Using Artificial Intelligence Planning to Automate Science Data Analysis for Large Image Databases

This paper describesthe use of AI planning techniques to representscientific, image processing, and software tool knowledge to automateknowledgediscoveryanddatamining (e.g.,sciencedata analysis) of large image databases.In particular, we describetwo fieldedsystems.TheMultimission VICAR Planner (MVP) which hasbeendeployed for 2 yearsandis currentlysupportingscienceproduct generationfor the Galileo mission. MVP has ..^rl..“^A G-n l ^ fll ^A..b.:.. -l.T”“^” ^C,,,..^“h” c-n‘GUULGU lullrj LV 1111 I;Ulillll UilDSGB “I Hxpwrs ll”lll 4 hours to 15 minutes. The Automated SAR Image Processingsystem(ASIP) which is currently in use by the Dept. of Geology at ASU supporting aeolian scienceanalysisof synthetic aperture radarimages. ASIP reducesthenumberof manual inputs in scienceproduct generationby lo-fold.

• Type: Conference
• Year: 1997
• Where: KDD
• Authors: Steve A. Chien, Forest Fisher, Helen Mortensen, Edisanter Lo, Ronald Greeley
• Keywords: AI Planning Techniques, Data Mining, Fieldedsystems.themultimission Vicar Planner, KDD 1997, Large Image Databases.In