An exploratory method for qualitative trend curve analysis - a robust method against low quality data
Abstract:This paper proposes an exploratory method for detecting qualitative change in trend curves that is robust against low quality data. First, a measure of qualitative similarity between trend curves is defined. Second, using this measure, a method of qualitative classification of trend curves and a method for detecting qualitative change in trend curves are developed. Last, these methods are applied to the analysis of land cover change in the Persian Gulf Area in 1982-1993, and advantages of these qualitative methods are shown in comparison with ordinary quantitative methods.
Document Type: Research Article
Affiliations: 1: Center for Spatial Information Science, University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan. 2: Department of Urban Engineering, University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan.
Publication date: January 1, 2001