A Feed-Forward Neural Network for Robust Segmentation of Color Images

A novel approach for segmentation of color images is proposed. The approach is based on a feed-forward neural network that learns to recognize the hue range of meaningful objects. Experimental results showed that the proposed method is effective and robust even in presence of changing environmental conditions. The described technique has been tested in the framework of the Robot Soccer World Cup Initiative (RoboCup). The approach is fully general and it may be successfully employed in any intermediate level image-processing task, where the color is a meaningful descriptor.

Reasoning about Goals in BDI Agents: the PRACTIONIST Framework

A BDI agent system for credit risk assessment based on fuzzy logic

Credit risk has always been an important issue for banks and other financial intermediaries. A reliable and consistent computing system is necessary to simplify the decision making process in uncertain domains such as the assessment of credit risk. In recent years fuzzy logic techniques have been in their wide-ranging use in modeling of uncertainties, vagueness, impreciseness and the human thought process. Therefore in this paper we present a fuzzy logic based intelligent system for the assessment of credit risk. It aims at efficiently and intelligently managing the process, handling its complexity, and monitoring large amounts of dynamic information in a distributed way, by using a society…