首页> 外文会议>Advances in Neural Networks - ISNN 2007 pt.3; Lecture Notes in Computer Science; 4493 >Determination of Storage Time of Rice Seed Using ANN Based on NIRS
【24h】

Determination of Storage Time of Rice Seed Using ANN Based on NIRS

机译:基于NIRS的ANN确定水稻种子的贮藏时间

获取原文
获取原文并翻译 | 示例

摘要

A simple, fast and nondestructive approach was put forward to classify rice seed of different storage time. This discrimination was conducted by integrated with wavelet transform (WT), principal component analysis (PCA) and artificial neural networks (ANN) based on near infrared reflectance spectroscopy (NIRS). Four classes' samples from four different storage times were used for Vis/NIR spectroscopy on 325-1075 nm using a field spectroradiometer. WT and PCA were used to reduce spectral data dimension and extract diagnostic information from spectra data. The first eight PCs, which accounted for 99.94% of the raw spectral variables, were used as input of the ANN model. The ANN model yielded high discrimination accuracy. The discrimination accuracy was 97.5% for rice seed samples of four different storage years.
机译:提出了一种简单,快速,无损的方法对不同贮藏时间的水稻种子进行分类。通过与小波变换(WT),主成分分析(PCA)和基于近红外反射光谱(NIRS)的人工神经网络(ANN)集成来进行这种区分。使用现场光谱辐射计,将来自四个不同存储时间的四类样品用于325-1075 nm的Vis / NIR光谱。 WT和PCA用于减少光谱数据的维数并从光谱数据中提取诊断信息。前八台PC(占原始光谱变量的99.94%)用作ANN模型的输入。人工神经网络模型具有很高的判别精度。四个不同贮藏年期的水稻种子样品的鉴别准确度为97.5%。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号