最小化支持向量数分类器的云检测

针对遥感卫星图像的云检测,提出了基于最小化支持向量数分类器的云检测方案,解决传统分类器训练样本多、易陷入局部最优的问题。使用该分类器对QuickBird高分辨率遥感图像进行云检测,检测正确率达99%以上。实验表明:在确定分类器内部结构参数过程中,与传统的交叉验证法相比,基于支持向量数的方法不仅能够准确预测分类器推广性能的变化趋势,从而确立最优化的参数组合,并且实现简单,大大减少了计算的复杂度。与传统的BP神经网络相比,该方法所需训练样本少,分类性能好。

基于特征提取的面向边缘数据中心的窃电监测

随着电网信息物理系统的发展,一部分数据处理功能逐渐下沉到靠近终端用户的边缘层。为了给后续分析提供可靠的数据源,及时发现异常用电行为,窃电监测是边缘数据中心重要功能之一。文中提出一种针对边缘数据中心的窃电监测方法,该方法利用深度卷积生成对抗网络(DCGAN)鉴别器提取得到的特征,在边缘数据中心对二范数线性支持向量机(L2SVM)进行训练。实验结果证实,DCGAN具有较好的收敛性能,鉴别器提取得到的正常与窃电行为用电特征具有明显划分,且比基于主成分分析(PCA)特征提取方法更加有效,此外,与基于径向基核函数的支持向量机(SVM)反窃电方法相比,所提方法准确度更好且计算复杂度低,适合边缘数据中心部署。

ESSENTIAL RELATIONSHIP BETWEEN DOMAIN-BASED ONE-CLASS CLASSIFIERS AND DENSITY ESTIMATION

One-class support vector machine （OCSVM） and support vector data description （SVDD） are two main domain-based one-class （kernel） classifiers. To reveal their relationship with density estimation in the case of the Gaussian kernel, OCSVM and SVDD are firstly unified into the framework of kernel density estimation, and the essential relationship between them is explicitly revealed. Then the result proves that the density estimation induced by OCSVM or SVDD is in agreement with the true density. Meanwhile, it can also reduce the integrated squared error （ISE）. Finally, experiments on several simulated datasets verify the revealed relationships.

DIMENSIONALITY REDUCTION BASED ON SVM AND LDA,AND ITS APPLICATION TO CLASSIFICATION TECHNIQUE

Some dimensionality reduction （DR） approaches based on support vector machine （SVM） are proposed. But the acquirement of the projection matrix in these approaches only considers the between-class margin based on SVM while ignoring the within-class information in data. This paper presents a new DR approach, call- ed the dimensionality reduction based on SVM and LDA （DRSL）. DRSL considers the between-class margins from SVM and LDA, and the within-class compactness from LDA to obtain the projection matrix. As a result, DRSL can realize the combination of the between-class and within-class information and fit the between-class and within-class structures in data. Hence, the obtained projection matrix increases the generalization ability of subsequent classification techniques. Experiments applied to classification techniques show the effectiveness of the proposed method.

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.

Rolling bearing performance degradation evaluation by VMD and embedding selection-based NPE

In order to improve the incipient fault sensitivity and stability of degradation index in the rolling bearing performance degradation evaluation process,an embedding selection-based neighborhood preserving embedding(ESNPE)method is proposed.Firstly,the acquired vibration signals are decomposed by variational mode decomposition(VMD),and the singular value and relative energy of each intrinsic mode function(IMF)are extracted to form a high-dimensional feature set.Then,the NPE manifold learning method is used to extract the embedded features in the feature space.Considering the problem that useful embedding information is easily suppressed in NPE,an embedding selection strategy is built based on the Spearman correlation coefficient.The effectiveness of embeddings is measured by the coefficient absolute value,and useful embeddings are preserved in the early stage of bearing degradation by using the first-order difference method.Finally,the degradation index is established using the support vector data description(SVDD)model and bearing performance degradation evaluation is achieved.The proposed method was tested with the whole life experiment data of a rolling bearing,and the result was compared with the feature extraction methods of traditional principal component analysis(PCA)and NPE.The results show that the proposed method is superior in improving the incipient fault sensitivity and stability of the degradation index.

Life prediction of ZPW-2000A track circuit equipment based on SVDD and gray prediction

Evaluation of the health state and prediction of the remaining life of the track circuit are important for the safe operation of the equipment of railway signal system.Based on support vector data description(SVDD)and gray prediction,this paper illustrates a method of life prediction for ZPW-2000A track circuit,which combines entropy weight method,SVDD,Mahalanobis distance and negative conversion function to set up a health state assessment model.The model transforms multiple factors affecting the health state into a health index named H to reflect the health state of the equipment.According to H,the life prediction model of ZPW-2000A track circuit equipment is established by means of gray prediction so as to predict the trend of health state of the equipment.The certification of the example shows that the method can visually reflect the health state and effectively predict the remaining life of the equipment.It also provides a theoretical basis to further improve the maintenance and management for ZPW-2000A track circuit.

Identification on rock and soil parameters for vibration drilling rock in metal mine based on fuzzy least square support vector machine

A single freedom degree model of drilling bit-rock was established according to the vibration mechanism and its dynamic characteristics. Moreover, a novel identification method of rock and soil parameters for vibration drilling based on the fuzzy least squares(FLS)-support vector machine(SVM) was developed, in which the fuzzy membership function was set by using linear distance, and its parameters, such as penalty factor and kernel parameter, were optimized by using adaptive genetic algorithm. And FLS-SVM identification on rock and soil parameters for vibration drilling was made by changing the input/output data from single freedom degree model of drilling bit-rock. The results of identification simulation and resonance column experiment show that relative error of natural frequency for some hard sand from identification simulation and resonance column experiment is 1.1% and the identification precision based on the fuzzy least squares-support vector machine is high.

Monitoring cyanobacteria-dominant algal blooms in eutrophicated Taihu Lake in China with synthetic aperture radar images

Monitoring algal blooms by optical remote sensing is limited by cloud cover.In this study,synthetic aperture radar(SAR) was deployed with the aim of monitoring cyanobacteria-dominant algal blooms in Taihu Lake in cloudy weather.The study shows that dark regions in the SAR images caused by cyanobacterial blooms damped the microwave backscatter of the lake surface and were consistent with the regions of algal blooms in quasi-synchronous optical images,confirming the applicability of SAR for detection of surface blooms.Low backscatter may also be associated with other factors such as low wind speeds,resulting in interference when monitoring algal blooms using SAR data alone.After feature extraction and selection,the dark regions were classified by the support vector machine method with an overall accuracy of 67.74%.SAR can provide a reference point for monitoring cyanobacterial blooms in the lake,particularly when weather is not suitable for optical remote sensing.Multi-polarization and multi-band SAR can be considered for use in the future to obtain more accurate information regarding algal blooms from SAR data.

New predictive control algorithms based on Least Squares Support Vector Machines

Used for industrial process with different degree of nonlinearity, the two predictive control algorithms presented in this paper are based on Least Squares Support Vector Machines (LS-SVM) model. For the weakly nonlinear system, the system model is built by using LS-SVM with linear kernel function, and then the obtained linear LS-SVM model is transformed into linear input-output relation of the controlled system. However, for the strongly nonlinear system, the off-line model of the controlled system is built by using LS-SVM with Radial Basis Function (RBF) kernel. The obtained nonlinear LS-SVM model is linearized at each sampling instant of system running, after which the on-line linear input-output model of the system is built. Based on the obtained linear input-output model, the Generalized Predictive Control (GPC) algorithm is employed to implement predictive control for the controlled plant in both algorithms. The simulation results after the presented algorithms were implemented in two different industrial processes model; respectively revealed the effectiveness and merit of both algorithms.

An edge-adaptive demosaicking method based on image correlation

To reduce the cost, size and complexity, a consumer digital camera usually uses a single sensor overlaid with a color filter array(CFA) to sample one of the red-green-blue primary color values, and uses demosaicking algorithm to estimate the missing color values at each pixel. A novel image correlation and support vector machine(SVM) based edge-adaptive algorithm was proposed, which can reduce edge artifacts and false color artifacts, effectively. Firstly, image pixels were separated into edge region and smooth region with an edge detection algorithm. Then, a hybrid approach switching between a simple demosaicking algorithm on the smooth region and SVM based demosaicking algorithm on the edge region was performed. Image spatial and spectral correlations were employed to create middle planes for the interpolation. Experimental result shows that the proposed approach produced visually pleasing full-color result images and obtained higher CPSNR and smaller S-CIELAB*ab?E than other conventional demosaicking algorithms.

WAVELET KERNEL SUPPORT VECTOR MACHINES FOR SPARSE APPROXIMATION

Wavelet, a powerful tool for signal processing, can be used to approximate the target func-tion. For enhancing the sparse property of wavelet approximation, a new algorithm was proposed by using wavelet kernel Support Vector Machines (SVM), which can converge to minimum error with bet-ter sparsity. Here, wavelet functions would be firstly used to construct the admitted kernel for SVM according to Mercy theory; then new SVM with this kernel can be used to approximate the target fun-citon with better sparsity than wavelet approxiamtion itself. The results obtained by our simulation ex-periment show the feasibility and validity of wavelet kernel support vector machines.

Combination of Multi-class Probability Support Vector Machines for Fault Diagnosis

To deal with multi-source multi-class classification problems, the method of combining multiple multi-class probability support vector machines (MPSVMs) using Bayesian theory is proposed in this paper. The MPSVMs are designed by mapping the output of standard support vector machines into a calibrated posterior probability by using a learned sigmoid function and then combining these learned binary-class probability SVMs. Two Bayes based methods for combining multiple MPSVMs are applied to improve the performance of classification. Our proposed methods are applied to fault diagnosis of a diesel engine. The experimental results show that the new methods can improve the accuracy and robustness of fault diagnosis.

Voice activity detection based on deep belief networks using likelihood ratio

A novel technique is proposed to improve the performance of voice activity detection(VAD) by using deep belief networks(DBN) with a likelihood ratio(LR). The likelihood ratio is derived from the speech and noise spectral components that are assumed to follow the Gaussian probability density function(PDF). The proposed algorithm employs DBN learning in order to classify voice activity by using the input signal to calculate the likelihood ratio. Experiments show that the proposed algorithm yields improved results in various noise environments, compared to the conventional VAD algorithms. Furthermore, the DBN based algorithm decreases the detection probability of error with [0.7, 2.6] compared to the support vector machine based algorithm.

P300 EEG Recognition Based on SVM Approach

In this paper, we used SVM method to detect P300 signal. Before training a classification parameter for the SVM, several preprocessing operations were applied to the data including filtering, downsampling, single trial extraction, windsorizing, electrode selection et al. With the SVM algorithm, the classification accuracy could be up to above 80%. In some cases, the accuracy could reach 100%. It is suitable to use SVM for P300 EEG recognition in the P300-based brain-computer interface (BCI) system. Our further work will include the improvement to yield higher classification accuracy using fewer trials.

Water inrush evaluation of coal seam floor by integrating the water inrush coefficient and the information of water abundance

The method of singular coefficient of water inrush to achieve safety mining has limitation and one sidedness. Aiming at the problem above, large amounts of data about water inrush were collected. Then the data, including the maximum water inrush, water inrush coefficient and water abundance in aquifers of working face, were processed by the statistical analysis. The analysis results indicate that both water inrush coefficient and water abundance in aquifers should be taken into consideration when evaluating the danger of water inrush from coal seam floor. The prediction model of safe-mining evaluation grade was built by using the support vector machine, and the result shows that this model has high classification accuracy. A feasible classification system of water-inrush safety evaluation can be got by using the data visualization method which makes the implicit support vector machine models explicit.

MATERIAL ELECTROMAGNETIC PARAMETERS EXTRACTION USING SVM METHOD

The method extracting the electromagnetic parameters from scattering coefficients was studied in this paper. The Support Vector Machine (SVM) method is used to solve the inverse problem of parameters extraction. The mapping relationship is set up by calculating a large number of S pa-rameters from the samples with different permittivity by using transmission line theory. The simulated data set is used as training data set for SVM. After the training, the SVM is used to predict the permittivity of material from the scattering coefficients.

Using Statistical Learning Algorithms in Regional Landslide Susceptibility Zonation with Limited Landslide Field Data

Regional Landslide Susceptibility Zonation(LSZ) is always challenged by the available amount of field data, especially in southwestern China where large mountainous areas and limited field information coincide. Statistical learning algorithms are believed to be superior to traditional statistical algorithms for their data adaptability. The aim of the paper is to evaluate how statistical learning algorithms perform on regional LSZ with limited field data. The focus is on three statistical learning algorithms, Logistic Regression(LR), Artificial Neural Networks(ANN) and Support Vector Machine(SVM). Hanzhong city, a landslide prone area in southwestern China is taken as a study case. Nine environmental factors are selected as inputs. The accuracies of the resulting LSZ maps are evaluated through landslide density analysis(LDA), receiver operating characteristic(ROC) curves and Kappa index statistics. The dependence of the algorithm on the size of field samples is examined by varying the sizes of the training set. The SVM has proven to be the most accurate and the most stable algorithm at small training set sizes and on all known landslide sizes. The accuracy of SVM shows a steadilyincreasing trend and reaches a high level at a small size of the training set, while accuracies of LR and ANN algorithms show distinct fluctuations. The geomorphological interpretations confirm the strength of SVM on all landslide sizes. Our results show that the strengths of SVM in generalization capability and model robustness make it an appropriate and efficient tool for regional LSZ with limited landslide field samples.

Linear Support Vector Machine Based Inter-harmonic Modeling and Parameter Estimation

There are often system. The high measure many inter-harmonics in power t accuracy of inter-harmonics order, amplitude and initial phase is needed. A new approach is presented for inter-harmonic modeling and parameter estimation based on linear support vector machine （SVM）. Firstly, parameter estimation of linear model is realized based on standard linear SVM. Then, interharmonic model is transformed to a linear model according to trigonometric functions. The approach obtains order of inter-harmonic model with windowed Blackman-Tukey （BT） spectrum analysis, and gets number and frequency of harmonics. Finally, the linear SVM is applied to estimate the inter-harmonic parameters, amplitude and initial phase. The simulation results show that the proposed approach has high precision and good antinoise. The accuracy of three parameters are all higher than 98%.