所提出方法应用于室内挂钟进化设计,并与已有典型方法进行比较.结果表明,所提出方法在提高优化质量、减轻用户疲劳、提高搜索效率等方面均具有优越性.     

新的基于相似度估计个体适应值的交互式遗传算法

该方法根据组成个体各基因意义单元值出现的频率,计算基因意义单元的权值,并基于此得到个体的相似度;根据个体与上代最优个体的相似度,选择需要由用户进行评价的个体;基于当代所有己评价个体的信息,估计未评价个体的适应值.将所提方法应用于窗帘进化设计系统,并与已有典型方法比较.结果表明,所提方法在减轻用户疲劳和提高搜索性能等方面均具有优越性.     

基于离散适应值灰度的交互式遗传算法

针对交互式遗传算法缺乏衡量评价不确定性的问题,采用离散适应值评价进化个体,利用灰度衡量评价的不确定性。通过确定离散适应值的灰度,获得反映种群进化分布的信息;基于此,给出了进化个体的自适应交叉和变异概率。将该算法应用于服装进化设计系统,仿真实例与分析结果表明,所提出的算法可以有效缓解人的疲劳,提高优化效率。     

交互式遗传算法基于NN的个体适应度分阶段估计

针对交互式遗传算法中人的疲劳问题,提出一种基于神经网络(NN)的个体适应度分阶段估计方法,给出了神经网络估计进化个体适应度与人的评价之问的转换策略以及神经网络学习效果的评价指标,并分析了算法的复杂性．实例结果验证了该方法的有效性。     

Interactive genetic algorithms with individual’s fuzzy fitness

Interactive genetic algorithms are effective methods to solve an optimization problem with implicit or fuzzy indices, and have been successfully applied to many real-world optimization problems in recent years. In traditional interactive genetic algorithms, many researchers adopt an accurate number to express an individual’s fitness assigned by a user. But it is difficult for this expression to reasonably reflect a user’s fuzzy and gradual cognitive to an individual. We present an interactive genetic algorithm with an individual’s fuzzy fitness in this paper. Firstly, we adopt a fuzzy number described with a Gaussian membership function to express an individual’s fitness. Then, in order to compare different individuals, we generate a fitness interval based on α-cut set, and obtain the probability of individual dominance by use of the probability of interval dominance. Finally, we determine the superior individual in tournament selection with size two based on the probability of individual dominance, and perform the subsequent evolutions. We apply the proposed algorithm to a fashion evolutionary design system, a typical optimization problem with an implicit index, and compare it with two interactive genetic algorithms, i.e., an interactive genetic algorithm with an individual’s accurate fitness and an interactive genetic algorithm with an individual’s interval fitness. The experimental results show that the proposed algorithm is advantageous in alleviating user fatigue and looking for user’s satisfactory individuals.     

An interactive genetic algorithm with the interval arithmetic based on hesitation and its application to achieve customer collaborative product configuration design

Complex product configuration design requires rapid and accurate response to customers’ demand. The participation of customers in product design will be a very effective solution to achieve this. The traditional interactive genetic algorithm (IGA) can solve the above problem to some extent by a computer-aided user interface. However, it is difficult to adopt an accurate number to express an individual's fitness because the customers’ cognition of evolutionary population is uncertain, and to solve the users’ fatigue problem in IGA. Thus, an interactive genetic algorithm with interval individual fitness based on hesitancy (IGA-HIIF) is proposed in this paper. In IGA-HIIF, the interval number derived from users’ evaluation time is adopted to express an individual's fitness, and the evolutionary individuals are compared according to the interval probability dominant strategy proposed in this paper. Then, the genetic operations are applied to generate offspring population and the evolutionary process doesn’t stop until it meets the termination conditions of the evolution or user manually terminates the evolution process. The IGA-HIIF is applied into the design system of the car console configuration, and compared to the other two kinds of IGA. The extensive experiment results are provided to demonstrate that our proposed algorithm is correct and efficient.     

基于文化算法的神经网络及其在建模中的应用

在深入研究文化算法和神经网络相关文献基础上,针对神经网络建模的特点提出了一种训练神经网络的文化算法流程构造文化神经网络,并将该网络用于乙烯精馏塔产品质量软测量建模.通过训练与泛化能力的比较分析,结果表明基于文化神经网络的软测量模型具有良好的性能和较好的应用前景.     

Minimum-phase criterion on sampling time for sampled-data interval systems using genetic algorithms

In this paper, a genetic algorithm-based approach is proposed to determine a desired sampling-time range which guarantees minimum phase behaviour for the sampled-data system of an interval plant preceded by a zero-order hold (ZOH). Based on a worst-case analysis, the identification problem of the sampling-time range is first formulated as an optimization problem, which is subsequently solved under a GA-based framework incorporating two genetic algorithms. The first genetic algorithm searches both the uncertain plant parameters and sampling time to dynamically reduce the search range for locating the desired sampling-time boundaries based on verification results from the second genetic algorithm. As a result, the desired sampling-time range ensuring minimum phase behaviour of the sampled-data interval system can be evolutionarily obtained. Because of the time-consuming process that genetic algorithms generally exhibit, particularly the problem nature which requires undertaking a large number of evolution cycles, parallel computation for the proposed genetic algorithm is therefore proposed to accelerate the derivation process. Illustrated examples in this paper have demonstrated that the proposed GA-based approach is capable of accurately locating the boundaries of the desired sampling-time range.     

Simple models of coevolutionary genetic algorithms

The use of evolutionary computing techniques in coevolutionary/multiagent systems is becoming increasingly popular. This paper presents some simple models of the genetic algorithm in such systems, with the aim of examining the effects of different types of interdependence between individuals. Using the models, it is shown that for a fixed amount of interdependence between homogeneous coevolving individuals, the existence of partner gene variance, gene symmetry, and the level at which fitness is applied can have significant effects. Similarly, for heterogeneous coevolving systems with fixed interdependence, partner gene variance and fitness application are also found to have a significant effect, as is the partnering strategy used.     

Metamodeling approach in solving the machine parameters optimization problem using neural network and genetic algorithms: A case study

The use of multilayer ceramic capacitors (MLCCs) is increasing because they are surface-mountable and are used primarily in the expanding communication and computing market. In the MLCC manufacturing process, some 80% of the loss in yield is attributable to paste-printing quality problems. Improvement in the quality of MLCC screen-printing is therefore tactically and strategically important. This research extends existing MLCC screen-printing robust design results to search for a universal optimum solution. A metamodeling approach has been applied to solving a variety of optimization problems. This is an abstraction model form from a model. The abstracted model aims to reduce model complexity, and yet maintain validity. This work involved building a screen-printing quality metamodel, based upon fractional factorial experimental design data using a neural network approach—that were then solved by genetic algorithms. The empirical results are promising. The paper concludes with practical constraints and insights for management.