Pretreatment of near-infrared spectroscopy of wood based on wavelet compression
-
摘要: 近红外光谱数据维数多、数据量大,直接保存需要庞大储存空间,且海量数据会对网络化在线检测的分析速度和准确性产生影响。为探讨应用小波压缩进行近红外光谱预处理的可行性及其对枫桦木材密度预测精度的影响,通过强光探头采集木材圆盘的近红外光谱,在Matlab软件中应用小波变换法对枫桦木材密度近红外光谱数据进行压缩。结果表明:当小波基sym2分解层为6时,基于均衡稀疏标准形式的全局硬阈值压缩效果最好,将2 151个变量压缩成38个小波系数,其能量保留成分、零系数成分、压缩比分别为99.66%、98.34%、56.61%。用未处理光谱数据和压缩后的38个小波系数分别建立偏最小二乘定标分析模型,同时做内部交叉验证,并用未处理和压缩后的预测集做外部检验,得知压缩后校正模型对压缩后样品预测能力较好,预测决定系数为0.913 9。因此,小波压缩可有效简化近红外光谱数据,提高近红外光谱对枫桦木材密度的预测精度。Abstract: Due to the multi-dimension of near infrared spectrum (NIRS) and large volume of data, huge storage space is needed for data processing, which directly affects the speed and accuracy of online data analysis. This study aims to discuss the feasibility of pretreatment of near-infrared spectroscopy of wood based on wavelet compression as well as its effect on prediction accuracy of Betula costata Trautv wood density using NIR technology. The NIRS data of B. costata wood were compressed using wavelet transform algorithm with the aid of Matlab. Results showed that the global threshold value based on balance sparsity norm and the heuristic threshold value were observed to be the best with decomposition layer of 6 for the sym2 wavelet. With the method, the 2 151 variables were compressed into 38 wavelet coefficients, and the corresponding energy reserved component, zero coefficient component and compression ratio were 99.66%, 98.34% and 56.61%, respectively. The partial least squares (PLS) models were developed based on both the original NIRS and the 38 wavelet coefficients after compression. The inner cross validation was used and the external validation was applied to both the original and the compressed dataset. The best prediction results were associated with the calibration model developed with the compressed NIR data with determination coefficient (R2) of 0.913 9. This study indicates that the wavelet compression method could effectively simplify NIRS data and improve the prediction accuracy.
-
Key words:
- NIRS /
- wavelet compression /
- Betula costata Trautv /
- wood density
-
[1] HAUGHEY S A, GRAHAM S F, CANCOUET E, et al. The application of near-infrared reflectance spectroscopy (NIRS) to detect melamine adulteration of soya bean meal[J]. Food Chemistry, 2013, 136(3): 1557-1561. [2] HAO S Q, SONG B Q, LI P, et al. Prediction of sawdust water content of Dahurian larch based on NIRS and BP neural network[J]. Forest Engineering, 2012, 28(4): 9-11. [3] ZHANG P, LI Y X. Theresearch progress on application of near-infrared spectroscopy in wood mechanical properties prediction[J]. Forest Engineering,2014,30(3):68-70. [4] NKANSAH K. Rapid characterization of biomass: the use of near infrared and fluorescence spectroscopy as process analytical technology (PAT) method[M]. West Virginia:West Virginia University, 2009. [5] DIAZ J T, VEAL M W, CHINN M S. Development of NIRS models to predict composition of enzymatically processed sweet potato[J]. Industrial Crops and Products, 2014, 59: 119-124. [6] HUO S Y, YAO C L, WANG N.Nondestructive estimation of the fiber length and crystallinity of Populus×euramericana by near-infrared spectroscopy[J]. Paper and Paper Making, 2012,31(1): 28-31. [7] KONG W Y, LIU Z B, LIU Y X,et al. Research status and prospect of acoustic vibration properties modification of wood used for soundboard[J]. World Forestry Research,2012,25(4):45-51. [8] 郝斯琪, 宋博骐, 李湃, 等. 基于近红外光谱与 BP 神经网络预测落叶松木屑的含水率[J]. 森林工程, 2012, 28(4): 9-11. [9] TANG Y F, HOU Z Z, WANG Z B, et al. Cluster analysis of rhubarb from different habitats based on near-infrared spectrometry by wavelet transform[J]. Journal of Anhui Agricultural Sciences, 2012, 40(30): 14726-14727. [10] 张鹏, 李耀翔. 近红外光谱分析技术在木材机械性能检测中的研究进展[J]. 森林工程, 2014, 30(3): 68-70. [11] TIAN G Y, YUAN H F, LIU H Y, et al. Application of wavelet transform to compressing near infrared spectra data [J]. Journal of Instrumental Analysis , 2005, 24(1): 17-20. [12] RAMADEVI P, MEDER R, VARGHESE M. Rapid estimation of kraft pulp yield and lignin in Eucalyptus camaldulensis and Leucaena leucocephala by diffuse reflectance near-infrared spectroscopy (NIRS)[J]. Southern Forests, 2010, 72(2): 107-111. [13] 霍淑媛, 姚春丽, 王娜. 近红外光谱法测定欧美杨纤维形态和结晶度[J]. 纸和造纸, 2012, 31(1): 28-31. [14] GB/T1933—2009 Method for determination of the density of wood[S].Beijing: Standards Press of China,2009. [15] 孔文杨,刘镇波,刘一星,等.近红外光谱技术在木材材性分析及木质复合材料生产中的应用[J].世界林业研究,2012,25(4):45-51. [16] ZHANG X C, WU J Z, XU Y. Modern NIR analysis technology and ite applictions in modern agriculture [M].Beijing: Electronic Industry Press, 2012. [17] NICOLAI B M, THERON K I, LAMMERTYN J. Kernel PLS regression on wavelet transformed NIR spectra for prediction of sugar content of apple[J]. Chemometrics and Intelligent Laboratory Systems, 2007, 85(2): 243-252. [18] QIU S J, HE Y, ZHANG G S,et al. Fast determination of coating thickness of the total saponin of radix bupleuri enteric coated tablets by NIRS[J]. Chinese Pharmaceutical Journal, 2013, 48(24): 2128-2133. [19] 汤彦丰, 侯占忠, 王志宝, 等. 中草药大黄小波变换的近红外光谱的聚类分析[J]. 安徽农业科学, 2012, 40(30): 14726-14727. [20] 田高友, 袁洪福, 刘慧颖, 等. 小波变换用于近红外光谱数据压缩[J]. 分析测试学报, 2005, 24(1): 17-20. [21] GB/T1933—2009木材密度测定方法 [S]. 北京:中国标准出版社,2009. [22] 张小超,吴静珠,徐云.近代外光谱分析技术及其在现代农业中的应用[M].北京:电子工业出版社,2012. [23] 邱素君,何雁, 张国松, 等. 近红外光谱快速测定柴胡总皂苷肠溶片包衣膜厚度研究[J]. 中国药学杂志, 2013, 48(24): 2128-2133. -
点击查看大图
计量
- 文章访问数: 546
- HTML全文浏览量: 55
- PDF下载量: 12
- 被引次数: 0
下载:
