In this book, anew method for hybrid intelligent systems is proposed. The proposed method isbased on a granular computing approach applied in two levels. The techniquesused and combined in the proposed method are modular neural networks (MNNs)with a Granular Computing (GrC) approach, thus resulting in a new concept ofMNNs; modular granular neural networks (MGNNs). In addition fuzzy logic (FL)and hierarchical genetic algorithms (HGAs) are techniques used in this researchwork to improve results. These techniques are chosen because in other workshave demonstrated to be a good option, and in the case of MNNs and HGAs, thesetechniques allow to improve the results obtained than with their conventionalversions; respectively artificial neural networks and genetic algorithms.

In this book, anew method for hybrid intelligent systems is proposed. The proposed method isbased on a granular computing approach applied in two levels. The techniquesused and combined in the proposed method are modular neural networks (MNNs)with a Granular Computing (GrC) approach, thus resulting in a new concept ofMNNs; modular granular neural networks (MGNNs). In addition fuzzy logic (FL)and hierarchical genetic algorithms (HGAs) are techniques used in this researchwork to improve results. These techniques are chosen because in other workshave demonstrated to be a good option, and in the case of MNNs and HGAs, thesetechniques allow to improve the results obtained than with their conventionalversions; respectively artificial neural networks and genetic algorithms.

In this book, anew method for hybrid intelligent systems is proposed. The proposed method isbased on a granular computing approach applied in two levels. The techniquesused and combined in the proposed method are modular neural networks (MNNs)with a Granular Computing (GrC) approach, thus resulting in a new concept ofMNNs; modular granular neural networks (MGNNs). In addition fuzzy logic (FL)and hierarchical genetic algorithms (HGAs) are techniques used in this researchwork to improve results. These techniques are chosen because in other workshave demonstrated to be a good option, and in the case of MNNs and HGAs, thesetechniques allow to improve the results obtained than with their conventionalversions; respectively artificial neural networks and genetic algorithms.