论文部分内容阅读
[目的]建立一种改进的基于聚类的模糊决策树,并研究其在玉米种质筛选中的应用。[方法]采用一种新型的基于聚类的决策树算法,该算法针对传统的决策树算法不能处理无类别样本的这一不足,进行了改进。同时,将改进算法应用在玉米品种的筛选问题中,通过对叶面积、株高、干重、钾利用率等指标的衡量,筛选出耐低钾性较强的玉米种子。[结果]该算法在玉米种质的筛选上,适用性强且性能较优。[结论]在今后工作中还需进一步验证比较改进的基于聚类的模糊决策树与传统的模糊聚类决策树的性能,并将其应用在更多的实际问题中。
[Objective] The research aimed to establish an improved fuzzy decision tree based on clustering and to study its application in maize germplasm screening. [Method] A new algorithm based on clustering decision tree was proposed. This algorithm improved the traditional decision tree algorithm which can not deal with the unclassified samples. At the same time, the improved algorithm was applied to the screening of maize varieties, and the maize seeds with low potassium tolerance were screened out by measuring the leaf area, plant height, dry weight and potassium utilization. [Result] The algorithm was suitable for maize germplasm screening and had better applicability and performance. [Conclusion] The performance of the improved clustering-based fuzzy decision tree and the traditional fuzzy clustering decision tree needs to be further verified in future work and applied to more practical problems.