Optimisation of multisource data analysis: an example using evidential reasoning for GIS data classification

• Authors: Derek R. Peddle;David T. Ferguson
• Venue: Computers & Geosciences - Intelligent methods for processing geodata
• Year: 2002

The classification of integrated data from multiple sources represents a powerful and synergistic approach to deriving important geoscience information from diverse data sets. These data often reside on Geographical Information Systems (GIS) and encompass a variety of sources and properties such as thematic data, remote sensing imagery, topographic data, or environmental map information in raster or vector formats in point, line or polygon representations. Multisource data classification algorithms often require the specification of user-defined parameters to guide data processing, however, these inputs can be numerous or difficult to determine, resulting in less than optimal results. This paper presents three methods for optimising the specification of user-defined inputs based on different levels of empirical testing and computational efficiency: (i) Exhaustive search by recursion, (ii) isolated independent search, and (iii) sequential dependent search. These methods have been implemented in an optimisation software program which is suitable for use with any data classification or analysis algorithm for which user specified inputs are required. In an example application of classifying sub-Arctic mountain permafrost in the Yukon Territory of northern Canada, these optimisation methods were compared in terms of classification accuracy, memory resources and run-time performance using a multisource evidential reasoning classifier, which has been shown to provide improved classification of multisource data compared to neural network, linear discriminant analysis, and maximum likelihood approaches. Using the optimisation software, higher evidential reasoning classification accuracies were achieved without excessive additional computing time. A two-stage approach was recommended for general use to ensure maximum efficiency. It was concluded that these methods are applicable to a wide variety of classification and data analysis algorithms and represent a useful approach to optimising user inputs which otherwise may be difficult or impractical to derive.