A Hierarchical Clustering and Fixed-Layer Local Learning Based Support Vector Machine Algorithm for Large Scale Classification Problems

It is a challenging topic to develop an efficient algorithm for large scale classification problems in many applications of machine learning. In this paper, a hierarchical clustering and fixed-layer local learning (HCFLL) based support vector machine(SVM) algorithm is proposed to deal with this problem. Firstly, HCFLL hierarchically clusters a given dataset into a modified clustering feature tree based on the ideas of unsupervised clustering and supervised clustering. Then it locally trains SVM on each labeled subtree at a fixed-layer of the tree. The experimental results show that compared with the existing popular algorithms such as core vector machine and decision-tree support vector machine, HCFLL can significantly improve the training and testing speeds with comparable testing accuracy.

Fast magnitude determination using a single seismological station record implementing machine learning techniques

In this work a Support Vector Machine Regression（SVMR） algorithm is used to calculate local magnitude（MI） using only five seconds of signal after the P wave onset of one three component seismic station. This algorithm was trained with 863 records of historical earthquakes, where the input regression parameters were an exponential function of the waveform envelope estimated by least squares and the maximum value of the observed waveform for each component in a single station. Ten-fold cross validation was applied for a normalized polynomial kernel obtaining the mean absolute error for different exponents and complexity parameters. The local magnitude（MI） could be estimated with 0.19 units of mean absolute error. The proposed algorithm is easy to implement in hardware and may be used directly after the field seismological sensor to generate fast decisions at seismological control centers, increasing the possibility of having an effective reaction.

Finger vein recognition using weighted local binary pattern code based on a support vector machine

Finger vein recognition is a biometric technique which identifies individuals using their unique finger vein patterns. It is reported to have a high accuracy and rapid processing speed. In addition, it is impossible to steal a vein pattern located inside the finger. We propose a new identification method of finger vascular patterns using a weighted local binary pattern (LBP) and support vector machine (SVM). This research is novel in the following three ways. First, holistic codes are extracted through the LBP method without using a vein detection procedure. This reduces the processing time and the complexities in detecting finger vein patterns. Second, we classify the local areas from which the LBP codes are extracted into three categories based on the SVM classifier: local areas that include a large amount (LA), a medium amount (MA), and a small amount (SA) of vein patterns. Third, different weights are assigned to the extracted LBP code according to the local area type (LA, MA, and SA) from which the LBP codes were extracted. The optimal weights are determined empirically in terms of the accuracy of the finger vein recognition. Experimental results show that our equal error rate (EER) is significantly lower compared to that without the proposed method or using a conventional method.

基于RLLE算法的脑力负荷分类

近年来,随着人工智能领域技术的不断发展,脑机接口(brain-computer interface,BCI)吸引了更多学者的关注。实时监测高强度脑力工作者的脑力负荷水平并根据其任务做出动态调整是保护国家财产和操作人员安全的重要手段。研究表明由脑电图(electroencephalogram,EEG)提取的特征功率谱密度对于脑力负荷的变化比较敏感,但由于其维数过高,容易造成数据灾难。传统的主成分分析降维(principal component analysis,PCA)算法会损失数据的部分非线性特征。局部线性嵌入(locally linear embedding,LLE)是常用的非线性降维算法,但该算法对噪声的敏感性高,降维结果受参数影响较大。稳健局部线性嵌入算法RLLE(robust locally linear embedding),在LLE优化权重矩阵时添加了正则项优化,不仅增强了模型的抗噪能力,也解决了解模型过程中可能会出现的矩阵病态和奇异性问题。实验结果表明,经过RLLE降维后的数据使用支持向量机(support vector machine,SVM)分类精度普遍高于经过PCA和LLE的降维方式,具有更强的抗干扰能力。

全矢融合的二元PELCD样本熵列车故障诊断

长期高速运行的服役状态会造成高速列车转向架关键部件性能蜕化甚至发生故障等情况,所导致的安全事件将造成严重的经济损失甚至人员伤亡。考虑到高速列车振动信号的特性,将部分集成的局部特征尺度分解方法拓展至二元信号处理领域,同时结合全矢谱理论对同阶分量信号进行信息融合,得到更加完备的数据特征,并对融合后的数据进行样本熵特征提取,得到列车的故障特征;采用灰狼优化算法对支持向量机进行参数寻优,通过实验对比单一故障工况、复合故障工况以及部件性能退化下的故障识别率,验证所提方法的有效性、优越性。

基于特征提取和图像分类的螺旋网疵点自动检测

为了解决当前螺旋网人工疵点检测效率低、误检率高等问题,提出了一种基于分类思想的螺旋网疵点检测方法。对螺旋网图像提取多模式多尺度的LBP特征,充分表征螺旋网图像的信息,通过构建支持向量机(Support vector machine,SVM)分类器实现螺旋网疵点自动检测。结果表明:对于螺旋网疵点图像的局部二值模式(Local binary pattern,LBP)特征,采样半径为2,采样点个数为8时的均匀模式LBP的分类准确率优于其他模式和尺度的LBP,达到了100%,检测速度为0.48 s/张。通过对比不同的特征提取方法和分类器,验证了该文方法对于螺旋网疵点自动检测的适用性,可以实现纺织企业中螺旋网的自动化检测。

通信干扰下无线传感器网络中微弱信号检测

微弱信号检测是保证无线传感器网络高效使用的重要环节,但检测过程易受噪声信号、传感器性能、虚拟信号等因素的干扰,从而导致误检。为了解决上述问题,提出一种通信干扰下无线传感器网络微弱信号检测方法。通过局部投影降噪法剔除信号中的噪声,避免噪声对检测过程产生影响。采用主分量分析算法提取去噪信号的特征,并根据遗传算法优化支持向量参数,将提取的特征输入到向量机中,通过特征的分类完成通信干扰下无线传感器网络微弱信号的检测。实验结果表明,所提方法的信号检测结果与实际结果基本一致,检测时间在30ms内,且抗噪性能强。

Large scale classification with local diversity AdaBoost SVM algorithm

Local diversity AdaBoost support vector machine（LDAB-SVM） is proposed for large scale dataset classification problems.The training dataset is split into several blocks firstly, and some models based on these dataset blocks are built.In order to obtain a better performance, AdaBoost is used in each model building.In the boosting iteration step, the component learners which have higher diversity and accuracy are collected via the kernel parameters adjusting.Then the local models via voting method are integrated.The experimental study shows that LDAB-SVM can deal with large scale dataset efficiently without reducing the performance of the classifier.

Local spatial properties based image interpolation scheme using SVMs

Image interpolation plays an important role in image process applications. A novel support vector machines （SVMs） based interpolation scheme is proposed with increasing the local spatial properties in the source image as SVMs input patterns. After the proper neighbor pixels region is selected, trained support vectors are obtained by training SVMs with local spatial properties that include the average of the neighbor pixels gray values and the gray value variations between neighbor pixels in the selected region. The support vector regression machines are employed to estimate the gray values of unknown pixels with the neighbor pixels and local spatial properties information. Some interpolation experiments show that the proposed scheme is superior to the linear, cubic, neural network and other SVMs based interpolation approaches.

Fault Diagnosis Model Based on Feature Compression with Orthogonal Locality Preserving Projection

Based on feature compression with orthogonal locality preserving projection（OLPP）,a novel fault diagnosis model is proposed in this paper to achieve automation and high-precision of fault diagnosis of rotating machinery.With this model,the original vibration signals of training and test samples are first decomposed through the empirical mode decomposition（EMD）,and Shannon entropy is constructed to achieve high-dimensional eigenvectors.In order to replace the traditional feature extraction way which does the selection manually,OLPP is introduced to automatically compress the high-dimensional eigenvectors of training and test samples into the low-dimensional eigenvectors which have better discrimination.After that,the low-dimensional eigenvectors of training samples are input into Morlet wavelet support vector machine（MWSVM） and a trained MWSVM is obtained.Finally,the low-dimensional eigenvectors of test samples are input into the trained MWSVM to carry out fault diagnosis.To evaluate our proposed model,the experiment of fault diagnosis of deep groove ball bearings is made,and the experiment results indicate that the recognition accuracy rate of the proposed diagnosis model for outer race crack、inner race crack and ball crack is more than 90%.Compared to the existing approaches,the proposed diagnosis model combines the strengths of EMD in fault feature extraction,OLPP in feature compression and MWSVM in pattern recognition,and realizes the automation and high-precision of fault diagnosis.

Loading Localization by Small-Diameter Optical Fiber Sensors

Structural health monitoring(SHM)in service has attracted increasing attention for years.Load localization on a structure is studied hereby.Two algorithms,i.e.,support vector machine(SVM)method and back propagation neural network(BPNN)algorithm,are proposed to identify the loading positions individually.The feasibility of the suggested methods is evaluated through an experimental program on a carbon fiber reinforced plastic laminate.The experimental tests involve in application of four optical fiber-based sensors for strain measurement at discrete points.The sensors are specially designed fiber Bragg grating(FBG)in small diameter.The small-diameter FBG sensors are arrayed in 2-D on the laminate surface.The testing results indicate that the loading position could be detected by the proposed method.Using SVM method,the 2-D FBG sensors can approximate the loading location with maximum error less than 14 mm.However,the maximum localization error could be limited to about 1 mm by applying the BPNN algorithm.It is mainly because the convergence conditions(mean square error)can be set in advance,while SVM cannot.

Using position specific scoring matrix and auto covariance to predict protein subnuclear localization

The knowledge of subnuclear localization in eukaryotic cells is indispensable for under-standing the biological function of nucleus, genome regulation and drug discovery. In this study, a new feature representation was pro-posed by combining position specific scoring matrix (PSSM) and auto covariance (AC). The AC variables describe the neighboring effect between two amino acids, so that they incorpo-rate the sequence-order information;PSSM de-scribes the information of biological evolution of proteins. Based on this new descriptor, a support vector machine (SVM) classifier was built to predict subnuclear localization. To evaluate the power of our predictor, the benchmark dataset that contains 714 proteins localized in nine subnuclear compartments was utilized. The total jackknife cross validation ac-curacy of our method is 76.5%, that is higher than those of the Nuc-PLoc (67.4%), the OET- KNN (55.6%), AAC based SVM (48.9%) and ProtLoc (36.6%). The prediction software used in this article and the details of the SVM parameters are freely available at http://chemlab.scu.edu.cn/ predict_SubNL/index.htm and the dataset used in our study is from Shen and Chou’s work by downloading at http://chou.med.harvard.edu/ bioinf/Nuc-PLoc/Data.htm.

Defocus Blur Segmentation Using Local Binary Patterns with Adaptive Threshold

Enormousmethods have been proposed for the detection and segmentation of blur and non-blur regions of the images.Due to the limited available information about blur type,scenario and the level of blurriness,detection and segmentation is a challenging task.Hence,the performance of the blur measure operator is an essential factor and needs improvement to attain perfection.In this paper,we propose an effective blur measure based on local binary pattern(LBP)with adaptive threshold for blur detection.The sharpness metric developed based on LBP used a fixed threshold irrespective of the type and level of blur,that may not be suitable for images with variations in imaging conditions,blur amount and type.Contrarily,the proposed measure uses an adaptive threshold for each input image based on the image and blur properties to generate improved sharpness metric.The adaptive threshold is computed based on the model learned through support vector machine(SVM).The performance of the proposed method is evaluated using two different datasets and is compared with five state-of-the-art methods.Comparative analysis reveals that the proposed method performs significantly better qualitatively and quantitatively against all of the compared methods.

基于SVM的含缺陷20钢弯管爆破压力预测

为快速、精确预测含局部减薄缺陷的弯管爆破压力,首先验证显式非线性有限元模型的模拟精确性,然后以168组不同缺陷尺寸下20钢弯管爆破压力的有限元模拟数据作为学习样本,建立含局部减薄缺陷20钢弯管爆破压力预测的支持向量机(SVM)模型;其次利用交叉验证(CV)、遗传算法(GA)、粒子群算法(PSO)分别优化SVM模型;最后分析对比用于预测弯管爆破压力的3种优化SVM模型与ASME B31G-2009、DNV RP-F101、SHELL 92等3种通用规范的计算误差。结果表明:CV-SVM、GA-SVM、PSO-SVM等3种模型的预测误差均小于3种规范的计算误差,其最大相对误差分别为-2.33%、-3.4%和1.94%;说明SVM模型用于预测弯管爆破压力时操作简单、计算时间短、预测精度高、工程实用性好。

多层次特征和粒子群优化的场景分类

针对遥感图像的场景分类精度问题,提出多层次特征和粒子群算法优化分类器的场景分类算法。利用聚集局部描述符编码算法对尺度不变特征变换算法提取的局部特征编码,获得中层特征,通过卷积神经网络提取高层特征,将提取的特征作为支持向量机的输入数据,引入粒子群算法优化该分类器的参数,进行场景分类。在RSC11和WHU-RS19两个公开的遥感图像数据集上进行实验,分类精度分别达到95.28和97.20。将WHU-RS19数据集的结果与其它方法比较,精度有明显提高。实验结果表明,在分类时对分类器参数进行优化,分类效果更佳。

基于LBP特征匹配算法的红外人脸图像表情识别技术

红外人脸图像表识别过程中易受到光照不均匀、角度多变、亮度差异大等问题的影响,导致红外人脸图像表情识别效率较差,为解决上述问题,提出基于LBP特征匹配算法的红外人脸图像表情识别方法。首先通过局部优化保留摄影法对红外人脸图像实行降维处理,获取优化后的图像,然后采用多角度分水岭法分割图像,保留图像的细节信息。并采用LBP算子提取预处理后的图像纹理特征,将提取的纹理特征输入支持向量机中,计算出特征的类内比重,完成红外人脸图像表情的识别。实验结果表明,所提方法的平均识别准确率为92%,识别100张人脸图像表情耗时129 s识别效率高、识别效果好、稳定性强。

一种数据驱动的气动热预示模型

高效、高精度的气动热预示是高超声速飞行器设计的关键。然而,随着高超声速飞行器外形的日益复杂化和设计周期的不断缩紧,现有方法已很难满足高效精准的气动热预示。本文基于边界层理论和支持向量机发展了一种数据驱动的当地化气动热预示建模方法。首先,通过求解Euler方程获得边界层外缘信息,采用RANS方法计算热流分布样本;然后,通过设计的特征选择方法确定边界层外缘特征;最后,利用支持向量机构建气动热预示模型,实现边界层外缘特征与壁面热流的映射。对双椭球和二级压缩面的热流预示结果表明,该模型考虑了非均匀分布壁面温度等边界条件,具有较高的预示精度和良好的外推与泛化性能,典型位置热流预示结果和RANS计算结果的相对误差均小于5%。同时,以双椭球上表面中心线热流预示为例,对比传统POD降阶方法,发现该模型的预示精度更高,外推状态下预示精度较POD方法提升了4倍以上。

基于深度学习特征融合的遥感图像场景分类应用

针对传统手工特征方法无法有效提取整体图像深层信息的问题,本文提出一种基于深度学习特征融合的场景分类新方法.利用灰度共生矩阵(GLCM)和局部二值模式(LBP)提取具有相关空间特性的纹理特征和局部纹理特征的浅层信息;通过基于AlexNet迁移学习网络提取图像的深层信息,在去除最后一层全连接层的同时加入一层256维的全连接层作为特征输出;将两种特征进行自适应融合,最终输入到网格搜索算法优化的支持向量机(GS-SVM)中对遥感图像进行场景分类识别.在公开数据集UC Merced的21类目标数据和RSSCN7的7类目标数据的实验结果表明,5次实验的平均准确率分别达94.77%和93.79%.该方法可有效提升遥感图像场景的分类精度.

基于局域均值分解的行星齿轮箱故障诊断方法

在低转速工况下,容易出现行星齿轮箱故障的微弱信号和强信号难以分离的情况,导致行星齿轮箱存在微弱故障诊断精度较差的问题,为此,提出了一种基于局域均值分解(LMD)的行星齿轮箱故障诊断方法。首先,采用DASP数据采集系统,采集了行星齿轮箱不同工况下的振动信号,采用平移不变量小波降噪方法,对其振动信号进行了降噪处理;然后,采用局域均值分解方法分解了其振动信号,分别采用了能量算子和循环频率对其进行了解调处理,获取了微弱故障信号分量所对应的幅值和相位调制信息,准确提取了行星齿轮箱的微弱故障信号特征;最后,采用最小二乘支持向量机(LSSVM)识别了齿轮箱不同故障特征,判断了行星齿轮箱的运行状态,实现了行星齿轮箱的故障诊断。研究结果表明:采用基于LMD的方法,可以对行星齿轮箱的微弱异常信号及强异常信号进行准确诊断,获得满意的行星齿轮箱故障诊断结果,有效保障行星齿轮箱的安全、稳定运转。

冷轧带钢表面相似线性缺陷检测

针对现有冷轧带钢表面的相似线状缺陷检测精度与识别率差的问题,提出一种局部二制模式LBP直方图特征与支持向量机SVM相结合的检测算法。通过对采集的大量划伤与夹杂的带钢表面缺陷图进行预处理,获得感兴趣区域,再进一步利用LBP等价模式获得目标区域的LBP直方图信息,结果显示可以很好地分辨缺陷与非缺陷,并描述的各种缺陷具有可分辨性。采用核函数为径向基函数核的SVM分类器训练识别,结果表明:该方法对划伤和夹杂的缺陷检测准确率达98%。