Integrating multiple knowledge sources using genetic algorithm applied to hierarchically structured sensor data

The paper presents a new approach for implementing a human expert´s proficient interpretation skills for data and knowledge fusion in signal understanding tasks. The authors start by recognizing the fact that signal interpretation is attributed much to a human expert´s domain-specific, pattern-perceiving capability of grasping raw signals by structured representations having multiple levels of abstraction. First, they attempt to organize such structured representations by using the hierarchical clustering method of data analysis. Then, based on these representations they formulate a human expert´s interpretation skills as an activity of searching for an optimum combination of those perceptual units within that structured representation space being constrained by the situational data. In order to implement this activity, they introduce a genetic algorithm and apply it to the structured representation space assimilating a human analyst´s creative interpreting task of flexibly shifting the focal view of attention from the coarse to the precise. They implement a working system for signal understanding of the remote sensing data of seismic prospecting