基于遗传算法的带钢表面缺陷特征降维优化选择

针对带钢表面的划痕、黑斑、翘皮、辊印、褶皱和压印6种典型缺陷,提取了样本图像的灰度、纹理和几何形状特征等32维特征向量。基于遗传算法对32维特征向量进行降维优化选择,选择了其中的20维以进行缺陷图像类型的分类。利用BP神经网络对降维前后的6种典型带钢表面缺陷分类进行对比识别,并同主成分降维方法进行了对比,验证了所提取的...     

冷轧带钢表面质量自动监测系统的模式识别方法研究

研究了冷轧带钢表面质量自动监测系统的模式识别过程，包括特征的提取和选择，样本的获取，分类器的设计等。提取了缺陷的83个特征量，并且采用基于信息熵的特征选择方法对这些特征量进行了优化选择，构建了基于BP神经网络的分类器模型，通过现场采集的样本对其进行训练作测试，结果表明该分类器能够很好地识别6种常见的冷轧带钢表面缺陷。     

多级图像分类系统在硅钢冷轧表面缺陷检测中的应用

针对硅钢冷轧生产过程中带钢表面缺陷的特点,采用一种基于专家经验和决策树分类器的多级带钢表面缺陷图像分类系统,包含训练集与测试集的采集、特征提取、专家经验训练分类器、决策树分类器等。实际应用表明,该系统能较好地识别结疤、重皮、孔洞和边裂等严重缺陷图像,提高了武钢硅钢冷轧生产过程的自动化水平。     

冷轧带钢表面缺陷智能检测技术的发展

介绍了冷轧带钢表面缺陷检测技术的现状、开发新检测装置的目的和要求及最近开发成功的在线智能检测仪表的原理、装置构成等。地缺陷的自动分类方法、神经网络分类器和用于地风质量进行自动分级的专家系统做了简要介绍。     

最优尺度分形维数在热轧带钢表面缺陷识别中的应用

热轧带钢的表面图像往往存在氧化铁皮等伪缺陷的干扰与光照不均的问题,目前的识别方法存在着误识率高的问题.将分形维数作为特征量,用于对热轧带钢表面缺陷的自动识别.利用peleg毯覆盖法计算图像在不同尺度下的分形维数,并提出最优尺度概念,通过尺度一分形维数曲线图估计最优尺度.对麻面、氧化铁皮和夹杂等进行试验,分别计算不同尺度下的分形维数,作为特征量输入Adaboost分类器进行训练和测试.试验结果表明用最优尺度下的分形维数作为特征量,分类器得到的识别率是所有尺度下最优的,即87.96%.     

冷轧带钢表面缺陷自动识别系统

德国尤格尔 ( Ungerer)公司开发出冷轧带钢表面缺陷自动识别系统“Fire”,它可在线自动并完整识别冷轧带钢表面缺陷。该系统完全采用软件数据处理 ,并配置了目前最先进的图像处理器。因而“Fire”系统从传感器到完成数据交换功能的数据库接口均具有高度的灵活性。尤格尔 ( U ngerer)公司的“Fire”系统的特点是 :可在冷轧带钢高速运行状态下可靠检测带钢表面微小缺陷并加以分类 ,以连续报告带钢表面质量。该系统可根据下游工序 ,如纵剪机组的要求进行目标控制 ,也可为本工艺过程的优化提供重要信息。为满足用户对冷轧带钢表面质量的更高要…     

1250热轧带钢冷轧基料“起皮”缺陷成因探究

针对德龙公司1 250生产线带钢冷轧基料表面大规模出现的"起皮"缺陷问题,研究了冷轧基料边部缺陷的宏观和微观特征,通过对冷轧基料和后续冷轧薄宽带钢缺陷组织金相观察、电镜和能谱分析,确定了带钢边部"起皮"的根本原因。在炼钢连铸环节,通过减少连铸过程中的水口总吹氩量,改变中间包水口插入深度等措施,"起皮"缺陷发生概率由7.2%降到1%以下。     

冷轧带钢表面缺陷识别与控制

针对冷轧带钢常见表面缺陷的种类、识别以及产生原因进行详细的论述,提出了主要预防和控制措施,对冷轧带钢表面缺陷有了进一步的认识,对提高带钢表面质量极其重要。     

铜锡夹杂对非合金软钢加工性能的影响

平炉钢的热轧带钢进行冷轧时,轧制一道或二道后,经常产生表面缺陷。这种表面缺陷是表面鳞皮或泡痕。表面看来,似乎是由于被轧入的小块氧化铁皮所引起。已经确定,用同样方法生产的再加工热轧带钢,产生缺陷的可能性是各不相同的。冷轧带钢的     

一种基于特征选择的组合分类器在带钢表面缺陷分类中的应用

针对大规模数据集的分类问题,提出一种基于特征选择的新型组合分类器算法FS-Bagging。首先利用Re-liefF算法和Pearson相关算法对原始特征集进行特征选择,得到次优特征集;然后利用Bagging的思想,对次优特征集进行随机放回采样后得到一系列的特征子集;再用各特征子集对应的训练数据分别构建分类器,并将得到的多个分类器采用投票方法进行组合。最后利用国内某钢厂带钢表面质量检测系统中的实际数据,对18种缺陷进行分类实验。实验结果表明,FS-Bagging算法在效率、分类正确率方面都优于Bagging算法。     

基于多维时间序列形态特征的相似性动态聚类算法

由于时间序列数据具有高维度、动态性等特点,这就导致传统的数据挖掘技术很难有效的对其进行处理,为此,提出了一种基于多维时间序列形态特征的相似性动态聚类算法(similarity dynamical clustering algorithm based on multidimensionalshape features for time series,SDCTS).首先,提取多维时间序列的特征点以实现降维,然后,根据多维时间序列的斜率、长度和幅值变化的形态特征定义了一种新的时间序列相似性度量标准,进而提出无需人为给定聚类个数的多维时间序列动态聚类算法.实验结果表明,与其他算法相比,此算法对时间序列具有良好的聚类效果.      

一种面向网络长文本的话题检测方法

提出了一种面向网络长文本的话题检测方法.针对文本表示的高维稀疏性和忽略潜在语义的问题,提出了Word2vec&LDA（latent dirichlet allocation）的文本表示方法.将LDA提取的文本特征词隐含主题和Word2vec映射的特征词向量进行加权融合既能够进行降维的作用又可以较为完整的表示出文本信息.针对传统话题发现方法对长文本输入顺序敏感问题,提出了基于文本聚类的Single-Pass&HAC（hierarchical agglomerative clustering）的话题发现方法,在引入时间窗口和凝聚式层次聚类的基础上对于文本的输入顺序具有了更强的鲁棒性,同时提高了聚类的精度和效率.为了评估所提出方法的有效性,本文从某大学社交平台收集了来自真实世界的多源数据集,并基于此进行了大量的实验.实验结果证明,本文提出的方法相对于现有的方法,如VSM（state vector space model）、Single-Pass等拥有更好的效果,话题检测的精度提高了10%~20%.      

Application of Kohonen Neural Networks in classification of biologically active compounds

Automated data classification is an indispensable tool in Drug Design. It allows to select homogeneous training sets or to distinguish compounds with required biological properties. The Kohonen Neural Networks (KNN) suggest new means for classification of biologically interesting compounds. In this paper, first, capabilities of KNN in data dimensionality reduction are presented as compared with the capabilities of Principal Component Analysis (PCA) and Hierarchical Cluster Analysis (HCA). The advantages of KNN become evident with increasing data dimensionality and size of the training set. Then, new methods are suggested to evaluate the quality of KNN models. Finally, a case study on chemical and biological data is presented. The database studied includes more than 2000 organophosphorous potent pesticides. The Kohonen maps were obtained which allow to distinguish compounds with different biological behavior.     

Integrating Novel Dimensions to Eliminate Category Exceptions: When More Is Less.

Category learning can be characterized as a process of discovering the dimensions that represent stimuli efficiently and effectively. Categories that are overlapping when represented in 1 dimensionality may be separate in a higher dimensional cue set. The authors report 2 experiments in which participants were shown an additional cue after learning to use 2 imperfect cues. The results revealed that participants can integrate new information into their categorization cue set. The authors discovered wide individual differences, however, with many participants favoring simpler, but less accurate, cue sets. Some participants demonstrated the ability to discard information previously used when new, more accurate information was introduced. The categorization model RASHNL (J. K. Kruschke & M. K. Johansen, 1999) gave qualitatively accurate fits of the data. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A taxometric investigation of the latent structure of worry.

Researchers have described 2 types of worriers, normal and pathological, who differ in the frequency, intensity, and controllability of their worry experiences. Although normal and pathological worry are generally treated as separate though related phenomena, no study has tested for separateness against the alternative hypothesis that all worry exists along a single dimension. In the present study, worry ratings of 1,588 college students were submitted to taxometric procedures designed to evaluate latent structure. Results provided evidence for the dimensionality of worry. These findings suggest that generalized anxiety disorder (GAD), whose central feature is worry, may also be quantitatively rather than qualitatively different from normal functioning. The authors argue that a focus on normal and pathological extremes has constrained the study of worry phenomena and that dimensional conceptualization of worry may significantly enhance understanding of both worry and GAD. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Analyzing the generality of conflict adaptation effects.

Conflict adaptation effects refer to the reduction of interference when the incongruent stimulus occurs immediately after an incongruent trial, compared with when it occurs after a congruent trial. The present study analyzes the key conditions that lead to adaptation effects that are specific to the type of conflict involved versus those that are conflict general. In the first 2 experiments, we combined 2 types of conflict for which compatibility arises from clearly different sources in terms of dimensional overlap while keeping the task context constant across conflict types. We found a clear pattern of specificity on conflict adaptation across conflict types. In subsequent experiments, we tested whether this pattern could be accounted in terms of feature integration processes contributing differently to repetition versus alternation of conflict types. The results clearly indicated that feature integration was not key to generating conflict type specificity on conflict adaptation. The data are consistent with there being separate modes of control for different types of cognitive conflict. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

基于主成分分析和PSO-ELM算法的排土场稳定性预测模型

针对排土场边坡稳定性分析,提出了一种利用主成分分析法降低数据冗余性、粒子群算法优化极限学习机权值阈值的PCA-PSO-ELM排土场边坡稳定性预测模型。确定了土壤黏聚力、内摩擦角、排土场斜角、地基承载力、地震烈度、降雨和降雪条件、排土工艺以及乱采乱挖状况8个排土场稳定性预测指标,针对100组相应排土场数据,采用训练时间、RMSE值和决定系数R²来评价和对比PCA-PSO-ELM模型与BP神经网络模型、ELM模型和PSO-ELM模型预测结果的有效性。研究结果表明：利用经PCA降维处理过的排土场稳定性样本数据作为输入变量去训练和测试PSO-ELM网络模型,预测值与真实值非常接近,其预测精度和效率不仅高于ELM算法,而且远远优于传统BP神经网络算法。经过PCA法优化的PSO-ELM模型与未经PCA处理过的PSO-ELM模型相比,前者在效率相差甚微的基础上大幅缩短了计算时间,证明了该方法具有一定的实用价值。     

Computer-assisted image classification: use of neural networks in anatomic pathology

Artificial neural networks (ANN) implemented on digital computers have received much attention for interpretation of images in pathology and cytology. Most such images are too complex for current ANN to interpret directly; instead, ANN usually classify the images according to numeric features extracted from them. In experiments on three distinct image classification problems, ANN classifiers performed as well or better than multivariate linear discriminant analysis (a traditional parametric statistical classifier). ANN empirically define non-linear multivariate decision boundaries, and can combine non-contiguous feature areas in mapping a classification. However, many training cases are required in order to map complex area boundaries precisely and with a low risk of 'overtraining.' Careful problem selection and attention to data dimensionality and format are important for efficient ANN use.     

Surface Detection of Continuous Casting Slabs Based on Curvelet Transform and Kernel Locality Preserving Projections

 Longitudinal cracks are common defects of continuous casting slabs and may lead to serious quality accidents. Image capturing and recognition of hot slabs is an effective way for on-line detection of cracks, and recognition of cracks is essential because the surface of hot slabs is very complicated. In order to detect the surface longitudinal cracks of the slabs, a new feature extraction method based on Curvelet transform and kernel locality preserving projections (KLPP) is proposed. First, sample images are decomposed into three levels by Curvelet transform. Second, Fourier transform is applied to all sub-band images and the Fourier amplitude spectrum of each sub-band is computed to get features with translational invariance. Third, five kinds of statistical features of the Fourier amplitude spectrum are computed and combined in different forms. Then, KLPP is employed for dimensionality reduction of the obtained 62 types of high-dimensional combined features. Finally, a support vector machine (SVM) is used for sample set classification. Experiments with samples from a real production line of continuous casting slabs show that the algorithm is effective to detect longitudinal cracks, and the classification rate is 91. 89%.