Readouts for echo-state networks built using locally regularized orthogonal forward regression

Echo state network (ESN) is viewed as a temporal expansion which naturally give rise to regressors of various relevance to a teacher output. We illustrate that often only a certain amount of the generated echo-regressors effectively explain the teacher output and we propose to determine the importance of the echo-regressors by a joint calculation of the individual variance contributions and Bayesian relevance using the locally regularized orthogonal forward regression (LROFR). This information can be advantageously used in a variety of ways for an analysis of an ESN structure. We present a locally regularized linear readout built using LROFR. The readout may have a smaller dimensionality than the ESN model itself, and improves robustness and accuracy of an ESN. Its main advantage is ability to determine what type of an additional readout is suitable for a task at hand. Comparison with PCA is provided too. We also propose a radial basis function (RBF) readout built using LROFR, since flexibility of the linear readout has limitations and might be insufficient for complex tasks. Its excellent generalization abilities make it a viable alternative to feed-forward neural networks or relevance-vector-machines. For cases where more temporal capacity is required we propose well studied delay&sum readout.     

A novel bagging approach for variable ranking and selection via a mixed importance measure

At present, ensemble learning has exhibited its great power in stabilizing and enhancing the performance of some traditional variable selection methods such as lasso and genetic algorithm. In this paper, a novel bagging ensemble method called BSSW is developed to implement variable ranking and selection in linear regression models. Its main idea is to execute stepwise search algorithm on multiple bootstrap samples. In each trial, a mixed importance measure is assigned to each variable according to the order that it is selected into final model as well as the improvement of model fitting resulted from its inclusion. Based on the importance measure averaged across some bootstrapping trials, all candidate variables are ranked and then decided to be important or not. To extend the scope of application, BSSW is extended to the situation of generalized linear models. Experiments carried out with some simulated and real data indicate that BSSW achieves better performance in most studied cases when compared with several other existing methods.     

Estimation of population mean on the most recent occasion under non response in h-occasion successive sampling using several auxiliary variables

In this article, general estimation procedures of population mean on the most recent occasion in the presence of non response on all occasions have been deduced in h-occasion successive sampling. In the estimation procedures, regression type estimators have been suggested with the aid of stable and mutually independent several auxiliary variables which are readily available only on the most recent occasion. To check the efficiency of the proposed estimators, they have been compared with similar estimator in absence of non response. Properties of the suggested estimation procedures have been studied and their empirical studies are carried out to validate the theoretical results. Suitable recommendations have been made.     

Estimating the population proportion in pair ranked set sampling with application to air quality monitoring

In this paper, we consider the problem of estimating the population proportion in pair ranked set sampling design. An unbiased estimator for the population proportion is proposed, and its theoretical properties are studied. It is shown that the estimator is more (less) efficient than its counterpart in simple random sampling (ranked set sampling). Asymptotic normality of the estimator is also established. Application of the suggested procedure is illustrated using a data set from an environmental study.     

Multivariate modelling of spatial extremes based on copulas

To model extreme spatial events, a general approach is to use the generalized extreme value (GEV) distribution with spatially varying parameters such as spatial GEV models and latent variable models. In the literature, this approach is mostly used to capture spatial dependence for only one type of event. This limits the applications to air pollutants data as different pollutants may chemically interact with each other. A recent advancement in spatial extremes modelling for multiple variables is the multivariate max-stable processes. Similarly to univariate max-stable processes, the multivariate version also assumes standard distributions such as unit-Fréchet as margins. Additional modelling is required for applications such as spatial prediction. In this paper, we extend the marginal methods such as spatial GEV models and latent variable models into a multivariate setting based on copulas so that it is capable of handling both the spatial dependence and the dependence among multiple pollutants. We apply our proposed model to analyse weekly maxima of nitrogen dioxide, sulphur dioxide, respirable suspended particles, fine suspended particles, and ozone collected in Pearl River Delta in China.     

On some new randomized item sum techniques

A recent quantified version of item count technique (ICT), called the item sum technique (IST), was developed by Trappmann et al. (2014 Trappmann, M., I. Krumpal, A. Kirchner, and B. Jann. 2014. Item sum—A new technique for asking quantitative sensitive questions. Journal of Survey Statistics and Methodology 2 (1):58–77. doi:10.1093/jssam/smt019.[Crossref] , [Google Scholar]). In this method, two subsamples are required to obtain reliable data on the sensitive issues. In this article, we propose three alternative item sum techniques by utilizing an additional randomization device. The main advantage associated with the current study is that in order to estimate population sensitive parameters, it requires only one sample to obtain reliable data on quantitative sensitive issue without jeopardizing the privacy of participants. Furthermore, it reduces the cost, effort, and time as compared to usual IST. It is also free from the requirement of finding optimum subsample sizes as in the usual IST. The mean and variance of these proposed estimators are also derived and compared with those of the usual IST. Through algebraic and nnumerical comparsions, it is observed that the proposed techniques perform better than the usual IST. Moreover, the proposed randomized IST 3 is observed to be unconditionally more effeicient than the proposed IST 1 and IST 2.     

An effective estimation strategy for population mean under random non-response situations in two-phase successive sampling

This paper presents a modified exponential type estimation strategy for the current population mean in the presence of random non-response situations in two-occasion successive sampling under two-phase set-up. The properties of the proposed estimators have been examined with the assumption that numbers of sampling units follow a distribution due to random non-response. The performances of the proposed estimators are compared with the estimators designated for the complete response situations. Empirical studies are carried out to show the dominance nature of the proposed estimators over the estimator defined for complete response situations. Appropriate recommendations have been made to the survey practitioners/researchers for their real-life practical applications.     

探地雷达横向等效变波速SAR成像算法研究

探地雷达应用中,由于土壤介质的影响,不同位置目标回波延时常常存在波动,传统的恒定波速成像算法不能修正这种波动,难以使成像性能达到最优。该文提出一种根据目标回波的曲线特征,快速估计横向等效波速,采用变波速F-K偏移进行合成孔径精确成像的新方法。实测数据处理结果显示该方法性能优于恒定波速成像。     

Model selection in regression based on pre-smoothing

In this paper, we investigate the effect of pre-smoothing on model selection. Christóbal et al 6 Christóbal Christóbal, J. A., Faraldo Roca, P. and González Manteiga, W. 1987. A class of linear regression parameter estimators constructed by nonparametric estimation. Ann. Statist.,, 15: 603–609. [Crossref], [Web of Science ®] [Google Scholar] showed the beneficial effect of pre-smoothing on estimating the parameters in a linear regression model. Here, in a regression setting, we show that smoothing the response data prior to model selection by Akaike's information criterion can lead to an improved selection procedure. The bootstrap is used to control the magnitude of the random error structure in the smoothed data. The effect of pre-smoothing on model selection is shown in simulations. The method is illustrated in a variety of settings, including the selection of the best fractional polynomial in a generalized linear model.