计算机图像处理在缺素叶片颜色特征识别方面的应用

文章采用Punix公司的CCD摄像头对缺素黄瓜叶片进行采样，提出了RGB系统的G／R，G／B的数字统计特征来区分缺素黄瓜叶片颜色特征，应用Ohta系统的I2-I3的数字特征来识别不同的黄瓜叶片颜色，提出了HSV系统中的H色调相对差值百分率直方图法确定缺素的病态区间。     

基于小波变换的番茄缺素识别研究

在利用计算机视觉技术进行番茄缺素识别研究中,提出利用多分辨率小波分析算法提取番茄叶片的G体特征。结果表明：小波变换各分解子图的均值,方差,熵可区分正常与缺氮叶片;随着叶片含氮量的减少,小波分解子图各特征值随之变大。为利用特征值的范围,诊断叶片的缺素程度提供了技术支持。     

基于支持向量机和遗传算法的皮肤显微图像特征选择

在皮肤显微图像症状识别系统研究中,如何选择出对皮肤症状分类能力强的特征项组合是识别诊断面临的关键问题.本文把遗传算法和支持向量机结合起来,既利用遗传算法优化搜索特征空间,又克服了传统统计学的苛刻要求.通过对初步提取的皮肤显微图像的特征参数进行优化组合,选择出使系统的识别率得到较大提高(由88.24%提高到97.06%)的特征组合.实验证明本文提出的算法得到的结果是较令人满意的.     

基于遗传算法的海底沉积物纹理特征优化方法

为了提高水下机器人对海底沉积物的自主分类感知能力,解决特征冗余问题,对利用遗传算法优化海底沉积物纹理特征进行了研究。以基于灰度共生矩阵和分形理论提取多种海底沉积物视觉纹理特征实现海底沉积物分类识别为背景,提出利用遗传算法对纹理特征项进行优化选择以实现对提取特征的降维,并将降维后的特征项作为自组织映射神经网络模型的输入,对海底沉积物进行视觉分类,提高水下机器人作业时的环境感知能力。实验结果表明,相对于未优化的纹理特征,优化后的纹理特征在海底沉积物分类识别中具有更优的分类效果。     

改进的遗传算法在车牌自动识别系统中的应用

在车牌自动识别系统中，如何选择对车牌字符分类能力强的特征组合是系统面临的关键问胚。针对传统组合优化方法用于特征选择的种种缺陷和简单遗传算法过早收敛的缺点，提出了利用伪并行、最优解保存和自适应参数调整相结合的改进的遗传算法对提取的车牌字符图像众多特征进行优化选择的策略。仿真实验证明，改进的遗传算法不但从收敛速度和搜索能力上优于简单的遗传算法，而且可以有效的避免出现早熟现象，防止陷入局部最优；所提出的特征选择算法不仅提高了车牌字符识别率。而且识别结果十分稳定。     

用于生理信号情感识别的自适应遗传算法

针对用生理信号识别情感中的最优情感特征组合的选择这一组合优化问题,将遗传算法中的交叉、变异操作加以改进形成新的算法.该算法用来选择最能代表相应情感状态的最优特征组合,并以最近邻法的分类正确率作为当前搜索到的最优特征组合的评价准则,对joy、anger、pleasure、sadness这4种情感状态进行识别,得到了较好的情感识别效果.仿真实验表明了该方法的可行性和有效性.     

基于进化策略的生理信号情感识别

针对生理信号的情感识别问题,采用进化策略方法对生理信号进行特征选择,利用智能优化算法的计算复杂度低和收敛速度快等特点,并结合使用近邻法进行分类,有效地解决了生理信号特征组合优化问题,筛选出一定的特征子集来表示相应的人类情感状态．实验仿真表明,该方法可以得到有效的特征组合来进行生理信号的情感状态识别．     

基于多特征融合和卷积神经网络的植物叶片识别

植物叶片识别是植物自动分类识别研究的重要分支和热点,利用卷积神经网络进行图像分类研究已成为主流.为了提高植物叶片识别准确率,提出了基于多特征融合和卷积神经网络的植物叶片图像识别方法.首先对植物叶片图像进行预处理,提取LBP特征和Gabor特征,将多特征相加融合输入网络进行训练,使用卷积神经网络(AlexNet)构架作为分类器,利用全连接层对植物叶片进行识别.为了避免过拟合现象,使用"dropout"方法训练卷积神经网络,通过调节学习率、dropout值、迭代次数优化模型.实验结果表明,基于多特征融合的卷积神经网络植物叶片识别方法对Flavia数据库32种叶片和MEW2014数据库189种叶片识别分类效果较好,平均正确识别率分别为93.25％和96.37％,相比一般的卷积神经网络识别方法,该方法可以提高植物叶片的识别准确率,鲁棒性更强.     

支持向量机在皮肤症状图像识别中的应用研究

研究皮肤图像特征提取问题,在皮肤图像症状识别过程中,针对选择出对皮肤症状分类能力强、准确识别图像诊断方法问题,为提高识别率,提出采用遗传算法和小样本、非线性的支持向量机结合起来.通过遗传算法优化对皮肤症状特征空间进行搜索的同时,采用支持向量机对提取的皮肤显微图像的特征参数进行优化组合.在对5类典型皮肤症状进行仿真,使皮肤图像症状的特征通过组合的诊断识别率由87.24%提高到98.15%.实验结果表明,所采用的遗传算法与支持向量机结合的方法对皮肤症状图像识别率的提高是十分有效的,有利于皮肤病症的临床诊断研究.     

结合差分演化和逻辑回归的构音障碍自动识别方法

针对传统的构音障碍诊断方法存在耗时高、成本高等问题，提出一种构音障碍语音的计算机自动识别方法。结合Gammatone频率倒谱系数(Gammatone Frequency Cepstrum Coefficients, GFCC)与常用声学特征形成组合声学特征，应用差分演化算法进行特征选择，并使用逻辑回归分类器对构音障碍语音进行识别。将Torgo构音障碍语音数据库分成3个语音子集，分别是非词、短词语、限制句子集，提取24维GFCC和37维常用的声学特征构成组合声学特征，最后使用差分演化算法和逻辑回归分类器进行分类识别。实验表明：使用差分演化算法可以有效选择出具有更佳识别能力的特征，从而显著提高构音障碍识别率。在非词子集上的实验准确率达到98.18%，召回率为98.3%，精确率为98.3%。     

A hybrid approach to input selection for complex processes

Input selection is a crucial stage for empirical modeling of complex processes with numerous features. This correspondence proposes a new hybrid method of case-based reasoning and genetic algorithm (GA) to identify significant inputs from a set of features. Case-based reasoning is performed repeatedly on a "leave-one-out" procedure to yield an unbiased error estimate for a hypothesis. This error estimate is then combined with the number of selected attributes to provide an evaluation function for the GA, which serves as a search engine to find the optimal hypothesis for the input selection problem. Simulation examples and their results are presented to demonstrate the effectiveness of the proposed approach.     

基于傅里叶变换特征遗传算法的人脸识别

提出了一种基于傅里叶变换特征遗传算法的人脸识别方法。首先对人脸图像进行傅里叶变换,并去掉不包含识别信息的零频率分量。然后以人脸图像傅里叶变换的模作为描述人脸模式的特征,考虑到并不是所有傅里叶特征都包含较好的分类信息,应用遗传算法进行特征选取。实验结果表明：给出的方法不仅具有较好的识别性能,而且可以在一定程度上减少人脸模式的存储空间。     

Use of leaf color images to identify nitrogen and potassium deficient tomatoes

Soilless culture has been popular in modern agriculture. However, plants in soilless culture often appear to be nutrient deficient. Therefore the intellective diagnostic system of plants disease of nutrients deficiency is important. In this paper, a novel idea based on computer vision is presented. Color and texture features of leaves are extracted by some methods such as percent intensity histogram, percent differential histogram, Fourier transform, and wavelet packet. Moreover, Genetic Algorithm (GA) has been used to select features to get the best information for diagnosing the disease. Experiments showed that the accuracy of this diagnostic system is above 82.5% and it can diagnose disease about 6-10 days before experts could determine.     

求解置换流水车间调度问题的改进遗传算法

针对置换流水车间调度问题的基本特征和传统遗传算法易早熟的缺陷,设计了改进遗传算法来求解此问题。采用NEH和Palmer启发式算法进行种群初始化,以提高初始解的质量;根据Metropolis准则对染色体进行选择操作,避免陷入局部最优;在变异过程中引入禁忌算法,避免迂回搜索;在算法迭代过程中引入了保优机制,避免丢失优秀染色体的基因信息;采用自适应终止准则,以保证解的质量。基于典型Benchmark算例的仿真实验结果表明,算法在求解质量和收敛速度方面明显优于NEH算法和种群经过初始优化的传统遗传算法。     

A novel genetic algorithm with different structure selection for circuit design optimization

In the traditional GA, the tournament selection for crossover and mutation is based on the fitness of individuals. This can make convergence easy, but some useful genes may be lost. In selection, as well as fitness, we consider the different structure of each individual compared with an elite one. Some individuals are selected with many different structures, and then crossover and mutation are performed from these to generate new individuals. In this way, the GA can increase diversification into search spaces so that it can find a better solution. One promising application of GA is evolvable hardware (EHW), which is a new research field to synthesize an optimal circuit. We propose an optimal circuit design by using a GA with a different structure selection (GAdss), and with a fitness function composed of circuit complexity, power, and signal delay. Its effectiveness is shown by simulations. From the results, we can see that the best elite fitness, the average fitness value of correct circuits, and the number of correct circuits with GAdss are better than with GA. The best case of optimal circuits generated by GAdss is 8.1% better in evaluation value than that by traditional GA.     

Use of particle swarm optimization for machinery fault detection

A study is presented on the application of particle swarm optimization (PSO) combined with other computational intelligence (CI) techniques for bearing fault detection in machines. The performance of two CI based classifiers, namely, artificial neural networks (ANNs) and support vector machines (SVMs) are compared. The time domain vibration signals of a rotating machine with normal and defective bearings are processed for feature extraction. The extracted features from original and preprocessed signals are used as inputs to the classifiers for detection of machine condition. The classifier parameters, e.g., the number of nodes in the hidden layer for ANNs and the kernel parameters for SVMs are selected along with input features using PSO algorithms. The classifiers are trained with a subset of the experimental data for known machine conditions and are tested using the remaining set of data. The procedure is illustrated using the experimental vibration data of a rotating machine. The roles of the number of features, PSO parameters and CI classifiers on the detection success are investigated. Results are compared with other techniques such as genetic algorithm (GA) and principal component analysis (PCA). The PSO based approach gave a test classification success rate of 98.6–100% which were comparable with GA and much better than with PCA. The results show the effectiveness of the selected features and the classifiers in the detection of the machine condition.     

An investigation of genetic algorithms for the optimization of multi-objective fisheries bioeconomic models

The use of genetic algorithms (GA) for optimization problems offers an alternative approach to the traditional solution methods. GA follow the concept of solution evolution, by stochastically developing generations of solution populations using a given fitness statistic, for example the achievement function in goal programs. They are particularly applicable to problems which are large, non-linear and possibly discrete in nature, features that traditionally add to the degree of complexity of solution. Owing to the probabilistic development of populations, GA do not distinguish solutions, e.g. local optima from other solutions, and therefore cannot guarantee optimality even though a global optimum may be reached. In this paper, a non-linear goal program of the North Sea demersal fisheries is used to develop a genetic algorithm for optimization. Comparisons between the GA approach and traditional solution methods are made, in order to measure the relative effectiveness. General observations of the use of GA in multi-objective fisheries bioeconomic models, and other similar models, are discussed.     

基于IGA优化WNN的产品质量建模方法

针对某轧钢厂的热连轧产品质量生产过程,对遗传算法（GA）的交叉和变异操作进行改进,给出了基于改进的遗传算法（IGA）优化小波神经网络（WNN）结构的产品质量建模方法。仿真实例表明：该建模方法既保留了GA的全局搜索能力和WNN学习算法简单有效的特点,又具有网络训练速度快、建模精度高等优点,表明了该方法的有效性。     

抑郁症患者脑电导联选择算法及分类研究

基于EGI公司64导脑电采集系统,采集了16位青少年抑郁症患者和16位正常人静息态下闭眼4分钟的脑电数据。运用频谱不对称分析法（Spectral Asymmetry Index,SASI）和去趋势波动分析（Detrended Fluctuation Analysis,DFA）算法提取脑电时域和频域特征。针对提取的特征的导联,一方面,选择最佳电极Pz作为分类的导联,另一方面,通过遗传算法对所有导联进行筛选,将筛选后的导联特征用于分类。使用支持向量机（Support Vector Machine,SVM）在单导联和多导联的情况下,对抑郁症患者和正常人进行分类,结果发现,单导联下,使用SVM分类器对抑郁组和对照组的SASI和DFA结果进行分类,分类精度分别为45.5%和51.5%,使用遗传算法的分类精度分别为78.1%和90.6%,SASI算法的计算实时性优于DFA算法,DFA算法的准确性优于SASI算法。该研究为抑郁症的计算机辅助诊断提供了理论依据。     

Evolving CBR and data segmentation by SOM for flow time prediction in semiconductor manufacturing factory

Flow time of semiconductor manufacturing factory is highly related to the shop floor status; however, the processes are highly complicated and involve more than 100 production steps. Therefore, a simulation model with the production process of a real wafer fab located in Hsin-Chu Science-based Park of Taiwan is built for further studying of the relationship between the flow time and the various input variables. In this research, a hybrid approach by combining Self-Organizing Map (SOM) and Case-Based Reasoning (CBR) for flow time prediction in semiconductor manufacturing factory is developed. And Genetic Algorithm (GA) is applied to fine-tune the weights of features in the CBR model. The flow time and related shop floor status are collected and fed into the SOM for clustering. Then, a corresponding SGA-CBR method is selected and applied for flow time prediction. Finally, using the simulated data, the effectiveness of the proposed method (SGA-CBR) is shown by comparing with other approaches.