Research on Identifying Maize Haploid Seeds Using Near Infrared Spectroscopy Based on Kernel Locality Preserving Projection
LIU Wen-jie1,2, LI Wei-jun1,2*, QIN Hong1,2, LI Hao-guang1,2, NING Xin1,2
1. Institute of Semiconductors, Chinese Academy of Sciences, Beijing 100083, China
2. School of Microelectronics, University of Chinese Academy of Sciences，Beijing 100049，China
Abstract：Haploid identification plays a key role in the field of maize-haploid breeding. To achieve mass and automated identification, Near-infrared Spectroscopy (NIRS) Analysis Technology is widely used. Its advantages include online monitoring, rapid analysis, easy operation, lossless process, cost-effectiveness, etc. At the beginning of the experiment, NIRS data of haploid and polyploidy maize seeds are cross collected via JDSU’s near-infrared spectrometer. To enhance validity, this experiment encompasses a testing set of data besides a training set. After pre-processing, experiment data is subsequently mapped in a higher-dimensional space to enhance its divisibility, and haploid feature is extracted. Then the experiment establishes identification models to predict whether maize seeds are haploid. It needs to point out that the experiment applies different feature extraction algorithms, thus different identification models are established accordingly. The experiment results show that the feature extraction algorithm of Kernel Locality Preserving Projection (KLPP) guarantees accurate recognition in a more stable way. Recognition rate of testing set and training set reaches up to 95.71% and 96.43%. The above experiment proves that NIRS data of maize seeds can be classified more effectively and accurately through non-linear transformation (Gaussian kernel transform in this experiment) and high-dimensional spatial mapping. The above process also maintains partial characteristics of NIRS data. Therefore, this paper may provide some new idea and method for Maize Haploid Identification technology.
刘文杰，李卫军，覃 鸿，李浩光，宁 欣. 基于核局部保持投影的近红外光谱玉米单倍体识别研究[J]. 光谱学与光谱分析, 2019, 39(08): 2574-2577.
LIU Wen-jie, LI Wei-jun, QIN Hong, LI Hao-guang, NING Xin. Research on Identifying Maize Haploid Seeds Using Near Infrared Spectroscopy Based on Kernel Locality Preserving Projection. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2019, 39(08): 2574-2577.
[1] ZHANG Qiang(张 强). Heilongjiang Agricultural Sciences(黑龙江农业科学), 2014，（9）: 150.
[2] CHEN Shao-jiang, SONG Tong-ming(陈绍江，宋同明). Acta Agronomica Sinica(作物学报)，2003，29(4)：587.
[3] DU He-wei, DAI Jing-rui, LI Jian-sheng(杜何为，戴景瑞，李建生). Journal of Maize Sciences(玉米科学), 2010, (6).
[4] CAI Zhuo, XU Guo-liang(才 卓，徐国良). Journal of Maize Sciences(玉米科学)，2014，（1）: 1.
[5] WEI Chang-song, XU Gui-ming, TIAN Pu-huan(魏昌松, 许贵明, 田甫焕). Crops(作物杂志), 2014, (6).
[6] LI Xiang-qun, SONG Bing, FU Yong-ping(李向群，宋 冰，付永平). Seed World(种子世界)，2014，（7）: 22.
[7] Hartwig H Geiger，G Andrés Gordillo，Silvia Koch. Crop Science，2013, 53: 2313.
[8] YAN Yan-lu, ZHAO Long-lian, HAN Dong-hai, et al(严衍禄, 赵龙莲, 韩东海, 等). Fundamentals and Applications of Near Infrared Spectroscopy(近红外光谱分析基础与应用). Beijing: China Light Industry Press(北京：中国轻工业出版社)，2005.
[9] Deng Xiaogang, Tian Xuemin. Chinese Journal of Chemical Engineering, 2013, 21(2)：163.
[10] Su Yu-Chuan, Chiu Tzu-Hsuan, Kuo Yin-His. Multimedia, IEEE Transactions on, 2014, 16(6): 1645.
[11] Luo Lijia，Bao Shiyi，Mao Jianfeng. Journal of Process Control, 2016，38：11.
[12] Wonga W K, Author Vitae，ZhaobAuthor Vitae H T. Pattern Recognition，2012，45(1)：186.
[13] Shikkenawis Gitam, Mitra K Suman. Neurocomputing，2016，173(2)：196.
[14] Jiang Rui，Fu Weijie，Li Wen. Neurocomputing, 2016, 187: 109.
[15] Zhong Fujin，Li Defang，Zhang Jiashu. Journal of Visual Communication and Image Representation, 2014，25(7)：1676.
[16] Yu Guoxian. Neurocomputing, 2011, 74(4): 598.
