未来社区智慧泊车的少样本计数模型研究

在未来社区中如何更加人性化、智慧化地为居民提供泊车引导服务是未来社区建设的基础之一。本文提供了一种基于目标计数的模型来准确实时地检测空缺车位,为该服务提供技术支持,该模型采用基于卷积神经网络的密度图估计方法对车辆以及空车位进行计数,除为居民提供泊车引导外,还能够为社区管理提供汽车出入流量控制数据依据以及为宏观统筹端提供各社区数据以实现多社区车位共享;并对现有目标计数方法进行数据增强,试验结果表明模型在数据增强后MAE提升15.7%,RMSE提升25.81%。同时,该模型有较好的可扩展性,可以应用在其他领域。

基于图像处理技术的浮游生物自动分类研究

目前利用图象处理和模式识别技术进行浮游生物的自动分类与计数是一个研究热点,该文根据浮游蚤类图像的特点,设计了一种自动分类计数算法。该算法首先通过有效的分割手段将蚤类个体从背景区域中提取出来;然后计算与其生物学特征相关的形状和纹理特征参量;最后选择特征参量输入神经网络分类器对不同蚤类进行分类和计数。样本主要采集自胶州湾海域,图像通过zeiss显微图像采集系统获取。实验证明,由于研究目标明确,算法简单有效,取得了很好的分类计数效果,很大程度上减轻了人工分类计数的工作量。

A Statistical Power Comparison of the Kolmogorov-Smirnov Two-Sample Test and the Wald Wolfowitz Test in Terms of Fixed Skewness and Fixed Kurtosis in Large Sample Sizes

In this study, the statistical powers of Kolmogorov-Smimov two-sample （KS-2） and Wald Wolfowitz （WW） tests, non-parametric tests used in testing data from two independent samples, have been compared in terms of fixed skewness and fixed kurtosis by means of Monte Carlo simulation. This comparison has been made when the ratio of variance is two as well as with equal and different sample sizes for large sample volumes. The sample used in the study is： （25, 25）, （25, 50）, （25, 75）, （25, 100）, （50, 25）, （50, 50）, （50, 75）, （50, 100）, （75, 25）, （75, 50）, （75, 75）, （75, 100）, （100, 25）, （100, 50）, （100, 75）, and （100, 100）. According to the results of the study, it has been observed that the statistical power of both tests decreases when the coefficient of kurtosis is held fixed and the coefficient of skewness is reduced while it increases when the coefficient of skewness is held fixed and the coefficient of kurtosis is reduced. When the ratio of skewness is reduced in the case of fixed kurtosis, the WW test is stronger in sample volumes （25, 25）, （25, 50）, （25, 75）, （25, 100）, （50, 75）, and （50, 100） while KS-2 test is stronger in other sample volumes. When the ratio of kurtosis is reduced in the case of fixed skewness, the statistical power of WW test is stronger in volume samples （25, 25）, （25, 75）, （25, 100）, and （75, 25） while KS-2 test is stronger in other sample volumes.

Strong Consistency for the Kernal Estimates of the Random Window Width of the Density Function and its Derivatives Under Φ-Mixing Samples

In the paper,we study the strong uniform consistency for the kernal estimates of random window w■th of density function and its derivatives under the condition that the sequence{X_n}of the ■ are the identically Φ-mixing random variabks.

Theorem of Logarithm Expectation and Its Application to Prove Sample Correlation Coefficient as Unbiased Estimate

In statistical theory, a statistic that is function of sample observations is used to estimate distribution parameter. This statistic is called unbiased estimate if its expectation is equal to theoretical parameter. Proving whether or not a statistic is unbiased estimate is very important but this proof may require a lot of efforts when statistic is complicated function. Therefore, this research facilitates this proof by proposing a theorem which states that the expectation of variable x 〉 0 is u if and only if the limit of logarithm expectation of x approaches logarithm of u. In order to make clear of this theorem, the research gives an example of proving correlation coefficient as unbiased estimate by taking advantages of this theorem.

Stratified Double Quartile Ranked Set Samples

The procedure of stratified double quartile ranked set sampling （SDQRSS） method is introduced to estimate the population mean. The SDQRSS is compared with the simple random sampling （SRS）, stratified ranked set sampling （SRSS） and stratified simple random sampling （SSRS）. It is shown that SDQRSS estimator is an unbiased of the population mean and more efficient than SRS, SRSS and SSRS for symmetric and asymmetric distributions. In addition, by SDQRSS we can increase the efficiency of mean estimator for specific value of the sample size.

Corporate Tax Differences under the New Accounting Standards

The tax differences is the enterprise according to the provisions of accounting standards to calculate the total profit and tax calculated according to the enterprise income tax＇s tax base taxable income differences. Enterprise accounting standards and tax for the same subject for different purposes, leading to both the principle is different, as well as for the same matter measurement and confirmation of different, resulting in tax differences. In this paper, from the aspect of theory to the study of tax differences, from tax differences that the tax law and accounting purposes different proceed with, on the basis of theoretical analysis, design a regression model from empirical research on tax differences. According to the 2009,2010 and201 lthree annual sample data regression results, discussed in the new＂ accounting standards for business enterprises＂ of corporate tax difference change tendency, and according to the tax law and accounting standards caused by the different effects of tax differences for the main project correlation analysis, so as to verify the theoretical expectations.

Combinatorial and Statistical Applications of Generalized Stirling Numbers

Here illustrated are certain combinatorial and statistical applications of the generalized Stirling numbers with integer parameters.

Convergence Rates of Wavelet Estimators in Semiparametric Regression Models Under NA Samples

Consider the following heteroscedastic semiparametric regression model：where {Xi, 1 〈 i 〈 n} are random design points, errors {ei, 1 〈 i 〈 n} are negatively associated （NA） random variables, （r2 = h（ui）, and {ui} and {ti} are two nonrandom sequences on [0, 1]. Some wavelet estimators of the parametric component β, the non- parametric component g（t） and the variance function h（u） are given. Under some general conditions, the strong convergence rate of these wavelet estimators is O（n- 1 log n）. Hence our results are extensions of those re, sults on independent random error settings.

Robust estimation for partially linear models with large-dimensional covariates

We are concerned with robust estimation procedures to estimate the parameters in partially linear models with large-dimensional covariates. To enhance the interpretability, we suggest implementing a noncon- cave regularization method in the robust estimation procedure to select important covariates from the linear component. We establish the consistency for both the linear and the nonlinear components when the covariate dimension diverges at the rate of o（√n）, where n is the sample size. We show that the robust estimate of linear component performs asymptotically as well as its oracle counterpart which assumes the baseline function and the unimportant covariates were known a priori. With a consistent estimator of the linear component, we estimate the nonparametric component by a robust local linear regression. It is proved that the robust estimate of nonlinear component performs asymptotically as well as if the linear component were known in advance. Comprehensive simulation studies are carried out and an application is presented to examine the finite-sample performance of the proposed procedures.

AN INTERVAL METHOD FOR STUDYING THE RELATIONSHIP BETWEEN THE AUSTRALIAN DOLLAR EXCHANGE RATE AND THE GOLD PRICE

This paper proposes an interval method to explore the relationship between the exchange rate of Australian dollar against US dollar and the gold price, using weekly, monthly and quarterly data. With the interval method, interval sample data are formed to present the volatility of variables. The ILS approach is extended to multi-model estimation and the computational schemes are provided. The empirical evidence suggests that the ILS estimates well characterize how the exchange rate relates to the gold price, both in the long-run and short-run. The comparison between the interval and point methods indicates that the difference between the OLS and the ILS estimates is increasing from weekly data to quarterly data, since the lowest frequency point data lost the most information of volatility.

Effective condition numbers and small sample statistical condition estimation for the generalized Sylvester equation

Abstract In this paper, we investigate the effective condition numbers for the generalized Sylvester equation （AX - YB, DX - YE） = （C,F）, where A,D ∈ Rm×m B,E ∈ Rn×n and C,F ∈ Rm×n. We apply the small sample statistical method for the fast condition estimation of the generalized Sylvester equation, which requires （9（m2n ＋ mn2） flops, comparing with （-O（m3 ＋ n3） flops for the generalized Schur and generalized Hessenberg- Schur methods for solving the generalized Sylvester equation. Numerical examples illustrate the sharpness of our perturbation bounds.

THE LARGE SAMPLE PROPERTIES OF THE SOLUTIONS OF GENERAL ESTIMATING EQUATIONS

This paper develops the large sample properties of the solutions of the general estimating equations which are unbiased or asymptotically unbiased or with nuisance parameters for correlated data.The authors do not make the assumption that the estimating equations come from some objective function when we establish the large sample properties of the solutions.So these results extend the work of Newey and McFadden(1994) and are more widely applicable.Furthermore,we provide some examples to justify the importance of our work.

Revised regional importance measures in the presence of epistemic and aleatory uncertainties

Two revised regional importance measures(RIMs),that is,revised contribution to variance of sample mean(RCVSM)and revised contribution to variance of sample variance(RCVSV),are defined herein by using the revised means of sample mean and sample variance,which vary with the reduced range of the epistemic parameter.The RCVSM and RCVSV can be computed by the same set of samples,thus no extra computational cost is introduced with respect to the computations of CVSM and CVSV.From the plots of RCVSM and RCVSV,accurate quantitative information on variance reductions of sample mean and sample variance can be read because of reduced upper bound of the range of the epistemic parameter.For general form of quadratic polynomial output,the analytical solutions of the original and the revised RIMs are given.Numerical example is employed and results demonstrate that the analytical results are consistent and accurate.An engineering example is applied to testify the validity and rationality of the revised RIMs,which can give instructions to the engineers about how to reduce variance of sample mean and sample variance by reducing the range of epistemic parameters.

NONPARAMETRIC REGRESSION UNDER DOUBLE-SAMPLING DESIGNS

This paper studies nonparametric estimation of the regression function with surrogate outcome data under double-sampling designs, where a proxy response is observed for the full sample and the true response is observed on a validation set. A new estimation approach is proposed for estimating the regression function. The authors first estimate the regression function with a kernel smoother based on the validation subsample, and then improve the estimation by utilizing the information on the incomplete observations from the non-validation subsample and the surrogate of response from the full sample. Asymptotic normality of the proposed estimator is derived. The effectiveness of the proposed method is demonstrated via simulations.

Some uniform convergence results for kernel estimators

This paper derives some uniform convergence rates for kernel regression of some index functions that may depend on infinite dimensional parameter. The rates of convergence are computed for independent, strongly mixing and weakly dependent data respectively. These results extend the existing literature and are useful for the derivation of large sample properties of the estimators in some semiparametric and nonparametric models.