Robustly stable model predictive control based on parallel support vector machines with linear kernel

Robustly stable multi-step-ahead model predictive control (MPC) based on parallel support vector machines (SVMs) with linear kernel was proposed. First, an analytical solution of optimal control laws of parallel SVMs based MPC was derived, and then the necessary and sufficient stability condition for MPC closed loop was given according to SVM model, and finally a method of judging the discrepancy between SVM model and the actual plant was presented, and consequently the constraint sets, which can guarantee that the stability condition is still robust for model/plant mismatch within some given bounds, were obtained by applying small-gain theorem. Simulation experiments show the proposed stability condition and robust constraint sets can provide a convenient way of adjusting controller parameters to ensure a closed-loop with larger stable margin.

基于MapReduce的最小二乘支持向量机回归模型

针对最小二乘支持向量机处理大规模数据集耗时长且受内存限制的特点,将局部多模型方法与MapReduce编程模式相结合,提出一种并行最小二乘支持向量机回归模型。模型由两组MapReduce过程组成,首先按照输入样本集对样本数据进行聚类操作,再对聚类后得到的子类按输出样本集进行二次聚类操作,分别得到局部模型数目和各局部模型综合加权输出计算结果。实验结果表明,并行最小二乘支持向量机回归模型具有较好的加速比和可扩展性。

基于MapReduce的支持向量机态势评估算法

支持向量机(SVM)可以解决传统态势评估算法无法兼顾的"维数灾难""过学习"及"非线性"等难题,却无法应对大规模样本的问题。为了有效应对态势评估中的大数据处理挑战,提出了一种基于MapReduce的SVM(MR-SVM)态势评估算法。该算法利用MapReduce并行计算模型,同时结合SVM可并行化的特点,通过设计主要的map函数和reduce函数,实现了SVM算法的并行化和主要参数的选取。在搭建的Hadoop平台上对改进算法与原算法进行了比较验证:对于小规模样本,改进算法反而"化简为繁",不比原算法效率高;但在大规模样本的处理上,原算法的训练时间随样本规模呈指数型增长,而改进算法的训练时间随样本规模并没有特别明显的增幅,体现出了较好的时间优势。实验结果表明,基于MapReduce改进的SVM很好地弥补了原算法"样本规模"的短板,更适用于大数据环境下的网络态势评估。

利用MapReduce模型训练支持向量机的人脸识别方法

为了在移动互联网中快速识别人脸图像,提出了利用云计算服务端的MapReduce模型训练支持向量机(SVM)进行人脸识别的方法.实验结果表明:该算法在保证人脸识别率的前提下,明显提升了支持向量机的训练速度.该算法对于移动互联网环境下的人脸识别有一定的实用价值.

一种基于MapReduce的动态数据流分类算法

当前动态数据流下的实时分类问题存在3个难点:针对海量数据的实时处理;概念漂移的跟踪和模型的更新;模型的稳定和鲁棒性.针对上述问题,将极端支持向量机(extreme support vector machine,ESVM)与MapReduce框架结合,提出了带遗忘因子的鲁棒ESVM算法.该方法通过构造残差权重矩阵,对残差进行修正,同时加入遗忘因子,提高新样本的作用,从而实现对海量数据处理问题的求解.实验结果显示,所提出方法能够快速有效地对动态数据流进行分类,且结果不易受到噪声干扰,稳定性强.

基于MapReduce的支持向量机参数选择研究

针对在分布式Hadoop集群环境下对支持向量机进行最优分类模型参数选择的问题,提出一种基于MapReduce框架的最优分类模型参数选择算法。该算法能以串行或单个MapReduce作业这两种方式完成最优模型参数的选择,在Map阶段读取存储在Hadoop分布式文件系统中的参数文件,并为每组参数生成具有不同键值的中间结果,以保证在Reduce阶段,每个并行执行的任务仅对一组参数进行交叉验证。实验结果表明,在集群内存资源合理消耗的前提下,为粗粒度最优参数搜索设置适当的Reduce数量,单个MapReduce作业方式相比于串行MapReduce作业方式算法运行效率至少提升了1.7倍,显著减少最优模型参数的获取时间。

基于MapReduce的层叠分组并行SVM算法研究

随着训练集规模的不断增大,支持向量机学习成为了密集型计算的过程。针对计算过程中存在占用内存大、寻优速度慢等问题,通过大量实验对分组训练和层叠训练两种并行SVM算法进行性能分析,给出层叠分组SVM并行算法,并利用MapReduce并行框架实现,解决了层叠训练模型效率低的问题。实验结果表明,采用这种学习策略,在保持精度损失较小的情况下,一定程度上减少了训练时间,提高了分类速度。

基于MapReduce和Bagging的并行组合支持向量机

为提高大规模支持向量机的运算效率,提出一种基于MapReduce和Bagging的并行组合支持向量机训练算法。该算法包括两个MapReduce流程:(1)分布式并行训练,利用标准SVM算法进行多任务并行的分块训练,保留所有的支持向量,迅速缩减数据集;(2)集成式并行训练,采用Bagging集成算法的思想,结合随机次梯度SVM算法对剩余的支持向量训练,以提高算法的分类精度。实验结果表明,并行组合支持向量机训练算法在保持较高分类精度的基础上,能提高算法运行效率及数据处理能力,能很好地应用于大规模数据集的SVM训练。

Integrated parallel forecasting model based on modified fuzzy time series and SVM

A dynamic parallel forecasting model is proposed, which is based on the problem of current forecasting models and their combined model. According to the process of the model, the fuzzy C-means clustering algorithm is improved in outliers operation and distance in the clusters and among the clusters. Firstly, the input data sets are optimized and their coherence is ensured, the region scale algorithm is modified and non-isometric multi scale region fuzzy time series model is built. At the same time, the particle swarm optimization algorithm about the particle speed, location and inertia weight value is improved, this method is used to optimize the parameters of support vector machine, construct the combined forecast model, build the dynamic parallel forecast model, and calculate the dynamic weight values and regard the product of the weight value and forecast value to be the final forecast values. At last, the example shows the improved forecast model is effective and accurate.

基于迭代式MapReduce并行虚拟筛选的研究

由于传统的SVM的应用最常用的是MPI(Message Passing Interface)技术,但是MPI对大数据集显得繁杂、不实用,并且基于并行向量机(Support Vector Machine)的虚拟筛选不仅要面对巨大数据集,还要进行O(n2).这样复杂庞大的计算.针对以上问题,在集群方面采用MapReduce对超大数据集进行数据分析.本文采用Spark一种迭代式MapReduce编程模型,提出一种基于SVM虚拟筛选的MapReduce执行方案,分析了HDFS和Spark结合使用才能实现对数据的并行化分布和处理,实验表明该方案对大数据表现理想,且为大规模的公共云架构进行有效虚拟筛选提供了可能.

SUPPORT VECTOR MACHINE FOR STRUCTURAL RELIABILITY ANALYSIS

Support vector machine （SVM） was introduced to analyze the reliability of the implicit performance function, which is difficult to implement by the classical methods such as the first order reliability method （FORM） and the Monte Carlo simulation （MCS）. As a classification method where the underlying structural risk minimization inference rule is employed, SVM possesses excellent learning capacity with a small amount of information and good capability of generalization over the complete data. Hence, two approaches, i.e., SVM-based FORM and SVM-based MCS, were presented for the structural reliability analysis of the implicit limit state function. Compared to the conventional response surface method （RSM） and the artificial neural network （ANN）, which are widely used to replace the implicit state function for alleviating the computation cost, the more important advantages of SVM are that it can approximate the implicit function with higher precision and better generalization under the small amount of information and avoid the ＂curse of dimensionality＂. The SVM-based reliability approaches can approximate the actual performance function over the complete sampling data with the decreased number of the implicit performance function analysis （usually finite element analysis）, and the computational precision can satisfy the engineering requirement, which are demonstrated by illustrations.

Structural Reliability Analysis Based on Support Vector Machine and Dual Neural Network Direct Integration Method

Aiming at the reliability analysis of small sample data or implicit structural function,a novel structural reliability analysis model based on support vector machine(SVM)and neural network direct integration method(DNN)is proposed.Firstly,SVM with good small sample learning ability is used to train small sample data,fit structural performance functions and establish regular integration regions.Secondly,DNN is approximated the integral function to achieve multiple integration in the integration region.Finally,structural reliability was obtained by DNN.Numerical examples are investigated to demonstrate the effectiveness of the present method,which provides a feasible way for the structural reliability analysis.

Developing a Support Vector Machine Based QSPR Model to Predict Gas-to-Benzene Solvation Enthalpy of Organic Compounds

The purpose of this paper is to present a novel way to building quantitative structure-property relationship(QSPR) models for predicting the gas-to-benzene solvation enthalpy(ΔHSolv) of 158 organic compounds based on molecular descriptors calculated from the structure alone. Different kinds of descriptors were calculated for each compounds using dragon package. The variable selection technique of enhanced replacement method(ERM) was employed to select optimal subset of descriptors. Our investigation reveals that the dependence of physico-chemical properties on solvation enthalpy is a nonlinear observable fact and that ERM method is unable to model the solvation enthalpy accurately. The standard error value of prediction set for support vector machine(SVM) is 1.681 kJ ? mol^(-1) while it is 4.624 kJ ? mol^(-1) for ERM. The results established that the calculated ΔHSolvvalues by SVM were in good agreement with the experimental ones, and the performances of the SVM models were superior to those obtained by ERM one. This indicates that SVM can be used as an alternative modeling tool for QSPR studies.

Using the Support Vector Machine Algorithm to Predict β-Turn Types in Proteins

The structure and function of proteins are closely related, and protein structure decides its function, therefore protein structure prediction is quite important.β-turns are important components of protein secondary structure. So development of an accurate prediction method ofβ-turn types is very necessary. In this paper, we used the composite vector with position conservation scoring function, increment of diversity and predictive secondary structure information as the input parameter of support vector machine algorithm for predicting theβ-turn types in the database of 426 protein chains, obtained the overall prediction accuracy of 95.6%, 97.8%, 97.0%, 98.9%, 99.2%, 91.8%, 99.4% and 83.9% with the Matthews Correlation Coefficient values of 0.74, 0.68, 0.20, 0.49, 0.23, 0.47, 0.49 and 0.53 for types I, II, VIII, I’, II’, IV, VI and nonturn respectively, which is better than other prediction.

The Comparison between Random Forest and Support Vector Machine Algorithm for Predicting β-Hairpin Motifs in Proteins

Based on the research of predictingβ-hairpin motifs in proteins, we apply Random Forest and Support Vector Machine algorithm to predictβ-hairpin motifs in ArchDB40 dataset. The motifs with the loop length of 2 to 8 amino acid residues are extracted as research object and thefixed-length pattern of 12 amino acids are selected. When using the same characteristic parameters and the same test method, Random Forest algorithm is more effective than Support Vector Machine. In addition, because of Random Forest algorithm doesn’t produce overfitting phenomenon while the dimension of characteristic parameters is higher, we use Random Forest based on higher dimension characteristic parameters to predictβ-hairpin motifs. The better prediction results are obtained;the overall accuracy and Matthew’s correlation coefficient of 5-fold cross-validation achieve 83.3% and 0.59, respectively.

Prediction of Glass Transition Temperatures of Polyarylates Using a Support Vector Machine Model

A three-descriptor quantitative structure-property relationship （QSPR） model, based on the support vector machine （SVM） algorithm, was constructed to predict the glass transition temperatures （Tgs） ofpolyarylates with complex structures. A total of 50 polyarylates were randomly divided into three sets, viz., the training set （30 polymers）, validation set （10 polymers） and prediction set （10 polymers）. By adjusting various parameters by trial and error, the final optimum SVM model based on Austin Model 1 （AM1） calculation is a polynomial kernel with the parameters C of 100, ε of 1.00E-05 and d of 2. The root-mean-square （RMS） errors obtained from the training set, validation set and prediction set are 19.4, 12.8 and 15.5 K, respectively. Research results show that the proposed SVM model has better statistical quality than the previous models. Thus, applying the SVM algorithm to predict Tgs of polymers is feasible.

Research on Natural Gas Short-Term Load Forecasting Based on Support Vector Regression

Natural gas load forecasting is a key process to the efficient operation of pipeline network. An accurate forecast is required to guarantee a balanced network operation and ensure safe gas supply at a minimum cost.Machine learning techniques have been increasingly applied to load forecasting. A novel regression technique based on the statistical learning theory, support vector machines (SVM), is investigated in this paper for natural gas shortterm load forecasting. SVM is based on the principle of structure risk minimization as opposed to the principle of empirical risk minimization in conventional regression techniques. Using a data set with 2 years load values we developed prediction model using SVM to obtain 31 days load predictions. The results on city natural gas short-term load forecasting show that SVM provides better prediction accuracy than neural network. The software package natural gas pipeline networks simulation and load forecasting (NGPNSLF) based on support vector regression prediction has been developed, which has also been applied in practice.

Support vector classification for structure-activity-relationship of 1-（ 1H- 1,2,4-triazole- 1-yl）- 2-（ 2,4-difluorophenyl）-3-substituted-2- propanols

The support vector classification （SVC） was employed to make a model for classification of antifungal activities of 1-（1H-1,2,4-triazole-l-yl）-2-（2,4-difluorophenyl）-3-substituted-2-propanols triazole derivatives. The compounds with high antifungal activities and those with low antifungal activities were compared on the basis of the following molecular descriptors： net atomic charge on the atom N connecting with R, dipole moment and heat of formation, By using the SVC, a mathematical model was constructed, which can predict the antifungal activities of the triazole derivatives, with an accuracy of 91% on the basis of the leave-one-out cross-validation （LOOCV） test, The results indicate that the performance of the SVC model can exceed that of the principal component analysis （PCA） and K-Nearest Neighbor （KNN） models for this real world data set.

直觉模糊的结构化最小二乘孪生支持向量机

针对最小二乘孪生支持向量机(least squares twin support vector machine,LSTSVM)对噪声或是异常数据敏感和忽略数据内在结构信息的问题,提出了一种直觉模糊的结构化最小二乘孪生支持向量机(intuition fuzzy and structural least squares twin support vector machine,IF-SLSTSVM)。首先采用孤立森林对输入样本点进行预处理;然后通过直觉模糊数的概念,赋予输入样本点不同的权重以减少噪声或是异常数据对分类超平面产生的影响;最后采用K-Means算法,以协方差的形式获取输入样本点之间的结构信息。IFSLSTSVM在LS-TSVM的基础上,考虑了输入样本点在特征空间中的分布信息及输入样本点之间的关系,提高了模型的鲁棒性。实验采取UCI数据集,在0%、5%、10%以及20%的不同比例噪声环境对IF-SLSTSVM算法的有效性进行验证。结果显示相较于6种对比算法,IF-SLSTSVM算法有更好的鲁棒性。

结构化最大间隔双支持向量机在股票预测中的应用

股票价格受政策、宏观经济以及公司经营状况等多方因素的影响,且各因素之间存在较高的相关性,因此股票数据存在的高噪声、非平稳等特性使得股票预测充满困难。为了减少数据中存在的噪声对股价预测准确性的影响,基于马氏距离的类间隔可分性,提出了结构化最大间隔双支持向量机,其分别针对正类样本和负类样本,寻找两个非平行的超平面,使每一类样本离本类样本的欧式距离尽可能小,同时离异类超平面的马氏距离尽可能大。8组基准数据集的实验结果表明,该方法在含噪声数据的分类问题上具有稳定的准确率,从而提升了模型的预测性能和抗噪能力。同时将其应用到股票涨跌趋势预测中,通过对上证综指、上证A指、上证380指数以及中国平安等14只股票实证分析的结果表明,相较于其他对比模型,结构化最大间隔双支持向量机表现出了较好的预测结果,具有一定的实用价值。