|
|
Optoelectronics 2024
利用对抗自编码器生成具有分析物属性信息的近红外光谱样本来增强近红外高斯过程回归模型
|
Abstract:
通过在近红外光谱校正模型中添加人工生成的光谱样本，是增强近红外校正模型预测效果的一种有效方法，尤其对于建模样本数不足的情况。本文提出一种基于对抗自编码器(Adversarial Autoencoder, AAE)的近红外光谱样本生成方法，并将利用该方法生成的光谱样本补充到近红外高斯过程回归建模集中，以增强模型的预测效果。该方法基于AAE模型，利用编码网络将光谱的低维特征分布映射成某种先验分布，利用解码网络将先验分布中的样本点重构成近红外光谱。因此，本文利用AAE模型成功的从三个典型的近红外光谱数据集中生成光谱，然后将这些生成的光谱应用到高斯过程回归模型中。实验结果显示，所提方法能够有效的生成与建模集同分布的近红外光谱样本，并提高高斯过程回归的预测性能。由此总结，AAE有潜力生成衍生同源光谱，并在一些小样本集中扩增光谱数量。
Adding artificially generated spectral samples to near-infrared spectral correction models is an effective method to enhance the prediction effect of near-infrared spectral correction models, especially when the number of modeling samples is insufficient. In this paper, a method of generating near-infrared spectral samples based on Adversarial Autoencoder (AAE) is proposed, and the spectral samples generated by this method are added to the near-infrared Gaussian process regression modeling set to enhance the prediction effect of the model. This method is based on AAE model, using the coding network to map the low-dimensional feature distribution of the spectrum to some prior distribution, using the decoding network to reconstruct the sample points in the prior distribution to form the NIR spectrum. Therefore, this paper successfully generates spectra from three typical NIR spectral datasets using AAE model, and then applies these generated spectra to Gaussian process regression models. Experimental results show that the proposed method can effectively generate NIR spectral samples with the same distribution as the modeling set, and improve the prediction performance of Gaussian process regression. In conclusion, AAE has the potential to generate derived homologous spectra and amplify spectral numbers in some small sample sets.
| [1] | Le, B.T. (2020) Application of Deep Learning and near Infrared Spectroscopy in Cereal Analysis. Vibrational Spectroscopy, 106, Article 103009. https://doi.org/10.1016/j.vibspec.2019.103009 |
| [2] | Qu, J., Liu, D., Cheng, J., Sun, D., Ma, J., Pu, H., et al. (2015) Applications of Near-Infrared Spectroscopy in Food Safety Evaluation and Control: A Review of Recent Research Advances. Critical Reviews in Food Science and Nutrition, 55, 1939-1954. https://doi.org/10.1080/10408398.2013.871693 |
| [3] | Li, R., Liu, Y., Xia, Z., Wang, Q., Liu, X. and Gong, Z. (2023) Discriminating Geographical Origins and Determining Active Substances of Water Caltrop Shells through Near-Infrared Spectroscopy and Chemometrics. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 303, Article 123198. https://doi.org/10.1016/j.saa.2023.123198 |
| [4] | N？rgaard, L., Saudland, A., Wagner, J., Nielsen, J.P., Munck, L. and Engelsen, S.B. (2000) Interval Partial Least-Squares Regression (ipls): A Comparative Chemometric Study with an Example from Near-Infrared Spectroscopy. Applied Spectroscopy, 54, 413-419. https://doi.org/10.1366/0003702001949500 |
| [5] | Pumarola, A., Agudo, A., Martinez, A.M, et al. (2018) Ganimation: Anatomically-Aware Facial Animation from a Single Image. Proceedings of the European Conference on Computer Vision (ECCV), Munich, 8-14 September 2018, 818-833. https://doi.org/10.1007/978-3-030-01249-6_50 |
| [6] | Chen, R.T., Rubanova, Y., Bettencourt, J., et al. (2018) Neural Ordinary Differential Equations. https://doi.org/10.48550/arXiv.1806.07366 |
| [7] | Brock, A., Donahue, J. and Simonyan, K. (2018) Large Scale GAN Training for High Fidelity Natural Image Synthesis. arXiv preprint arXiv: 1809.11096. https://doi.org/10.48550/arXiv.1809.11096 |
| [8] | Salzer, R. (2008) Practical Guide to Interpretive Near-Infrared Spectroscopy. Wiley Online Library. https://doi.org/10.1201/9781420018318 |
| [9] | Xiang, B.R., Li, R., Wu, Y.J., et al. (1999) Applications of Near-Infrared Spectroscopy in Pharmaceutical Analysis. Computers and Applied Chemistry, 16, 327-328. |
| [10] | Creswell, A., White, T., Dumoulin, V., Arulkumaran, K., Sengupta, B. and Bharath, A.A. (2018) Generative Adversarial Networks: An Overview. IEEE Signal Processing Magazine, 35, 53-65. https://doi.org/10.1109/msp.2017.2765202 |
| [11] | Xie, Q., Dai, Z., Hovy, E., et al. (2020) Unsupervised Data Augmentation for Consistency Training. Advances in Neural Information Processing Systems, 33, 6256-6268. |
| [12] | Arjovsky, M., Chintala, S. and Bottou, L. (2017) Wasserstein Generative Adversarial Networks. PMLR, 70, 214-223. |
| [13] | Zhong, Z., Zheng, L., Zheng, Z., Li, S. and Yang, Y. (2018) Camera Style Adaptation for Person Re-identification. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 5157-5166. https://doi.org/10.1109/cvpr.2018.00541 |
| [14] | Yu, L., Zhang, W., Wang, J. and Yu, Y. (2017) Seqgan: Sequence Generative Adversarial Nets with Policy Gradient. Proceedings of the AAAI Conference on Artificial Intelligence, 31. https://doi.org/10.1609/aaai.v31i1.10804 |
| [15] | Frid-Adar, M., Klang, E., Amitai, M., Goldberger, J. and Greenspan, H. (2018) Synthetic Data Augmentation Using GAN for Improved Liver Lesion Classification. 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Washington, 4-7 April 2018, 289-293. https://doi.org/10.1109/isbi.2018.8363576 |
| [16] | Teng, G.E., Wang, Q.Q., Kong, J.L., Dong, L.Q., Cui, X.T., Liu, W.W., et al. (2019) Extending the Spectral Database of Laser-Induced Breakdown Spectroscopy with Generative Adversarial Nets. Optics Express, 27, Article 6958. https://doi.org/10.1364/oe.27.006958 |
| [17] | Zhu, D., Xu, L., Chen, X., Yuan, L., Huang, G., Li, L., et al. (2020) Synthetic Spectra Generated by Boundary Equilibrium Generative Adversarial Networks and Their Applications with Consensus Algorithms. Optics Express, 28, Article 17196. https://doi.org/10.1364/oe.390070 |
| [18] | Makhzani, A., Shlens, J., Jaitly, N., et al. (2015) Adversarial Autoencoders. arXiv preprint arXiv: 1511.05644. https://doi.org/10.48550/arXiv.1511.05644. |
| [19] | SEEGER, M. (2004) Gaussian Processes For Machine Learning. International Journal of Neural Systems, 14, 69-106. https://doi.org/10.1142/s0129065704001899 |
| [20] | Huang, G., Ruan, X., Chen, X., Lin, D. and Liu, W. (2014) A Segmented PLS Method Based on Genetic Algorithm. Analytical Methods, 6, Article 2900. https://doi.org/10.1039/c3ay41765d |
| [21] | Nikzad-Langerodi, R., Zellinger, W., Lughofer, E. and Saminger-Platz, S. (2018) Domain-Invariant Partial-Least-Squares Regression. Analytical Chemistry, 90, 6693-6701. https://doi.org/10.1021/acs.analchem.8b00498 |
