|
|
|
|
|
|
Regression Prediction of Photometric Redshift Based on Particle Warm Optimization Neural Network Algorithm |
MU Yong-huan1, QIU Bo1*, WEI Shi-ya1, SONG Tao1, ZHENG Zi-peng1, GUO Ping2* |
1. School of Electronics and Information Engineering, Hebei University of Technology, Tianjin 300400, China
2. School of Systems Science of Beijing Normal University, Beijing 100875, China |
|
|
Abstract In addition to the spectral redshift of galaxies, the prediction of galaxies redshift has important research significance for studying the large-scale structure and evolution of the universe. In this paper, we use the metering and spectral data of 150 000 galaxies of SDSS DR13 released by the Sloan Sky Survey project to analyze the galaxies according to the color characteristics and clustering methods. The classification results show that the early galaxies account for a large proportion. In this paper, three different machine learning algorithms are compared to measure the redshift regression prediction of early galaxies and find the optimal method. In the experiment, the photometric values of the galaxy samples u, g, r, i, z and the 10 color features obtained by the difference between the two bands are used as input data. First, the BP network is constructed, and the BP algorithm is used to measure the galaxies redshift. Then the Genetic Algorithm (GA) is used to optimize the parameters of the BP network, and the optimized GA-BP algorithm is applied to the regression prediction experiment of the early galaxies; considering the complex operation of the GA algorithm will affect the prediction efficiency. Moreover, the Particle Swarm Optimization algorithm not only has high stability and simple operation, so the Particle Swarm Optimization algorithm is used to optimize the BP network (PSO-BP) and Particle Swarm Optimization is used to optimize BP network (PSO-BP). By adjusting the weight method to improve the prediction efficiency and increase the stability, the particle swarm optimization algorithm is used to predict the redshift of the early galaxies in the galaxy samples. In the experiment, the spectral redshift is taken as the expected value, and the mean square error (MSE) is used as the error analysis index to judge the accuracy of the three algorithms. The PSO-BP regression prediction results are compared with the BP network model and the GA-BP network model. The experimental results show that the MSE value of the BP network is 0.001 92, the MSE value of the GA-BP network is 0.001 728, and the MSE value of the PSO-BP network is 0.001 708. The experimental results show that the PSO-BP optimization model used in this paper is superior to the BP neural network model and the GA-BP neural network model in terms of accuracy, which is respectively improved by 11.1% and 1.2%. It is superior to the traditional K-nearest neighbor test in efficiency, which overcomes the shortcomings of traversing all data samples in KNN algorithm and its generalization performance is better than that of other BP network optimization models.
|
Received: 2018-07-19
Accepted: 2018-11-25
|
|
Corresponding Authors:
QIU Bo, GUO Ping
E-mail: qiubo@hebut.edu.cn; pguo@bnu.edu.cn
|
|
[1] Cohen S H, Kim H, Petty S M, et al. Pixel-by-Pixel SED Fitting of Intermediate Redshift Galaxies (C), 2015. 225.
[2] Kügler S D, Gianniotis N, Kai L P. A Spectral Model for Multimodal Redshift Estimation (C). Computational Intelligence, IEEE Xplore, 2016. 1.
[3] Zheng H, Zhang Y. Review of Techniques for Photometric Redshift Estimation. International Society for Optics and Photonics, Software and Cyberinfrastructure for Astronomy Ⅱ, 2012. 8451.
[4] Franco D Albareti, Carlos Allende Prieto, Andres Almeida, et al. The Astrophysical Journal Supplement Series, 2017, 233(2): 25.
[5] Robert Beck, Laszl Dobos, Tamas Budavari, et al. Monthly Notices of the Royal Astronomical Society, 2016, 460(2): 1371.
[6] Almosallam I A, Jarvis M J, Roberts S J. Monthly Notices of the Royal Astronomical Society, 2016, 462(1): 726.
[7] Cavuoti S, Amaro V, Brescia M, et al. Monthly Notices of the Royal Astronomical Society, 2017, 465(2): 1959.
[8] Shaun Cole, Steve Hatton, David H Weinberg, et al. Monthly Notices of the Royal Astronomical Society, 2013, 300(4): 945.
[9] Beck R, Dobos L, Budavári T, et al. Monthly Notices of the Royal Astronomical Society, 2016, 460(2): 1371.
[10] Kadim Ta瘙塂demir, Pavel Milenov, Brooke Tapsall. Computers & Electronics in Agriculture, 2012, 79(1): 92.
[11] Yao H Q, Jiang Y L. Applied Mechanics & Materials, 2014, 584-586: 1346.
[12] Kennedy J, Eberhart R. IEEE International Conference on (IEEE), 1995, 4: 1942. |
[1] |
LI Hu1, ZHONG Yun1, 2, FENG Ya-ting1, LIN Zhen1, ZHU Shi-jiang1, 2*. Multi-Vegetation Index Soil Moisture Inversion Model Based on UAV
Remote Sensing[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 207-214. |
[2] |
ZHU Yan-ping1, CUI Chuan-jin1*, CHENG Peng-fei1, 2, PAN Jin-yan1, SU Hao1, 2, ZHANG Yi1. Measurement of Oil Pollutants by Three-Dimensional Fluorescence
Spectroscopy Combined With BP Neural Network and SWATLD[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(08): 2467-2475. |
[3] |
LUO Dong-jie, WANG Meng, ZHANG Xiao-shuan, XIAO Xin-qing*. Vis/NIR Based Spectral Sensing for SSC of Table Grapes[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(07): 2146-2152. |
[4] |
ZHOU Qi1, 2, WANG Jian-jun1, 2*, HUO Zhong-yang1, 2*, LIU Chang1, 2, WANG Wei-ling1, 2, DING Lin3. UAV Multi-Spectral Remote Sensing Estimation of Wheat Canopy SPAD Value in Different Growth Periods[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(06): 1912-1920. |
[5] |
ZHANG Fu1, 2, 3, CAO Wei-hua1, CUI Xia-hua1, WANG Xin-yue1, FU San-ling4*, ZHANG Ya-kun1. Non-Destructive Detection of Soluble Solids in Cherry Tomatoes by
Visible/Near Infrared Spectroscopy Based on SG-CARS-IBP[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(03): 737-743. |
[6] |
ZHU Chen-guang1, LIU Ya-jun2, LI Xin-xing1, 3, GONG Wei-wei4*, GUO Wei1. Detection Method of Freshness of Penaeus Vannamei Based on
Hyperspectral[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(01): 107-110. |
[7] |
LIU Meng-xuan1, 2, 3, 4, WU Qiong5, WANG Xu-quan1, 2, 4, CHEN Qi5, ZHANG Yong-gang1, 2, HUANG Song-lei1, 2*, FANG Jia-xiong1, 2*. Validity and Redundancy of Spectral Data in the Detection Algorithm of Sucrose-Doped Content in Tea[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(11): 3647-3652. |
[8] |
LI Zi-zhao, BI Shou-dong, CUI Yu-huan, HAO Shuang*. Comparison of Forest Stock Volume Inversion Methods Coupled With Multiple Features——A Case Study of Forest in Yarlung Zangbo River Basin[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3263-3268. |
[9] |
SONG Ni-na1, XIAO Dong1*, LI Sen1, GAO Yu-jie2. Analysis of Soil Salinity Based on Spectrum and RVIPSO-MELM[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(08): 2482-2487. |
[10] |
XU Liang-ji1, 2, MENG Xue-ying2, WEI Ren2, ZHANG Kun2. Experimental Research on Coal-Rock Identification Method Based on
Visible-Near Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(07): 2135-2142. |
[11] |
YU Yue, YU Hai-ye, LI Xiao-kai, WANG Hong-jian, LIU Shuang, ZHANG Lei, SUI Yuan-yuan*. Hyperspectral Inversion Model for SPAD of Rice Leaves Based on Optimized Spectral Index[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(04): 1092-1097. |
[12] |
LIN Xiao-mei1, WANG Xiao-meng1, HUANG Yu-tao1*, LIN Jing-jun2*. PSO-LSSVM Improves the Accuracy of LIBS Quantitative Analysis[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(11): 3583-3587. |
[13] |
MA Li1, 2, FAN Xin-li1, 2, ZHANG Shuo1, 2, WANG Wei-feng1, 2, WEI Gao-ming1, 2. Research on CH4 Gas Detection and Temperature Correction Based on TDLAS Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(11): 3632-3638. |
[14] |
PING Li1, ZHAO Rong1, YANG Bin1*, YANG Yang1, CHEN Xiao-long2, WANG Ying1. Inversion of Particle Size Distribution in Spectral Extinction Measurements Using PCA and BP Neural Network Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(11): 3639-. |
[15] |
XIAO Wen1, CAO Ying-li1,2*, FENG Shuai1, LIU Ya-di1, JIANG Kai-lun1, YU Zheng-xin1, YAN Li1. Detection of Rice Sheath Blight Disease Index Based on Split-Window Gram-Schmidt Transformation and PSO-SVR Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(07): 2181-2187. |
|
|
|
|