Kernel principal component analysis and support vector machines for stock price prediction

Technical indicators are used with two heuristic models, kernel principal component analysis and factor analysis in order to identify the most influential inputs for a forecasting model. Multilayer perceptron (MLP) networks and support vector regression (SVR) are used with different inputs. We assume that the future value of a stock price/return depends on the financial indicators although there is no parametric model to explain this relationship, which comes from the technical analysis. Comparison studies show that SVR and MLP networks require different inputs. Furthermore, proposed heuristic models produce better results than the studied data mining methods. In addition to this, we can say that there is no difference between MLP networks and SVR techniques when we compare their mean square error values.     

A particle swarm‐optimized support vector machine for reliability prediction

System reliability depends on inherent mechanical and structural aging factors as well as on operational and environmental conditions, which could enhance (or smoothen) such factors. In practice, the involved dependences may burden the modeling of the reliability behavior over time, in which traditional stochastic modeling approaches may likely fail. Empirical prediction methods, such as support vector machines (SVMs), become a valid alternative whenever reliable time series data are available. However, the prediction performance of SVMs depends on the setting of a number of parameters that influence the effectiveness of the training stage during which the SVMs are constructed based on the available data set. The problem of choosing the most suitable values for the SVM parameters can be framed in terms of an optimization problem aimed at minimizing a prediction error. In this work, this problem is solved by particle swarm optimization (PSO), a probabilistic approach based on an analogy with the collective motion of biological organisms. SVM in liaison with PSO is then applied to tackle reliability prediction problems based on time series data of engineered components. Comparisons of the obtained results with those given by other time series techniques indicate that the PSO + SVM model is able to provide reliability predictions with comparable or great accuracy. Copyright © 2011 John Wiley & Sons, Ltd.     

基于支持向量机的非概率可靠性分析

针对具有隐式极限状态函数的不确定性结构的非概率可靠性分析,提出一种基于支持向量机回归的不确定性结构非概率可靠性分析方法,并给出了该方法的分析流程.抽取数据样本,优化支持向量机回归参数,使用训练后的支持向量机替代隐式极限状态函数.利用非概率集合理论中的区间分析法,引入尺寸比例因子,构造合适的不确定性结构非概率可靠性指标迭...     

Forecasting systems reliability based on support vector regression with genetic algorithms

This study applies a novel neural-network technique, support vector regression (SVR), to forecast reliability in engine systems. The aim of this study is to examine the feasibility of SVR in systems reliability prediction by comparing it with the existing neural-network approaches and the autoregressive integrated moving average (ARIMA) model. To build an effective SVR model, SVR's parameters must be set carefully. This study proposes a novel approach, known as GA-SVR, which searches for SVR's optimal parameters using real-value genetic algorithms, and then adopts the optimal parameters to construct the SVR models. A real reliability data for 40 suits of turbochargers were employed as the data set. The experimental results demonstrate that SVR outperforms the existing neural-network approaches and the traditional ARIMA models based on the normalized root mean square error and mean absolute percentage error.     

Multi-objective optimization based on meta-modeling by using support vector regression

Practical engineering design problems have a black-box objective function whose forms are not explicitly known in terms of design variables. In those problems, it is very important to make the number of function evaluations as few as possible in finding an optimal solution. So, in this paper, we propose a multi-objective optimization method based on meta-modeling predicting a form of each objective function by using support vector regression. In addition, we discuss a way how to select additional experimental data for sequentially revising a form of objective function. Finally, we illustrate the effectiveness of the proposed method through some numerical examples.     

A two-stage procedure for forecasting freight inspections at Border Inspection Posts using SOMs and support vector regression

The number of goods which passes through a border inspection post (BIP) may cause important congestion problems and delays in the port system, having an effect in the level of service of the port. Therefore, a prediction of the daily number of goods subject to inspection in BIPs seems to be a potential solution. This study proposes a two-stage procedure to better predict freight inspections. In the first stage, a Kohonen self-organising map (SOM) is employed to decompose the whole data into smaller regions which display similar statistical characteristics. In the second stage, support vector regression (SVR) is used to forecast the different homogeneous regions individually. The results obtained are compared with the single SVR technique. The experiment shows that SOM–SVR models outperform the single SVR models in the inspection forecasting. The application of the proposed technique may become a supporting tool for the prediction of the number of goods subject to inspection in BIPs of other international seaports or airports, and provides relevant information for decision-making and resource planning.     

Modeling thermal conductivity enhancement of metal and metallic oxide nanofluids using support vector regression

Enhancing thermal conductivity of nanofluids is an important objective in heat transfer applications. Experimental measurement of thermal conductivity is time consuming, laborious and expensive. One of the common ways to address these limitations involves developing theoretical models to study thermo-physical properties of nanofluid. However, most classical and empirical models fail in predicting experimental results with good precision. In this study, we developed support vector regression (SVR) models that are capable of predicting the thermal conductivity enhancement for metallic and metallic-oxide nanofluids. The accuracy and reliability of the developed models were assessed using statistical parameters such as correlation coefficient (R²), root mean square error (RMSE) and mean absolute error (MAE). The models were characterized with very high correlation coefficients of 99.3 and 96.3% for the metallic and metallic oxide nanofluids, respectively. While the RMSE obtained were 1.11 and 1.33 for the metallic and metallic oxide nanofluids, respectively. In addition, the results of the models were compared with Hamilton-Crosser (HC) model and other empirical models. The SVR models performed much better than all the models examined. Furthermore, the effects of temperature, volume fractions, nanoparticle size and type, and basefluids types were correlated with experimental data in order to assess the performance of the developed models. The results indicate that SVR predictions were accurate and better than common theoretical models.     

Modelling and analysis of waviness reduction in soft-pad grinding of wire-sawn silicon wafers by support vector regression

The manufacturing of silicon wafers forms the most important step in the construction of integrated circuit (IC) chips. One of the difficulties in this manufacture process is the removal of the waviness from the resulting wafers. In this paper, mathematical modelling and analysis of this removal process is carried out by the use of the support vector regression (SVR) algorithm. The results show that SVR is ideally suited for the modelling of this complicated process. Furthermore, by the use of the learning ability of SVR, the model can be continuously improved as more data become available. Based on the resulting model, the influences of the various factors on the rate of removal and the ease of control of the removal process are also discussed.     

Performance enhancement of respiratory tumor motion prediction using adaptive support vector regression: Comparison with adaptive neural network method

The breathing motion moves internal organs and targeted regions determined by radiation therapy planning. For the radiation therapy, accurate prediction for breathing motion is of great interest as the outer targeted region treatment could endanger sensitive tissue. In this study, the use of a prediction algorithm with adaptive support vector regression (aSVR) was proposed and compared with the adaptive neural network (ANN) algorithm considering the prediction accuracy and training and predicting time. Respiration data from 87 patients treated by radiation therapy, were acquired with an optical marker at 30 Hz. Five types of prediction filters with the ANN or aSVR filters, were implemented and their performance was compared according to the size of the sliding window (2.5 and 5.0 sec), and the prediction latencies (100, 200, 300, 400, and 500 msec). Training and testing of the prediction algorithms with aSVR and ANN were performed. The root mean square error (RMSE) was used as the accuracy metric. The aSVR with an RBF kernel outperformed other prediction filters, including not only various types of ANN filters but also the aSVR with a linear kernel. A sliding window of 2.5 sec significantly and independently enhanced the overall accuracy. Otherwise, the training and prediction testing times were significantly prolonged in case of aSVR with an RBF kernel. The aSVR filter with the RBF kernel is in all cases superior to other filters regarding its accuracy; it also shows clinically applicable results from the viewpoint of training and predicting time, which may be effective for predicting patient breathing motion and thus enhancing the efficacy of radiation therapy.     

最小二乘支持向量机和小波电铲供电机组状态预测

针对电铲供电机组振动时间序列是个非线性、非平稳的复杂时间序列,难以用单一预测方法进行有效预测的问题,建立了一种基于小波分解和最小二乘支持向量机混合模型进行状态预测的方法.首先通过小波分解,将原始振动时间序列分解到不同层次,然后根据分解后各层次分量的特点选择不同的嵌入维数和LS-SVM参数分别进行预测,最后重构得到原始序列的预测值.对某电铲供电机组振动趋势的预测结果表明,该模型的预测性能好于单一的支持向量机预测方法.     

Optimization of extended-release hydrophilic matrix tablets by support vector regression

Background: In this work, support vector regression (SVR) was applied to the optimization of extended release from swellable hydrophilic pentoxifylline matrix-tablets and compared to multiple linear regression (MLR). Methods: Binary mixtures comprising ethylcellulose and sodium alginate were used as the matrix-former. The matrix-former : drug weight ratio and the percentage of sodium alginate in the matrix-former were the formulation factors (independent variables) and the percentages of drug release at four different time intervals were the responses (dependent variables). Release was determined according to United States Pharmacopeia 31 for 11 pentoxifylline matrix-tablet formulations of different independent variable levels and the corresponding results were used as tutorial data for the construction of an optimized SVR model. Six additional checkpoint matrix-tablet formulations, within the experimental domain, were used to validate the external predictability of SVR and MLR models. Results: It was found that the constructed SVR model fitted better to the release data than the MLR model (higher coefficients of determination, R^?2, lower prediction error sum of squares, narrower range of residuals, and lower mean relative error), outlining its advantages in handling complex nonlinear problems. Superimposed contour plots derived by using the SVR model and describing the effects of polymer and sodium alginate content on pentoxifylline release showed that formulation of optimal release profiles, according to United States Pharmacopeia limitations, could be located at drug : matrix ratio of 1 and sodium alginate content 25% w/w in the matrix-former. Conclusion: The results indicate the high potential for SVR in formulation development and Quality by Design.     

Quantitative analysis of carbon content in fly ash using LIBS based on support vector regression

Laser-induced breakdown spectroscopy (LIBS) has been proved as an on-line detection technology to measure the carbon content in fly ash, which is beneficial for immediate assessment of the boiler combustion efficiency. Support vector regression (SVR) was adopted as the quantitative model for the carbon content measurement in fly ash in this study. Ash species was one of the key factors affecting quantitative accuracy. Experiments have proven that, the index of plasma temperature and the electron density among different species could be similar, while the partition function ratios and the temperature correction factor showed obvious differences among different ash species. Based on the partition function ratios, the Matrix Effect Correction Factor (MECF) was defined. SVR model was optimized by MECF and the analysis results showed that the correlation coefficient of calibration (R²) increased from 0.989 to 0.991, the root-mean-square error of calibration (RMSEC) decreased from 2.02% to 0.850%, the root-mean-square error of prediction (RMSEP) decreased from 2.13% to 1.07%, and averaged relative standard deviation (ARSD) decreased from 8.62% to 1.89%. The results showed that SVR combined with MECF was an effective method to improve the accuracy of LIBS quantitative analysis of the carbon content in fly ash.     

基于互信息与支持向量回归的盾构掘进载荷预测方法研究

掘进载荷是盾构施工中的重要控制量,直接关系着施工安全与效率。通过对掘进载荷影响因素的分析,建立了一种基于工程实测数据分析的掘进载荷特征选择及预测方法。首先,对工程实测数据进行极值归一化预处理,以降低不同参数间量纲和量级的差异产生的支配性影响;其次,通过参数分析和基于互信息的特征选择选取主要的影响参数作为输入;最后,通过支持向量回归（support vector regression,SVR）建立掘进载荷的预测模型,并结合天津地铁9号线盾构施工工程案例检验其预测表现。结果表明,所建立的掘进载荷预测方法能够在工程实测数据包含的众多影响参数中筛选出少量关键特征,实现对掘进载荷的合理预测。研究结果可以为盾构掘进参数的调控提供参考,也为具有众多参数的工程实测数据的分析提供一种思路。     

基于支持向量回归外推的统计最优近场声全息研究

通过数值仿真方法,研究统计最优近场声全息中全息面孔径大小对重建精度影响。结果表明当全息面孔径大于重建面孔径2个采样间隔便能获得较高的重建精度,再继续增大全息面孔径也可以提高重建精度,但是趋势变缓。在此基础上,进一步提出了一种利用支持向量回归对全息面孔径进行外推的方法,在不增加测量孔径的前提下,可以通过数据外推增大全息面孔径,提高重建精度。对方形简支钢板辐射声场的仿真结果,验证了方法的有效性。     

基于核主成分分析及支持向量机的水轮机叶片裂纹源定位

结合核主成分分析(KPCA)以及支持向量机对水轮机转轮叶片裂纹源的声发射信号进行定位。结果表明,利用核主成分分析提取的特征参数进行定位的精度高于原始参数的定位精度,即输入9个特征参数时,支持向量机在叶片区域的识别率为100%,在裂纹源对焊缝距离的支持向量回归分析中的最大误差为20cm。因而结合KPCA和支持向量机对复杂的大尺寸结构进行定位是一种较好的方法,既减少了输入信号的维数,又提高了定位精度。     

Relative contributions of aleatory and epistemic uncertainty sources in time series prediction

This paper develops a novel computational framework to compute the Sobol indices that quantify the relative contributions of various uncertainty sources towards the system response prediction uncertainty. In the presence of both aleatory and epistemic uncertainty, two challenges are addressed in this paper for the model-based computation of the Sobol indices: due to data uncertainty, input distributions are not precisely known; and due to model uncertainty, the model output is uncertain even for a fixed realization of the input. An auxiliary variable method based on the probability integral transform is introduced to distinguish and represent each uncertainty source explicitly, whether aleatory or epistemic. The auxiliary variables facilitate building a deterministic relationship between the uncertainty sources and the output, which is needed in the Sobol indices computation. The proposed framework is developed for two types of model inputs: random variable input and time series input. A Bayesian autoregressive moving average (ARMA) approach is chosen to model the time series input due to its capability to represent both natural variability and epistemic uncertainty due to limited data. A novel controlled-seed computational technique based on pseudo-random number generation is proposed to efficiently represent the natural variability in the time series input. This controlled-seed method significantly accelerates the Sobol indices computation under time series input, and makes it computationally affordable.     

Influence of the number and location of design parameters in the aerodynamic shape optimization of a transonic aerofoil and a wing through evolutionary algorithms and support vector machines

Surrogate-based optimization (SBO) has recently found widespread use in aerodynamic shape design owing to its promising potential to speed up the whole process by the use of a low-cost objective function evaluation, to reduce the required number of expensive computational fluid dynamics simulations. However, the application of these SBO methods for industrial configurations still faces several challenges. The most crucial challenge nowadays is the ‘curse of dimensionality’, the ability of surrogates to handle a high number of design parameters. This article presents an application study on how the number and location of design variables may affect the surrogate-based design process and aims to draw conclusions on their ability to provide optimal shapes in an efficient manner. To do so, an optimization framework based on the combined use of a surrogate modelling technique (support vector machines for regression), an evolutionary algorithm and a volumetric non-uniform rational B-splines parameterization are applied to the shape optimization of a two-dimensional aerofoil (RAE 2822) and a three-dimensional wing (DPW) in transonic flow conditions.     

A support vector machine integrated system for the classification of operation anomalies in nuclear components and systems

A support vector machine (SVM) approach to the classification of transients in nuclear power plants is presented. SVM is a machine-learning algorithm that has been successfully used in pattern recognition for cluster analysis. In the present work, single- and multiclass SVM are combined into a hierarchical structure for distinguishing among transients in nuclear systems on the basis of measured data. An example of application of the approach is presented with respect to the classification of anomalies and malfunctions occurring in the feedwater system of a boiling water reactor. The data used in the example are provided by the HAMBO simulator of the Halden Reactor Project.