摘要
蔬菜病虫害的预警通常依靠植保专家知识来进行,较少采用数学建模方法来进行定量分析。为此,利用部分已知类别的训练样本抽取其关联规则作为监督信息,结合非监督学习的K-mean聚类算法,建立蔬菜黄曲条跳甲的预警模型。半监督学习算法既能发挥有监督学习准确率高的优点,又能充分地利用无监督学习的灵活性,具有一定的研究意义和实际意义。通过对广东省蔬菜黄曲条跳甲数据实验表明,半监督学习算法预警准确率比同条件下K-mean聚类算法的准确率高出24.31%。
The forecast of vegetable plant diseases and insect pests commonly bases on experts＇ knowledge of plant protection while math modeling methods are used to analyze the associated data quantitatively scarcely. This paper takes advantage of some classified samples to extract association rules as the supervised information, and combining with the use of the unsupervised learning method K-mean algorithm, the paper establishes the forecast model for vegetable pest flea beetle. Semi-supervised learning method not only obtains a high accuracy of supervised learning method, but also takes advantage of the flexibility of unsupervised learning method, which is meaningful for both research and practice. The experimental results of Guangdong vegetable pest flea beetle show the forecast accuracy of semi-supervised learning method provides a higher accuracy rate of 24.31% than that of K-mean cluster in the same condition.
出处
《农机化研究》
北大核心
2008年第3期150-152,156,共4页
Journal of Agricultural Mechanization Research
基金
国家星火计划项目(2004EA780023)
广东省自然科学基金项目(04300504
980150)
广东省科技计划项目(2005B20701008
2005B101028
2004B20701006)
广州市科技计划项目(2004Z2-E0171)
