ABSTRACT
Utilizing of soft computing methods besides hard computing methods, such support vector machine and neural network, in the reverse procedures have been experienced, successfully. This chapter describes application of information granulation theory, on the back analysis of ‘‘Jeffrey mine-southeast wall-Quebec’’. In this manner, using a combining of Self Organizing Map (SOM) and Rough Set Theory, crisp and rough granules are obtained. SOM has been successfully employed in different fields of applied science. Specially, in geomechanics, for example, in clustering of lugeon data. Applying of SOM as a preprocessing step and discretization tool is second process. The role of uncertainty and vague information in geomechnaic analysis is undeniable feature. Indeed, with developing of new approaches in information theory and computational intelligence, as well as soft computing approaches, it is necessary to consider these approaches within and inside of current and conventional analysis, especially in geomechanic field.
