|
|
|
|
|
|
| Research on Fast ICA Blind Separation Algorithm of Mixed Hyperspectral and Influencing Factors |
| DAI Jia-le, WANG Jin-hua*, LI Meng-qian, HAN Xiu-li, MIAO Ruo-fan |
College of Mining Engineering, North China University of Science and Techonlogy，Tangshan 063210，China
|
|
|
|
|
Abstract Hyperspectral analysis of mixtures is a key technology for nondestructive testing of minerals. The spectral reflectance variation of mixtures in the 350 nm to 2 500 nm interval is regarded as a one-dimensional sequence signal with time-domain variation, and the mixture spectral separation is transformed into a blind source separation problem of time-domain signals in the paper. In order to analyze the influencing factors of the speed and accuracy of mixture spectral demixing, a blind source demixing test was conducted on the measured hyperspectral reflectance curve of the mixture using Fast ICA mathematical model, and the results of spectral demixing were analyzed from three aspects of the demixing process: the whitening mode, the initial power array, and the Gaussianity of the source spectrum, which provided a research basis for the later analysis of the mixture spectral detection. The chemically pure copper oxide and cuprous oxide mixtures, alkaline copper carbonate and copper hydroxide mixtures were selected as test objects. The source spectral Gaussianity was compared with the g-function, ZCA and PCA whitening methods, and three initial weights of unitary, random and specified weights on the unmixing spectral results using the unmixing performance index PI, the root mean square error of the spectrum and the angular distance of the spectrum as evaluation indexes. The experimental results show that the Fast ICA algorithm can effectively separate the mixture component source spectra based on unknown hyperspectral a priori information of mixed minerals. The sample separation accuracy PI values are all less than 0.18, and the effect of spectral blind source unmixing is remarkable. The spectral curves after unmixing are consistent with the source spectral curves in terms of characteristic trends, with the same absorption positions and characteristic peaks, but there are certain scale differences. In addition, the Gaussianity of the source spectrum and the selection of the unmixing g function directly affect the value of the unmixing results, and the separation accuracy of the sub-Gaussian interval curve is better than that of the super-Gaussian part. The absorption characteristics of the segmental demixing results based on Gaussianity are prominent, and the difference with the reflectance values of the source spectra increases; the whitening method of spectral preprocessing has a small impact on the accuracy of the demixing results, and the separation accuracy and spectral accuracy of the demixing results are slightly higher after ZCA whitening than PCA whitening; the comparison of the demixing results of the three initial weights of the Fast ICA model shows that the initial iterations with In the comparison of the three initial weights of the Fast ICA model, it was found that the separation accuracy, demixing accuracy and demixing time were the best and the demixing process was easier to converge when the specified weights calculated by the first iteration were used for the iterative demixing. The results show that the g-function is selected according to the full-band Gaussian performance to demix the best. The separation index PI is less than 0.14, the spectral angular distance is about 0.1, ZCA whitening has less effect on the demixing spectrum than PCA whitening, the separation index of the two groups of mixtures after ZCA whitening is about 0.1, and the separation index PI of PCA whitening is higher than 0.13 when the designation right is used as the initial weight, it helps to improve the convergence speed in the Newton iteration, so that the unmixing spectrum is closer to the known spectrum of the components, the unmixing time of the specified weight is less than 0.2 seconds, and the other two weighting methods are more than 0.3 seconds.
|
|
Received: 2022-12-19
Accepted: 2023-01-30
|
|
|
|
Corresponding Authors:
WANG Jin-hua
E-mail: jinhua66688@126.com
|
|
[1] CHENG Gong-wei, ZHAO Si-ying, NI Cai-ying(陈功伟, 赵思颖, 倪才英). Journal of University of Chinese Academy of Sciences(中国科学院大学学报) , 2019, 36(4): 560.
[2] YAN Shou-xun, ZHANG Bing, ZHAO Yong-chao, et al(燕守勋, 张 兵, 赵永超, 等). Remote Sensing Technology and Application(遥感技术与应用) , 2004，(1): 52.
[3] YANG Xiao-li, WAN Xiao-xia(杨晓莉, 万晓霞). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2017, 37(7): 2158.
[4] Pece Sherovski，Goran Stojkovic，Natasha Ristovska. Analytical Biochemistry, 2018, 558: 35.
[5] WU Bing, WANG Jin-hua, ZHANG Bo, et al(吴 兵, 汪金花, 张 博, 等). Journal of Materials Science & Engineering(材料科学与工程学报), 2021, 39(5): 814.
[6] ZHAN Xian-da, BAO Zheng(张贤达, 保 铮). Acta Electronica Sinica(电子学报)，2001，(S1): 1766.
[7] ZHAO Chun-hui, CUI Shi-ling, ZHAO Gen-ping(赵春晖, 崔士玲, 赵艮平). Journal of Harbin Engineering University(哈尔滨工程大学学报), 2015, 36(9): 1281.
[8] LIN Na, YANG Wu-nian, WANG Bin（林 娜, 杨武年, 王 斌）. Geomatics and Information Science of Wuhan University(武汉大学学报信息科学版) , 2017, 42(3): 355.
[9] YANG Lei, WANG Hui-qin, WANG Ke, et al(杨 蕾, 王慧琴, 王 可, 等). Acta Optica Sinica(光学学报), 2020, 40(5): 0530001.
[10] WU Wei, ZHANG Fan, ZHOU Zhi-jun, et al（吴 微, 张 帆, 周志军, 等）. Journal of Information Engineering University(信息工程大学学报), 2016, 17(6): 681.
[11] SUN Ting-ting, CUI Shao-hua（孙婷婷, 崔少华）. Journal of Hebei Normal University(Natural Science）[河北师范大学学报(自然科学版)], 2020，(3)：209.
[12] JIANG Xi-ping, YU Han-wen, WU Fang, et al（蒋夕平, 于瀚文, 吴 芳, 等）. Journal of Basic Science and Engineering(应用基础与工程科学学报), 2015, 23(5): 992.
[13] Raghavendra Sharma. Materials Today: Proceedings, 2020，29(Part 2): 536.
[14] GAN Yu-quan, LIU Wei-hua, FENG Xiang-peng, et al(甘玉泉, 刘伟华, 冯向朋, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2019, 39(4): 1118.
[15] Palsson B, Sigurdsson J, Sveinsson J R, et al. IEEE Access, 2018, 6: 25646.
|
| [1] |
WANG Lei1, 2, QIN Hong1,2*, LI Jing3, ZHANG Xiao-bo3, YU Li-na1, 2, LI Wei-jun1, 2, HUANG Lu-qi4*. Geographical Origin Identification of Lycium Barbarum Using Near-Infrared Hyperspectral Imaging[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(04): 1270-1275. |
| [2] |
YANG Hui-hua1, 2, LUO Zhi-chao1, JIANG Shu-jie1, ZHANG Xue-bo3, YIN Li-hui3 . Sparse Denoising Autoencoder Application in Identification of Counterfeit Pharmaceutical [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2016, 36(09): 2774-2779. |
| [3] |
HUANG Jun1, ZHAI Hua-min1*, WANG Xiao-jun2 . Synthesis and Spectroscopic Study of Polyamine-Type Cellulose-Based Chelating Fiber [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2010, 30(06): 1606-1609. |
|
|
|
|
