应用小波包能量谱及SVM的安瓿内浮类异物识别

目的：为了解决安瓿内漂浮物与悬浮物的识别问题,本文提出了一种基于小波包能量谱的特征提取及支持向量机的识别方法。方法：首先通过图像序列差分及点检测分割提取杂质存在区图像作为目标区;然后将目标区沿安瓿瓶轴线方向逐行叠加形成一维信号;对一维信号进行小波包分解,采用主成分分析方法提取小波包分解特征向量中独立主成分;以小波包特征向量中独立主成分的能量谱作为异物类型特征;将提取的特征作为支持向量机的输入向量,采用序列最小优化方法实现训练样本快速分类。实验过程中选择不同类型的核函数和相应参数进行训练和测试。结果：实验结果显示,相对于传统BP网络,SVM在将识别用时减少近60%,识别精度提高了35%。结论：能够满足在生产中对浮类杂质的提取和快速识别的要求。     

基于二维主成分分析的掌纹识别研究

掌纹作为一种新的生物特征可用来进行人的身份识别.论文提出了将二维主成分分析方法(2DPCA)应用于掌纹识别的特征提取,并在PolyU掌纹数据库上利用最近邻分类器与余弦距离度量进行了相应的实验,得到了99.4%的正确识别率.二维主成分分析方法相比主成分分析方法(PCA)方法具有更高的识别率和更快的计算速度,尤其是在小样本训练数据的情况下优势更明显.同时论文也研究了不同应用系统下阈值的选取方法.     

基于MSKPCA和SVM的转子故障诊断模型及应用

为提高转子故障分类与辨识的准确率,围绕故障数据的降维问题开展了研究工作。在构造了多核函数的一种特殊形式多尺度核函数前提下,研究了多尺度核函数主成分分析(Multi-Scale Kernel Principal Component Analysis,MSKPCA)法在转子故障原始特征集降维中的应用途径。将获得的新的故障特征集输入到支持向量机(SVM)进行训练与辨识,建立了具有多尺度核多层核的转子故障诊断模型。研究结果表明,在多尺度核主成分分析法中合理地选用多尺度核函数,能够更好地提取转子故障不同尺度下的敏感信息,可为转子故障辨识提供更加精确的样本,能有效地提高转子故障诊断的准确率。该研究为转子系统故障数据特征降维提供了一种新方法,为核方法在转子故障诊断中的应用提供了新的思路。     

利用SVM和相关山形聚类分析识别滚动轴承状态

状态识别是机械设备故障诊断的关键环节。提出了一种结合支持向量机、主成分分析及相关山形聚类分析的滚动轴承状态识别方法。首先利用支持向量机对轴承特征参数进行分类,辨别是否异常;再利用主成分分析得到独立的、包含原参数主要信息的主成分;最后对这些主成分作聚类分析,达到诊断故障部位的目的。实例分析的结果表明,该方法可以有效地识别轴承状态,正确率达到96%。     

基于异常识别和关联分析的桥梁数据复合诊断

提出了一种基于异常识别和多传感器关联分析的桥梁数据复合诊断方法。该方法利用超球面一类支持向量机对传感器数据特征进行异常识别,通过ε-支持向量回归机对多传感器测量值进行位置关联分析,从而判定该传感器数据异常是由外部荷载还是传感器自身故障引起。通过江阴大桥主梁加速度传感器的相关测量数据,表明了该方法的有效性。     

基于KPCA SVM的柴油机状态识别方法的研究

为了有效地对柴油机的运行状态进行状态识别,根据柴油机的特征信息和识别的特点,研究了基于核主元分析(KPCA)和支持向量机(SVM)进行柴油机状态识别的故障诊断方法.首先,对柴油机进行特征提取,构成一个特征向量.然后对其进行核主元分析,计算得到能反映设备状态的特征向量,有效去除信息的冗余.最后,将得到的特征向量进行支持向量机的训练学习,识别柴油机的状态.通过实验室柴油机燃烧系统不同运行状态下的识别分析,验证了此方法的可行性和实用性.     

基于离散Curvelet变换和LS-SVM的虹膜特征提取与识别

提出了一种基于离散曲波变换和最小二乘支持向量机(LS-SVM)的虹膜特征提取与分类识别的新方法。对虹膜纹理采用离散Curvelet变换,提取低频子带系数矩阵的均值方差和高频子带能量作为虹膜图像的特征向量,利用最优二叉树多类LS-SVM分类器进行分类与识别。MATLAB仿真实验结果表明,与现有方法相比,该算法识别准确率较高,能有效应用于身份认证系统中。     

Bearing running state recognition based on non-extensive wavelet feature scale entropy and support vector machine

In order to effectively recognize the bearing running state, a new method based on non-extensive wavelet feature scale entropy and the Morlet wavelet kernel support vector machine (MWSVM) was proposed. Firstly, the gathered vibration signals were decomposed by the wavelet to obtain the corresponding wavelet coefficients. Then, based on the integration of non-extensive entropy and the coefficients, the features were extracted by the wavelet feature scale entropy. However, the extracted features remained high-dimensional and excessive redundant information still existed. Therefore, the manifold learning algorithm locality preserving projection (LPP) was introduced to extract the characteristic features and to reduce the dimension. The extracted characteristic features were inputted into the MWSVM to train and construct the running state identification model; the bearing running state identification was thereby realized. Cases of test and actual fault were analyzed. The results validate the effectiveness of the proposed algorithm.     

Accelerometer-based fall detection using feature extraction and support vector machine algorithms

Falls by the elderly may result in hip fractures, paraplegia, and even death. Hence, over the past few decades, considerable research has been conducted on fall detection. Here, an accelerometer-based fall detector is reported that is fastened to a person's waist and includes an accelerometer, a multiplexer, a fifth-order low-pass Butterworth filter, and a microcontroller. Acceleration sensing, noise filtering, and analog-to-digital conversion were performed by the circuitry. The processed signal was sent to a personal computer through Bluetooth and analyzed by customized software. The fall detection algorithm included feature extraction and a support vector machine algorithm for classifying the features. Twenty volunteers performed 12 trials of 6 daily activities and 6 fall events. The results show that the algorithm had high sensitivity (95%) and specificity (96.7%). Thus, this device is expected to have significant application for fall detection.     

灰度直方图和支持向量机在磁环外观检测中的应用

本文提出了一套基于灰度直方图和支持向量机的磁环自动分类系统。为了用低维的灰度信息来描述磁环的特征，提出了一套图像处理的算法。将图像从背景分离之后，进行灰度直方图处理来提取灰度特征。接着采用主分量分析法，将灰度统计信息由256维向量降低到20维向量，以这20维向量作为输入，用支持向量机进行分类。最后，经过训练得到最优分类函数，分类正确率达到97．3％。     

基于局部特征提取的目标自动识别

提出一种基于局部特征提取的目标识别方法,用于自动识别不同尺度,视角和照度条件下的目标.首先,建立图像的尺度空间;结合海森矩阵和Harris算法提取局部特征点,计算该特征区域的方向和灰度梯度及方向;统计出每块子区域的标准灰度梯度直方图,得到128维的特征向量.然后,基于主成分分析的降维算法来降低特征向量的维数,加快识别的计算速度.最后,采用特征空间分类器增加目标识别的速度.实验结果表明:基于局部特征提取的目标识别达到了较高的识别率,在视角、尺度和照度变化下的识别率分别为61.9％,80.5％和84.4％,平均识别时间为130.9 ms.与尺度不变特征变换(SIFT)和加速鲁棒特征(SURF)算法相比,本算法不仅在不同的视角,目标尺度及照度条件下具有较高识别率,而且识别速度比SIFT方法高.     

A new sense-through-foliage target recognition method based on hybrid particle swarm optimization-based wavelet twin support vector machine

In order to improve the accuracy of sense-through-foliage target recognition, a new recognition method based on sparse representation-based adaptive feature extraction and hybrid particle swarm optimization (HPSO)-optimized wavelet twin support vector machine (WTSVM) is proposed in this paper. First, an adaptive feature extraction approach based on sparse representation is applied to extract the target features from the measured radar echo waveforms, the target feature set is constructed by sparse coefficients that contain most target information. Then, a new recognition method based optimized WTSVM is developed to perform target recognition. Twin SVM (TSVM) is a powerful tool in the field of machine learning, but the kernel and parameters selection problem still affects the performance of TSVM directly. A novel HPSO is developed in this study to determine the optimal parameters for WTSVM with the highest accuracy and generalization ability. As a hybridization strategy, local search is integrated in the PSO algorithm to further refine the performance of individuals and accelerate their convergence toward the global optimality. Finally, the performance of the proposed method is verified by experiments taken in the forest, and the results conform the improved accuracy of target recognition.     

基于改进SVM的网络流量分类方法研究

针对网络环境中存在大量噪声和网络流量中存在过多的冗余特征属性,提出了一种具有特征有效度的模糊支持向量机(FW-FSVM),并将FW-FSVM应用于网络流量分类领域。该方法根据不同样本点对分类贡献的大小赋予相应的模糊因子,可以有效地消除噪声对分类精度的影响;同时计算网络流量中各个特征的有效度,消除弱特征属性或冗余特征属性对网络流量分类精度的影响。实验结果表明,FW-FSVM相比于其他网络流量分类方法能有效地提高网络流量分类精度且分类稳定性较高。     

基于改进支持向量机的客户流失分析研究

针对客户关系管理中的客户流失问题,建立了基于支持向量机的预测模型.基于实际客户流失数据样本数据量大、正负样本分布不平衡的特点,提出了一种改进支持向量机算法,并将其用于电信行业的客户流失预测.通过实际电信客户数据集测试,与传统的预测算法比较,证明这种算法适合解决大数据集和不平衡数据,具有更高的精确度.     

基于最小二乘支持向量机和机电综合特征的发电机故障诊断

提出了1种最小二乘支持向量机和机电综合特征相结合的发电机故障诊断模型.用二次损失函数代替传统支持向量机中的不敏感损失函数,将不等式约束条件变为等式约束,从而将二次规划问题转变为线性方程组求解,降低了计算的复杂性.提取发电机故障中的综合特征,即振动信号和电流信号,整理后作为诊断模型的特征值,从而得到了故障的典型特征,提高了诊断的准确率.最后从SDF 9型模拟发电机中实测数据进行分析,结果表明,与常规的方法相比,该模型具有较高的分类速度和较好的故障诊断准确率.     

Support vector machine and optimised feature extraction in integrated eddy current instrument

Eddy current, especially pulsed eddy current (PEC), is known as an effective tool to detect defects in aircraft structures. Current PEC defect classification methods require highly trained personnel and the results are usually influenced by human subjectivity. Therefore, automated defect classification is desirable in a PEC instrument. In this work, five eddy current based methods are integrated into an instrument using a universal model and modular structure. Then, a Support Vector Machine (SVM) is used to build the classifier model and predict the type of defect. Principal component analysis (PCA) and independent component analysis (ICA) are investigated for feature extraction and compared for classification results using SVM. Two-layer Al–Mn alloy specimens with four kinds of defects are used for classification. The experimental results show that the proposed methods have great potential for in-situ defect inspection of multi-layer aircraft structures.     

基于支持向量机的布匹图案匹配算法设计

为了解决布匹印花过程中能够快速实现模板匹配的问题,提出了一种基于支持向量机(SVM)的匹配算法.匹配算法采用两级分类器,首先对样本布匹图像进行二值化和轮廓提取等处理得到了图像中各种图形的轮廓曲线,选择模板图形的轮廓曲线长度和面积作为简单特征量,建立了基于置信区间的分类器作为一级分类器,实现了初步匹配;然后提取模板与非模...