Crop Disease Dynamic Forecast Integrated with Case-based Reasoning Methodology

摘要

Taking cucumber downy mildew (CDM) as research object, this research explores a technology of crop disease dynamic forecast integrated with case-based reasoning (CBR) methodology. A case indexing mechanism guided by idea of vantage case is developed to speed up the retrieval process and rapidly generate a similar case set for a new case in this CBR system. The range of optimal cluster number for this application is determined through the analysis and comparison between the exhaustive search and the search using proposed indexing mechanism. The precision and recall evaluations are conducted for each testing case using the X fold cross-validation approach, the reasoning effectiveness employing different thresholds of dissimilarity distance (TDD) is figured out and the optimal TDD for this CBR system is determined.