基于支持向量机协同训练的半监督回归

将支持向量机与半监督学习理论相结合,提出基于支持向量机协同训练的半监督回归模型,使用两个支持向量机回归模型相互影响,协同训练。利用实验数据集进行实验,并与监督支持向量机回归模型、半监督自训练支持向量机回归模型作比较。实验结果表明,基于支持向量机协同训练的半监督回归模型在缺少标记样本的情况下,提高了回归估计的精度。     

基于深度学习与有向无环图SVM的局部调整年龄估计

为了进一步提高年龄估计的精度，提出一种基于深度学习与有向无环图SVM的局部调整年龄估计算法。在训练阶段，将经过VGGFace2数据集预训练的SE-ResNet-50网络进行微调，待到收敛时提取出全连接层，将其首尾相连形成的向量作为表征并训练出多个One-Versus-One SVM。在测试阶段，将待估计人脸图像送入SE-ResNet-50以得到一个较为粗略的年龄估计值；设定具体邻域；将训练而成的SVM组合为一个有向无环图SVM并以全局估计值为中心进行精准的年龄估计。为了表明算法的普适性，在不同种族的MORPH和AFAD图像集中进行实验，结果验证了算法的有效性。     

基于改进的SVMR的混沌时间序列预测

针对标准支持向量机处理大规模数据集会出现训练速度慢、计算量大的缺点,提出了一种基于二叉树模型的支持向量机回归方法。通过二叉树模型将大样本数据集自适应分解成若干个子集,利用支持向量机分段提出支持向量,再把这些支持向量汇合成一个训练样本集进行训练产生决策函数,并将其应用到混沌时间序列的预测。与标准算法相比,该方法在保证泛化精度一致的前提下,极大地加快了训练速度。     

超球体单类支持向量机的SMO训练算法

由于One-class支持向量机能用于无监督学习,被广泛用于信息安全、图像识别等领域中.而超球体One class支持向量机能生成一个合适的球体,将训练样本包含其中,故更适合于呈球形分布的样本学习.但由于超球体One-class支持向量机没有一种快速训练算法,使其在应用中受到限制.SMO算法成功地训练了标准SVM,其训练思想也可用于超球体One-class支持向量机的训练.本文提出了超球体One-class支持向量机的SMO训练算法,并对其空间和时间复杂度进行了分析.实验表明,这种算法能迅速、有效地训练超球体One-class支持向量机.     

一种基于Word2Vec的训练效果优化策略研究

Word2Vec是谷歌在2013年开源的一款语言处理工具包,它能够在基于神经网络训练语言模型的同时将词表示成实数值向量,并根据向量空间余弦距离来寻找语义相似度高的词,训练效率较高。在应用Word2 Vec训练词向量的过程中,对其中可能影响Word2 Vec词向量训练的中文分词和算法选择环节进行试验,配合深入解析部分核心源代码,发现能使训练效果最优的策略,使得Word2Vec的性能获得一定的提升,为下一步的应用提供了更好的词向量。     

一种新的基于统计向量和神经网络的边缘检测方法

通过构造不同的统计量定量描述了边缘点邻域灰度的分布特征,并将4个统计量组成统计向量.计算训练图像的统计向量作为样本对BP神经网络训练,然后将训练的BP网络直接用于边缘检测.新方法在统计向量的构造上充分考虑了边缘点和噪声点的区别,具有较好的抗噪性能;BP网络的结构和训练都比较简单;而且不需要设定阈值检测边缘.实验表明,新方法抗噪性能好,达到了令人满意的边缘检测效果.     

基于SVM的信息融合新方法*

利用SVM对大规模数据进行训练时,需要占用很大的内存空间,甚至会因内存不够而无法训练。为此,提出了将大规模数据分块求解,然后将分块求解的结果进行信息融合的新方法。首先训练得到各模块的支持向量,将所有支持向量进行融合,得到决策模型和一组支持向量。当有新的数据加入时,将其作为一个子模块,训练得到该模块的支持向量,与原模型中获得的支持向量进行融合,训练得到新的决策模型。利用KDDCUP99数据进行实验,结果表明该方法的测试精度与在所有数据集上训练的精度相当,花费时间少,适用于增量学习。     

一种基于凸壳算法的SVM集成方法

为提高支持向量机(SVM)集成的训练速度,提出一种基于凸壳算法的SVM集成方法,得到训练集各类数据的壳向量,将其作为基分类器的训练集,并采用Bagging策略集成各个SVM。在训练过程中,通过抛弃性能较差的基分类器,进一步提高集成分类精度。将该方法用于3组数据,实验结果表明,SVM集成的训练和分类速度平均分别提高了266％和25％。     

基于壳向量和中心向量的支持向量机

针对支持向量机(Support vector machines,SVMs)中大规模样本集训练速度慢且分类精度易受野点影响的问题,提出一个基于样本几何信息的支持向量机算法.其基本步骤是,首先分别求取每类样本点的壳向量和中心向量,然后将求出的壳向量作为新的训练集进行标准的SVM训练得到超平面的法向量,最后利用中心向量来更新法向量从而减少野点的影响得到最终的分类器.实验表明,采用这种学习策略,不仅加快了训练速度,而且在一般情况下也提高了分类精度.     

基于RS-SVR的企业信用评分模型

准确的信用评分模型可以提升银行的决策能力,将支持向量回归模型应用于企业信用评分问题,并提出基于随机子集的支持向量回归集成模型。首先使用随机子集抽样模型获得足够多不同的训练数据集,接下来使用不同的训练集子集训练得到不同的支持向量回归模型,最后使用简单平均方法整合不同模型的预测结果,在企业信用评分数据上的实验结果证明了模型的有效性。     

一种基于反例样本修剪支持向量机的事件追踪算法

支持向量机（SVM）在各类别样本数目分布不均匀时，样本数量越多其分类误差越小，而样本数量越少其分类误差越大．在分析这种倾向产生原因的基础上，提出了一种基于反例样本修剪支持向量机（NEP—SVM）的事件追踪算法．该算法首先修剪反例样本，根据距离和类标决定一反例样本的取舍，然后使用SVM对新的样本集进行训练以得到分类器，补偿了上述倾向性问题造成的不利影响．另外，由于后验概率对于提高事件追踪的性能至关重要，而传统的支持向量机不提供后验概率，本文通过一个sigmoid函数的参数训练将SVM的输出结果映射成概率．实验结果表明NEP—SVM是有效的．     

基于DAGSVM的高炉故障诊断研究

针对高炉故障诊断智能化程度低，对操作人员技术水平要求高等不足，提出了基于支持向量机的多类分类故障诊断方法．根据统计学原理，使用核函数将样本映射到高维空间进行训练．综合各种核函数的测试准确率，得到解决该问题的最佳核函数．通过比较不同的多类分类算法，提出了基于DAGSVM的诊断模型．实验结果表明该算法具有较高的识别准确率．     

基于马氏距离的孪生多分类支持向量机

孪生支持向量机(TWSVM)的研究是近来机器学习领域的一个热点。TWSVM具有分类精度高、训练速度快等优点,但训练时没有充分利用样本的统计信息。作为TWSVM的改进算法,基于马氏距离的孪生支持向量机(TMSVM)在分类过程中考虑了各类样本的协方差信息,在许多实际问题中有着很好的应用效果。然而TMSVM的训练速度有待提高,并且仅适用于二分类问题。针对这两个问题,将最小二乘思想引入TMSVM,用等式约束取代TMSVM中的不等式约束,将二次规划问题的求解简化为求解两个线性方程组,得到基于马氏距离的最小二乘孪生支持向量机(LSTMSVM),并结合有向无环图策略(DAG)设计出基于马氏距离的最小二乘孪生多分类支持向量机。为了减少DAG结构的误差累积,构造了基于马氏距离的类间可分性度量。人工数据集和UCI数据集上的实验均表明,所提算法不仅有效,而且相对于传统多分类SVM,其分类性能有明显提高。     

Binary tree of SVM: a new fast multiclass training and classification algorithm

We present a new architecture named Binary Tree of support vector machine (SVM), or BTS, in order to achieve high classification efficiency for multiclass problems. BTS and its enhanced version, c-BTS, decrease the number of binary classifiers to the greatest extent without increasing the complexity of the original problem. In the training phase, BTS has N-1 binary classifiers in the best situation (N is the number of classes), while it has log/sub 4/3/((N+3)/4) binary tests on average when making a decision. At the same time the upper bound of convergence complexity is determined. The experiments in this paper indicate that maintaining comparable accuracy, BTS is much faster to be trained than other methods. Especially in classification, due to its Log complexity, it is much faster than directed acyclic graph SVM (DAGSVM) and ECOC in problems that have big class number.     

A novel pattern recognition algorithm: Combining ART network with SVM to reconstruct a multi-class classifier

Based on the principle of one-against-one support vector machines (SVMs) multi-class classification algorithm, this paper proposes an extended SVMs method which couples adaptive resonance theory (ART) network to reconstruct a multi-class classifier. Different coupling strategies to reconstruct a multi-class classifier from binary SVM classifiers are compared with application to fault diagnosis of transmission line. Majority voting, a mixture matrix and self-organizing map (SOM) network are compared in reconstructing the global classification decision. In order to evaluate the method’s efficiency, one-against-all, decision directed acyclic graph (DDAG) and decision-tree (DT) algorithm based SVM are compared too. The comparison is done with simulations and the best method is validated with experimental data.     

基于结构优化的DDAG-SVM上肢康复训练动作识别方法

针对上肢康复训练系统中训练评估方法核心的动作识别问题,提出一种面向Brunnstrom 4~5期患者上肢康复训练动作的SODDAG-SVM(Structure-optimized decision directed acyclic graph-support vector machine)多分类识别方法.首先将多分类问题分解成一组二分类问题,并使用支持向量机构建各二分类器,分别采用遗传算法和特征子集区分度准则对各二分类器的核函数参数及特征子集进行优化.然后使用类对的SVM二分类器泛化误差来衡量每个类对的易被分离程度,并由其建立类对泛化误差上三角矩阵.最后由根节点开始,依次根据各节点的泛化误差矩阵,通过选择其中最易被分离类对的SVM分类器构成该节点的方式,来构建SODDAG-SVM多分类器结构.当待预测的实例较少时,直接构建实例经过的SODDAG-SVM部分结构并对实例进行预测;当待预测的实例较多时,先构建完整的SODDAG-SVM结构,再代入所有实例进行预测.通过人体传感技术获得Brunnstrom 4~5阶段上肢康复训练的常用动作样本集,进行SODDAG-SVM动作识别实验,准确率达到了95.49%,结果均优于常规的决策有向无环图(Decision directed acyceic graph,DDAG)和MaxWins方法,实验表明本文方法能有效地提高上肢康复训练动作识别的准确率.     

Active learning SVM with regularization path for image classification

In classification problems, many different active learning techniques are often adopted to find the most informative samples for labeling in order to save human labors. Among them, active learning support vector machine (SVM) is one of the most representative approaches, in which model parameter is usually set as a fixed default value during the whole learning process. Note that model parameter is closely related to the training set. Hence dynamic parameter is desirable to make a satisfactory learning performance. To target this issue, we proposed a novel algorithm, called active learning SVM with regularization path, which can fit the entire solution path of SVM for every value of model parameters. In this algorithm, we first traced the entire solution path of the current classifier to find a series of candidate model parameters, and then used unlabeled samples to select the best model parameter. Besides, in the initial phase of training, we constructed a training sample sets by using an improved K-medoids cluster algorithm. Experimental results conducted from real-world data sets showed the effectiveness of the proposed algorithm for image classification problems.     

基于频域相关和SVM的宽带多信号测向方法研究

提出一种基于SVM的宽带测向新方法,利用频域相关技术提取宽带范围内感兴趣的信号的相位差,利用此相位差作为支持向量机的输入特征训练DOA（Direction Of Arrival）估计模型,对宽带范围内的多个窄带或宽带信号进行测向。训练后的模型针对的是一个较宽的频段范围,有效避免了其他算法要针对不同频率频繁调整模型的问题,大大降低了计算量。实验结果也验证了该方法具有较高的测向精度和较快的测向速度。     

A fast classification strategy for SVM on the large-scale high-dimensional datasets

The challenges of the classification for the large-scale and high-dimensional datasets are: (1) It requires huge computational burden in the training phase and in the classification phase; (2) it needs large storage requirement to save many training data; and (3) it is difficult to determine decision rules in the high-dimensional data. Nonlinear support vector machine (SVM) is a popular classifier, and it performs well on a high-dimensional dataset. However, it easily leads overfitting problem especially when the data are not evenly distributed. Recently, profile support vector machine (PSVM) is proposed to solve this problem. Because local learning is superior to global learning, multiple linear SVM models are trained to get similar performance to a nonlinear SVM model. However, it is inefficient in the training phase. In this paper, we proposed a fast classification strategy for PSVM to speed up the training time and the classification time. We first choose border samples near the decision boundary from training samples. Then, the reduced training samples are clustered to several local subsets through MagKmeans algorithm. In the paper, we proposed a fast search method to find the optimal solution for MagKmeans algorithm. Each cluster is used to learn multiple linear SVM models. Both artificial datasets and real datasets are used to evaluate the performance of the proposed method. In the experimental result, the proposed method prevents overfitting and underfitting problems. Moreover, the proposed strategy is effective and efficient.     

Automatic content-based retrieval and semantic classification of video content

The problem of video classification can be viewed as discovering the signature patterns in the elemental features of a video class. In order to solve this problem, a large and diverse set of video features is proposed in this paper. The contributions of the paper further lie in dealing with high-dimensionality induced by the feature space and in presenting an algorithm based on two-phase grid searching for automatic parameter selection for support vector machine (SVM). The framework thus is directed to bridge the gap between low-level features and semantic video classes. The experimental results and comparison with state-of-the-art learning tools on more than 5000 video segments show the effectiveness of our approach.