Modeling for Rapeseed’s Leaf Nitrogen Nutrient Diagnosis Based on Multifractal Detrended Moving Average Analysis

doi:10.11924/j.issn.1000-6850.casb15120055

Abstract

Abstract: In order to identify and diagnose the texture features of rape leaf under different nitrogen levels, eleven kinds of generalized Hurst indexes and other six kinds of related multifractal characteristic parameters of the rape leaf images were calculated by using multifractal detrended moving average analysis (MF-DMA) with three key position parameters, namely, θ=0, 0.5 and 1, respectively. By applying different combinations of characteristic parameters, the nitrogen nutrition diagnosis and recognition were conducted for the base leaf, central leaf and top leaf, respectively. The results showed that the performance of diagnosis with position parameter of θ=0 was better than that with 0.5 and 1. In addition, the best diagnose accuracy came from the base leaf and the central leaf, which demonstrated that the base leaf and the central leaf were more sensitive to the nitrogen deficiency than the top leaf. By diagnosing the nitrogen deficiency and nitrogen moderation of the three parts of the mixed rape leaf samples, it showed that support vector machines and kernel method (SVMKM) and the random forest were the best two methods to obtain the accuracy, by which the best recognition accuracy rate reached 95.81% and 96.63%, respectively. It indicated that our model possessed good effectiveness.

Su Le,Zou Ruibiao and Wang Fang. Modeling for Rapeseed’s Leaf Nitrogen Nutrient Diagnosis Based on Multifractal Detrended Moving Average Analysis[J]. Chinese Agricultural Science Bulletin, 2016, 32(12): 65-70.

References

[1] Jua X T, Xing G X, Chen X P, et al. Reducing environmental risk by improving N management in intensive Chinese agricultural systems[J]. PNAS, 2009,106(9):3041-3046.
[2] 王勃,徐静.计算机视觉技术在苹果叶片营养诊断上的应用[J].农机化研究, 2008(3):238-239.
[3] 袁道军,刘安国,刘志雄,等.利用计算机视觉技术进行作物生长监测的研究进展[J].农业网络信息,2007(2):21-25.
[4] 刘洪见,郑丽敏,廖树华,等.计算机视觉技术在农作物氮素营养诊断上的应用研究进展[J].麦类作物学报,2005,25(5):117-121.
[5] 李锦卫,廖桂平.作物图像光照亮度补偿方法[J].农机化研究,2012(8):26-30.
[6] 李锦卫,廖桂平,金晶,等.基于灰度截留分割与十色模型的马铃薯表面缺陷检测方法[J].农业工程学报,2010,26(10):236-242.
[7] 王访,廖桂平,王晓乔,等.基于多重分形理论的油菜缺素叶片特征提取[J].农业工程学报,2013,29(24):181-189.
[8] Wendt H, Roux S, Jaffard S, et al. Wavelet leaders and bootstrap for multifractal analysis of images[J].Signal Process,2009,6(89):1100-1114.
[9] Abry P, Wendt H, Jaffard S. When Van Gogh meets Mandelbrot: multifractal classication of painting’s texture[J].Signal Process,2013,93(3):554-572.
[10] Stojic T, Reljin I, Reljin B. Adaptation of multifractal analysis to segmentation of micro-calcifications in digital mammograms[J].Physica A, 2006,367(15):494-508.
[11] Kantelhardt J W, Zschiegner S A, Bunde E K, et al. Multifractal detrended fluctuation analysis of non- stationary time series[J].Physica A: Statistical Mechanics and its Applications,2002(316):87-114.
[12] Gu G F, Zhou W X. Detrended fluctuation analysis for fractals and multifractals in higher dimensions[J].Physical Review E,74,061104,2006.
[13] Wang F, Liao G P, Li J W, et al. Multifractal detrended fluctuation analysis for clustering structures of electricity price periods[J].Physica A: Statistical Mechanics and its Applications,2013,392(22):5723-5734.
[14] Zhou Y, Leung Y. Multifractal temporally weighted detrended fluctuation analysis and its application in the analysis of scaling behavior in temperature series[J].Journal of Statistical Mechanics: Theory and Experiment, 2010, 2010(2010):361-394.
[15] Wang F, Li Z S, Liao G P. Multifractal Detrended Fluctuation Analysis for Image Texture Feature Representation[J].International Journal of Pattern Recognition and Artificial Intelligence,2014,28(3):145-505.
[16] Wang F, Li Z S, Li J W. Local Multifractal Detrended Fluctuation Analysis for Non-stationary Image''s Texture Segmentation[J].Applied Surface Science,2014,233:116-125.
[17] Wang F, Li J W, Shi W, et al. Leaf image segmentation method based on multifractal detrended fluctuation analysis[J].Journal of Applied Physics, 2013, 114(21):214905-214905-9.
[18] Alessio E, Carbone A, Castelli G, et al. Second-order moving average and scaling of stochastic time series[J].The European Physical Journal B-Condensed Matter and Complex Systems,2002,27(2):197-200.
[19] Gu G F, Zhou W X. Detrending moving average algorithm for multifractals[J].Physical Review E, 2010, 82(1 Pt 1):1859-1860.
[20] Schumann A Y, Kantelhardt J W. Multifractal moving average analysis and test of multifractal model with tuned correlations[J].Physica A: Statistical Mechanics and its Applications,2011,390(14):2637-2654.
[21] Wang Y, Wu C, Pan Z. Multifractal detrending moving average analysis on the US Dollar exchange rates[J].Physica A: Statistical Mechanics and its Applications,2011,390(20):3512-3523.
[22] Wang F, Wang L, Zou R B. Multifractal detrended moving average analysis for texture representation[J].Chaos: An Interdisciplinary Journal of Nonlinear Science, 2014, 24(3):5880-5885.
[23] Shi W, Zou R B, Wang F, et al. A new image segmentation method based on multifractal detrended moving average analysis[J].Physica A, Volume 432, 2015,432:197-205.
[24] Duda R O, Hart P E, Stork D G. Pattern classi?cation[M].2nd.New York:John Wiley & Sons,2001.
[25] Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: theory and applications[J].Neuro-computing,2006,12(1):489-501.
[26] Vladimir N. Vapnik. 统计学习理论[M].北京:电子工业出版社,2009.
[27] Nello Cristianini, JohnShawe, Taylor. An Introduction to Support Vector Machines and Other Kernel-based Learning Methods[M].北京:电子工业出版社,2004.
[28] Ho, Kam T. Random Decision Forest. Proc. of the 3rd Int''l Conf. on Document Analysis and Recognition[C].Montreal,Canada,August 14-18,1995:278-282.
[29] Bremner D, Demaine E, Erickson J, et al. Output-sensitive algorithms for computing nearest-neighbor decision boundaries[J].Discrete and Computational Geometry,2005,33(4):593-604.
[30] 李锦卫. 基于计算机视觉的水稻、油菜叶色-氮营养诊断机理与建模[D].长沙:湖南农业大学,2010,12.
[31] Hastie T, Tibshirani R, Friedman J等译. 统计学习基础-数据挖掘[M].北京:电子工业出版社, 2007.