BACNN: Multi-scale feature fusion-based bilinear attention convolutional neural network for wood NIR classification

doi:10.1007/s11676-023-01652-z

Abstract

Abstract:

Effective development and utilization of wood resources is critical. Wood modification research has become an integral dimension of wood science research, however, the similarities between modified wood and original wood render it challenging for accurate identification and classification using conventional image classification techniques. So, the development of efficient and accurate wood classification techniques is inevitable. This paper presents a one-dimensional, convolutional neural network (i.e., BACNN) that combines near-infrared spectroscopy and deep learning techniques to classify poplar, tung, and balsa woods, and PVA, nano-silica-sol and PVA-nano silica sol modified woods of poplar. The results show that BACNN achieves an accuracy of 99.3% on the test set, higher than the 52.9% of the BP neural network and 98.7% of Support Vector Machine compared with traditional machine learning methods and deep learning based methods; it is also higher than the 97.6% of LeNet, 98.7% of AlexNet and 99.1% of VGGNet-11. Therefore, the classification method proposed offers potential applications in wood classification, especially with homogeneous modified wood, and it also provides a basis for subsequent wood properties studies.

Key words: Wood classification, Near infrared spectroscopy, Bilinear network, SE module, Anti-noise algorithm

Zihao Wan, Hong Yang, Jipan Xu, Hongbo Mu, Dawei Qi. BACNN: Multi-scale feature fusion-based bilinear attention convolutional neural network for wood NIR classification[J]. JOURNAL OF FORESTRY RESEARCH, 2024, 35(1): 4-.

Zihao Wan, Hong Yang, Jipan Xu, Hongbo Mu, Dawei Qi. [J]. 林业研究(英文版), 2024, 35(1): 4-.

References 38

1	Acquarelli J, van Laarhoven T, Gerretzen J, Tran TN, BuydensMarchiori LME. Convolutional neural networks for vibrational spectroscopic data analysis. Anal Chim Acta, 2017, 954: 22-31, DOI
2	Asadi K, Littman M L (2017) In: An alternative softmax operator for reinforcement learning. In: Proc. 28th int’l conf. mach. Learn. Bellevuepp, WA, 243–252
3	Chen YY, Wang ZB. Quantitative analysis modeling of infrared spectroscopy based on ensemble convolutional neural networks. Chemometr Intell Lab Syst, 2018, 181: 1-10, DOI
4	Gao SH, Han Q, Li D, Chen MM, Peng P. Representative batch normalization with feature calibration. Virtual, 2021, 1: 8669-8679
5	Gao MY, Wang F, Song P, Liu JY, Qi DW. BLNN: multiscale feature fusion-based bilinear fine-grained convolutional neural network for image classification of wood knot defects. J Sens, 2021, 2021: 1-18
6	Graham B, Engelhardt B, Van den Oord A (2014) Fractional max-pooling. arXiv preprint arXiv:1412.6071
7	He KM, Zhang XY, Ren SQ, Sun J. Deep residual learning for image recognition. CVPR, 2016 Las Vegas Nevada 770-778
8	Hu C, Qu JJ, Xu CP, Zhu AJ. Garment image recognition based on adaptive pooling neural network. J Comput Appl, 2018, 38(8): 2211
9	Hu J, Shen L, Sun G. Squeeze-and-excitation networks, 2018 Salt Lake City Utah CVPR 7132-7141
10	Huang PG, Fan Z, Li XP, Guan C, Zhang YF, Wu ZK. Review of computer-based wood feature extraction and identification. World for Res, 2020, 33(01): 44-48
11	Huang G, Liu Z, Van Der Maaten L, Weinberger Kilian Q (2017) Densely Connected Convolutional Networks. CVPR 2017. Honolulu Hawaii. 4700–4708
12	Jia WS, Zhang HZ, Ma J, Liang G, Wang JH, Liu X. Study on the predication modeling of COD for water based on UV-VIS spectroscopy and CNN algorithm of deep learning. Spectrosc Spectr Anal, 2020, 40(9): 2981
13	Jiao LC, Zhang F, Liu F, Yang SY, Li LL, Feng ZX, Qu R. A survey of deep learning-based object detection. IEEE Access, 2019, 7: 128837-128868, DOI
14	Kauppinen JK. Fourier Self-Deconvolution in Spectroscopy. Spectrom Tech, 1983, 1983: 199-232, DOI
15	Krizhevsky A, Sutskever I, Hinton G. Imagenet classification with deep convolutional neural networks. Commun ACM, 2012, 60(6): 84-90, DOI
16	Kuesel AC, Stoyanova R, Aiken NR, Li CW, Szwergold BS, Shaller C, Brown TR. Quantitation of resonances in biological 31P NMR spectra via principal component analysis: potential and limitations. NMR Biomed, 1996, 9(3): 93-104, DOI
17	Laakmann F, Petersen P. Efficient approximation of solutions of parametric linear transport equations by ReLU DNNs. Adv Comput Math Dio, 2021, DOI
18	Lecun Y, Bottou L, Bengio Y. Gradient-based learning applied to document recognition. Proc IEEE, 1998, 86(11): 2278-2324, DOI
19	Lecun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015, 521(7553): 436-444, DOI
20	Ma HY, Li XH, Qiang L, Xie XB, Chong J. Zhao CX (2020) Research on identification technology of explosive vibration based on EEMD energy entropy and multiclassification SVM. Shock Vib, 2020, 2: 1-10
21	Macior A, Zaborniak I, Chmielarz P, Smenda J, Wolski K, Ciszkowicz E, Lecka-Szlachta K. A new protocol for ash wood modification: synthesis of hydrophobic and antibacterial brushes from the wood surface. Molecules, 2022, 27(3): 890, DOI
22	Nisgoski S, DeOliveira A, DeMuñiz G. Artificial neural network and SIMCA classification in some wood discrimination based on near-infrared spectra. Wood Sci Technol, 2017, 51(4): 929-942, DOI
23	Pachuta SJ. Enhancing and automating TOF-SIMS data interpretation using principal component analysis. Appl Surf Sci, 2004, 231(6): 217-223, DOI
24	Pan X, Qiu J, Yang Z. Identification of softwood species using convolutional neural networks and raw near-infrared spectroscopy. Wood Mater Sci Eng, 2022, 1: 1-11
25	Pradhan T, Kumar P, Pal S. CLAVER: an integrated framework of convolutional layer, bidirectional LSTM with attention mechanism based scholarly venue recommendation. Inf Sci, 2021, 559: 212-235, DOI
26	Qin YH, Ding XQ, Gong HL. High dimensional feature selection in near infrared spectroscopy classification. Infrared Laser Eng, 2013, 42(5): 1355-1359
27	Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propagating errors. Nature, 1986, 323(6088): 533-536, DOI
28	Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv, https://arxiv.org/abs/1409.1556.
29	Soares SFC, Medeiros EP, Pasquini C. Classification of individual cotton seeds with respect to variety using near-infrared hyperspectral imaging. Anal Methods, 2016, 8(48): 8498-8505, DOI
30	Szegedy C, Liu W, Jia YQ, Sermanet P, Reed S, Anguelov D, Rabinovich A. Going deeper with convolutions, 2015 Boston Massachusetts CVPR 1-9
31	Tang YS, Chen ZG. Soil pH prediction based on convolution neural network and near infrared spectroscopy. Spectrosc Spectr Anal, 2021, 41(3): 892
32	Wang XS, Sun YD, Huang AM. Research on infrared spectrum for timber species identification. For Eng, 2015, 31(6): 65-70
33	Wang XS, Sun YD, Huang MG, Huang AM. Back propagation artificial neural network combined with near infrared spectroscopy for timber recognition. J Northeast for Univ, 2015, 43(12): 82-85
34	Wang QQ, Gao QX, Gao XB, Nie FP. l(2, p)-Norm based PCA for image recognition. IEEE Trans Image Process, 2017, 27(3): 1336-1346, DOI
35	Wang WQ, Zhang J, Wang FL. Attention bilinear pooling for fine-grained classification. Symmetry, 2019, 11(8): 1033, DOI
36	Xia JJ, Huang Y, Li QQ, Xiong YM, Min SG. Convolutional neural network with near-infrared spectroscopy for plastic discrimination. ECL, 2021, 19(5): 3547-3555
37	Yang SY, Kwon O, Park Y, Chung H, Kim H, Park SY, Choi IG, Yeo H. Application of neural networks for classifying softwood species using near infrared spectroscopy. J near Infrared Spectrosc, 2020, 28(5–6): 298-307, DOI
38	Zhang W, Li CH, Peng GL, Chen YH, Zhang ZJ. A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load. Mech Syst Signal Process, 2017, 100: 439-453, DOI