Cooperating agents for 3-D scientific data interpretation

摘要

Many organizations collect vast quantities of 3D scientific datanin volumetric form for a range of purposes, including resourcenexploration, market forecasting and process modeling. Traditionally,nthese data have been interpreted by human experts with only minimalnsoftware assistance. However, such manual interpretation is anpainstakingly slow and tedious process. Moreover, since interpretationninvolves subjective judgments and each interpreter has differentnscientific knowledge and experience, the formulation of an effectiveninterpretation often requires the cooperation of numerous such experts.nHence there is a pressing need for a software system in which individualninterpretations can be generated automatically and then refined throughnthe use of cooperative reasoning and information sharing. To this end, anprototype system, SurfaceMapper, has been developed in which a communitynof cooperating software agents automatically locate and displayninterpretations in a volume of 3D scientific data. The challenges andnexperiences in designing and building such a system are discussed.nParticular emphasis is given to the agents' interactions and annempirical evaluation of the effectiveness of different cooperationnstrategies is presented