|
|
|
|
|
|
Terahertz Spectral Recognition Based on Bidirectional Long Short-Term Memory Recurrent Neural Network |
YU Hao-yue, SHEN Tao*, ZHU Yan, LIU Ying-li, YU Zheng-tao |
Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650504, China |
|
|
Abstract Feature extraction, the key process of the terahertz spectral recognition, typically uses the dimensionality reduction techniques. However, when the overall difference of terahertz spectra of some compounds is small, dimensionality reduction methods often lack important feature information of sample differences, which leads to classification errors. If the dimensionality reduction process is not performed, the traditional machine learning algorithm cannot be well classified because the original spectral data have a high dimensionality. Therefore, this paper proposes a terahertz recognition method based on bidirectional long short-term memory recurrent neural network (BLSTM-RNN), which performs automatic feature extraction with containing full spectrum information of terahertz spectrum. BLSTM-RNN is a special recurrent neural network, whose LSTM unit can be used effectively to solve the problem that the original terahertz spectral data dimension is high. Then, it becomes easier to train the model. What’s more, the architectural model combined with bi-directional spectral information can enhance the ability of the model to extract valid feature information from complex spectral data automatically. In this paper, three types and 15 compounds terahertz transmission spectra are used as test objects. The terahertz transmission spectrum samples data of 15 organic compounds such as Anthraquinone, Benomyl and Carbazole were firstly normalized in 0.9~6 THz by S-G filtering and cubic spline interpolation. Then a recurrent neural network with bidirectional Long short-term memory unit (LSTM) is constructed to automatically extract the full spectrum information of the terahertz spectrum and classify it by Softmax classifier. Through experimentation of optimizing the network structure and various parameters, the prediction model of the complex terahertz transmission spectrum data is obtained, and the comparative experiment is done by contrasting with the traditional machine learning algorithm SVM, KNN and neural network algorithm MLP, CNN. The results show that compared with other methods,the recognition accuracy of both dataset-1 and dataset-2 is improved. Dataset-1 and dataset-2 are two terahertz transmission spectral data sets of five compounds with large difference and no obvious peak characteristics, and the average recognition accuracy of the former is 100% and the latter 98.51%. Most importantly, dataset-3 is a dataset of terahertz transmission spectra with five similar spectral lines. The average recognition accuracy is 96.56%. Compared with other methods, the recognition accuracy is significantly improved. Dataset-4 as a collection of transmission spectral data sets for dataset-1, dataset-2, and dataset-3 has an average recognition accuracy of 98.87%. It is verified that the BLSTM-RNN model can automatically extract effective terahertz spectral characteristics and meanwhile ensure the prediction accuracy of complex terahertz spectra. In the selection of model training optimization algorithm, the Adam optimization algorithm is better than the RMSProp, SGD and AdaGrad optimization algorithms, and the target function loss value of the model has the fastest convergence rate. At the same time, as the number of training iterations increases, the prediction accuracy of similar terahertz transmission spectral datasets also increases. The proposed method can provide a new identification method for spectral recognition retrieval of complex terahertz spectral databases.
|
Received: 2018-10-22
Accepted: 2019-02-15
|
|
Corresponding Authors:
SHEN Tao
E-mail: shentao@kmust.edu.cn
|
|
[1] Choi K, Hong T, Sim K I, et al. Journal of Applied Physics, 2014, 115(2): 023105.
[2] Qin J, Xie L, Ying Y. Analytical Chemistry, 2014, 86(23): 11750.
[3] Baek S H, Lim H B, Chun H S. Journal of Agricultural & Food Chemistry, 2014, 62(24): 5403.
[4] Yan L, Liu C, Qu H, et al. Journal of Infrared Millimeter & Terahertz Waves, 2018, 39(5): 492.
[5] Xu W, Xie L, Ye Z, et al. Sci. Rep., 2015, 5: 11115.
[6] Zhan H, Xi J, Zhao K, et al. Food Control, 2016, 67: 114.
[7] Gavenda T, Křesálek V. Millimetre Wave and Terahertz Sensors and Technology Ⅵ. International Society for Optics and Photonics, 2013, 8900: 89000H.
[8] JIN Wu-jun, LI Jun(金武军, 李 军). Science China Physics, Mechanics & Astronomy(中国科学: 物理学 力学 天文学), 2015, 45(8): 84207.
[9] Lian F, Xu D, Fu M, et al. IEEE Transactions on Terahertz Science & Technology, 2017, 7(4): 378.
[10] NI Jia-peng, SHEN Tao, ZHU Yan, et al(倪家鹏, 沈 韬, 朱 艳, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2017, 37(8): 2360.
[11] Graves A, Jaitly N, Mohamed A R. Automatic Speech Recognition and Understanding. IEEE, 2013: 273.
[12] Yao Y S, Huang Z. arXiv: 1602. 04874v1[cs. LG], 2016.
[13] Ma X, Hovy E. arXiv: 1603. 01354, 2016.
[14] Kingma D P, Ba J. arXiv: 1412. 6980, 2014.
[15] Srivastava N, Hinton G, Krizhevsky A, et al. Journal of Machine Learning Research, 2014, 15(1): 1929. |
[1] |
YU Yang1, ZHANG Zhao-hui1, 2*, ZHAO Xiao-yan1, ZHANG Tian-yao1, LI Ying1, LI Xing-yue1, WU Xian-hao1. Effects of Concave Surface Morphology on the Terahertz Transmission Spectra[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(09): 2843-2848. |
[2] |
CHU Zhi-hong1, 2, ZHANG Yi-zhu2, QU Qiu-hong3, ZHAO Jin-wu1, 2, HE Ming-xia1, 2*. Terahertz Spectral Imaging With High Spatial Resolution and High
Visibility[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(02): 356-362. |
[3] |
LU Xue-jing1, 2, GE Hong-yi2, 3, JIANG Yu-ying2, 3, ZHANG Yuan3*. Application Progress of Terahertz Technology in Agriculture Detection[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(11): 3330-3335. |
[4] |
TANG Xin, ZHOU Sheng-ling*, ZHU Shi-ping*, MA Ling-kai, ZHENG Quan, PU Jing. Analysis and Identification of Terahertz Tartaric Acid Spectral
Characteristic Region Based on Density Functional Theory and
Bootstrapping Soft Shrinkage Method[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2740-2745. |
[5] |
LI Yan1, LIU Qi-hang2, 3, HUANG Wei1, DUAN Tao1, CHEN Zhao-xia1, HE Ming-xia2, 3, XIONG Yu1*. Terahertz Imaging Study of Dentin Caries[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(08): 2374-2379. |
[6] |
CHEN Yan-ling, CHENG Liang-lun*, WU Heng*, XU Li-min, HE Wei-jian, LI Feng. A Method of Terahertz Spectrum Material Identification Based on Wavelet Coefficient Graph[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(12): 3665-3670. |
[7] |
LIU Yan-de, XU Zhen, HU Jun, LI Mao-peng, CUI Hui-zhen. Research on Variety Identification of Fritillaria Based on Terahertz Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(11): 3357-3362. |
[8] |
WANG Wen-ai, LIU Wei*. Terahertz Spectroscopy Characteristics of Sugar Compounds[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(08): 2391-2396. |
[9] |
LU Shi-yang1, 2, ZHANG Lei-lei1, 2, PAN Jia-rong1, 2, YANG De-hong1, 2, SUI Ya-nan1, 2, ZHU Cheng1, 2*. Study on the Indetification of the Geographical Origin of Cherries Using Raman Spectroscopy and LSTM[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(04): 1177-1181. |
[10] |
MIAO Xin-yang1,2,3, LIU Xue-cong1,3, CHEN Meng-xi3, CHEN Si-tong3, ZHANG Shan-zhe1, LU Wan-ting3, PENG Xue3, ZHAN Hong-lei2,3, ZHU Ming-da1, ZHAO Kun1,2,3*. Terahertz Spectral Characteristics of Rocks With Different Lithologies[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(04): 1314-1319. |
[11] |
ZHU Rong-sheng1, 2, SHEN Tao1, 2*, LIU Ying-li1, 2, ZHU Yan1, 2, CUI Xiang-wei1, 2. Wasserstein GAN for the Classification of Unbalanced THz Database[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(02): 425-429. |
[12] |
College of Information Science and Technology, Nanjing Forestry University, Nanjing 210037, China
. Investigation on Terahertz Spectroscopy of Food Additives Based on Dispersion-Correction Functional Theory[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(01): 100-104. |
[13] |
SONG Xue-yan1, LI Yan1, XIA Qi-ying2*, JU Xue-hai1*. Theoretical Study on Terahertz Spectra of TKX-50[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(10): 3056-3060. |
[14] |
HU Yin, WANG Min-chang, PAN Qing, NING Yan-li, KANG Ying, WANG Ming, LUAN Jie-yu, CHEN Zhi-qun. Spectroscopic Analysis of Endo and Exo-Tetrahydrodicyclopentadiene[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(10): 3161-3166. |
[15] |
LU Mei-hong1, GONG Peng2, ZHANG Fan1, WANG Zhi-jun1, FENG Duo1,MENG Tian-hua3. Terahertz and Raman Spectra of EDTA-2Na[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(09): 2707-2712. |
|
|
|
|