FUSING MULTIPLE DATA AND KNOWLEDGE SOURCES FOR SIGNAL UNDERSTANDING BY GENETIC ALGORITHM

This paper presents a new approach to partially automating a human exp ert's proficient interpretation skills For data and knowledge fusion i n signal-understanding tasks. We start by recognizing the fact that si gnal interpretation is;attributed much to a human expert's domain-spec ific, pattern perceiving capability of grasping raw signals by structu red representations having multiple levels of abstraction, rather than to some objectively defined knowledge, In other words, that is an eme rgent or self-organizing process, where information is regarded as per ceptual as opposed to objectively defined, First, we attempt to organi ze such structured representations by usage of a hierarchical clusteri ng method of data analysis, Then, based on these representations we mo del a human expert's interpretation skill as an activity of searching for an optimum combination of those perceptual units within that struc tured representation space being constrained by the data, In order to implement this activity, we introduce a genetic algorithm and apply it to the structured representation space assimilating a human analyst's creative interpreting task in flexibly shifting the focal view of att ention from the coarse to the precise. We implement a working system f or signal understanding of the remote sensing data of seismic prospect ing and show the results output by the system.