Prediction Method of Wool Content in Waste Spinning Samples Based on Semi Supervised Regression of Generative Adversarial Network
HU Jin-quan1, 2, YANG Hui-hua1, ZHAO Guo-liang3, ZHOU Rui-zhi4, LI Ling-qiao5
1. School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China
2. School of Electronic Engineering and Automation Chemistry, Guilin University of Electronic Technology, Guilin 541004, China
3. Beijing Institure of Fashion Technology，Beijing 100029, China
4. Shanghai Jicai Environmental Protection Technology Co., Ltd., Shanghai 200131, China
5. School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin 541004, China
Abstract：In this paper, a semi-supervised regression method based on a Generative adversarial network is proposed to meet the demand for online sorting for waste textile recycling, which uses some labeled samples and a large number of unlabeled samples to train the semi-supervised regression. The semi-supervised regression consists of a generator composed of neural networks and a discriminator composed of neural networks. The generator generates a mixed sample that is as close as possible to the actual labeled and unlabeled training dataset content. The discriminator is used to validate the samples generated by the generator and predict the continuous labeling of these samples. The generated network is trained through feature matching loss, which is the average error between the output of the actual sample in the middle layer of the discriminator and the generated sample. The discriminant has two outputs, one for predicting sequence markers and the other for determining the probability of whether the generated sample is a true or false sample. Train discriminants by using a combination of traditional unsupervised generative adversarial network loss functions and supervised regression losses. The generated network is trained through feature matching loss, which is the average error between the output of the actual sample in the middle layer of the discriminator and the generated sample. We have collected 400 blended samples with different wool contents and 3 000 blended samples with unknown components. 70% of labeled and unlabeled mixed samples were randomly selected as the training set, while the remaining 30% of labeled samples were used as the test set for repeated experiments. This article has conducted multiple experiments for verification. The first experiment is a blended spectrum generation experiment, which is used to verify that the generative adversarial network can effectively generate mixed sample spectra based on intrinsic laws. The second experiment is a semi-supervised adversarial network quantitative analysis performance comparison experiment, which trains and tests the wool composition analysis model, and compares the performance of this semi-supervised adversarial network quantitative analysis model with other quantitative models. The third experiment is a prediction and comparison experiment of on-site high wool content blended yarn segmentation models. Composition analysis is conducted on blended yarn samples with wool content between 80% and 99%, and the performance of this semi-supervised adversarial network quantitative analysis model is compared with that of other quantitative models. The fourth is a field prediction experiment for the subdivision comprehensive model of medium to high wool content blended fabrics. A semi-supervised adversarial network quantitative analysis model is trained using blended fabric samples with wool content between 40% and 99% and deployed in the sorting system. The operator conducts on-site testing data for accuracy, analysis time, and other tests. The experimental results show that the semi-supervised regression method based on a Generative adversarial network is superior to PCR，PLSR, SVR, BPNN and other models, and the prediction R2 of this model reaches 0.94. After repeated on-site testing, the model can quickly extract blended samples with a wool content of over 40%.
胡锦泉，杨辉华，赵国樑，周瑞知，李灵巧. 一种生成对抗网络半监督回归的废纺样品中羊毛含量的预测方法[J]. 光谱学与光谱分析, 2024, 44(05): 1417-1424.
HU Jin-quan, YANG Hui-hua, ZHAO Guo-liang, ZHOU Rui-zhi, LI Ling-qiao. Prediction Method of Wool Content in Waste Spinning Samples Based on Semi Supervised Regression of Generative Adversarial Network. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(05): 1417-1424.
[1] ZHANG Guo-li, WANG Wu(张国丽, 王 武). Chinese Journal of Sensors and Actuators(传感技术学报), 2021, 34(12): 1651.
[2] TIAN Ling-ling(田玲玲). China Fiber Inspection(中国纤检), 2022, (6): 68.
[3] DU Wen-qian, DU Yu-jun, ZHENG Jia-hui, et al(杜文倩, 杜宇君, 郑佳辉, 等). Journal of Beijing Institute of Clothing Technology (Natural Science Edition)[北京服装学院学报(自然科学版)], 2021, 41(3): 29.
[4] ZHENG Jia-hui, DU Yu-jun, LI Wen-xia, et al(郑佳辉, 杜宇君, 李文霞, 等). Journal of Instrumental Analysis(分析测试学报), 2020, 39(11): 1365.
[5] SHI Yao, LI Wen-xia, ZHAO Guo-liang, et al(时 瑶，李文霞，赵国梁，等). Journal of Instrumental Analysis(分析测试学报), 2016, 35(11): 1390.
[6] Shi Y, Li Q，Zhu X X. IEEE Geoscience and Remote Sensing Letters, 2019，16(4)：603.
[7] Alsharay N M, Dobre O A, Chen Y. IEEE Sensors Letters, 2023, 7(4)：6002004.
[8] Ullah I，Mahmoud Q H. IEEE Access, 2021, 9: 165907.
[9] Kim H, Kim J. Infrared Image Colorization Network Using Variational Auto Encode. 2021 36th International Conference on Circuits/Systems, Computers and Communications (ITC-CSCC), 2021.
[10] Skotere T, Nilsson D, Xiong S J. Analytical Chemistry, 2019, 91(5): 3516.
[11] LI Ling-qiao, LI Yan-hui, YIN Lin-lin, et al(李灵巧, 李彦晖, 殷琳琳, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2021, 41(2): 400.
[12] Zheng A B, Yang H H, Pan X P, et al. IEEE Access, 2021, 9: 3195.
[13] SIliyasu A，Deng H. IEEE Access, 2020, 8：118.
[14] Davi C，Braga-Neto U. A Semi-Supervised Generative Adversarial Network for Prediction of Genetic Disease Outcomes, 2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP), Gold Coast, Australia, 2021.
[15] Min C, Li Y, Fang L, et al. Conditional Generative Adversarial Network on Semi-Supervised Learning Task, 2019 IEEE 5th International Conference on Computer and Communications (ICCC), Chengdu, China, 2019, 1448.
[16] Meng D, Wu B, Liu N. Semi-Supervised Deep Learning Seismic Impedance Inversion Using Generative Adversarial Networks, IGARSS 2020—2020 IEEE International Geoscience and Remote Sensing Symposium, Waikoloa, HI, USA, 2020, 1393.
