径向基神经网络结合近红外光谱技术分析安络小皮伞发酵组分的研究

采用径向基神经网络(RBFNN)结合近红外光谱(NIRS)技术建立一种分析安络小皮伞发酵菌丝体中甘露醇、多糖和腺苷三种组分的定量分析模型。收集164个安络小皮伞液体发酵菌丝体样本的近红外光谱数据，采用常规方法分别测定样本中甘露醇、多糖和腺苷的含量。在应用蒙特卡罗偏最小二乘法（MCPLS）识别异常样本、确定校正集样本数量的基础上，以逼近度（Da）为评价指标，采用可移动窗口径向基神经网络(MWRBFNN)筛选特征波长变量，筛选最佳光谱预处理方法、隐含层节点数(NH)等模型参数。建立甘露醇、多糖和腺苷组分定量分析模型，最佳RBFNN-NIRS模型中校正集和预测集样本实验测定值与预测值间相关系数分别为0.9274、0.9009、0.9440和0.9354、0.9018、0.8847，表明模型具有很好的拟合度和预测性能。

Abstract

Radial basis function neural network (RBFNN) combining with near infrared spectroscopy (NIRS) is applied to develop quantitative analyzing models of mannitol, polysaccharide and adenosine in Marasmius androsaceus fermentation mycelium. Using submerge fermentation, 164 Marasmius androsaceus mycelium samples are obtained. The contents of mannitol, polysaccharide and adenosine are determined via traditional methods and the near infrared spectroscopy data of the 164 samples are collected. The outliers are removed and the number of calibration set is confirmed via Monte Carlo partial least square (MCPLS) method. Based on the values of degree of approach (Da), the moving window radial basis function neural network (MWRBFNN) is applied to optimize characteristic wavelength variables, pre-processing methods, hidden layer nodes (NH) and spreads in the models. The quantitative analyzing models of mannitol, polysaccharide and adenosine in Marasmius androsaceus fermentation mycelium are developed successfully. The correlation coefficients between the reference values and predictive values of mannitol, polysaccharide and adenosine in both of the calibration set and validation set of optimum RBFNN-NIRS models are 0.9274, 0.9009, 0.9440 and 0.9354, 0.9018, 0.8847 respectively. All the data suggest that these models possess excellent fitness and predictive ability.

参考文献

[1] 陈西广, 张翼伸, 李润秋, 等. 安络小皮伞中水溶性多糖的研究[J]. 真菌学报, 1990, 9(2): 155-160.

Chen Xiguang, Zhang Yishen, Li Runqiu, et al.. Study on water soluble polysaccharide from Marasmius androsaceus [J]. Acta Mycologica Sinica, 1990, 9(2): 155-160.

[2] 周婷婷, 姜翔之, 王颖, 等. 安络小皮伞提取物特征图谱研究[J]. 中国药师, 2013, 16(3): 325-328.

Zhou Tingting, Jiang Xiangzhi, Wang Ying, et al.. Study on characteristic spectrum of the extract of Marasmius androsaceus [J]. China Pharmacist, 2013, 16(3): 325-328.

[3] 梁启明, 徐扬, 王艳珍, 等. 安络小皮伞菌丝体多糖的提取及其抗脂质过氧化作用的研究[J]. 食品工业科技, 2007, 28(9): 127-129.

[4] L Zhang, M Yang, Y Song, et al.. Anti hypertensive effect of 3,3,5,5-tetramethyl-4-piperidone, a new compound extracted from Marasmius androsaceus [J]. Journal of Ethnopharmacology, 2009, 123(1): 34-39.

[5] 赵杰文, 毕夏坤, 林颢, 等. 鸡蛋新鲜度的可见近红外透射光谱快速识别 [J]. 激光与光电子学进展, 2013, 50(5): 053003.

Zhao Jiewen, Bi Xiakun, Lin Hao, et al.. Visible-near-infrared transmission spectra for rapid analysis of the freshness of eggs [J]. Laser & Optoelectronics Progress, 2013, 50(5): 053003.

[6] 吴春阳, 卢启鹏, 丁海泉, 等. 利用人体组织液进行近红外无创血糖测量[J]. 光学学报, 2013, 33(11): 1117001.

Wu Chunyang, Lu Qipeng, Ding Haiquan, et al.. Noninvasive blood glucose sensing with near-infrared spectroscopy based on interstitial fluid [J]. Acta Optica Sinica, 2013, 33(11): 1117001.

[7] 张益波, 何欢, 孟庆繁, 等. 近红外光谱结合径向基神经网络在云芝菌丝体无损分析中的应用[J]. 光学学报, 2010, 30(12): 3552-3557.

Zhang Yibo, He Huan, Meng Qingfan, et al.. Application of near infrared reflectance spectroscopy-radial basis function neural network for non-destructive determination of Coriolus Versicolor [J]. Acta Optica Sinica, 2010, 30(12): 3552-3557.

[8] J Moody, C Darken. Fast learning in network of locally-tuned processing units [J]. Neural Computation, 1989, 2(2): 281-284.

[9] 刘银, 付广伟, 张燕君, 等. 基于径向基函数神经网络的传感布里渊散射谱特征提取[J]. 光学学报, 2012, 32(2): 0206002.

Liu Yin, Fu Guangwei, Zhang Yanjun, et al.. A novel method for Brillouin scattering spectrum of distributed sensing systems based on radial basis function neural networks to extract features [J]. Acta Optica Sinica, 2012, 32(2): 0206002.

[10] C-N Ko. Reinforcement radial basis function neural networks with an adaptive annealing learning algorithm [J]. Applied Mathematics and Computation, 2013, 221: 503-513.

[11] 郭伟良, 张卓勇, 逯家辉, 等. 近红外光谱法在蛹虫草诱变筛选及其发酵条件优化中应用[J]. 光谱学与光谱分析, 2010, 30(8): 2077-2082.

Guo Weiliang, Zhang Zhuoyong, Lu Jiahui, et al.. Application of near infrared spectroscopy in screening Cordyceps militaris mutation strains and optimizing their fermentation process [J]. Spectroscopy and Spectral Analysis, 2010, 30(8): 2077-2082.

[12] 郭伟良, 王丹, 宋佳, 等. 近红外光谱法同时快速定量分析蛹虫草菌丝体中4种有效成分[J]. 光学学报, 2011, 31(2): 0230002.

Guo Weiliang, Wang Dan, Song Jia, et al.. Simultaneous and rapid quantitative analysis of four components in Cordyceps militaris mycelium powder using near infrared spectroscopy [J]. Acta Optica Sinica, 2011, 31(2): 0230002.

[13] 中华人民共和国药典委员会. 中华人民共和国药典, 第一部 [M]. 北京: 中国医药科技出版社, 2010. 106.

Chinese Pharmacopoeia Commission. Pharmacopoeia of the People′s Republic of China, Part I [M]. Beijing: Chinese Medical Science and Technology Press, 2010. 106.

[14] 王黎明, 夏文水. 蒽酮硫酸法测定茶多糖含量的研究[J]. 食品科学, 2005, 26(7): 185-188.

Wang Liming, Xia Wenshui. Determination of TPS by improvement of anthrone-sulfuric acid method [J]. Food Science, 2005, 26(7): 185-188.

[15] 蔡友华, 范文霞, 刘学铭, 等. 比色法测定巴西虫草菌丝体中虫草酸的含量[J]. 现代食品科技, 2008, 24(1): 76-79.

Cai Youhua, Fan Wenxia, Liu Xueming, et al.. Determination of cordycepic acid content in the mycelia of Cordyceps brasiliensis Henn by colorimetry [J]. Modern Food Science and Technology, 2008, 24(1): 76-79.

[16] W L Guo, Y P Du, Y C Zhou, et al.. At-line monitoring of key parameters of nisin fermentation by near infrared spectroscopy, chemometric modeling and model improvement [J]. World J Microbiol Biotechnol, 2012, 28(3): 993-1002.

[17] 高静, 卢启鹏, 彭忠琦, 等. 近红外无创生化分析中集光椭球反射镜参数设计与优化[J]. 光学学报, 2012, 32(8): 0822007.

Gao Jing, Lu Qipeng, Peng Zhongqi, et al.. Parameter design and optimization of collecting light ellipsoidal reflector in near infrared noninvasive biochemical analysis [J]. Acta Optica Sinica, 2012, 32(8): 0822007.

宋佳, 李臣亮, 邢高杨, 孟庆繁, 逯家辉, 曹家铭, 周毓麟, 王迪, 滕利荣. 径向基神经网络结合近红外光谱技术分析安络小皮伞发酵组分的研究[J]. 光学学报, 2014, 34(12): 1230001. Song Jia, Li Chenliang, Xing Gaoyang, Meng Qingfan, Lu Jiahui, Cao Jiaming, Zhou Yulin, Wang Di, Teng Lirong. Study on Analyzing Active Ingredient of Marasmius androsaceus via Radial Basis Function Neural Network Combining with Near Infrared Spectroscopy[J]. Acta Optica Sinica, 2014, 34(12): 1230001.

径向基神经网络结合近红外光谱技术分析安络小皮伞发酵组分的研究

关于本站 Cookie 的使用提示

全站搜索

径向基神经网络结合近红外光谱技术分析安络小皮伞发酵组分的研究

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索