| 基于概率神经网络的烤烟烟叶质量的相关性分析 |
| |
| 引用本文： | 陈津.基于概率神经网络的烤烟烟叶质量的相关性分析[J].北京轻工业学院学报,2010(6):66-70. |
| |
| 作者姓名： | 陈津 |
| |
| 作者单位： | 北京工商大学计算机与信息工程学院,北京100048 |
| |
| 摘 要： | 根据烟叶样本的近红外光谱定量分析得出3种烟叶成分：烟碱、还原糖和蛋白质的含量,加入8种烟叶外观特征,然后使用因子分析方法对概率神经网络输入进行压缩和特征提取,在简化样本的同时对概率神经网络进行优化.应用概率神经网络根据外观质量因素对降维后的烟叶样本建立内在质量的数学预测模型并获得较理想的预测效果.
|
| 关 键 词： | 烤烟烟叶 近红外光谱 因子分析 概率神经网络 |
ANALYSIS OF CORRELATION BETWEEN INNER QUALITY AND APPEARANCE CHARACTERISTIC OF FLUE-CURED TOBACCO LEAF BY PROBABILISTIC NEURAL NETWORK |
| |
| CHEN Jin.ANALYSIS OF CORRELATION BETWEEN INNER QUALITY AND APPEARANCE CHARACTERISTIC OF FLUE-CURED TOBACCO LEAF BY PROBABILISTIC NEURAL NETWORK[J].Journal of Beijing Institute of Light Industry,2010(6):66-70. |
| |
| Authors: | CHEN Jin |
| |
| Affiliation: | CHEN Jin(College of Computer Science and Information Engineering,Beijing Technology and Business University,Beijing 100048,China) |
| |
| Abstract: | The content of nicotine,reducing sugar and protein of the tobacco was determined based on the near-infrared spectrum of tobacco samples.Principal component analysis method was used to compress data and extract figures when combining with eight appearance characteristics of tobacco.The dimension of sample was simplified and the input of probabilistic neural network was optimized.Then the correlation between inner qualities and appearance characteristics of tobacco was analyzed by the probabilistic neural network.The results indicated that the inner quality could be predicted by the probabilistic neural networks. |
| |
| Keywords: | flue-cured tobacco leaf near-infrared spectrum principal component analysis probabilistic neural network |
| 本文献已被 维普 等数据库收录！ |
