基于改进粒子群算法的SVR参数优化选择的研究基于改进粒子群算法的SVR参数优化选择的研究

支持向量回归机（SVR）模型的拟合精度和泛化能力取决于其相关参数的选取,由于在参数的选择范围内可选择的数量是无穷的,在多个参数中盲目搜索最优参数是需要极大的时间代价,并且很难逼近最优。因此提出了基于改进粒子群算法的SVR参数优化选择方法。仿真结果表明：该改进粒子群算法优化SVR参数方法可行、有效,由此得到的SVR模型具有更好的学习精度和推广能力。     

基于带极值扰动粒子群算法的不确定性需求下最优采购决策

通过分析采用模糊数学方法拟合具有明显时间和季节变化规律的不确定需求比一般随机分布函数具有显著优势的原因,建立了基于模糊数学的最优采购决策模型。基于数理推导和证明,设计了带极值扰动的优化粒子群算法。通过实验证明了改进的优化算法在收敛速度、精度以及摆脱局部极值的能力上有大幅提高,是一种实用而高效的优化算法。     

基于粒子群算法优化最小二乘支持向量机在基坑施工过程中周围环境沉降预测研究

随着城市化进程的加快,越来越多的深基坑的周围环境日趋复杂,近年来预测模型在基坑施工过程中周围环境的沉降预测应用日益广泛,在预测精度方面取得了较为有效的成果,但模型的预测精度取决于参数选择,传统的参数选择往往基于试算法,该方法无确定的参数选择目标且计算体量过大。因此,本文提出一种基于粒子群优化算法来确定LSSVM参数的方法,计算结果表明通过PSO算法选择LSSVM参数,进而提高模型的预测精度和计算速度是切实可行的。     

基于混合DE算法的改进海豚群算法

为了提高海豚群优化算法的优化能力,针对基本海豚群算法搜索阶段易陷入局部最优和早熟收敛的缺陷,将DE入算法,提出了一种改进的海豚群算法。算法通过DE的交叉和变异机制避免局部最优。测试结果表明,改进的算法在收敛速度和寻优精度方面有更好的表现。     

SVM分类器在继发性干燥综合征诊断中的应用

本文为解决SLE患者并发继发性干燥综合征不易诊断及确诊主观性较强等问题,提出了一种可供计算机学习的支持向量机智能算法预测诊断模型。首先对材料中141名患者的26种相关诊断指标进行数据预处理,使之成为能够适合支持向量机计算的量化数据;其次运用交叉验证法、网格搜索法、改进的粒子群优化算法分别对支持向量机模型中的惩罚系数C与核参数g进行优化选择,并利用MATLAB软件分别画出以上3种优化方式得出的支持向量机参数模型;最终对比选出对SLE患者并发继发性干燥综合征疾病诊断预测度最高的预测模型。结果表明,基于改进的粒子群算法优化的支持向量机分类模型参数的自优化,对该疾病预测诊断精度最高。     

一种改进的粒子群优化算法

介绍基本粒子群优化算法的原理、特点,并在此基础上提出了一种改进的粒子群算法。通过在粒子初始化时引入相对基的原理使粒子获得更好的初始解,以及在迭代过程中引入变异模型,部分粒子生成相对应的扩张及收缩粒子,比较其适应度,保留最佳粒子进行后期迭代,使算法易跳出局部最优。通过经典函数的测试结果表明,新算法的全局搜索能力有了显著提高,并且能够有效避免早熟问题。     

基于PSO优化LSSVM在基坑开挖过程中周围建筑物沉降预测研究

本文提出一种用粒子群优化算法来确定LSSVM参数的方法。该方法是在对LSSVM进行分析的基础上,融合PSO的群搜索特征来提高LSSVM预测精度。文章最后采用昆明市某基坑周围建筑物沉降数据对此模型进行了验证,并与其他算法进行了对比分析,计算结果表明用该模型进行沉降预测相比其他算法具有较快的收敛速度和更高的预测精度。     

基于改进PSO算法的物流配送中心选址

首先对物流配送中心选址进行分析,在考虑固定建设费用及运输成本等的基础上建立数学模型。针对模型的特点,采用流行的群智能算法—粒子群优化算法进行求解。在对基本粒子群算法的分析基础上,提出了改进的粒子群算法,克服了基本粒子群算法早熟以及易于陷入局部最优的缺点。利用典型的基准测试函数Shaffer对算法进行验证,最后给出仿真实例,证明了算法的合理性。     

一类VRP问题的改进PSO算法求解

VRP问题是物流领域的热点研究问题。在对一类典型的VRP问题建立了数学模型,提出了一种改进粒子群优化算法以求解该模型。算法针对问题设计了顺序编码方案,并引入了局部搜索以提高算法的局部搜索能力。仿真结果表明了所提离散粒子群优化算法求解此类VRP问题的有效性。     

基于反向学习策略粒子群的物流配送路径优化研究

针对粒子群优化算法后期寻优能力,并易陷入局部最优等不足,提出了一种反向学习粒子群的物流配送路径优化算法(OBLPSO)。首先建立物流配送路径优化的数学模型,然后通过粒子之间的相互协作和信息交流进行求解,并引入反向学习机制提高粒子群寻优能力和收敛速度,最后在Matlab2012平台上对OBLPSO算法性能进行仿真测试。仿真结果表明,相对其它物流配送路径优化算法,OBLPSO算法可以获得时间短、路径合理的物流配送方案,具有一定的实用价值。     

基于支持向量回归的供应链管理绩效评价研究

供应链管理的绩效评价,对于供应链的运作和管理是至关重要的。本文将基于支持向量回归的数据挖掘方法,用于供应链管理的绩效评价研究中。并结合实例,讨论了支持向量回归在供应链管理绩效评价中的应用及其特点。     

Semiparametric Bayesian inference in smooth coefficient models

We describe procedures for Bayesian estimation and testing in cross-sectional, panel data and nonlinear smooth coefficient models. The smooth coefficient model is a generalization of the partially linear or additive model wherein coefficients on linear explanatory variables are treated as unknown functions of an observable covariate. In the approach we describe, points on the regression lines are regarded as unknown parameters and priors are placed on differences between adjacent points to introduce the potential for smoothing the curves. The algorithms we describe are quite simple to implement—for example, estimation, testing and smoothing parameter selection can be carried out analytically in the cross-sectional smooth coefficient model.     

SCAD‐penalized quantile regression for high‐dimensional data analysis and variable selection

The present penalized quantile variable selection methods are only applicable to finite number of predictors or do not have oracle property associated with estimator. This technique is considered as an alternative to ordinary least squares regression in case of the outliers and the heavy‐tailed errors existing in linear models. The variable selection through quantile regression with diverging number of parameters is investigated in this paper. The convergence rate of estimator with smoothly clipped absolute deviation penalty function is also studied. Moreover, the oracle property with proper selection of tuning parameter for quantile regression under certain regularity conditions is also established. In addition, the rank correlation screening method is used to accommodate ultra‐high dimensional data settings. Monte Carlo simulations demonstrate finite performance of the proposed estimator. The results of real data reveal that this approach provides substantially more information as compared with ordinary least squares, conventional quantile regression, and quantile lasso.     

基于小波变换和支持向量的国际原油价格预测

本文将小波分析与支持向量回归结合应用于国际原油价格预测,通过小波多尺度分析方法将油价时间序列分解为长期趋势和随机扰动项,然后采用支持向量回归对分解后的油价长期趋势进行预测。油价长期趋势的预测采用多因素预测方法,主要考虑市场供需基本面、库存、经济、投机等因素对石油价格走势的影响,建立多输入单输出的支持向量回归模型。实证研究表明,支持向量回归模型具有较高的预测性能,对原油价格长期趋势预测中,该方法比回归方法的预测精度高。     

基于Logistic方法的上市公司会计舞弊检测研究

中国新型加转轨经济的特征,监管制度等方面的不完善,决定了根据发达国家相对成熟资本市场上市公司财务数据建立的会计舞弊检测模型的不适用。通过采用会计舞弊检测中应用普遍并具有较高预测正确率的logistic回归方法,在对现有文献中预测效果较好的财务指标进行方差分析基础上,选择具有显著性的变量建立舞弊检测模型。基于SPSS13.0平台,选择2002～2006年间被中国证监会出具处罚公告的舞弊上市公司及其与之匹配的非舞弊公司控制样本数据,完成了确定样本规模、回归模型与回归参数选择等实验。结果发现,样本规模对舞弊检测正确率有显著影响,而参数中分类点的变化对正确率无明显影响,参数选择对混合逐步回归模型具有显著影响。最终通过比较实验获得具有八个指标的最佳拟合数据检测模型,该模型与现有会计舞弊检测模型相比具有较高的判定率。     

Inference on endogenously censored regression models using conditional moment inequalities

Under a quantile restriction, randomly censored regression models can be written in terms of conditional moment inequalities. We study the identified features of these moment inequalities with respect to the regression parameters where we allow for covariate dependent censoring, endogenous censoring and endogenous regressors. These inequalities restrict the parameters to a set. We show regular point identification can be achieved under a set of interpretable sufficient conditions. We then provide a simple way to convert conditional moment inequalities into unconditional ones while preserving the informational content. Our method obviates the need for nonparametric estimation, which would require the selection of smoothing parameters and trimming procedures. Without the point identification conditions, our objective function can be used to do inference on the partially identified parameter. Maintaining the point identification conditions, we propose a quantile minimum distance estimator which converges at the parametric rate to the parameter vector of interest, and has an asymptotically normal distribution. A small scale simulation study and an application using drug relapse data demonstrate satisfactory finite sample performance.     

Optimal rebalance rules for the constant proportion portfolio insurance strategy – Evidence from China

The constant proportion portfolio insurance (CPPI) strategy is one of the most popular asset allocation strategies employed by guaranteed-return financial products investors. Rebalance disciplines play an important role in determining the CPPI performance in practice. This paper examines whether the selection of rebalance rules affects CPPI strategy performance in the context of Chinese equity markets and, if so, in what pattern, and whether an optimal parameter of rebalance exists. We find that, (1) the three alternative rebalance disciplines – time discipline, market move discipline and lag discipline – are indifferent in affecting the performance of CPPI strategy; (2) in terms of optimal parameters of each rebalance rule, the optimal rebalancing period for the time discipline is 3 trading days, the optimal trading threshold of the market move discipline 4%, and the optimal lag factor of the lag discipline 6%. These optimal parameters are not influenced by the length of investment.     

Ridge regression revisited

In general ridge (GR) regression p ridge parameters have to be determined, whereas simple ridge regression requires the determination of only one parameter. In a recent textbook on linear regression, Jürgen Gross argues that this constitutes a major complication. However, as we show in this paper, the determination of these p parameters can fairly easily be done. Furthermore, we introduce a generalization of the GR estimator derived by Hemmerle and by Teekens and de Boer. This estimator, which is more conservative, performs better than the Hoerl and Kennard estimator in terms of a weighted quadratic loss criterion.     

On a bayesian criterion for choosing predictive sub-models in linear regression

Summary We treat the model selection problem in regression as a decision problem in which the decisions are the alternative predictive distributions based on the different sub-models and the parameter space is the set of possible future values of the regressand. The loss function balances out the conflicting needs for a predictive distribution with mean close to the true value ofy but without too great a variation. The treatment is Bayesian and the criterion derived is a Bayesian generalization of Mallows (1973)C _p , the Bivar criterion (Young 1982) and AIC (Akaike 1974). An application using a graphical sensitivity analysis is presented.     

A novel LASSO – TLBO – SVR hybrid model for an efficient portfolio construction

In this study a LASSO – TLBO – SVR hybrid model is used for portfolio construction. Relevant economic parameters are determined and used for stock selection. Along with stock selection, weights for the stocks are obtained by solving a portfolio optimization problem using three methods: GRG Nonlinear, Evolutionary method based on Genetic Algorithm, and Equal weight method. The portfolio return in the proposed model is compared with the return of the Indian market portfolio (NSE and BSE). It is observed that the proposed model outperforms the market portfolio.