89 Abstract— This paper investigates the performance of a multiresolution technique and statistical features for facial expression recognition using Haar wavelet transform. Multiresolution was conducted up to fifth level of decomposition. Six statistical features namely variance, standard deviation, mean, power, energy and entropy were derived from the approximation coefficients for each level ...

Many fields require computing the trace of the inverse of a large, sparse matrix. Since dense matrix methods are not practical, the typical method used for such computations is the Hutchinson method which is a Monte Carlo (MC) averaging over matrix quadratures. To improve its slow convergence, several variance reductions techniques have been proposed. In this paper, we study the effects of defl...

Using the methodology developed in Alvarez et al. (2014), we decompose variance of unemployment duration Spain into three main components: labour market frictions, dependence and heterogeneity. Crucial to our analysis are comparisons by different demographic groups over business cycle shed light mechanisms behind dependence. We offer a general approach for interpreting administrative data that ...

The bay scallop ( Argopecten irradians ) is one of the most important shellfish species in China. Since their introduction into China, only mass selection has been used breeding. With its gradual expansion and shortage mate selection, population homozygosity increased, fitness decreased. To investigate effects inbreeding provide reference for improving breeding strategies mating management, var...

This paper focuses on a bias variance decomposition analysis of a local learning algorithm, the nearest neighbor classiier, that has been extended with error correcting output codes. This extended algorithm often considerably reduces the 0-1 (i.e., classiication) error in comparison with nearest neighbor (Ricci & Aha, 1997). The analysis presented here reveals that this performance improvement ...

In this paper various ensemble learning methods from machine learning and statistics are considered and applied to the customer choice modeling problem. The application of ensemble learning usually improves the prediction quality of flexible models like decision trees and thus leads to improved predictions. We give experimental results for two real-life marketing datasets using decision trees, ...

in this paper we investigate the effect of oil price shocks on stock market index in iran, by using of a structural var (svar) approach. we used four variables in the model namely kilian index, global oil supply, real oil price and real stock market index. the data are monthly and spanning the period 1997m10-2014m12. we identify the effect of four different shocks on stock market including oil ...