Wood Quality of Chinese Zither Panels Based on Convolutional Neural Network and Near-Infrared Spectroscopy
MENG Shi-yu1, HUANG Ying-lai1*, ZHAO Peng1, LI Chao1, LIU Zhen-bo2, LIU Yi-xing2, XU Yan3
1. College of Information and Computer Engineering, Northeast Forestry University, Harbin 150040, China
2. College of Materials Science and Engineering, Northeast Forestry University, Harbin 150040, China
3. Yangzhou Liangjiang Ancient Zither Making Academe Co., Ltd., Yangzhou 225001, China
Abstract:Currently, the instrument production industry relies mainly on the subjective judgment of instrumental technicians when selecting the wood for Chinese zither panels. However, this method lacks a summary of scientific theories and is inefficient, which limits the objectivity of the selection and the improvement of the yield. Moreover, the current model for judging the wood grade cannot satisfy the large demand of the musical instrument market. Therefore, achieving rapid and intelligent grading of wood for Chinese zither panels is an urgent problem to be solved. Near-infrared spectroscopy contains information about the molecular structure of an object and is very suitable for measuring organic substances containing hydrogen. The chemical bonds of the main chemical components of wood used in Chinese zither panels are composed of hydrogen-containing groups, and the chemical compositions of the panels of different grades are different. These differences are reflected in near-infrared spectral data by light, which makes it possible to judge the wood grade. Simultaneously, convolutional neural network (CNN) has a strong feature extraction ability for nonlinear data. Therefore, this paper proposes a method to analyze the spectral data by using the CNN model to determine the wood grade. In the experiment, this paper applied two spectral preprocessing methods, like the Savitzky Golay first-derivative and second-derivative preprocessing methods, and two data compression methods, like kernel principal component analysis (KPCA) and successive projections algorithm. Through the CNN model designed in the paper, the optimal preprocessing and data compression methods were selected by using the classification accuracy rate of samples and the loss value in the model construction process as the judgment indicators. In order to improve the ability of the experimental model to extract and analyze spectral data and avoid overfitting, this experiment applied multi-channel convolution kernel, batch normalization and early stopping strategies. Finally, the feature information extracted by the two convolution layers was sent into the fully connected layers to extract other residual features, and the prediction grade of the panel was obtained using the softmax function. Thus, the final experimental model was determined. Finally, Savitzky Golay first-derivative and KPCA were the optimal data processing methods. At the same time, the main key bands for distinguishing different wood grades were obtained, which were 1 163~1 243 and 1 346~1 375 and 1 525~1 584 nm, respectively. Applying the proposed model to the test set samples, the grade classification accuracy of the wood for Chinese zither panels was 95.5%. Experimental results revealed that the proposed method can efficiently process spectral data and identify the key features of different grades of wood for Chinese zither panels. Therefore, it can provide specific technical support for the broad instrument market.
Key words:Convolutional neural network; Kernel principal component analysis; Successive projections algorithm; Chinese zither panels
孟诗语,黄英来,赵 鹏,李 超,刘镇波,刘一星,徐 艳. 卷积神经网络用于近红外光谱古筝面板木材分级[J]. 光谱学与光谱分析, 2020, 40(01): 284-289.
MENG Shi-yu, HUANG Ying-lai, ZHAO Peng, LI Chao, LIU Zhen-bo, LIU Yi-xing, XU Yan. Wood Quality of Chinese Zither Panels Based on Convolutional Neural Network and Near-Infrared Spectroscopy. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(01): 284-289.
[1] Beena G Sood, Kathleen McLaughlin, Josef Cortez. Seminars in Fetal and Neonatal Medicine, 2015, 20(3): 164.
[2] Hwang S W, Horikawa Y, Lee W H, et al. Journal of Wood Science, 2016, 62(2): 156.
[3] Inagaki Tetsuya, Matsuo Miyuki, Tsuchikawa Satoru. Applied Physics A, 2016, 122: 208.
[4] PANG Xiao-yu, YANG Zhong, LÜ Bin(庞晓宇, 杨 忠, 吕 斌, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2016, 36(11): 3552.
[5] Lee Hyungtae, Kwon Heesung. IEEE Transactions on Image Processing, 2017, 26(10): 4843.
[6] Justin Salamon, Juan Pablo Bello. IEEE Signal Processing Letters, 2017, 24(3): 279.
[7] Bulat Ibragimov, Lei Xing. Medical Physics, 2017, 44(2): 547.
[8] XU Shan-shan, LIU Ying-an, XU Sheng(徐姗姗,刘应安,徐 昇). Journal of Shandong University·Engineering Science(山东大学学报·工学版), 2013, 43(2): 23.
[9] WEI Xian(魏 弦). Journal of Electronic Measurement and Instrument (电子测量与仪器学报), 2017, 31(12): 2017.
[10] Diniz P H G D, Pistonesi M F, Alvarez M B. et al. Journal of Food Composition and Analysis, 2015, 39: 103.
[11] Manfred Schwanninger, José Carlos Rodrigues, Karin Fackler. Journal of Near Infrared Spectroscopy, 2011, 19(5): 287.
[12] ZHOU Zhu, YIN Jian-xin, ZHOU Su-yin, et al(周 竹, 尹建新, 周素茵,等). Laser & Optoelectronics Progress(激光与光电子学进展), 2017, 54(2): 311.