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.

Localizing structural damage based on auto-regressive with exogenous input model parameters and residuals using a support vector machine based learning approach

Machine learning algorithms operating in an unsupervised fashion has emerged as promising tools for detecting structural damage in an automated fashion.Its essence relies on selecting appropriate features to train the model using the reference data set collected from the healthy structure and employing the trained model to identify outlier conditions representing the damaged state.In this paper,the coefficients and the residuals of the autoregressive model with exogenous input created using only the measured output signals are extracted as damage features.These features obtained at the baseline state for each sensor cluster are then utilized to train the one class support vector machine,an unsupervised classifier generating a decision function using only patterns belonging to this baseline state.Structural damage,once detected by the trained machine,a damage index based on comparison of the residuals between the trained class and the outlier state is implemented for localizing damage.The two-step damage assessment framework is first implemented on an eight degree-of-freedom numerical model with the effects of measurement noise integrated.Subsequently,vibration data collected from a one-story one-bay reinforced concrete frame inflicted with progressive levels of damage have been utilized to verify the accuracy and robustness of the proposed methodology.

Rapid bacteria identification using structured illumination microscopy and machine learning

Traditionally,optical microscopy is used to visualize the morphological features of pathogenic bacteria,of which the features are further used for the detection and ident ification of the bacteria.However,due to the resolution limitation of conventional optical microscopy as well as the lack of standard pattern library for bacteria identification,the ffectiveness of this optical microscopy-based method is limited.Here,we reported a pilot study on a combined use of Structured Illumination Microscopy(SIM)with machine learning for rapid bacteria identification.After applying machine learning to the SIM image datasets from three model bacteria(including Escherichia coli,Mycobacterium smegmatis,and Pseudomonas aeruginosa),we obtained a classifcation accuracy of up to 98%.This study points out a promising possibility for rapid bacterial identification by morphological features.

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.

Prediction of Protein Structural Classes Using the Theory of Increment of Diversity and Support Vector Machine

Based on the concept of the pseudo amino acid composition （PseAAC）, protein structural classes are predicted by using an approach of increment of diversity combined with support vector machine （ID-SVM）, in which the dipeptide amino acid composition of proteins is used as the source of diversity. Jackknife test shows that total prediction accuracy is 96.6% and higher than that given by other approaches. Besides, the specificity （Sp） and the Matthew＇s correlation coefficient （MCC） are also calculated for each protein structural class, the Sp is more than 88%, the MCC is higher than 92%, and the higher MCC and Sp imply that it is credible to use ID-SVM model predicting protein structural class. The results indicate that： 1 the choice of the source of diversity is reasonable, 2 the predictive performance of IDSVM is excellent, and3 the amino acid sequences of proteins contain information of protein structural classes.

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.

Yarn Properties Prediction Based on Machine Learning Method

Although many works have been done to construct prediction models on yarn processing quality,the relation between spinning variables and yarn properties has not been established conclusively so far.Support vector machines(SVMs),based on statistical learning theory,are gaining applications in the areas of machine learning and pattern recognition because of the high accuracy and good generalization capability.This study briefly introduces the SVM regression algorithms,and presents the SVM based system architecture for predicting yarn properties.Model selection which amounts to search in hyper-parameter space is performed for study of suitable parameters with grid-research method.Experimental results have been compared with those of artificial neural network(ANN)models.The investigation indicates that in the small data sets and real-life production,SVM models are capable of remaining the stability of predictive accuracy,and more suitable for noisy and dynamic spinning process.

LS-SVM在桥梁结构健康预测评估中的研究

桥梁的结构变形包含的桥梁结构内涵信息丰富,具有非线性、时序性和样本容量小的特点.利用支持向量机,以杭州湾大桥实测变形数据为研究对象,提出了基于LS-SVM的桥梁结构变形预测模型,通过实验证明了运用其对桥梁结构健康状况进行评估的可行性和有效性,并且通过实验结果对比显示了最小二乘支持向量机在变形预测中的优势.

基于GA和LS-SVM的AGV变结构控制

为了提高自动引导车控制的精度,提出了一种基于遗传算法和支持向量机的变结构控制方法。利用遗传算法结合支持向量机在线调整变结构控制律中的参数,克服了常规变结构控制方法中需预先设定趋近律参数的限制,既保留了传统趋近律的优点,又有效的改善了系统的控制品质,消除了系统抖振,使系统最终以理想方式在滑模面上运动,理论分析和仿真结果表明了所提出方法的有效性。

基于LS-SVM的压电智能结构损伤主动监测

基于被动监测技术的局限性,搭建了损伤主动监测系统,对监测信号进行了功率谱密度最大值(PSM)特征提取,并提出了一种基于最小二乘支持向量机(LS-SVM)的损伤检测方法。采用该方法,对压电智能复合材料层板进行了损伤定位的研究,并与改进的BP网络进行了对比,结果表明:在相同性能指标下,LS-SVM有比BP网络更高的损伤定位精度及更强的泛化能力。LS-SVM与主动监测技术的融合,为结构实现在线实时准确监测提供了一种新途径。

加权特征向量LS-SVM在线结构损伤识别

在增量式最小二乘支持向量机(SILS-SVM)方法的基础上,提出了加权特征向量最小二乘支持向量机(WEVLS-SVM)在线结构损伤识别方法。该方法根据训练数据贡献量的大小对数据进行加权,从而更适合于对结构的时变参数进行在线识别,同时较增量式算法有更小的累积误差。以一剪切型结构为例进行了数值模拟,分析结果表明,该方法与非加权的SILS-SVM方法相比,能更好地适应系统参数的变化,从而能很好地识别结构的损伤及其程度。

用LS-SVMs整体构造B样条曲线

由给定的空间数据点集构造B样条曲线是CAGD中一个重要研究课题,常用的逼近方法实质上是基于“经验风险”意义下的最小二乘逼近。文章讨论了基于“结构风险”意义下用最小二乘支持向量回归机整体构造B样条曲线的逼近问题,其出发点是最小化结构风险,而不是传统学习的经验风险最小化,从而在理论上保证了好的推广能力,能够实现对原始曲线的逼近而不仅仅是对测量数据点的逼近。文章建立了B样条曲线拟合的数学模型,并构造了一种特殊的核函数来保证曲线的B样条表示形式。该方法为曲线拟合问题提供了新思路,数值实验证实了可行性。

灰色Verhulst型LS-SVM的构建及参数估计方法

为提高灰色Verhulst模型的预测能力,文章用统计学习理论的观点研究灰色Verhulst模型的建立问题。通过两种方式构造了以背景值序列和原始序列为训练样本的灰色Verhulst型LS-SVM,将一维样本空间里的Verhulst模型转化为一个二维特征空间里的LS-SVM模型,进而将Verhulst模型的灰参数的估计问题转化为一个LS-SVM模型的回归系数估计问题,实现了小样本体系下灰色Verhulst模型的建立和参数估计。实验结果表明该方法是可行且有效的,可有效提高Verhulst模型的推广性,比传统参数估计方法的预测精度更高。

基于DMS和LS-SVM的复合材料结构健康预测方法

复合材料结构损伤机理复杂,其损伤破坏一般呈现缓慢扩展趋势。为了有效地对复合材料结构健康状态进行预测,将距离形态相似度(DMS)和最小二乘支持向量机(LS-SVM)模型引入复合材料结构健康状态预测中,提出了基于DMS和LS-SVM的复合材料结构健康状态预测方法。首先,以复合材料层合板(T300/QY8911)为具体研究对象,对其进行损伤试验,采集其振动加速度作为表征其健康状态的原始信息,并进行小波包分解,利用分解得到的各个频带信号的样本熵作为特征向量;然后,采用距离形态相似度(DMS)方法确定结构健康指数;最后,将结构健康指数作为建模数据用以构建LS-SVM预测模型,预测复合材料结构健康指数。结果表明,该方法可以有效实现复合材料结构裂纹损伤的预测,具有很好的应用前景。

基于LS-SVM的结构可靠度评估

针对大型复杂结构极限状态方程一般难以显式表达的特点,提出了基于最小二乘支持向量机(the leastsquare support vector machine,LS-SVM)的结构可靠度评估方法。该方法采用均匀抽样法抽取随机变量样本,应用确定性有限元求解器进行数值计算。将样本数据进行训练,利用最小二乘支持向量机建立随机变量与结构响应之间的非线性映射关系,模拟结构极限状态方程。通过计算极限状态方程值和偏导数值,求解优化问题,计算结构可靠指标。结果表明,该方法能够评估隐式极限状态方程的结构可靠度,具有较高的计算精度和较好的计算效率。