|
|
|
|
|
|
| An Improved WGAN-GP Generative Adversarial Model in View of NIR Spectral 1st Derivative Constraint |
| LI Zhen-yu1, ZHAO Peng1, 2* |
1. College of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, China
2. School of Computer Science and Software Engineering, Guangxi University of Science and Technology, Liuzhou 545006, China
|
|
|
|
|
Abstract The Generative Adversarial Network (GAN) has recently become a hot branch in deep neural networks. The mainstream GAN model consists of many improved versions used in image processing and computer vision. These GAN versions are rarely used in spectral analysis. In spectral analysis, they are mainly used to generate synthetic spectral curves so as to extend the classifier's training set for its augmentation and improve its classification performance. Because of the trend of 1D near infrared (NIR) spectral curve, which is an important classification feature and can be quantitatively denoted by a curve derivation, we improve the current one-class Wasserstein GAN with Gradient Penalty (WGAN-GP) model by imposing a spectral 1st derivative constraint. Specifically, the original NIR spectral vector is connected with the corresponding spectral derivative vector in the revised model L loss function. The concatenated vector is used for model training and spectral curve production. Finally, only the first half is retained in the artificially produced spectral vector to generate the synthetic spectral curves. In our NIR classification experiments of wood species and apple classes, the classification accuracy in some classifiers such as Support Vector Machine (SVM), 1D-Convolutional Neural Network (1D-CNN) and LeNet-5 neural network is increased to some extents after the training set augmentation by use of our improved WGAN-GP model compared with that by use of original WGAN-GP model. Moreover, the NIR spectral curve quality produced by our improved WGAN-GP model has increased greatly, which is indicated by some evaluation measures such as Inception Score, which is computed by use of 1D-CNN instead of the original 2D Inception Net-V3 network, the correlation coefficient between original and synthetic spectral vectors, and these two vectors' difference L1 and L2 norms,compared with that by use of the original WGAN-GP model.
|
|
Received: 2025-01-02
Accepted: 2025-02-25
|
|
|
|
Corresponding Authors:
ZHAO Peng
E-mail: bit_zhao@aliyun.com; 595388114@qq.com
|
|
[1] Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative Adversarial Nets, Part of Advances in Neural Information Processing Systems 27 (NIPS 2014), 2014.
[2] Kingma D P, Welling M. Auto-Encoding Variational Bayes, 2013, arXiv: 1312. 6114.
[3] Arjovsky M, Chintala S, Bottou L. Wasserstein GAN, 2017, arXiv: 1701. 07875v3.
[4] Berthelot D, Schumm T, Metz L. BEGAN: Boundary Equilibrium Generative Adversariul Networks, 2017, arXiv: 1703. 10717.
[5] Radford A, Metz L, Chintala S. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks, arXiv: 1511: 06434v2.
[6] Odena A, Olah C, Shlens J. Conditional Image Synthesis with Auxiliary Classifier GANs, 2017, arXiv, 1610. 09585v4.
[7] Wu M, Wang S, Pan S, et al. Scientific Reports, 2021, 11: 23842.
[8] Mishra P, Herrmann I. Chemometrics and Intelligent Laboratory Systems, 2021, 215: 104362.
[9] McHardy R G, Antoniou G, Conn J J A, et al. Analyst, 2023, 148: 3860.
[10] WANG Zhi-hui, DING Li-xia（王志辉，丁丽霞）. Spectroscopy and Spectral Analysis（光谱学与光谱分析）, 2010, 30(7): 1825.
[11] Gulrajani I, Ahmed F, Arjovsky M, et al. Improved Training of Wasserstein GANs, Proceedings of 31st International Conference on Neural Information Processing Systems, 2017, 5769.
[12] Salimans T, Goodfellow I, Zaremba W, et al. Improved Techniques for Training GANs, 30th Conference on Neural Information Processing Systems (NIPS 2016), 2016, 2226.
|
| [1] |
WANG Xiao-min1, GAO Jun-ping1*, PU Yuan2*, QIU Bo1*, ZHANG Jian-nan3, YAN Jing1, LI Rong1. The “Unknown” Spectral Classification Study of LAMOST:
ODS-YOLOv7 Model[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(07): 1960-1967. |
| [2] |
LI Hao1, ZHAO Qing1*, CUI Chen-zhou2, FAN Dong-wei2, ZHANG Cheng-kui1, SHI Yan-cui1, WANG Yuan1. A Stellar Spectrum Classification Algorithm Based on CNN and LSTM Composite Deep Learning Model[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(06): 1668-1675. |
| [3] |
MENG Xing-zhi, LIU Ya-qiu*, LIU Li-na. Raman Spectroscopy Combined With the WGANGP-ResNet Algorithm to Identify Pathogenic Species[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(02): 542-547. |
| [4] |
WU Chao1, QIU Bo1*, PAN Zhi-ren1, LI Xiao-tong1, WANG Lin-qian1, CAO Guan-long1, KONG Xiao2. Application of Spectral and Metering Data Fusion Algorithm in Variable Star Classification[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(06): 1869-1874. |
| [5] |
LI Shuang-chuan, TU Liang-ping*, LI Xin, WANG Li-li. Besvm: A-Type Star Spectral Subtype Classification Algorithm Based on Transformer Feature Extraction[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(05): 1575-1581. |
| [6] |
LU Ya-kun1, QIU Bo1*, LUO A-li2, GUO Xiao-yu1, WANG Lin-qian1, CAO Guan-long1, BAI Zhong-rui2, CHEN Jian-jun2. Classification of 2D Stellar Spectra Based on FFCNN[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(06): 1881-1885. |
| [7] |
WANG Tao1, 2, LIU Jian-xun2, GE Xiao-tian2, WANG Rong-xin2, SUN Qian2, NING Ji-qiang2*, ZHENG Chang-cheng3*. Fine Photoluminescence Spectroscopic Characterization of Interfacial Effects on Emission Properties of InGaN/GaN Multiple Quantum Wells in a Blue-Light Laser Diode Structure[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(04): 1179-1185. |
| [8] |
LIU Zhong-bao1, WANG Jie2*. Research on the Improvement of Spectra Classification Performance With the High-Performance Hybrid Deep Learning Network[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(03): 699-703. |
| [9] |
LI Ling-qiao1,2, LI Yan-hui2, YIN Lin-lin4, YANG Hui-hua1,2*, FENG Yan-chun3, YIN Li-hui3, HU Chang-qin3. Data Augmentation of Raman Spectral and Its Application Research Based on DCGAN[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(02): 400-407. |
| [10] |
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. |
| [11] |
HE Jin-xin1, REN Xiao-yu1, CHEN Sheng-bo2*, XIONG Yue1, XIAO Zhi-qiang1, ZHOU Hai1. Automatic Classification of Rock Spectral Features Based on Fusion Learning Model[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(01): 141-144. |
| [12] |
CHEN Ying1，XU Yang-mei1, DI Yuan-jian1，CUI Xing-ning1，ZHANG Jie1，ZHOU Xin-de1，XIAO Chun-yan2， LI Shao-hua3. COD Concentration Prediction Model Based on Multi-Spectral Data Fusion and GANs Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(01): 188-193. |
| [13] |
CAO Jie-hua1, 2, TIAN Ming1, 2, LIN Tao1, 2*, FENG Zhe-chuan1, 2. Investigation of Carrier Recombination Dynamics of Light-Emitting Diode Based on InGaN Quantum Dots[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(09): 2727-2731. |
| [14] |
JIANG Bin, ZHAO Zi-liang, WANG Shu-ting, WEI Ji-yu, QU Mei-xia*. Decomposition and Classification of Stellar Spectra Based on t-SNE[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(09): 2913-2917. |
| [15] |
ZHANG Xiao1，2, LUO A-li1*. XGBOOST Based Stellar Spectral Classification and Quantized Feature[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2019, 39(10): 3292-3296. |
|
|
|
|
