Improved Approach Based on SVM for License Plate Character Recognition

An improved approach based on support vector machine （SVM） called the center distance ratio method is presented for license plate character recognition. First the support vectors are pre-extraeted. A minimal set called the margin vector set, which contains all support vectors, is extracted. These margin vectors compose new training data and construct the classifier by using the general SVM optimized. The experimental resuhs show that the improved SVM method does well at correct rate and training speed.     

A new method for PQ disturbance detection and identification

A new method based on phase-shift and N-1 Support Vector Machines(SVMs)is presented for power quality(PQ)disturbance detection and identification.Through phase-shift and simple algebra operation,the method detects out the PQ disturbances easily and effectively.Then a data dealing process is carried out to extract features from the detecting outputs.Then SVM theory is introduced into the identification of PQ disturbances.N kinds of PQ disturbances are classified with an N-1 SVMs classifier.The testing results show that the proposed method can detect and classify the PQ disturbances successfully.Moreover,the classifier has a good performance on training speed and correct ratio.     

SVM with discriminative dynamic time alignment

In the past several years, support vector machines (SVM) have achieved a huge success in many fields, especially in pattern recognition. But the standard SVM cannot deal with length-variable vectors, which is one severe obstacle for its applications to some important areas, such as speech recognition and part-of-speech tagging. The paper proposed a novel SVM with discriminative dynamic time alignment (DDTA-SVM) to solve this problem. When training DDTA-SVM classifier, according to the category information of the training samples, different time alignment strategies were adopted to manipulate them in the kernel functions, which contributed to great improvement for training speed and generalization capability of the classifier. Since the alignment operator was embedded in kernel functions, the training algorithms of standard SVM were still compatible in DDTA-SVM. In order to increase the reliability of the classification, a new classification algorithm was suggested. The preliminary experimental results on Chinese confusable syllables speech classification task show that DDTA-SVM obtains faster convergence speed and better classification performance than dynamic time alignment kernel SVM (DTAK-SVM). Moreover, DDTA-SVM also gives higher classification precision compared to the conventional HMM. This proves that the proposed method is effective, especially for confusable length-variable pattern classification tasks.     

Stability classification model of mine-lane surrounding rock based on distance discriminant analysis method

Based on the principle of Mahalanobis distance discriminant analysis （DDA） theory, a stability classification model for mine-lane surrounding rock was established, including six indexes of discriminant factors that reflect the engineering quality of surrounding rock： lane depth below surface, span of lane, ratio of directly top layer thickness to coal thickness, uniaxial comprehensive strength of surrounding rock, development degree coefficient of surrounding rock joint and range of broken surrounding rock zone. A DDA model was obtained through training 15 practical measuring samples. The re-substitution method was introduced to verify the stability of DDA model and the ratio of mis-discrimination is zero. The DDA model was used to discriminate 3 new samples and the results are identical with actual rock kind. Compared with the artificial neural network method and support vector mechanic method, the results show that this model has high prediction accuracy and can be used in practical engineering.     

Novel manufacturing method of optical fiber coupler

Based on the coupling mode theory that the coupling ratio of fiber coupler changes periodically with center distance of two optical fibers, a novel manufacturing method of optical fiber couplers was developed with fused biconical taper experimental system. Its fabrication process is that the fiber is fused but not stretched when light begins to split, and the reduction of diameter of fiber is dependent on the theological characteristic of the fused fiberglass. The performance of the coupler was tested. The results show that the performance of the novel optical fiber coupler meets the performance expectations, and its diameter of coupling region （about 30 μm） is twice as long as that of classical fused biconical taper coupler （about 16 μm）, so the default, that is, the device is easy to fracture, is restrained and the reliability is greatly improved.     

An Improved Minimum Distance Method Based on Artificial Neural Networks

MDM（minimum distance method)is a very popular algorithm in state recognition.But it has a presupposition,that is ,the diatance within one class must be shorter enough than the distance between classes.When this presupostion is not satisfied,the method is no loger valid.In order to overcome the shortcomings of MDM,an improved minimum distance method (IMDM) based on ANN(artificial neural networks)is presented.The simulation results demonstrate that IMDM has two advantages ,that is ,the rate of recognition is faster and the accuracy of recognition is higher compared with MDM.     

Time series online prediction algorithm based on least squares support vector machine

Deficiencies of applying the traditional least squares support vector machine （LS-SVM） to time series online prediction were specified. According to the kernel function matrix＇s property and using the recursive calculation of block matrix, a new time series online prediction algorithm based on improved LS-SVM was proposed. The historical training results were fully utilized and the computing speed of LS-SVM was enhanced. Then, the improved algorithm was applied to timc series online prediction. Based on the operational data provided by the Northwest Power Grid of China, the method was used in the transient stability prediction of electric power system. The results show that, compared with the calculation time of the traditional LS-SVM（75 1 600 ms）, that of the proposed method in different time windows is 40-60 ms, proposed method is above 0.8. So the improved method is online prediction. and the prediction accuracy（normalized root mean squared error） of the better than the traditional LS-SVM and more suitable for time series online prediction.     

New Individual Identification Method of Radiation Source Signal Based on Entropy Feature and SVM

In this paper, according to the defect of methods which have low identification rate in low SNR, a new individual identification method of radiation source based on information entropy feature and SVM is presented. Firstly, based on the theory of multi-resolution wavelet analysis, the wavelet power spectrum of non- cooperative signal can be gotten. Secondly, according to the information entropy theory, the wavelet power spectrum entropy is defined in this paper. Therefore, the database of signal＇ s wavelet power spectrum entropy can be built in different SNR and signal parameters. Finally, the sorting and identification model based on SVM is built for the individual identification of radiation source signal. The simulation result indicates that this method has a high individual＇ s identification rate in low SNR, when the SNR is greater than 4 dB, the identification rate can reach 100%. Under unstable SNR conditions, when the range of SNR is between 0 dB and 24 dB, the average identification rate is more than 92.67%. Therefore, this method has a great application value in the complex electromagnetic environment.     

A new support vector machine optimized by improved particle swarm optimization and its application

A new support vector machine （SVM） optimized by an improved particle swarm optimization （PSO） combined with simulated annealing algorithm （SA） was proposed. By incorporating with the simulated annealing method, the global searching capacity of the particle swarm optimization（SAPSO） was enchanced, and the searching capacity of the particle swarm optimization was studied. Then, the improyed particle swarm optimization algorithm was used to optimize the parameters of SVM （c,σ and ε）. Based on the operational data provided by a regional power grid in north China, the method was used in the actual short term load forecasting. The results show that compared to the PSO-SVM and the traditional SVM, the average time of the proposed method in the experimental process reduces by 11.6 s and 31.1 s, and the precision of the proposed method increases by 1.24% and 3.18%, respectively. So, the improved method is better than the PSO-SVM and the traditional SVM.     

Single Radar Measurement Method for Antiaircraft Projectile Miss Distance

To measure miss distance for antiaircraft projectile,a radial velocity identification and positioning method with a single radar is proposed.By analyzing the spatial resolution of multi-frequency ranging radar,the discrimination and testing model of this radar for multi-targets (projectile and target) is established to analyze the systematic error of antiaircraft miss distance.Then through the aerial target flight test and contrast test with optical test equipment,the validity of the measurement method is verified.This new method has the potential to be used in the measurement of antiaircraft projectile miss distance.     

支持向量机的快速分类算法

支持向量机（SVM）算法在训练集的规模很大特别是支持向量很多时,支持向量机的学习过程需要占用大量的内存,算法的速度较慢。为此,笔者提出一种新的SVM快速分类算法。该算法通过选择边界向量,构造新的训练样本,减少了参与训练的样本数目。实验证明,该算法不仅能保证原算法的精度,具有良好的推广能力,而且提高了算法的速度。     

一种基于马氏距离的支持向量快速提取算法

针对用支持向量机解决分类问题，提出了一种采用样本到某一类的马氏距离来提取可能为支持向量的数据的方法，同时阐明了如何解决在输入空间和特征空问中求马氏距离所遇到的问题．利用特征值、特征矢量及伪逆运算的并行计算方法，建立了一种提取支持向量的快速算法．用该方法对训练数据进行预处理后，可以加快支持向量机的训练速度．实验结果也表明了该方法的有效性．     

一种基于支持向量机的目标定位方法

为了提高声纳在浅水域的性能，提出了一种基于统计学习理论的目标识别器的目标定位方法.该方法选择支持向量机（SVM）作为学习算法的核心.从已知训练样本得到多通道数据的协方差矩阵，将得到的矩阵转化为SVM的输入多维特征向量，并训练SVM而获得权向量.利用此权向量和SVM输出估计，可以得到目标位置信息.理论推导和仿真结果表明，与多重信号分类（MUSIC）算法相比较，该方法具有高的定位精度和快的收敛速度.该方法能有效地对在平面波模型下的目标进行测向，并具有鲁棒性.     

一种具有统计不相关性的最优边界鉴别向量集

为了解决现有维数约简算法受样本分布影响较大、不支持小样本学习等问题,在分析线性鉴别分析(LDA)中最优鉴别向量与支持向量机(SVM)中分类超平面法向量之间关系的基础上,基于统计不相关最优鉴别向量集优于正交最优鉴别向量集的事实,提出了通过对改进的SVM的二次优化问题进行递归求解来获取具有统计不相关性的最优边界鉴别向量集的算法,并使用核方法将其推广到可以解决非线性特征抽取问题.结果表明:在采用相同参数并使用k-最近邻分类器进行训练和测试的情况下,提出的算法对实际数据集Waveform,Heart,Diabetis的分类精度均高于SVM和RSVM,不会出现当抽取超过最优维数时随着抽取维数的增加分类精度反而降低的现象,体现了本算法在抽取不相关特征向量方面的有效性.     

一种改进的快速嵌入式字符识别方法

针对手持式字符识别系统开发中系统对实时性要求较高、系统资源有限以及传统的支持向量机(SVM)分类方法难以同时满足识别率和识别速度的缺点,提出一种快速的SVM(FCSVM)分类算法。对支持向量集采用变换的方式,用少量的支持向量代替全部支持向量进行分类计算,在保证不损失分类精度的前提下使得分类速度较传统SVM算法有较大提高。实验结果表明,FCSVM算法较大幅度地减少了计算复杂度,提高了分类速度,尤其在嵌入式系统中效果更加明显。     

基于支持向量机与粗糙集理论的病例诊断

针对支持向量分类机在病例诊断中,训练样本大、诊断速度慢的不足,根据粗糙集理论的属性约简和支持向量机的分类机理,提出了一种混合分类算法,对病例进行诊断.应用粗糙集理论在不损失有效信息的情况下对属性进行预处理,从决策表中删除冗余的属性和冲突对象,降低支持向量机的维数和分类过程中的复杂度.然后利用支持向量机的分类机原理,对对象进行分类和预测,从而达到对病例进行诊断.实验证明在通过粗糙集对信息约简后,在合理降低准确率的情况下提高了诊断速度,从而解决了支持向量分类机在处理大量病例信息情况下,诊断速度慢的问题.     

基于壳向量的线性支持向量机快速增量学习算法

提出了一种新的基于壳向量的增量式支持向量机快速学习算法.在增量学习的过程中，利用训练样本集中的几何信息，在样本中选取一部分最有可能成为支持向量的样本--壳向量，它是支持向量集的一个规模较小的扩展集，将其作为新的训练样本集，再进行支持向量训练.这在很大程度上减少了求取支持向量过程中的二次优化运算时间，使增量学习的训练速度大为提高.与单纯使用支持向量代表样本数据集合进行增量学习的传统算法相比，使用该算法使分类精度得到了提高.针对肝功能检测标准数据集（BUPA）的实验验证了该算法的有效性.