基于EEMD和关联维数的矿山微震信号特征提取和分类

针对岩体工程中岩体破裂信号与爆破振动信号难以自动区分的问题,提出了一种基于集合经验模态分解(EEMD)关联维数与机器学习相结合的微震信号特征提取和分类方法。利用EEMD将微震信号分解为本征模态函数(IMF)分量,并从得到的IMF分量中筛选出主分量IMF1～IMF4,再通过相空间重构计算出各个主分量的关联维数,最后将所得到的关联维数作为特征向量,使用SVM方法进行微震信号自动识别,并与其他机器学习方法进行对比分析。试验结果表明:该方法对微震信号的自动识别具有较高的准确率,且基于高斯核函数的SVM的识别效果明显优于逻辑回归(LR)和K-近邻算法(KNN)判别法的识别结果,其准确率达到93.7%。     

基于KPCA的非线过程监视研究

核主元分析(KPCA)是最近出现的一种颇具前景的处理大量线性问题的有效方法.该方法可通过集成算子与非线性核函数有效计算高维特性空间的主元成分,与线性PCA相比,显示出更高的过程监视性能.本文以一个三维非线性系统为对象,在MATLAB防真环境下分别进行PCA和KPCA监视仿真.仿真结果表明了KPCA对于非线性系统监视的良好效果.     

基于核主成分分析与SVM的岩爆烈度组合预测模型

为了更好地预测岩土工程中的岩爆烈度,建立了基于多类型核函数的主成分分析方法与遗传算法或粒子群优化算法(GA/PSO)优化的支持向量机(SVM)相结合的组合预测模型。选取围岩最大切向应力σ_θ、岩石单轴抗拉强度σ_t、岩石单轴抗压强度σ_c、应力集中系数SCF、脆性指数B_1和B_2以及弹性应变能指数Wet共7个指标构成岩爆预测指标体系。基于统计的246个国内外岩爆实例数据,分别运用主成分分析和基于线性核函数、RBF核函数以及MLP核函数的主成分分析对数据进行预处理,得到2～4个线性无关的主成分。再将降维后的数据输入GA/PSO优化的SVM模型进行训练和预测。经测试,基于RBF核函数的主成分分析方法与PSO-SVM相结合的模型预测准确率达到了92.3%,为最佳组合模型,为岩土工程中的岩爆烈度预测提供了一种可靠的方法。     

基于深度映射多核的热镀锌镀层厚度预测

连续热镀锌的镀层厚度控制具有高维、非线性和时变的特点，很难用传统的数学模型和浅层神经网络来预测。深度学习通过多层非线性网络结构，能实现复杂函数关系的良好逼近，而核学习是处理复杂非线性数据的强大工具。提出了一种基于深度神经网络多层信息的深度映射多核学习算法，通过将此深度映射核与多尺度高斯基核做非线性乘积，得到新的具有高度表达能力的改进核，其蕴含数据深层特征信息。大量基准数据集和实际工业数据表明，本算法通过结合深度学习和多核学习的优势，解决了镀锌过程强非线性、时变大滞后和多变量的控制难点，实现镀层厚度的更高精度预测，预测的平均绝对误差从3.04 g/m²降低到1.22 g/m²。     

基于图像混合核的列生成PM2.5预测

传统PM_2.5预测方法获取污染物浓度数据需要大型精密仪器，成本较高。本文尝试利用图像数据进行PM_2.5浓度预测。大气PM_2.5浓度的变化与图像的暗通道强度、对比度和HSI（Hue-saturation-intensity）颜色差异有密切联系。大气中PM_2.5浓度的升高会导致非天空区域的暗通道强度值下降，图像对比度下降和HSI空间颜色差异变小。通过分析PM_2.5浓度与图像特征的关系，提出了一种基于图像混合核的列生成空气质量PM_2.5预测模型。首先，以1 h为采样周期，每日8:00～17:00为采样范围，采集多种天气条件下的景物图像，提取图像的对比度、暗通道强度和HSI颜色差异共5个图像特征。其次，数据存在样本规模大、样本不平坦分布等特点，单个核函数构成的预测模型难以满足预测精度需求，因此本文按照核结构从简单到复杂的原则，选择线性核函数、多项式核函数和高斯核函数三种核函数建立组合模型。然后计算每个核基于训练样本的Gram矩阵，并将所有Gram矩阵并列成一个混合核矩阵。利用列生成算法和混合核矩阵建立预测模型，求解模型参数。最后，进行仿真实验，实验结果表明本文提出的可满足预测精度要求，与单核预测模型相比，该预测模型预测精度更高，模型稳定性更好。计算复杂度分析结果显示基于图像混合核的列生成模型与单核预测模型相比计算量无明显增加。      

基于软超球体的高维非线性数据异常点识别算法

在冶金、化工等流程型工业领域,生产中的过程控制参数往往具有高维非线性结构特征.为了解决这类高维复杂数据的异常点检测问题,本文引入了软超球体的概念,采用非线性核函数将原始数据映射到高维的特征空间,并在特征空间中确定软超球体的边界.通过检测待识别样本映射到特征空间的位置信息来判定过程参数的设定值是否为异常点,从而避免出现批量的产品质量问题.以某类汽车用钢为应用实例,对实际生产数据进行检测,证明了所提出的基于软超球体的异常点识别算法对于高维的非线性数据具有良好的检测能力.      

基于支持向量机的围岩定性智能分级研究

本文将数据挖掘的新方法支持向量机应用于隧道围岩分级.支持向量机是一种基于统计学习理论的新的学习算法,比神经网络算法能更好地解决小样本问题.选用岩层厚度、岩体结构、嵌合程度、风化程度、地下水特征、节理发育程度、榔头敲击声和地应力等 8 个定性指标作为评判因子,用泥巴山隧道采集的实际数据作为样本对不同核函数的支持向量机进行训练,并得到评判因子与围岩级别的映射关系,从而可以对未知的围岩样本进行级别判别.判别结果表明:采用多项式核的支持向量机对围岩级别进行判别有较高的准确率,是一种值得推广和应用的围岩智能分级方法.     

基于机器视觉和SVM的AOD炉终点预测方法

针对AOD炉冶炼中低碳铬铁合金工艺过程终点判别依靠人工看火操作的难题,提出了利用机器视觉技术模拟传统人工看火过程进行终点判别的方法。利用灰度级提取AOD炉口火焰特征,采用支持向量机（SVM）算法实现图像特征的训练和测试,对比了3种核函数的测试精度。实验结果表明,采用机器视觉技术提取火焰图像特征并与支持向量机结合的方法能够有效识别冶炼终点,并具有较好的识别精度。     

基于时滞混沌系统的带密钥Hash函数的设计与分析

提出了一种基于时滞混沌系统的带密钥Hash函数算法,该算法利用时滞混沌系统非线性动力学特性,将需要传送的明文信息调制在时滞混沌迭代的轨迹中,并通过HMAC-MD5算法计算得出Hash值,Hash值的每个比特都与需传送的明文信息相关.该算法使Hash值对明文信息及时滞混沌迭代初始条件的微小变化高度敏感.理论分析和仿真结果均表明,该算法在保证Hash值的混乱性和散布性的同时,由于其混沌特性的加入而增大了参数空间,并且混沌Hash值与初始明文信息之间的非线性关系可以有效地抵御线性分析.因此,本文设计的基于时滞混沌系统的Hash函数算法具有很好的安全性、抗碰撞性和抗攻击能力,在数字签名等认证技术领域有很好的应用前景.     

核函数方法(下)

２主分量分析法２．１经典的主分量分析法［５］主分量分析 (ＰＣＡ)是一种经典的统计方法 ,它对多元统计观测数据的协方差结构进行分析 ,以期求出能简约地表达这些数据依赖关系的主分量。具体地说 ,通过线性变换将原始ｎ维观测矢量化为个数相同的一组新特征 ,即每一个新特征都是原始特征的线性组合 ,如果这些新特征互不相关 ,其中少数ｍ个（ｍ ｎ）包含了原始数据主要信息的最重要的特征就是主分量。因此 ,主分量分析是一种特征抽取的方法 ,也可以认为是一种数据压缩 (降维 )的方法。设以ｍ个正交矢量｛ｕｉ∈Ｒｎ；ｉ＝１，２，… ,ｍ｝…     

基于全局优化支持向量机的多类别高炉故障诊断

针对高炉故障诊断系统快速性和准确性的要求,提出基于全局优化最小二乘支持向量机的策略.首先,采用变尺度离散粒子群对最小二乘支持向量机的参数和故障特征的选取进行优化;然后,利用核主元分析法对选取的特征向量进行压缩整理;最后,构造了以Fisher线性判别率为标准的启发式纠错输出编码.仿真结果表明,通过对故障训练样本有意义地分割重组,用较少的最小二乘支持向量机分类器,得到较高的故障判断准确率且增强了整个系统的实时性.      

基于核主成分分析与PSO-SVM的充填管道失效风险性分级评价模型

为了更精确地对充填管道失效风险性进行预测,建立核主成分分析与PSO-SVM相结合的评价模型。选取8项定量指标作为充填管道失效风险性的评价指标。统计15个矿山的样本数据,运用核主成分分析法对15个样本进行预处理,得出主成分,再利用改进的SVM模型进行预测,进而得到更加精确的管道失效风险性预测结果。研究结果表明,所得到的实际预测结果与期望值之间的平均相对误差控制在5%以内。利用核主成分分析法与PSO-SVM相结合的评价模型具有精度高和运算速度快的优点,为充填管道失效风险预测提供了一种可靠的方法。     

From magnetic resonance spectroscopy to classification of tumors. A review of pattern recognition methods

This article reviews the wealth of different pattern recognition methods that have been used for magnetic resonance spectroscopy (MRS) based tumor classification. The methods have in common that the entire MR spectra is used to develop linear and non-linear classifiers. The following issues are addressed: (i) pre-processing, such as normalization and digitization, (ii) extraction of relevant spectral features by multivariate methods, such as principal component analysis, linear discriminant analysis (LDA), and optimal discriminant vector, and (iii) classification by LDA, cluster analysis and artificial neural networks. Different approaches are compared and discussed in view of practical and theoretical considerations.     

Computerized analysis of mammographic microcalcifications in morphological and texture feature spaces

We are developing computerized feature extraction and classification methods to analyze malignant and benign microcalcifications on digitized mammograms. Morphological features that described the size, contrast, and shape of microcalcifications and their variations within a cluster were designed to characterize microcalcifications segmented from the mammographic background. Texture features were derived from the spatial gray-level dependence (SGLD) matrices constructed at multiple distances and directions from tissue regions containing microcalcifications. A genetic algorithm (GA) based feature selection technique was used to select the best feature subset from the multi-dimensional feature spaces. The GA-based method was compared to the commonly used feature selection method based on the stepwise linear discriminant analysis (LDA) procedure. Linear discriminant classifiers using the selected features as input predictor variables were formulated for the classification task. The discriminant scores output from the classifiers were analyzed by receiver operating characteristic (ROC) methodology and the classification accuracy was quantified by the area, Az, under the ROC curve. We analyzed a data set of 145 mammographic microcalcification clusters in this study. It was found that the feature subsets selected by the GA-based method are comparable to or slightly better than those selected by the stepwise LDA method. The texture features (Az = 0.84) were more effective than morphological features (Az = 0.79) in distinguishing malignant and benign microcalcifications. The highest classification accuracy (Az = 0.89) was obtained in the combined texture and morphological feature space. The improvement was statistically significant in comparison to classification in either the morphological (p = 0.002) or the texture (p = 0.04) feature space alone. The classifier using the best feature subset from the combined feature space and an appropriate decision threshold could correctly identify 35% of the benign clusters without missing a malignant cluster. When the average discriminant score from all views of the same cluster was used for classification, the Az value increased to 0.93 and the classifier could identify 50% of the benign clusters at 100% sensitivity for malignancy. Alternatively, if the minimum discriminant score from all views of the same cluster was used, the Az value would be 0.90 and a specificity of 32% would be obtained at 100% sensitivity. The results of this study indicate the potential of using combined morphological and texture features for computer-aided classification of microcalcifications.     

Variational learning in nonlinear gaussian belief networks

We view perceptual tasks such as vision and speech recognition as inference problems where the goal is to estimate the posterior distribution over latent variables (e.g., depth in stereo vision) given the sensory input. The recent flurry of research in independent component analysis exemplifies the importance of inferring the continuous-valued latent variables of input data. The latent variables found by this method are linearly related to the input, but perception requires nonlinear inferences such as classification and depth estimation. In this article, we present a unifying framework for stochastic neural networks with nonlinear latent variables. Nonlinear units are obtained by passing the outputs of linear gaussian units through various nonlinearities. We present a general variational method that maximizes a lower bound on the likelihood of a training set and give results on two visual feature extraction problems. We also show how the variational method can be used for pattern classification and compare the performance of these nonlinear networks with other methods on the problem of handwritten digit recognition.     

Acoustic Monitoring of Plasma Arcs in Direct Current Electric Arc Furnaces

In this article, the extraction of features from acoustic signals generated by a 60-kW direct current electric arc furnace and the use of these features to infer the arc length of the plasma jets in the furnace were considered. A sensor capable of such measurements would be more robust to the unobservable fluctuations of the arc length and would, in principle, allow better control of smelting operations. The collected data comprised sets of five separate 10-second recordings of the acoustic signal, furnace current, and voltage, each at nominal arc lengths of 5, 15, and 25 mm. In the approach, time-frequency features initially were obtained through filter bank analysis of the signals. Reduction of the dimensionality of these filter bank features was then performed using a nonlinear subspace method called kernel Fisher discriminant analysis. Finally, kernel discriminant features were used to infer the arc length via a nearest neighbor classification model that associated three classes of arc lengths (5, 15, and 25 mm) with their corresponding features. The results of the small number of experiments suggest that a significant statistical relationship exists between the length of a plasma arc and its acoustic signal despite potentially large variations in arc phenomena inside the furnace.     

基于核主成分分析的热连轧断带故障诊断

热连轧生产过程中经常出现设备和质量故障,为了快速确定故障原因并排除故障,需要对生产过程开展监控以及对故障进行诊断。基于热连轧生产过程采集的数据,采用核主成分分析法对热连轧轧制过程中精轧机组相关数据进行监控,并对断带故障进行诊断。先使用平方预测误差(SPE)统计量监控生产过程,再基于核主成分分析绘制出各变量贡献率图,最后依据贡献率大小找出造成故障的主要影响变量。与主成分分析法相比,采用核主成分分析法更为高效和准确。基于核主成分分析的热连轧断带故障诊断可节省故障分析时间,为热连轧生产过程调整和故障排除提供依据,具有重要的理论意义和实际应用价值。     

Use of neural networks to diagnose acute myocardial infarction. I. Methodology

We investigated several aspects of using neural networks as a diagnostic tool: the design of an optimal network, the amount of patients' data needed to train the network, the question of training the network optimally while avoiding overfitting, and the influence of redundant variables. The specific clinical problem chosen for illustration was the diagnosis of acute myocardial infarction, given only the electrocardiogram and the concentration of potassium in serum at the time of admission. We found that, in contrast to usual practice, the termination of the training process should be based on the generalization performance and not on the training performance. We also found that a principal component analysis can be used to eliminate redundant variables, thereby reducing the data space. The diagnostic performance of the neural network we used was 78%--superior to that of linear discriminant function analysis but similar to that of quadratic discriminant function analysis.     

Supervised mutual-information based feature selection for motor unit action potential classification

A new supervised mutual information-based feature selection method is presented. Using real motor unit action potential (MUAP) data from 10 EMG signals, the performances of 32 time-sample feature sets, feature subsets selected using first- and second-order mutual information and features obtained using linear discriminant analysis (LDA) and principal component analysis (PCA) were evaluated using a minimum Euclidean distance (MED) classifier. The evaluation showed that by using only 20 first-order features or only 15 second-order features mean error rates and error rate variations equivalent to using all 32 samples or LDA or PCA could be obtained. The computational cost of first-order feature selection was considerably less than LDA, PCA and second-order feature selection. The performance of first-order features was further evaluated using a more robust classifier. Unlike the MED classifier, the robust classifier only assigned a candidate MUAP if the assignment was sufficiently certain. For the robust classifier the average error rates using 20 features were similar to using the full feature set, yet higher assignment rates were obtained. Results from both evaluations suggest that the sets of first-order features were an efficient representation of lower dimension, which provided high accuracy classification with reduced computational requirements.     

Classification of observational data with artificial neural networks versus discriminant analysis in pharmacoepidemiological studies--can outcome of fluoxetine treatment be predicted?

For several years, there has been an ongoing discussion about appropriate methodological tools to be applied to observational data in pharmacoepidemiological studies. It is now suggested by our research group that artificial neural networks (ANN) might be advantageous in some cases for classification purposes when compared with discriminant analysis. This is due to their inherent capability to detect complex linear and nonlinear functions in multivariate data sets, the possibility of including data on different scales in the same model, as well as their relative resistance to "noisy" input. In this paper, a short introduction is given to the basics of neural networks and possible applications. For demonstration, a comparison between artificial neural networks and discriminant analysis was performed on a multivariate data set, consisting of observational data of 19738 patients treated with fluoxetine. It was tested, which of the two statistical tools outperforms the two other in regard to the therapeutic response prediction from the clinical input data. Essentially, it was found that neither discriminant analysis nor ANN are able to predict the clinical outcome on the basis of the employed clinical variables. Applying ANN, we were able to rule out the possibility of undetected suppressor effects to a greater extent than would have been possible by the exclusive application of discriminant analysis.