Wavelet-based feature extraction and selection for classification of power system disturbances using support vector machines

This paper presents a new approach for the classification of the power system disturbances using support vector machines (SVMs). The proposed approach is carried out at three serial stages. Firstly, the features to be form the SVM classifier are obtained by using the wavelet transform and a few different feature extraction techniques. Secondly, the features exposing the best classification accuracy of these features are selected by a feature selection technique called as sequential forward selection. Thirdly, the best appropriate input vector for SVM classifier is rummaged. The input vector is started with the first best feature and incrementally added the chosen features. After the addition of each feature, the performance of the SVM is evaluated. The kernel and penalty parameters of the SVM are determined by cross-validation. The parameter set that gives the smallest misclassification error is retained. Finally, both the noisy and noiseless signals are applied to the classifier given above stages. Experimental results indicate that the proposed classifier is robust and has more high classification accuracy with regard to the other approaches in the literature for this problem.     

结合高光谱和机器学习的无线充电金属异物检测

金属异物侵入会造成无线充电系统效率和稳定性降低,并且可能引发安全事故,因此必须进行金属异物检测。 针对现 有技术存在检测盲区以及无法检测微小异物的问题,提出一种深度学习目标分割与机器学习目标分类相结合的金属异物检测 方法。 首先采用 YOLO v3 网络对充电区域 RGB 图像进行异物目标分割,然后通过支持向量机对各个目标区域对应的高光谱图 像进行分类,最后搭建实验平台验证方法的有效性。 结果表明,该方法不仅能够检测螺母和回形针等微小金属异物,而且具有 检测包裹金属异物的潜能;与仅采用支持向量机进行逐像素检测相比,该方法的检测速度提升了约 38. 9%。     

Power quality disturbance classificationbased on time-frequency domain multifeatureand decision tree

Accurate classification of power quality disturbance is the premise and basis for improving and governing power quality. A method for power quality disturbance classification based on time-frequency domain multi-feature and decision tree is presented. Wavelet transform and S-transform are used to extract the feature quantity of each power quality disturbance signal, and a decision tree with classification rules is then constructed for classification and recognition based on the extracted feature quantity. The classification rules and decision tree classifier are established by combining the energy spectrum feature quantity extracted by wavelet transform and other seven time-frequency domain feature quantities extracted by S-transform. Simulation results show that the proposed method can effectively identify six types of common single disturbance signals and two mixed disturbance signals, with fast classification speed and adequate noise resistance. Its classification accuracy is also higher than those of support vector machine (SVM) and k-nearest neighbor (KNN) algorithms. Compared with the method that only uses S-transform, the proposed feature extraction method has more abundant features and higher classification accuracy for power quality disturbance.     

电能质量复合扰动分类识别

电能质量扰动的分类分为信号特征提取和分类器2个阶段,采用S变换和支持向量机构造电能质量复合扰动的分类识别方案.利用S变换进行扰动信号特征提取,构造支持向量机静态分类树,再通过基于Mercer核的聚类方法对静态分类树进行动态扩展,形成动态分类树,实现对复合扰动的识别.给出了电能质量复合扰动分类算法的4个步骤:构建静态分类树;用基于Mercer核的聚类方法进行聚类分析;构建动态分类树;对新发现的扰动确定其具体类型,并给其命名.算例表明该方法不仅可以有效分类识别电压突降、电压突升、电压中断、暂态振荡、电压尖峰、电压缺口和谐波等7种电能质量扰动,还可以识别由其组合而成的电能质量复合扰动.     

基于S变换的电能质量扰动支持向量机分类识别

采用s变换和支持向量机进行电能质量扰动的分类识别。作为连续小波变换和短时傅立叶变换的发展，S变换引入了宽度与频率成反向变化的高斯窗，具有与频率相关的分辨率。由于S变换具有良好的时频特性，因而非常适合于进行电能质量扰动信号特征提取。首先通过S变换进行扰动信号特征提取，然后构造支持向量机分类树进行扰动分类。算例表明该方案具有分类准确率高，对噪声不敏感，训练样本少等优点，是电能质量扰动识别的有效方法。     

结合负荷形态指标的电力负荷曲线两步聚类算法

为改善基于欧式距离的全维度负荷曲线聚类算法在负荷形态相似度上的不足,提出了结合负荷形态特征指标的电力系统负荷曲线两步聚类算法。算法第一步采用基于欧式距离的负荷曲线聚类方法获得初步聚类结果,并通过负荷聚类评价指标选取一次聚类算法和聚类数目;第二步基于负荷形态特征指标采用监督学习算法对负荷进行重新分类。之后比较了不同算法的分类效果,最后给出了聚类结果的应用建议。算例结果表明,所提出的两步聚类算法可以改善传统的负荷曲线聚类方法在形态相似度上的不足,在二次分类方法中,支持向量机（support vector machine,SVM）算法表现较好,所提出的方法具有实际应用意义。     

基于小波变换及最小二乘支持向量机的短期电力负荷预测

提出了采用小波变换和最小二乘支持向量机混合模型进行电力系统短期负荷预测的方法。首先基于小波多分辨率分析方法将负荷序列分解成具有不同频率特征的序列：然后根据分解后各分量的特点构造不同的支持向量机模型对各分量分别进行预测：最后对各分量预测信号进行重构得到最终预测结果。在构建支持向量机模型时考虑了气候因素的影响，并将其作为模型的一组输入点。实验结果表明基于该方法的负荷预测系统具有较高的预测精度。     

Content-based event retrieval using semantic scene interpretationfor automated traffic surveillance

This paper proposes an object segmentation and tracking algorithm for visual surveillance applications. In order to detect moving objects from a dynamic background scene which may have temporal clutters such as swaying plants, we devised an adaptive background update method and a motion classification rule. A two-dimensional token-based tracking system using a Kalman filter is designed to track individual objects under occlusion conditions. We propose a new occlusion reasoning approach where we consider two different types of occlusion: explicit occlusion and implicit occlusion. By tracking individual objects with segmented data, we can generate motion trajectories and set a motion model using polynomial curve fitting. The trajectory model is used as an indexing key for accessing the individual object in the semantic level. We also propose an efficient way of indexing and searching based on object-specific features at different semantic levels. The proposed searching scheme supports various queries including query by example, query by sketch, and query on weighting parameters for event-based retrieval. When retrieving an interested video clip, the system returns the best matching event in the similarity order. In addition, we implement a temporal event graph for direct accessing and browsing of a specific event in the video sequence     

Smoke detection in open areas with texture analysis and support vector machines

Early and certain fire detection is one of the important issues to keep infrastructures safe. Especially, it becomes an urgent problem for open places such as port facilities, large factories, and power plants, due to its large harmful effect to the surrounding areas. In these places, direct detection of fire or flame has some difficulties because they are open and hence have problem to set sensor devices. Therefore, smoke is an important and useful sign to detect fire or flames robustly even in such cases. In this paper, we present a novel smoke detection method based on image information. First, we extract moving objects in an image sequence as smoke candidate regions in a preprocessing step. Since smoke has a characteristic pattern as image information, we focus on the texture pattern of smoke. Here, we use texture analysis to extract feature vectors of the images. To classify extracted areas of moving objects to smoke or nonsmoke, we use support vector machines (SVMs) with texture features as an input feature vector. Extraction of moving objects is sometimes easily and greatly affected by environmental conditions such as wind, background objects, and so forth. It obviously causes bad classification results. To solve this problem, we additionally accumulate the results of classification with SVM about time to obtain accurate extraction result of smoke regions under these conditions. Experimental results using real‐scene data show that our method works effectively under several different environmental conditions. © 2012 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

A Prior Neurophysiologic Knowledge Free Tensor-Based Scheme for Single Trial EEG Classification

Single trial electroencephalogram (EEG) classification is essential in developing brain-computer interfaces (BCIs). However, popular classification algorithms, e.g., common spatial patterns (CSP), usually highly depend on the prior neurophysiologic knowledge for noise removing, although this knowledge is not always known in practical applications. In this paper, a novel tensor-based scheme is proposed for single trial EEG classification, which performs well without the prior neurophysiologic knowledge. In this scheme, EEG signals are represented in the spatial-spectral-temporal domain by the wavelet transform, the multilinear discriminative subspace is reserved by the general tensor discriminant analysis (GTDA), redundant indiscriminative patterns are removed by Fisher score, and the classification is conducted by the support vector machine (SVM). Applications to three datasets confirm the effectiveness and the robustness of the proposed tensor scheme in analyzing EEG signals, especially in the case of lacking prior neurophysiologic knowledge.     

结合高斯核与各向异性邻域抑制的模糊聚类图像分割

针对模糊C均值聚类算法对图像噪声点敏感且抑制力不足问题,所导致收敛慢去噪效果差分割效果的不足,提出一种结合高斯核和各向异性邻域抑制的模糊聚类图像分割方法。算法首先根据邻域窗均值及其邻域灰度值快速评估各向异性邻域权值,通过该权值抑制局部空间噪声,达到去噪模糊聚类目的;再通过高斯核将图像数据转为核函数矩阵,在特征空间对核函数矩阵实施线性算法。通过对测试图像加入噪声,比较其他算法,该算法在去噪、迭代次数和模糊聚类分割上有显著提升。     

基于相空间重构和支持向量机的电能扰动分类方法

电能扰动的分类需要信号特性提取和分类器构造2个阶段,文中采用相空间重构和支持向量机的组合,提出了一种全新的电能扰动信号的分类方法。首先利用相空间重构方法构造扰动信号轨迹,通过编码获得二进制轨迹图像。针对该图像定义了4类具有区别性的指标,以表征不同扰动类型的特性。然后将特性指标作为支持向量机分类器的输入矢量,实现自动分类识别。算例表明该方法计算量少,正确率高,所需训练样本少,可以有效分类识别电压暂降、电压瞬升、电压中断、脉冲振荡、谐波、闪变等6种电能扰动。     

基于小波能量矩的输电线路暂态信号分类识别方法

信号能量的时频分布可以反映不同信号的本质区别,小波能量矩既可以反映信号能量在频域上的分布,也可以间接体现能量在时域上的分布。文章将基于小波能量矩的信号特征提取方法用于区分输电线路的故障暂态信号与非故障暂态信号。首先基于500 kV输电线路仿真模型得到电容投切、三相断路器操作、单相接地短路、一次电弧故障、非故障性雷击和故障性雷击6种类型的暂态信号;然后利用小波变换提取这些信号各频带的能量矩,得到能量矩统计图并对各暂态信号小波能量矩的分布特点进行分析,在此基础上提出了暂态信号分类识别判据。基于小波能量矩方法提取的暂态信号特征较明显,分类识别简便,仿真结果验证了该方法的可行性和有效性。     

基于Morlet小波核多类支持向量机的故障诊断

故障诊断问题实质上是一个模式识别问题,即多分类问题.采用Morlet小波来构造支持向量机(Support Vector Machine, SVM)的核函数,Morlet小波核SVM比普通SVM具有更好的鲁棒性和更强的泛化能力.在一对一算法的基础上实现Morlet小波核多类支持向量机的故障诊断,并将此方法成功应用于电厂汽轮发电机组的故障诊断.实验仿真结果表明Morlet小波核多类SVM故障分类器比BP神经网络训练和测试速度快,且其分类精度在高斯噪声干扰下还保持100%,比BP神经网络高出11.8%.因此该方法能够快速而准确地对电厂汽轮发电机组的故障进行诊断,满足电力系统实时操作的要求.     

电力电缆故障放电声自动识别与起点标定算法

针对电力电缆故障精确定点方法中存在的依赖人工判断、效率低下的缺点,提出了一种电缆故障放电声波自动识别及波形起点标定算法。通过对电缆故障放电声波进行特征分析,定义了4个概括性特征,对大量故障、非故障波形进行了特征提取并组建了训练、验证样本集;提出了基于AdaBoost-SVM(支持向量机)的故障放电声波识别算法,对所提出的4个特征在放电和噪声信号中的空间分布差异进行了学习;结合离散小波变换和高斯分布规律提出了故障波形起点自动标定算法。实验证明,所提算法在保证准确性的同时,可提升电缆故障精确定点的效率。     

基于离散小波变换和模糊K-modes的负荷聚类算法

为了研究智能电网背景下用户的用电模式,考虑到现有聚类算法的不足,提出了一种基于离散小波变换的模糊K-modes聚类算法。利用离散小波变换将时域的负荷曲线转换到频域,从而将负荷曲线的不同特征隔离在不同的频域水平,并利用低阶近似的思想选取原始曲线的有效分量曲线;对所选的分量曲线进行趋势编码,将连续负荷数据转化为离散类属性数据;基于平均密度确定初始聚类条件,利用模糊K-modes聚类算法对曲线进行形态聚类,得到负荷曲线模板;将所提算法与传统K-means算法及层次聚类算法进行比较,从而验证了所提算法的有效性。     

基于形态小波范数熵和支持向量机的电能质量分类研究

针对电能质量信号分类存在实时性差、准确度低的问题,提出了一种基于HMT(hit or miss transform)小波范数熵(norm entropy,NE)和支持向量机(support vector machine,SVM)的电能质量扰动识别方法。根据HMT小波分解每一层能量不同的特点,取扰动信号的10层小波分解的范数熵组成特征矩阵。特征量起到了对扰动信号分形的作用,以此作为SVM的输入。为了提高分类的准确度,研究采用了粒子群算法(particle search optimization,PSO)对SVM参数进行了寻优,分类准确度达到99%左右。同时比较了HMT小波和传统db4小波分别和SVM结合时的准确度,证明了HMT小波的优势和本文特征量提取法的有效性。而对于含噪声的电能质量信号,采用了广义形态滤波器进行了滤波预处理。仿真结果表明,该方法识别准确率高,稳定性好,适用于电能质量扰动识别系统。     

基于提升小波变换和SVM的模拟电路故障诊断

故障特征提取和分类器设计是模拟电路故障诊断的两个重要环节,为了提高模拟电路故障辨识的准确率,提出了提升小波变换与支持向量机相结合的故障诊断方法。根据提升小波变换的原理,提取被测电路单脉冲响应信号的小波系数构成故障特征,建立以支持向量机为分类器的故障诊断系统。该方法对两个滤波器电路的故障诊断取得了满意的效果,在故障模式较多的情况下故障分类的精度达到了99%以上,优于传统的小波方法。     

基于小波系数Hu矩的生物组织损伤监测方法

提出了一种基于B超图像的小波系数Hu矩特征值并结合支持向量机监测生物组织损伤的方法。利用高强度聚焦超声(HIFU)对新鲜离体猪肉组织进行辐照,实时获取辐照前后的B超图像,并对其进行预处理获取减影图像。提取减影图像的Hu矩、小波系数均值和基于小波系数的Hu矩3个特征值,分别利用支持向量机对生物组织样本进行学习、分类处理。结果表明:小波系数Hu矩特征值比Hu矩和小波系数均值的总辨识率分别高出2.70%和2.05%,从而可以更有效地监测HIFU治疗中生物组织损伤情况。该方法可以帮助临床医生客观地监控HIFU治疗过程,对提高HIFU疗效有实际意义。     

基于SVM和能量最小化的PolSAR图像分类方法

极化合成孔径雷达(PolSAR)采用全极化的工作方式可以获取地物的多种特征,利用这些特征对地物进行分类是PolSAR图像的重要应用方向。不同的特征和分类器对分类精度有着较大的影响。提出了一种基于支持向量机(SVM)和能量最小化(EM)的极化SAR图像地物分类方法。该方法选择基于6种散射模型的分解方法(6SD)所得的6部分散射能量、总散射能量span和3个极化相干矩阵旋转域角参数作为SVM的输入,得到图像分类结果,并使用基于图割的能量最小化算法α-expansion对分类结果进行优化。最后使用AIRSAR系统获得的Flevoland地区的数据进行实验,结果表明所提算法可以提高总体分类精度,总体分类精度为95.6%,高于其他方法的92.3%。所提算法可以较大幅度地提高散射机理明显的区域,如建筑、森林、水域、草地等区域的分类精度。另外,结合EM优化结果可以提高所有种类的分类精度,其中在苜蓿、小麦1、小麦2、裸地、草地、油菜籽等区域的分类精度可提高1%以上。