Improved Twin Support Vector Machine Algorithm and Applications in Classification Problems

The distribution of data has a significant impact on the results of classification.When the distribution of one class is insignificant compared to the distribution of another class,data imbalance occurs.This will result in rising outlier values and noise.Therefore,the speed and performance of classification could be greatly affected.Given the above problems,this paper starts with the motivation and mathematical representing of classification,puts forward a new classification method based on the relationship between different classification formulations.Combined with the vector characteristics of the actual problem and the choice of matrix characteristics,we firstly analyze the orderly regression to introduce slack variables to solve the constraint problem of the lone point.Then we introduce the fuzzy factors to solve the problem of the gap between the isolated points on the basis of the support vector machine.We introduce the cost control to solve the problem of sample skew.Finally,based on the bi-boundary support vector machine,a twostep weight setting twin classifier is constructed.This can help to identify multitasks with feature-selected patterns without the need for additional optimizers,which solves the problem of large-scale classification that can’t deal effectively with the very low category distribution gap.

Accelerated Recursive Feature Elimination Based on Support Vector Machine for Key Variable Identification

Key variable identification for classifications is related to many trouble-shooting problems in process indus-tries. Recursive feature elimination based on support vector machine (SVM-RFE) has been proposed recently in applica-tion for feature selection in cancer diagnosis. In this paper, SVM-RFE is used to the key variable selection in fault diag-nosis, and an accelerated SVM-RFE procedure based on heuristic criterion is proposed. The data from Tennessee East-man process (TEP) simulator is used to evaluate the effectiveness of the key variable selection using accelerated SVM-RFE (A-SVM-RFE). A-SVM-RFE integrates computational rate and algorithm effectiveness into a consistent framework. It not only can correctly identify the key variables, but also has very good computational rate. In comparison with contribution charts combined with principal component aralysis (PCA) and other two SVM-RFE algorithms, A-SVM-RFE performs better. It is more fitting for industrial application.

Fault Diagnosis Based on Fuzzy Support Vector Machine with Parameter Tuning and Feature Selection

This study describes a classification methodology based on support vector machines(SVMs),which offer superior classification performance for fault diagnosis in chemical process engineering.The method incorporates an efficient parameter tuning procedure(based on minimization of radius/margin bound for SVM's leave-one-out errors)into a multi-class classification strategy using a fuzzy decision factor,which is named fuzzy support vector machine(FSVM).The datasets generated from the Tennessee Eastman process(TEP)simulator were used to evaluate the clas-sification performance.To decrease the negative influence of the auto-correlated and irrelevant variables,a key vari-able identification procedure using recursive feature elimination,based on the SVM is implemented,with time lags incorporated,before every classifier is trained,and the number of relatively important variables to every classifier is basically determined by 10-fold cross-validation.Performance comparisons are implemented among several kinds of multi-class decision machines,by which the effectiveness of the proposed approach is proved.

Support vector classification algorithm based on variable parameter linear programming

To solve the problems of SVM in dealing with large sample size and asymmetric distributed samples, a support vector classification algorithm based on variable parameter linear programming is proposed. In the proposed algorithm, linear programming is employed to solve the optimization problem of classification to decrease the computation time and to reduce its complexity when compared with the original model. The adjusted punishment parameter greatly reduced the classification error resulting from asymmetric distributed samples and the detailed procedure of the proposed algorithm is given. An experiment is conducted to verify whether the proposed algorithm is suitable for asymmetric distributed samples.

基于VMD-IMPA-SVM的超短期风电功率预测

针对风力发电强波动性带来的预测精度不高问题,构建一种基于变模态分解(VMD)、灰狼优化算法(GWO)、海洋捕食者算法(MPA)和支持向量机(SVM)的组合预测模型。采用GWO对VMD的模态数和惩罚因子进行寻优,将原始功率序列分解为子序列进行降噪处理;运用对立学习和柯西变异等方法改进MPA的种群生成与变异方式,得到改进MPA(IMPA)并优化SVM中的核参数与惩罚参数,进而构建VMD-IMPA-SVM组合预测模型,对各子序列进行预测并叠加得到最终预测值。实际算例分析表明,所提组合预测模型具有较高的预测精度,同时具备强鲁棒性。

基于变量敏感度筛选的回归型支持向量机的数控机床热误差预测

随着机械制造行业的迅猛发展,对于数控机床的定位精度要求越来越高。为了提高机床定位精度,建立了基于变量敏感度筛选与回归型支持向量机(SVR)混合模型,并将其用于数控机床热误差预测方法。该方法基于对变量敏感度分析,筛选掉敏感度低的干扰自变量。本方法与基本SVR模型对数控机床热误差预测值进行对比,结果表明基本SVR受到敏感度低的干扰自变量影响,预测结果与实测热误差结果偏差较大;经过变量敏感度筛选之后的SVR混合模型预测值具有更高的准确度,验证了此模型的可行性。

基于近红外高光谱图像的花生内部霉变快速判别方法研究

目的针对外观正常但内部存在不同程度霉变的花生,探索采用近红外高光谱成像技术结合机器学习方法构建花生内部霉变快速无损判别模型的可行性。方法采集100粒内部霉变和100粒健康花生的近红外高光谱图像构成数据集,将多种经典光谱预处理方法与支持向量机(support vector machine,SVM)组合建立花生内部霉变判别模型,并采用蒙特卡洛-无信息变量消除法(Monte Carlo-uninformative variable elimination,MC-UVE)找出霉变判别中有效的光谱特征波长。结果将Savitzky-Golay卷积平滑方法和二阶求导光谱预处理方法与SVM组合,对内部霉变严重样本判别的总体识别准确率可达95%,对不同程度内部霉变样本的平均识别准确率为88%;基于MC-UVE筛选得到10、5、3个特征波长构建的模型总体识别准确率为90%、85%和82%。结论实验结果表明高光谱技术结合机器学习可为花生内部霉变的快速、无损判别提供可行的解决方案,同时特征波长筛选为基于光电原理的霉变花生色选机系统开发提供了参考。

利用i-vectors构建区分性话者模型的话者确认

对于电话手机语音的文本无关话者确认,运用联合因子分析构建话者信息子空间与信道信息子空间来进行失配信道补偿取得了较好的效果.然而研究表明,信道信息子空间仍然包含了可以用来区分话者的信息.因此,本文运用一种既包含话者信息又包含信道信息的全变量信息子空间来提取i-vectors低维特征矢量,再运用类内协方差规整进行失配信道补偿,最后用补偿后的i-vectors特征矢量构建支持向量机话者模型.在NIST08数据库上实验表明,本文所构建系统的性能在等误识率和最小检测代价函数上有相对近70%的提高.

风力发电机高速旋转齿轮箱轴承变速故障信号检测研究

高速运转会导致轴承产生大量的振动和噪声,使得故障信号与背景噪声相混合,难以准确检测,一旦出现轴承变速故障将会威胁风力发电机的正常运行。为解决这一问题,提出风力发电机高速旋转齿轮箱轴承变速故障信号检测方法。通过小波阈值和经验模态分解方法,对采集到的风电机高速旋转齿轮箱轴承振动信号去噪处理;基于奇异值分解方法,提取风电机高速旋转齿轮箱轴承振动信号特征向量;通过灰狼算法-支持向量机模型,实现对其轴承变速故障检测。实验结果表明,所提方法的风力发电机高速旋转齿轮箱轴承变速故障检测的准确率高。

基于VMD-GWO-SVR的短期电力负荷预测方法

短期电力负荷预测对电力系统的安全稳定运行和电力市场交易具有重要作用,提出了一种基于“分解与重构”框架的短期电力负荷预测方法。首先,通过变分模态分解(variable mode decomposition,VMD)将负荷序列分解为5个分量,建立了5个分量的支持向量回归(support vector regression,SVR)预测模型;其次,对电力负荷分量进行预测,并采用灰狼优化(grey wolf optimization,GWO)算法对SVR的参数进行优化;最后,将5个分量的预测值进行叠加,得到最终的电力负荷预测结果。将该方法与无模态分解的SVR方法及其他预测方法进行对比,该方法的3个评价指标均为最优,表明该方法在短期电力负荷预测中具有良好的应用前景。

基于Latent SVM的多视角行为识别方法

为了在静态图像中获取有效信息,构建行为模型,提出了行为覆盖区ACA(Action Coverage Area)和行为核心AC(Action Core)的概念,基于Latent SVM(Support Vector Machine)目标识别方法,设计了一种多视角行为模型MVAM(Multiple Viewpoint Action Model)。建立了独立的用于行为模型训练和测试的行为数据库。实验表明,该表示法对静态图像中的人体行为能有效地进行分类和检测。

Intelligent control for large-scale variable speed variable pitch wind turbines

Large-scale wind turbine generator systems have strong nonlinear multivariable characteristics with many uncertain factors and disturbances. Automatic control is crucial for the efficiency and reliability of wind turbines. On the basis of simplified and proper model of variable speed variable pitch wind turbines, the effective wind speed is estimated using extended Kaiman filter. Intelligent control schemes proposed in the paper include two loops which operate in synchronism with each other. At below-rated wind speed, the inner loop adopts adaptive fuzzy control based on variable universe for generator torque regulation to realize maximum wind energy capture. At above-rated wind speed, a controller based on least square support vector machine is proposed to adjust pitch angle and keep rated output power. The simulation shows the effectiveness of the intelligent control.

Semi-supervised learning based probabilistic latent semantic analysis for automatic image annotation

In recent years,multimedia annotation problem has been attracting significant research attention in multimedia and computer vision areas,especially for automatic image annotation,whose purpose is to provide an efficient and effective searching environment for users to query their images more easily. In this paper,a semi-supervised learning based probabilistic latent semantic analysis( PLSA) model for automatic image annotation is presenred. Since it's often hard to obtain or create labeled images in large quantities while unlabeled ones are easier to collect,a transductive support vector machine( TSVM) is exploited to enhance the quality of the training image data. Then,different image features with different magnitudes will result in different performance for automatic image annotation. To this end,a Gaussian normalization method is utilized to normalize different features extracted from effective image regions segmented by the normalized cuts algorithm so as to reserve the intrinsic content of images as complete as possible. Finally,a PLSA model with asymmetric modalities is constructed based on the expectation maximization( EM) algorithm to predict a candidate set of annotations with confidence scores. Extensive experiments on the general-purpose Corel5k dataset demonstrate that the proposed model can significantly improve performance of traditional PLSA for the task of automatic image annotation.

Fast Variable Selection by Block Addition and Block Deletion

We propose the threshold updating method for terminating variable selection and two variable selection methods. In the threshold updating method, we update the threshold value when the approximation error smaller than the current threshold value is obtained. The first variable selection method is the combination of forward selection by block addi-tion and backward selection by block deletion. In this method, starting from the empty set of the input variables, we add several input variables at a time until the approximation error is below the threshold value. Then we search deletable variables by block deletion. The second method is the combination of the first method and variable selection by Linear Programming Support Vector Regressors (LPSVRs). By training an LPSVR with linear kernels, we evaluate the weights of the decision function and delete the input variables whose associated absolute weights are zero. Then we carry out block addition and block deletion. By computer experiments using benchmark data sets, we show that the proposed methods can perform faster variable selection than the method only using block deletion, and that by the threshold updating method, the approximation error is lower than that by the fixed threshold method. We also compare our method with an imbedded method, which determines the optimal variables during training, and show that our method gives comparable or better variable selection performance.

基于机器学习技术的逐时雾事故判别气象模型

为进一步提高雾天交通安全气象保障精细化能力,以江苏、安徽高速公路雾事故多发路段为例,利用2012—2018年事故信息与气象资料,建立一种基于变量选择和特征提取的逐时雾事故判别支持向量机模型。模型参照递归特征消除思路选择事故发生时间、地理位置、气象环境等重要变量,使用主成分分析提取重要变量的主要特征,并以径向基为核函数、以网络搜索确定最优参数。结果表明:结合重要变量选择和主成分分析的支持向量机混合模型能够成功识别出训练集81.4%和测试集83.0%的事故样本,AUC分数均为0.946;判别效果优于支持向量机单独算法,以及仅基于重要变量选择或主成分分析的支持向量机算法;3个典型实例分析也说明该模型对于阶段性或持续性大雾天气下的交通事故发生有一定判识与警示意义。

线性判别分析优化孪生支持向量机的网络入侵检测

为了提高大规模网络数据入侵类型实时检测的准确率,采用线性判别分析(LDA)对网络样本特征进行降维处理,降低孪生支持向量机(TWSVM)的运算复杂度,增强TWSVM的网络入侵检测适用度;首先,采用LDA基于类内和类间散度计算获得网络入侵检测样本的降维特征变量;然后,建立LDA-TWSVM网络入侵检测算法,分别求解TWSVM一次规划和二次规划的核心参数;最后,输入降维特征变量,通过TWSVM输出获得网络入侵检测结果。结果表明:LDA网络样本特征降维对网络入侵检测的正向激励效果较为显著,使得所提出的算法在网络入侵检测中具有较高的适应度;相比于几种常用入侵检测算法,所提出的算法具有更高的检出率(0.9943)和更优的均方根误差(1.1328)。

基于InMPE和MFO-SVM的变负载滚动轴承故障诊断

由于在变负载工况下,提取滚动轴承故障特征较为困难,且其故障识别准确率也较低,为此,提出了一种基于插值多尺度排列熵(InMPE)和飞蛾火焰优化支持向量机(MFO-SVM)的滚动轴承故障诊断方法。首先,在粗粒化时采用三次样条插值代替传统多尺度排列熵(MPE)中的线性插值,设计了InMPE算法,利用美国凯斯西储大学(CWRU)轴承数据集,分析了不同序列长度、嵌入维数和负载对InMPE的影响;然后,使用飞蛾火焰算法(MFO)优化了支持向量机(SVM),构建了基于InMPE和MFO-SVM的故障诊断模型;最后,搭建了轴承故障诊断试验台,制作了变负载工况下滚动轴承故障特征样本集,对基于InMPE与MFO-SVM的故障诊断方法的有效性和先进性进行了验证。研究结果表明:在变负载工况下,采用基于InMPE与MFO-SVM方法所得的故障识别准确率达到了98.5%,而采用传统MPE方法所得的故障识别准确率为95.9%;在噪声背景下,采用基于InMPE与MFO-SVM方法所得的识别准确率为92.4%,优于后者的80.0%准确率;证明基于InMPE与MFO-SVM的方法能有效识别出滚动轴承的故障信息,且对噪声具有较好的鲁棒性。

基于积分均值模式分解和固有模态函数样本熵的阵发性房颤识别

针对阵发性房颤(PAF)发作持续时间较短难以捕捉,且现有识别算法抗噪性能较差易导致误检、漏检等问题,本研究提出一种基于积分均值模式分解(IMMD)和固有模态函数样本熵(IMFSE)的PAF识别方法。首先,对时长为20 min的心率变异性(HRV)信号片段进行IMMD分解得到一系列固有模态函数(IMF)分量,并计算IMFSE;然后,通过对IMFSE结果进行统计分析选取PAF识别的特征量;最后,利用支持向量机与交叉验证完成PAF识别。从PAF Prediction Challenge Database(AFPDB)数据库提供的正常受试者、PAF发作与远离PAF发作受试者心电信号中,分别获取25段时长为20 min的HRV信号片段,构成正常组、PAF发作组与PAF未发作组。通过对这75段HRV信号片段的实验发现:利用本方法进行PAF识别,识别准确率、敏感性、特异性分别可达到94%、96%、92%。所提出的PAF识别算法为进一步地快速准确自动检测PAF提供了参考,在可穿戴设备的长期自动检测识别PAF方面具有较大的应用前景。

基于WOA-VMD与WOA-SVM的PMSM退磁故障诊断策略

为解决高温和退磁磁场引起的永磁同步电机退磁问题,该文提出一种基于变模态分解和支持向量机的退磁故障诊断策略。首先分析了永磁同步电机退磁故障的故障机理和传播路径,并利用Matlab/Simulink建立了退磁故障模型;然后选取不同退磁程度下的相电流信号作为故障信号,采用鲸鱼算法优化变模态分解(whale optimization algorithm variable mode decomposition,WOA-VMD)的方法提取退磁故障特征;最后利用鲸鱼算法优化支持向量机(whale optimization algorithm support vector machine,WOA-SVM)的方法对故障数据进行诊断分类,并与未优化的支持向量机和其他故障诊断算法对比,说明其有效性和准确性。

基于熵权法优化组合的PSO-SVR-NGM边坡位移预测

基于边坡监测数据建立数学模型,是边坡变形和稳定性分析的重要方法。但是单一预测模型的形式和应用范围具有一定的确定性,不同模型对数据的利用程度也有所差别,往往不能充分运用已知信息,导致模型精度不高,适用性不强。针对单一预测模型存在的问题,提出一种基于熵权法的PSO-SVR-NGM优化组合模型。该模型结合高精度变权缓冲NGM(1,1,k,c)模型和PSO-SVR模型,能够减小单一预测模型的误差,大幅度提高预测精度。首先通过引入变权缓冲算子λ和背景值权重系数η、κ改进无偏NGM(1,1,k,c)模型,构建新的3参数变权缓冲NGM(1,1,k,c)模型。结合最大灰色关联度和最小平均相对拟合误差重新构造粒子群算法的适应度函数,利用改进的粒子群算法对提出的变权缓冲模型进行搜索寻优,确定最佳的参数组合。然后通过熵权法对改进的变权缓冲NGM(1,1,k,c)模型和PSO-SVR模型进行赋权建立优化组合模型。最后,将该组合模型应用于3个不同变形特征的边坡工程中,并与其他单一模型进行对比分析。结果表明,相对于单一模型,本文所提出的组合模型的拟合和预测误差较小,与原始位移数据的相关性较好,能够更真实地反映边坡变形规律,具有较强的工程适应性。同时组合模型的提出与发展也促进了单一模型的优化改进,为解决实际工程问题提供了良好的思路。