An Evolutionary-Strategy-Based CHC Genetic Algorithm and Its Application to Rock Spectrum Discrimination
-
摘要: 野外实测岩性波谱数据的数据挖掘可以为高光谱遥感建模提供依据.针对实测波谱数据的特点, 设计了一种基于Monte Carlo抽样进化机制的CHC (cross generation elitist selection, heterogeneous recombination, cataclysmic mutation , 跨世代精英选拔、异物种重组、灾变变异) 遗传算法用于多类岩性判别.应用于云南北衙金矿蚀变岩的识别, 表明该方法具有快速高效性.Abstract: Data mining from field rock spectrums is important for hyper-spectral remote sensing modeling. The characteristics of the field spectrum data are used to reform and combine evolutionary strategies with CHC (cross generation elitist selection, heterogeneous recombination and cataclysm mutation) and to design a genetic algorithm to conduct rock spectrum discrimination: to build a linear discriminating equation with many variables (wavelength intervals). Floating encoding is used for the coefficients of the equation (genes). Two optimization objectives are compared with each other: one is to maximize the right-judgment ratio of known samples, and the other is to minimize the ratio of in-class versus between-class distances. The results show that the former is briefer and faster while both of them are effective. Monte Carlo sampling is employed to adjust searching spaces. Uniform and Gaussian distribution models are employed to produce new-generation genes, showing that the former model has better performance, because the genes have various unknown distributions. An experimental study is presented based on the data of 1 823 wavelength intervals from Beiya gold deposit, Yunnan, China, obtained with the FieldSpectr Fr equipment (ASD Co. US). The algorithm proves high efficiency in identification of altered dolomitic limestone, a potentially gold-bearing rock, from other rocks.
-
图 1 深灰色白云质灰岩露头的相对反射率及其规格化一阶导数曲线
Fig. 1. Spectrum curves of relative reflectance and its normalized one-order differential of a dark gray dolomitic limestone outcrop
图 2 4种流程的进化曲线
1.流程①进化曲线; 2.流程②进化曲线; 3.流程③进化曲线; 4.流程④进化曲线; 5.流程③判对率曲线; 6.流程④判对率曲线
Fig. 2. Evolutionary curves of the four algorithms
-
[1] Eshelman L J. The CHC adaptive search algorithm: how to have safe search when engaging in non-traditional genetic recombination[A]. In: Gregory J E, ed. Foundations of genetic algorithms[C]. San Meteo, CA: Morgan Kaufmann Publishers, 1991. 265-283. [2] Back T, Hoffmeister F, Schwefel H P. A survey of evolution strategies[A]. In: ICGA, ed. Proceedings of the fourth international conference on genetic algorithms [C]. San Meteo, CA: Morgan Kaufmann Publishers, 1991. 2-9. [3] Mustard J F, Sunshine J M. Spectral analysis for earth science: investigations using remote sensing data[A]. In: Renz A N, ed. Remote sensing for the earth science: manual of remote sensing(vol. 3)[C]. New York: John Wiley & Sons, 1999. 251-360. [4] 王学仁. 地质数据的多变量统计分析[M]. 北京: 科学出版社, 1982. 147-155.WANG X R. Multi-variable statistics for geological data [M]. Beijing: Science Press, 1982. 147-155. [5] Goldberg D E. Genetic algorithms in search, optimization and learning[M]. New Nork: Addison-Wesley, 1989. 1-83. [6] 王秀峰. 实数编码的遗传算法及其在逆变器馈电交流电机中的应用[J]. 自动化学报, 1998, 24(2): 250-253. https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO802.018.htmWANG X F. Genetic algorithm using floating encoding and its application to inverter-fed induction machines[J]. Acta Automatica Sinica, 1998, 24(2): 250-253. https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO802.018.htm [7] Georges R H, Fernando G L, David E. The compact genetic algorithm[J]. IEEE Transactions on Evolutionary Computation, 1999, 3(4): 287-297. https://ieeexplore.ieee.org/document/797971 -
下载:
点击查看大图
图(3)
计量
- 文章访问数: 3596
- HTML全文浏览量: 292
- PDF下载量: 6
- 被引次数: 0
