中文摘要：太赫兹光谱技术因其低能量、非电离特性而被广泛应用于食品安全和质量的快速无损检测。本研究的目的是建立一种基于太赫兹（THz）光谱技术的转基因水稻和非转基因水稻种子的柔性辨识模型。为了提取太赫兹光谱特征和减少特征维数，本文采用稀疏表示法（SR）。首先选择足够的稀疏度来训练太赫兹数据的稀疏编码，然后采用随机森林（RF）方法获得辨识模型。研究发现，转基因和非转基因水稻种子的THz光谱带存在差异，用最小二乘支持向量机（LS-SVM）方法进行比较发现，SR-RF是一种用于识别的较好模型。研究结果表明，SR可能适用于THz光谱的降维过程，基于太赫兹光谱技术的SR-RF方法为转基因和非转基因水稻种子的检测和识别提供了一种新的、有效的、更适用的方法。
外文摘要：Terahertz (THz) spectroscopy technique has been researched and developed for rapid and non-destructive detection of food safety and quality due to its low-energy and non-ionizing characteristics. The objective of this study was to develop a flexible identification model to discriminate transgenic and non-transgenic rice seeds based on terahertz (THz) spectroscopy. To extract THz spectral features and reduce the feature dimension, sparse representation (SR) is employed in this work. A sufficient sparsity level is selected to train the sparse coding of the THz data, and the random forest (RF) method is then applied to obtain a discrimination model. The results show that there exist differences between transgenic and non-transgenic rice seeds in THz spectral band and, comparing with Least squares support vector machines (LS-SVM) method, SR-RF is a better model for discrimination (accuracy is 95% in prediction set, 100% in calibration set, respectively). The conclusion is that SR may be more useful in the application of THz spectroscopy to reduce dimension and the SR-RF provides a new, effective, and flexible method for detection and identification of transgenic and non-transgenic rice seeds with THz spectral system.
外文关键词：Transgenic; Terahertz; Non-destructive; Sparse representation
作者：Hu, Xiaohua; Lang, Wenhui; Liu, Wei; 等.
作者单位：Hefei Univ Technol
期刊名称：JOURNAL OF INFRARED MILLIMETER AND TERAHERTZ WAVES
期刊影响因子：2.54
出版年份：2017
出版刊次：8
点击下载：基于非破坏性太赫兹光谱的转基因水稻种子识别方法