摘要
采用广义回归神经网络分别对烤烟的主要化学成分与香气质、香气量、杂气、刺激、余味、劲头和烟气浓度等感官质量进行建模。结果表明,在训练集样本数据较少时,广义回归神经网络的预测准确度仍然很高。
The correlation model between main chemical compositions and sensory qualities of flue-cured tobaccos was constructed by generalized regression neural network(GRNN). The results showed that the prediction accuracy is satisfied,even though there are a few data in training sets.
出处
《安徽农业大学学报》
CAS
CSCD
北大核心
2005年第3期406-410,共5页
Journal of Anhui Agricultural University
基金
河南省教委自然科学基金项目(9815007)资助。
关键词
广义回归神经网络
化学成分
感官质量
烤烟
<Keyword>GRNN
main chemical composition
sensory quality
flue-cured tobacco
