基于IFSR异常样本剔除的落叶松木材密度近红外优化模型的研究

doi:10.3964/j.issn.1000-0593(2022)11-3395-08

Abstract
References
Related Citation (15)

Download: PDF (4973 KB)
Export: BibTeX | EndNote (RIS)

Abstract Wood density is an important physical property of wood which can reflect a variety of physical properties such as wood shrinkage, compressive and tensile strength. Using near-infrared spectroscopy technology can rapidly predict wood density, which can overcome the disadvantages of traditional detection methods that consume workforce, material resources and time. However, the modeling results are often affected by abnormal samples. In order to accurately identify and eliminate abnormal samples in the sample set, an isolation forest combined with the studentized residual method (IFSR) was proposed. Based on the advantages of integrated features of isolated forests, the influence of samples on the model is considered, and abnormal samples and strong influence samples can be detected simultaneously. This study measured the near-infrared spectra of 181 larch wood samples and their air-dry density at room temperature. By comparing a variety of preprocessing and feature selection methods, the preprocessing method was determined to adopt the standard normal variable change (SNV) + detrending processing (DT) + mean centralization (MC) + standardization (Auto) method and the feature wavelength selection was determined to adopt competitive adaptive reweighted sampling (CARS) method. Eliminated the influence of noise and irrelevant information on the algorithm, simplified the dataset, and improved the algorithm’s accuracy in removing abnormal samples. In order to verify the ability of the IFSR method to eliminate abnormal samples, it was compared with the other six anomaly detection methods such as Monte Carlo Interactive Verification (MCCV), Mahalanobis Distance (MD), etc. The partial least squares (PLS) model was established to evaluate its anomaly detection performance. At the same time, the particle swarm optimization-support vector machine regression (PSO-SVR), BP neural network (BPNN) and PLS were used to establish the near-infrared prediction model of larch wood density. The results show that the optimized model obtained by IFSR combined with PSO-SVR has the strongest predictive ability, and IFSR can effectively eliminate singular samples and improve the model’s accuracy.

Key words：Near-infrared spectrum; Wood density; Outlier detection; Isolation forest algorithm; Support vector regression

Received: 2021-09-23 Accepted: 2022-01-19

ZTFLH:

O657.3

Corresponding Authors: LI Yao-xiang E-mail: yaoxiangli@nefu.edu.cn

Cite this article:

ZHANG Zhe-yu,LI Yao-xiang,WANG Zhi-yuan, et al. NIR Model Optimization Study of Larch Wood Density Based on IFSR Abnormal Sample Elimination[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(11): 3395-3402.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2022)11-3395-08 OR https://www.gpxygpfx.com/EN/Y2022/V42/I11/3395

[1] HE Xiao-yu, WANG Yan-wei, HUANG Rong-feng, et al(何啸宇，王艳伟，黄荣凤，等). Forest Engineering(森林工程)，2020，36(6): 72.
[2] Balasso Michelle, Hunt Mark, Jacobs Andrew, et al. Forest Ecology and Management, 2021，491：118992.
[3] GAO Ming-yu, NI Hai-ming, ZHANG Bo-yang, et al(高明宇，倪海明，张博洋，等). Forest Engineering(森林工程)，2021，37(4): 66.
[4] JIANG Xin-bo, SONG Jing, XIA Peng(姜新波，宋靖，夏鹏). Forest Engineering(森林工程)，2022，38(1): 34.
[5] Cappozzo A, Duponchel L, Greselin F, et al. Analytica Chimica Acta, 2021, 1153(3): 338245.
[6] Wang B, He J, Zhang S, et al. Journal of Food Process Engineering, 2021, 44: 10.
[7] SHI Lu-zhen, ZHANG Jing-chuan, WANG Yan-qun, et al（石鲁珍，张景川，王彦群，等）. Journal of Chinese Agricultural Mechanization（中国农机化学报）, 2016，37(6)：99.
[8] Silalahi D D, Midi H, Arasan J, et al. Symmetry, 2021，13: 4.
[9] WANG Lin, MA Xue-jie, MENG Dan-rui, et al（王林，马雪洁，孟丹蕊，等）. Spectroscopy and Spectral Analysis（光谱学与光谱分析）, 2019，39(9)：2774.
[10] YIN Bao-quan, SHI Yin-xue, SUN Rui-zhi（尹宝全，史银雪，孙瑞志）. Journal of University of Science and Technology of China（中国科学技术大学学报）, 2016，46(3)：208.
[11] Brownfield B，Kalivas J H. Analytical Chemistry, 2017，89(9)：5087.
[12] HUANG Yuan-cheng, XUE Yuan-yuan，LI Peng-fei（黄远程，薛园园，李朋飞）. Acta Geodaetica et Cartographica Sinica（测绘学报）, 2021，50(3)：416.
[13] LI Xin-peng, GAO Xin, YAN Bo, et al（李新鹏，高欣，阎博，等）. Power System Technology（电网技术）, 2019，43(4)：1447.
[14] Amirvaresi A, Nikounezhad N, Amirahmadi M, et al. Food Chemistry, 2021，344: 128647.
[15] LIU Xiu-ying, YU Jun-ru，WANG Shi-hua（刘秀英，余俊茹，王世华）. Transactions of the Chinese Society of Agricultural Engineering（农业工程学报）, 2020，36(22)：308.
[16] Leng Tuo, Li Feng, Chen Yi, et al. Meat Science, 2021，180：108559.
[17] Li S T, Zhang K Z, Duan P H, et al. IEEE Transactions on Geoscience and Remote Sensing, 2020，58(1)：319.
[18] Sun Y, Yuan M, Liu X, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2021, 10: 258.