摘要
Different from the conventional methods, this paper presents a case-based reasoning (CBR) method for cucumber fusarium wilt (CFW) prevention and treatment, with vantage case-based indexing and retrieval mechanism, sensitivity analysis based reasoning method and Recall evaluation based case retaining strategy. The optimal interval of case dissimilarity distance threshold T is inferred from the experimental results by X fold cross-validation method. The experiments and application show that useful information can be generated for CFW prevention and treatment and the dynamic adjustment for decision-making of cucumber planting can be assisted by the proposed CBR system.