融合粗糙集和二元萤火虫算法的雾霾关键影响因素预测方法

程美英, 倪志伟, 朱旭辉

系统工程理论与实践 ›› 2017, Vol. 37 ›› Issue (1) : 241-252.

PDF(1376 KB)
PDF(1376 KB)
系统工程理论与实践 ›› 2017, Vol. 37 ›› Issue (1) : 241-252. DOI: 10.12011/1000-6788(2017)01-0241-12
论文

融合粗糙集和二元萤火虫算法的雾霾关键影响因素预测方法

    程美英1,2, 倪志伟1,2, 朱旭辉1,2
作者信息 +

Rough set combine with binary glowworm swarm optimization for key haze influence factors

    CHENG Meiying1,2, NI Zhiwei1,2, ZHU Xuhui1,2
Author information +
文章历史 +

摘要

雾霾对人类的日常生活带来极大的危害,因而分析产生雾霾的关键影响因素尤为重要.针对目前传统算法预测雾霾关键影响因素存在的缺陷,从一维细胞自动机入手,提出了一种以基于群落弱连接机制的二元萤火虫算法(CWLBGSO)为搜索策略,粗糙集为评价准则的混合方法.CWLBGSO基于自然界中萤火虫间协同进化的“弱连接”机制,划分搜索空间,为每个子空间分配相应的种群,各子种群中的次优个体相互交互产生新个体,从而保持种群的动态多样性,然后将CWLBGSO结合粗糙集,应用于北京,广州和上海三地雾霾关键影响因素的预测中,并结合10交叉验证和SVM算法对预测结果分类准确率和影响因素进行分析,通过与其它算法进行对比,结果表明本文算法能有效剔除冗余因素,预测结果具有较高的稳定性和可行性.

Abstract

Haze has brought great harm to human daily life, so it is very important to analyze the factors which influence the haze badly. Starting from one-dimensional cellular automata (CA) and the drawbacks of the traditional method,a novel BGSO algorithm with weak-link Coevolution mechanism (CWLBGSO) combine with Rough Set is introduced in this paper. In CWLBGSO, the whole search space was divided into several sub-spaces, and each sub-space has a subpopulation, then after several iterations, suboptimum in each subpopulation will perform crossover operation to keep the dynamic diversity. After that CWLBGSO combined with rough set is applied to forecast the key factors which influence haze badly. The datasets of Beijing, Guangzhou and Shanghai are used to conduct experiments, also 10-fold and SVM is involved to analyze the classification accuracy and influence factors, the experimental results show that our method can effectively eliminate redundant factors, also has relatively higher stability and credibility.

关键词

雾霾 / 一维细胞自动机 / 二元萤火虫算法 / 弱连接机制 / 粗糙集 / SVM

Key words

haze / one-dimensional cellular automata / binary glowworm swarm optimization / weak-link coevolution / rough set / SVM

引用本文

导出引用
程美英 , 倪志伟 , 朱旭辉. 融合粗糙集和二元萤火虫算法的雾霾关键影响因素预测方法. 系统工程理论与实践, 2017, 37(1): 241-252 https://doi.org/10.12011/1000-6788(2017)01-0241-12
CHENG Meiying , NI Zhiwei , ZHU Xuhui. Rough set combine with binary glowworm swarm optimization for key haze influence factors. Systems Engineering - Theory & Practice, 2017, 37(1): 241-252 https://doi.org/10.12011/1000-6788(2017)01-0241-12
中图分类号: TP391   

参考文献

[1] 张小曳,孙俊英,王亚强,等.我国雾-霾成因及其治理的思考[J].科学通报, 2013, 58(13): 1178-1187.Zhang X Y, Sun J Y, Wang Y Q, et al. The cause of fog-haze and its governance thinking in our country[J]. Chinese Science Bulletin, 2013, 58(13): 1178-1187.
[2] 吴兑.近十年中国灰霾天气研究综述[J].环境科学学报, 2012, 32(2): 257-269.Wu D. Hazy weather research in China in the last decade: A review[J]. Acta Scientiae Circumstantiae, 2012, 32(2): 257-269.
[3] 王硕,李木元,孙金诚,等.苍穹之下,我们如何共同洁净呼吸[N].人民政协报, 2015年3月5日,第4版.Wang S, Li M Y, Sun J C, et al. Under the dome, how do we clean together breathing[N]. People's Political Consultative Conference Paper, 2015-3-5, 4th ed.
[4] 王珊,修天阳,孙杨,等. 1960-2012年西安地区天气雾霾日数与气象因数变化规律分析[J].环境科学学报, 2014, 34(1): 19-26.Wang S, Xiu T Y, Sun Y, et al. The changes of mist and haze days and meteorological element during 1960-2012 in Xi'an[J]. Acta Scientiae Circumstantiae, 2014, 34(1): 19-26.
[5] 常清,杨复沫,李兴华,等.北京冬季雾霾天气下颗粒物及其化学组分的粒径分布特征研究[J].环境科学学报, 2015, 35(2): 363-370.Chang Q, Yang F M, Li X H, et al. Characteristics of mass and chemical species size distributions of particulate matter during haze pollution in the winter in Beijing[J]. Acta Scientiae Circumstantiae, 2015, 35(2): 363-370.
[6] 张人禾,李强,张若楠. 2013年1月中国东部持续性强雾霾天气产生的气象条件分析[J].中国科学·地球科学, 2014, 44(1): 27-36.Zhang R H, Li Q, Zhang R N. January 2013, In eastern China sustained strong fog haze weather produce analysis of the meteorological conditions[J]. Science China, Earth China, 2014, 44(1): 27-36.
[7] Krishnanand K N, Ghose D. Glowworm swarm optimisation: A new method for optimising multimodal functions[J]. International Journal of Computational Intelligence Studies, 2009, 1(1): 93-119.
[8] Yang X S. Nature-inspired etaheutistic algorithms[M]. Luniver Press, 2008.
[9] Jayakumar D N, Venkatesh P. Glowworm swarm optimization algorithm with topsis for solving multiple objective environmental economic dispatch problem[J]. Applied Soft Computing, 2014, 23: 375-386.
[10] Wu B, Qian C H, Ni W H, et al. The improvement of glowworm swarm optimization for continuous optimization problems[J]. Expert Systems with Applications, 2013, 39(7): 6335-6342.
[11] 倪志伟,肖宏旺,伍章俊,等.基于改进离散型萤火虫群优化算法和分形维数的属性选择方法[J]. 模式识别与人工智能, 2013, 26(12): 1169-1178.Ni Z W, Xiao H W, Wu Z J, et al. Attribute selection method based on improved discrete glowworm swarm optimization and fractal dimension[J]. PR&AI, 2013, 26(12): 1169-1178.
[12] 杜鹏桢,唐振民,陆建峰,等.不确定环境下基于改进萤火虫算法的地面自主车辆全局路径规划方法[J].电子学报, 2014, 42(3): 616-624.Du P Z, Tang Z M, Lu J F, et al. Global path planning for ALV based on Improved glowworm swarm optimization under uncertain environment[J]. ACTA Electronica Sinica, 2014, 42(3): 616-624.
[13] 范阳寿,汪民乐,文苗苗,等.基于萤火虫算法-层次分析法的弹道突防效能分析[J].系统工程与电子技术, 2015, 37(4): 845-850.Fan Y S, Wang M L, Wen M M, el at. Analysis of ballistic missile penetration effectiveness based on FA-AHP[J]. Systems Engineering and Electronics, 2015, 37(4): 845-850.
[14] Chouchoulas A, Shen Q. Rough set-aided keyword reduction for text categorization[J]. Applied Artificial Intelligence, 2001, 15(9): 843-873.
[15] 叶春明,李永林,刘长平.新型仿生群智能算法及其生产调度应用[M].北京: 科学出版社, 2015.Ye C M, Li Y L, Liu C P. A novel bionic swarm intelligence algorithm and its application in scheduling[M]. Beijing: Science Press, 2015.
[16] 欧阳#
[17],周永权.自适应步长萤火虫优化算法[J].计算机应用, 2011, 31(7): 1804-1807.Ouyang Z, Zhou Y Q. Self-adaptive step glowworm swarm optimization algorithm[J]. Journal of Computer Application, 2011, 31(7): 1804-1807.
[17] 杜晓昕,张剑飞,孙明.基于自适应t分布混合变异的人工萤火虫算法[J].计算机应用, 2013, 33(7): 1922-1925.Du X X, Zhang J F, Sun M. Artificial glowworm swarm optimization algorithm based on adaptive distribution mixed mutation[J]. Journal of Computer Applications, 2013, 33(7): 1922-1925.
[18] 孟庆全,梅灿华.一种新的属性集依赖度[J].计算机应用, 2007, 27(7): 1748-1750.Meng Q Q, Mei C H. Research on a new dependability of attribute sets[J]. Computer Application, 2007, 27(7): 1748-1750.
[19] 程美英,倪志伟,朱旭辉.基于生命周期的二元蚁群优化算法[J].模式识别与人工智能, 2014, 27(11): 1005-1014.Cheng M Y, Ni Z W, Zhu X H. Lifecycle-based binary ant colony algorithm[J]. PR&AI, 2014, 27(11): 1005-1014.

基金

国家自然科学基金(71271071,71301041);国家自然科学基金重点项目(71490725);国家"863"云制造主题项目(2015AA042101)
PDF(1376 KB)

359

Accesses

0

Citation

Detail

段落导航
相关文章

/