zhpsЖурнал прикладной спектроскопииZhurnal Prikladnoii Spektroskopii0514-7506B. I. Stepanov Institute of Physics of the National Academy of Scienceszhps-1441Research ArticleАННОТАЦИИ АНГЛОЯЗЫЧНЫХ СТАТЕЙABSTRACTS ENGLISH-LANGUAGE ARTICLESРаспознавание сортов древесины с использованием терагерцового спектра и гиперспектральной технологииWood Recogition Based on Terahertz Spectrum and Hyperspectral TechnologyYunX.YunX. D.

Пекин

Xing Da Yun

Beijing

WangY.WangYu.

Пекин

Yuan Wang

Beijing

wangyuan@bjfu.edu.cnMaW.MaW. J.

Пекин

Wen Jin Ma

Beijing

ZhaoI.ZhaoL.

Пекин

Lei Zhao

Beijing

Пекинский университет лесного хозяйства; Государственное управление лесного хозяйства и пастбищ лесохозяйственной техники и автоматизации; Исследовательский центр интеллектуального мониторинга биоразнообразия Пекинского университета лесного хозяйстваSchool of Technology, Beijing Forestry University; Key Lab of State Forestry and Grassland Administration for Forestry Equipment and Automation; Research Center for Biodiversity Intelligent Monitoring, Beijing Forestry University202325112023906976976Copyright © Yun X.D., Wang Y., Ma W.J., Zhao I., 20232023Yun X., Wang Y., Ma W., Zhao I.Yun X.D., Wang Y., Ma W.J., Zhao L.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://zhps.ejournal.by/jour/article/view/1441

Для распознавания сортов древесины использованы терагерцовая спектроскопия во временной области (THz-TDS) и гиперспектральная технология. Десять образцов древесины различных пород, в том числе пять видов хвойных (Pinus sylvestris, Pinus tabulaeformis, Pinus massoniana, Larix gmelinii и Pinus koraiensis) и пять видов лиственных (Xylosma racemosum, Populus davidiana, Fraxinus rhynchophylla, Betula platyphylla и Tilia tuan Szyszyl), выбраны в качестве экспериментальных. Исследование спектральных характеристик проведено на наборах из 400 ТГц-спектров поглощения и гиперспектральных данных. Использованы три метода предварительной обработки спектра: алгоритм сглаживания Савицкого–Голея, стандартное нормальное переменное преобразование и коррекция многомерного рассеяния. Созданы модели распознавания методом опорных векторов и анализа эффектов распознавания. Показано, что с помощью THz-TDS и гиперспектральной технологии можно идентифицировать лиственные породы из разных семейств и родов с наивысшими показателями точности 92 и 94 %. Уровень распознавания THz-TDS для пяти образцов древесины хвойных пород из одного семейства 92 %, что является хорошим показателем, в то время как гиперспектральная технология не дает таких результатов.

Terahertz time-domain spectroscopy (THz-TDS) and hyperspectral technology were used for wood recognition. As wood is a valuable national resource, it is essential to utilize it efficiently and reasonably by classifying the species of wood. To accomplish this, ten distinct species of wood, including five types of softwood (Pinus sylvestris, Pinus tabulaeformis, Pinus massoniana, Larix gmelinii, and Pinus koraiensis) and five types of hardwood (Xylosma racemosum, Populus davidiana, Fraxinus rhynchophylla, Betula platyphylla, and Tilia tuan Szyszyl), were selected as experimental samples. Four hundred groups of data for terahertz absorption coefficient spectra and four hundred groups of hyperspectral data were acquired using THz-TDS and hyperspectral technology, respectively, and then examined for their spectral features. Three spectral preprocessing techniques, including the Savitsky–Golay smoothing algorithm, standard normal variable transformation, and multivariate scattering correction, were employed to preprocess the spectrum. Support vector machine recognition models were then created to compare and analyze the effects of recognition. The results demonstrated that both THz-TDS and hyperspectral approaches could successfully identify five different species of hardwood from various families and genera, with the highest accuracy rates of 92 and 94%, respectively. THz-TDS achieved a 92% recognition rate for five different species of softwood from the same family, indicating good recognition effects, while hyperspectral technology did not achieve such results.

терагерцовая спектроскопиягиперспектральная технологияметод опорных векторовлиственная древесинахвойная древесинаTHz spectroscopyhyperspectral technologysupport vector machinehardwoodsoftwoodReferencesE. A. Wheeler, P. Baas, IAWA J., 19, No. 3, 241–264 (1998).E. A. Wheeler, P. Baas, IAWA J., 19, No. 3, 241–264 (1998).M. Yu, K. Liu, L. Zhou, L. Zhao, S. Q. Liu, Holzforschung, 70, No. 2, 127–136 (2016).M. Yu, K. Liu, L. Zhou, L. Zhao, S. Q. Liu, Holzforschung, 70, No. 2, 127–136 (2016).L. Pang, J. Xiao, J. J. Ma, L. Yan, J. For. Res., 32, No. 2, 461–469 (2021).L. Pang, J. Xiao, J. J. Ma, L. Yan, J. For. Res., 32, No. 2, 461–469 (2021).V. Shenbaga Priya, D. Ramyachitra, Cluster. Comp., 22, No. S6, 13569–13581 (2019).V. Shenbaga Priya, D. Ramyachitra, Cluster. Comp., 22, No. S6, 13569–13581 (2019).G. J. Qiu, E. L. Lu, H. Z. Lu, S. Xu, F. G. Zeng, Q. Shui, Sensors, 18, No. 4, 1010–1025 (2018).G. J. Qiu, E. L. Lu, H. Z. Lu, S. Xu, F. G. Zeng, Q. Shui, Sensors, 18, No. 4, 1010–1025 (2018).J. Sun, Y. C. Zhang, H. P. Mao, S. L. Cong, X. H. Wu, P. Wang, Optik, 153, 156–163 (2018).J. Sun, Y. C. Zhang, H. P. Mao, S. L. Cong, X. H. Wu, P. Wang, Optik, 153, 156–163 (2018).S. Nisgoski, A. A. de Oliveira, G. I. B. de Muñiz, Wood. Sci. Technol., 51, No. 4, 929–942 (2017).S. Nisgoski, A. A. de Oliveira, G. I. B. de Muñiz, Wood. Sci. Technol., 51, No. 4, 929–942 (2017).G. Y. Shi, J. Cao, C. Li, Y. L. Liang, J. For. Res., 31, No. 3, 1061–1069 (2020).G. Y. Shi, J. Cao, C. Li, Y. L. Liang, J. For. Res., 31, No. 3, 1061–1069 (2020).L. Yu, Y. L. Liang, Y. Z. Zhang, J. Cao, J. For. Res., 31, No. 3, 1053–1060 (2020).L. Yu, Y. L. Liang, Y. Z. Zhang, J. Cao, J. For. Res., 31, No. 3, 1053–1060 (2020).M. Peccianti, R. Fastampa, A. M. Conte, O. Pulci, C. Violante, J. Łojewska, M. Clerici, R. Morandotti, M. Missori, Phys. Rev. Appl., 7, No. 6, 064019 (2017).M. Peccianti, R. Fastampa, A. M. Conte, O. Pulci, C. Violante, J. Łojewska, M. Clerici, R. Morandotti, M. Missori, Phys. Rev. Appl., 7, No. 6, 064019 (2017).T. Trafela, M. Mizuno, K. Fukunaga, M. Strlič, Appl. Phys. A Mater., 111, No. 1, 83–90 (2013).T. Trafela, M. Mizuno, K. Fukunaga, M. Strlič, Appl. Phys. A Mater., 111, No. 1, 83–90 (2013).F. S. Vieira, C. Pasquini, Anal. Chem., 86, No. 8, 3780–3786 (2014).F. S. Vieira, C. Pasquini, Anal. Chem., 86, No. 8, 3780–3786 (2014).M. Naftaly, R. E. Miles, IEEE, 95, No. 8, 1658–1665 (2007).M. Naftaly, R. E. Miles, IEEE, 95, No. 8, 1658–1665 (2007).K. Okada, Q. Cassar, H. Murakami, G. MacGrogan, J. P. Guillet, P. Mounaix, M. Tonouchi, K. Serita, Photonics, 8, No. 5, 151 (2021).K. Okada, Q. Cassar, H. Murakami, G. MacGrogan, J. P. Guillet, P. Mounaix, M. Tonouchi, K. Serita, Photonics, 8, No. 5, 151 (2021).F. F. Qu, L. Lin, Y. He, P. C. Nie, C. Y. Cai, T. Dong, Y. Pan, Y. Tang, S. M. Luo, Molecules, 23, No. 7, 1607 (2018).F. F. Qu, L. Lin, Y. He, P. C. Nie, C. Y. Cai, T. Dong, Y. Pan, Y. Tang, S. M. Luo, Molecules, 23, No. 7, 1607 (2018).S. Tsuzuki, N. Kuzuu, H. Horikoshi, K. Saito, K. Yamamoto, M. Tani, Appl. Phys. Express, 8, No. 7, 072402 (2015).S. Tsuzuki, N. Kuzuu, H. Horikoshi, K. Saito, K. Yamamoto, M. Tani, Appl. Phys. Express, 8, No. 7, 072402 (2015).H. Wang, Y. Horikawa, S. Tsuchikawa, T. Inagaki, Cellulose, 27, No. 17, 9767–9777 (2020).H. Wang, Y. Horikawa, S. Tsuchikawa, T. Inagaki, Cellulose, 27, No. 17, 9767–9777 (2020).T. Inagaki, I. D. Hartley, S. Tsuchikawa, M. Reid, Holzforschung, 68, No. 1, 61–68 (2014).T. Inagaki, I. D. Hartley, S. Tsuchikawa, M. Reid, Holzforschung, 68, No. 1, 61–68 (2014).K. Krügener, S. Sommer, E. Stübling, R. Jachim, M. Koch, W. Viöl, J. Infrared. Millim. Terahertz. Waves, 40, No. 7, 770–774 (2019).K. Krügener, S. Sommer, E. Stübling, R. Jachim, M. Koch, W. Viöl, J. Infrared. Millim. Terahertz. Waves, 40, No. 7, 770–774 (2019).M. Reid, R. Fedosejevs, Appl. Opt., 45, No. 12, 2766–2772 (2006).M. Reid, R. Fedosejevs, Appl. Opt., 45, No. 12, 2766–2772 (2006).S. Tanaka, K. Shiraga, Y. Ogawa, Y. Fujii, S. Okumura, J. Wood. Sci., 60, No. 2, 111–116 (2014).S. Tanaka, K. Shiraga, Y. Ogawa, Y. Fujii, S. Okumura, J. Wood. Sci., 60, No. 2, 111–116 (2014).Y. Wang, S. She, N. Zhou, P. X. Jia, J. G. Zhang, Spectrosc. Spectr. Anal., 39, No. 9, 2719–2724 (2019).Y. Wang, S. She, N. Zhou, P. X. Jia, J. G. Zhang, Spectrosc. Spectr. Anal., 39, No. 9, 2719–2724 (2019).A. Subasi, Comp. Biol. Med., 43, No. 5, 576–586 (2013).A. Subasi, Comp. Biol. Med., 43, No. 5, 576–586 (2013).R. Pouteau, A. Collin, Remote Sens. Lett., 4, No. 7, 686–695 (2013).R. Pouteau, A. Collin, Remote Sens. Lett., 4, No. 7, 686–695 (2013).C. M. Salvador, C. C. K. Chou, Atm. Environ., 95, 288–295 (2014).C. M. Salvador, C. C. K. Chou, Atm. Environ., 95, 288–295 (2014).J. W. Zhang, W. L. Song, B. Jiang, M. B. Li, J. For. Res., 29, No. 2, 557–564 (2018).J. W. Zhang, W. L. Song, B. Jiang, M. B. Li, J. For. Res., 29, No. 2, 557–564 (2018).Y. Wang, S. She, N. Zhou, J. G. Zhang, H. Yan, W. B. Li, Bioresources, 14, No. 1, 1033–1048 (2019).Y. Wang, S. She, N. Zhou, J. G. Zhang, H. Yan, W. B. Li, Bioresources, 14, No. 1, 1033–1048 (2019).T. D. Dorney, R. G. Baraniuk, D. M. Mittleman, J. Opt. Soc. Am. A, 18, No. 7, 1562–1571 (2001).T. D. Dorney, R. G. Baraniuk, D. M. Mittleman, J. Opt. Soc. Am. A, 18, No. 7, 1562–1571 (2001).L. Duvillaret, F. Garet, J. L. Coutaz, Appl. Opt., 38, No. 2, 409–415 (1999).L. Duvillaret, F. Garet, J. L. Coutaz, Appl. Opt., 38, No. 2, 409–415 (1999).M. Kamruzzaman, Y. Makino, S. Oshita, J. Food. Eng., 170, 8–15 (2016).M. Kamruzzaman, Y. Makino, S. Oshita, J. Food. Eng., 170, 8–15 (2016).

The authors declare that there are no conflicts of interest present.