Let PN be the number of logical operations needed for constructing all lconv tables for an N bit image. We denote such a lconv table as LCTABLE( N ) . PN can be calculated on the basis of PNcorresponding to LCTABLE( N 1). The first row in the LCTABLE( N ) requires N more logical operations than Phijust for a given first bit of the N-bit threshold value. There are two cases (either “0” or “1”) f...

This paper presents a new method to determine the susceptances of a reduced transmission network representation by using nonlinear optimization. We use Power Transfer Distribution Factors (PTDFs) to convert the original grid into a reduced version, from which we determine the susceptances. From our case studies we find that considering a reduced injectionindependent evaluated PTDF matrix is the...

An infrared thermography equipment is used to measure the temperature rise at the rear surface of a sample submitted to the pulse irradiation of a flash source, in order to derive simultaneously two thermal properties of the sample. The Levemberg Marquadt technique is used to match the experimental data to the analytical model. Care is taken to tune sample features and the experimental set-up. ...

The selection and evaluation task of attributes is of great importance for knowledge-based systems. It is also a critical factor affecting systems' performance. By using the genetic operator as the searching approach and correlation-based heuristic strategy as the evaluating mechanism, this paper presents a GA-CFS method to select the optimal subset of attributes from a given case library. Base...

A new two-step fuzzy filter that adopts a fuzzy logic approach for the enhancement of images corrupted with impulse noise is presented in this paper. The filtering method (entitled as Fuzzy Random Impulse Noise Reduction method (FRINR)) consists of a fuzzy detection mechanism and a fuzzy filtering method to remove (random-valued) impulse noise from corrupted images. Based on the criteria of pea...

Often recognition systems must be designed with a relatively small amount of training data. Plug-in test statistics suuer from large estimation errors, often causing the performance to degrade with increasing size of the measurement vector. Choosing a better test statistic or applying a method of dimensionality reduction are two possible solutions to the problem above. In this paper we consider...

In this paper, we focused our attention on the creation of an almost unbiased predictive product estimator after estimating and correcting bias classical under approach. Considering mean square error as performance measure, superiority proposed has been analyzed compared to Robson’s [1] (i) a finite population set-up, (ii) infinite set-up assuming bivariate normal distribution between variables...