摘要
针对果实品质质量难于客观评定的问题,提出基于加速遗传算法的投影寻踪模型用于解决果实品质质量高低的判定问题,该模型通过优化指标投影方向,将多维数据指标(样本评价指标)转换到低维子空间,并根据投影函数值的大小评价出各样本的优劣,最大限度避免了权重矩阵取值的人为干扰。在2种蔷薇属植物果实品质质量综合评价中的应用结果表明:采用投影寻踪法来确定权重,减小了人为因素的干扰,分析结果更加科学、准确。
In order to assess the fruit quality objectively in practical production, PPC （ Projection Pursuit Classification） model based on RAGA （ Real coding based Accelerating Genetic Algorithm） was applied to the assessment on it. Projection direction was optimized and high-dimension data were converted into low-dimension space with PPC, value of projection indexes could be obtained. Based on these projection function values, the sequence of samples from the big to the small was gained, at the same time, subjective impact on weight matrix farthest could be avoided with PPC model. As the subjective factor was avoided, the evaluation results was scientific and precise.
出处
《西南农业学报》
CSCD
北大核心
2010年第5期1644-1647,共4页
Southwest China Journal of Agricultural Sciences
基金
西藏自治区一般科技计划研究项目"西藏野生果树种质资源及其多样性研究"
