Mobile robot recognition using Bayesian penalization with neural approach

Author

Larbi, Mesbahi ; Aek, Benyettou

Author_Institution

Dept. of Comput. Sci., Univ. of Sci. & Technol. of Oran

fYear

0

fDate

0-0 0

Abstract

We present in this paper a Bayesian classifier, based on neural probabilistic approach using radial basis function (RBF) and based on an improved version of orthogonal least square algorithm (OLS) for fast and incremental learning and automatic creation of hidden neurons. Applied to the famous case like inside a building, this classifier must assure a semantic localization, established on a realistic approach. The will wish to have a discrimination approach in the most possible case by using a generic and powerful representation of knowledge based on conditional and priori probabilities, error costs - case of decision throws etc., this classifier have been generated by neural network. Therefore in place to have a binary decision such as the hard decision like impasse, the mobile robot decides for example 90% of impasse situation

Keywords

Bayes methods; image recognition; knowledge representation; learning (artificial intelligence); least squares approximations; mobile robots; pattern classification; radial basis function networks; robot vision; Bayesian classifier; Bayesian penalization; incremental learning; knowledge representation; mobile robot recognition; neural network; neural probabilistic approach; orthogonal least square algorithm; radial basis function; Bayesian methods; Buildings; Computer science; Costs; Kernel; Laboratories; Least squares methods; Mobile robots; Neural networks; Radial basis function networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence Methods and Applications, 2005 ICSC Congress on

Conference_Location

Istanbul

Print_ISBN

1-4244-0020-1

Type

conf

DOI

10.1109/CIMA.2005.1662322

Filename

1662322