基于遗传支持向量机的城市扩张非线性组合模型
收稿日期: 2010-01-17
修回日期: 2010-02-08
网络出版日期: 2010-06-25
基金资助
国家自然科学基金项目(40874010); 江西省数字国土重点实验室开放基金(DLLJ201014)
A Nonlinear Polynomial Model for Urban Expansion Incorporating Genetic Algorithm and Support Vector Machines
Received date: 2010-01-17
Revised date: 2010-02-08
Online published: 2010-06-25
Supported by
National Natural Science Foundation of China, No.40874010; Open Foundation of Jiangxi Provincial Key Laboratory of Digital Land, DLLJ201014
在分析当前城市扩张模拟模型优缺点的基础上，利用支持向量机能有效表达、拟合复杂非线性系统的功能，将多个单项城市扩张模型进行非线性组合，有机融合各单项模型优点，最后构建支持向量机的城市空间扩张非线性组合模拟模型。利用遗传算法优化支持向量机的参数，减小参数设置不合理对支持向量机建模精度引起的影响，有效提高支持向量机模型精度。通过分析组合模型误差和各参与组合的单项模型之间的关系，总结出提高支持向量机的城市扩张非线性组合模型精度的方法是：① 提高参与组合的各单项模型精度；② 增加单项模型之间的差异性。以长沙市为例，分别构建多元回归、GM(1,8)、BP网络和LS-SVM单项城市空间扩张模拟模型，并在此基础上建立线性组合城市扩张模型和遗传支持向量机非线性组合城市扩张模型。通过各模型精度对比分析证明，遗传支持向量机的城市扩张非线性组合模型精度远优于各单项模型，并且优于线性组合模型，是一种有效的城市扩张新模型。
张豪, 罗亦泳, 张立亭 . 基于遗传支持向量机的城市扩张非线性组合模型[J]. 地理学报, 2010 , 65(6) : 656 -664 . DOI: 10.11821/xb201006003
With comparative analysis of strengths and weaknesses of current urban expansion simulation models and nonlinearly combining the advantages of best individual-based models, a nonlinear polynomial model of urban spatial expansion has been proposed by using the powerful functions of support vector machine to describe highly complicated nonlinear systems and then to make a better fit for them. The accuracy of the proposed model has been effectively improved by using the parameters of support vector machine optimized with genetic algorithm to reduce the negative influence, exerted by the non-rational design of parameters, on the modeling accuracy of support vector machine. With analyzing the relationship between the error arising from the combined model and all individual-based models, we conclude the ways to improve the accuracy of the nonlinear polynomial model of urban expansion equipped with support vector machine as follows: The first is to improve the accuracy of individual-based models; the second is to enlarge differences between individual models. In the case study of Changsha city, individual-based simulation models of urban spatial expansion constructed by multiple regression model, GM(1,8), BP network and LS-SVM are used to build a linear combination model of urban spatial expansion and a nonlinear combination model of urban spatial expansion equipped with genetic algorithm and support vector machine. A comparison of accuracy of selected models shows that the accuracy of nonlinear polynomial model of urban expansion equipped with genetic algorithm and support vector machine is much higher than any individual-based simulation model, and also higher than the linear combination model, and therefore, an efficient new model of urban expansion is established.
[1] Bao Liping, Wang Jinggang. Driving forces of urban construction land expansion in the Mainland of China. China Land Science, 2009, 23(8): 68-72.
[鲍丽萍, 王景岗. 中国大陆城市建设用地扩展动因浅析. 中国土地科学, 2009, 23(8): 68-72.]
[2] Zhang Honghui, Zeng Yongnian, Jin Xiaobin et al. Urban land expansion model based on multi-agent system and application. Acta Geographica Sinica, 2008, 63(8): 869-881.
[张鸿辉, 曾永年, 金晓斌等. 多智能体城市土地扩张模型 及其应用. 地理学报, 2008, 63(8): 869-881.]
[3] Yang Qingsheng, Li Xia. Integration of multi-agent systems with cellular automata. Scientia Geographica Sinica, 2007, 27(4): 542-548.
[杨青生, 黎夏. 多智能体与元胞自动机结合及城市用地扩张模拟. 地理科学, 2007, 27(4): 542-548.]
[4] Hu Jing, Chen Yinrong. An analysis of driving force and GM (1, N) prediction of urban expansion and GM (1, N) prediction of urban expansion. Scientific and Technological Management of Land and Resources, 2005, 22(5): 69-72.
[胡静, 陈银蓉. 城市扩张驱动力分析及GM(1, N)预测. 国土资源科技管理, 2005, 22(5): 69-72.]
[5] Zhao Liming, Li Zhenhua. Study of the city construction system using system dynamics mode. China Shoft Science, 2004, (11): 147-151.
[赵黎明, 李振华. 城市建设系统的动力学模型研究. 中国软科学, 2004, (11): 147-151.]
[6] Wang Liangjian, Shi Yingchun, Lin Muxuan. Applications of BP neural network theory on urban expansion forecasts with Wavelet treatment: A case of Changsha urban Area. China Land Science, 2008, 22(1): 39-47.
[王良健, 师迎春, 林 目轩. BP神经网络结合小波处理在城市扩张预测中的应用. 中国土地科学, 2008, 22(1): 39-47.]
[7] Huang B, Xie C L . Support vector machines for urban growth modeling. Geoinformatica, 2010, 14(1): 83-99.
[8] Bates J M, Granger C W J. Combination of forecasts. Operations Research Quarterly, 1969, 20(4): 451-468.
[9] Reeves G R, Lawrence K D. Combining forecasts give different types of objectives. European Journal of Operational Research, 1991, 51(1): 65-70.
[10] Zhang Jinchun, Zhai Jingchun. Estimating the development expenses of anti-ship missiles by a joint forecasting method of artificial neural network. Systems Engineering and Electronics, 2002, 24(9): 111-113.
[张金春, 翟景春. 用神 经网络组合预测法估算反舰导弹研制费用. 系统工程与电子技术, 2002, 24(9): 111-113.]
[11] Huang Weiyong, Tong Minming, Ren Zihui et al. Nonlinear combination forecast of gas emission amount based on SVM. Journal of China University of Mining & Technology, 2009, 38(2): 234-239.
[黄为勇, 童敏明, 任子晖等. 基于 SVM的瓦斯涌出量非线性组合预测方法. 中国矿业大学学报, 2009, 38(2): 234-239.]
[12] Jiang Wenliang. Urban spatial forecast based on GIS & spatial logistic model. Economic Geography, 2007, 27(5): 800-804.
[姜文亮. 基于GIS和空间Logistic模型的城市扩展预测. 经济地理, 2007, 27(5): 800-804.]
[13] Vapnik V. The Nature of Statistical Learning Theory. New York: Springer, 1995.
[14] Xiong Jianqiu, Li Zuoyong. Sediment carrying capacity forecasting based on support vector machine. Journal of Hydraulic Engineering, 2005, (10): 1171-1175.
[雄建秋, 李祚泳. 基于支持向量机的水流挟沙力预测研究. 水利学报, 2005, (10): 1171-1175.]
[15] Vapnik V. Estimation of Dependencies Based on Empirical Data. Berlin: Springer-Verlag, 1982.
[16] Wan Shuting, Guan Sensen, Liu Hongliang et al. Generator fault diagnosis using least squares-based support vector machine and mechanical features extraction. Chinese Journal of Construction Machinery, 2009, 7(1): 80-85.
[万书亭, 管森森, 刘洪亮等. 基于最小二乘支持向量机和机电综合特征的发电机故障诊断. 中国工程机械学报, 2009, 7(1): 80-85.]
[17] Song Zhiyu, Li Junjie. Prediction model based on least support vector machine with harmony search and its application. Journal of Harbin Institute of Technology, 2009, 41(8): 207-210.
[宋志宇, 李俊杰. 和声搜索最小二乘支 持向量机预测模型及其应用. 哈尔滨工业大学学报, 2009, 41(8): 207-210.]
[18] Zhou Ming, Sun Shudong. Theories and Application of Genetic Algorithms. Beijing: National Defense Industry Press, 1999.
[周明, 孙树栋. 遗传算法原理及应用. 北京: 国防工业出版社, 1999.]
[19] Huo Yingjie et al. Matlab GA Toolbox and Application. Xi'an: Xidian University Press, 2005.
[雷英杰等. MATLAB遗 传算法工具箱及应用. 西安: 西安电子科技大学出版社, 2005.]
[20] Hao Zhangang. Clustering and classification of data and text using such technologies as genetic algorithm
[D]. Tianjin: Tianjin University, 2006.
[郝占刚. 基于遗传算法等技术的数据与文本聚分类研究
[D]. 天津: 天津大学, 2006.]
[21] Li Huayou. Theory and Application of Combination Forecast Model. Beijing: Science Press, 2008.
[李华友. 组合预测 方法有效性理论及其应用. 北京: 科学出版社, 2008.]
[22] Collobert R, Bengio S, Benggio Y. A parallel mixture of SVM for very large scale problems. Neural Computation, 2002, 14(5): 1105-1114.
[23] Wolpert D H. Stacked generalization. Neural Networks, 1992, 5: 241-259.
[24] Wu Hong'an, Jiang Jianjun, Zhou Jie et al. Dynamics of urban expansion in Xi'an city using landsat TM/ETM+Data. Acta Geographica Sinica, 2005, 60(1): 143-150.
[吴宏安, 蒋建军, 周杰等. 西安城市扩张及其驱动力分析. 地理学 报, 2005, 60(1): 143-150.]
[25] Zbou Guohua, He Yanhua. Characteristics and influencing factors of urban land expansion in Changsha. Acta Geographica Sinica, 2006, 61(11): 1171-1180.
[周国华, 贺艳华. 长沙城市土地扩张特征及影响因素. 地理学报, 2006, 61(11): 1171-1180.]
[26] Chen Ligen, Chen Huiguang, Qu Futian et al. Economic development industrial restructuring and scale regulation of urban construction land: The case of Maanshan city. Resources Science, 2004, 26(6): 137-144.
[陈利根, 陈会广, 曲福 田等. 经济发展、产业结构调整与城镇建设用地规模控制. 资源科学, 2004, 26(6): 137-144.]
[27] Zhang Zhanlu. An analysis of driving forces of urban land expansion in Beijing. Economic Geography, 2009, 29(7): 1182-1185.
[张占录. 北京市城市用地扩张驱动力分析. 经济地理, 2009, 29(7): 1182-1185.]
[28] Deng Lingyun, Yu Dingquan. The influencing factor analysis of the urban expanding of Changsha. Modern Economic Research, 2006, (10): 22-28.
[邓凌云, 喻定权. 长沙市城市扩张的影响因素分析. 现代城市研究, 2006, (10): 22-28.]
[29] Zhang Hao, Luo Yiyong, Zhang Liting et al. Research on new method of the cultivated land change forecast based on genetic algorithm and least squares support vector machine. Transactions of the CSAE, 2009, 25(7): 226-231.
[张豪, 罗 亦泳, 张立亭等. 基于遗传算法最小二乘支持向量机的耕地变化预测. 农业工程学报, 2009, 25(7): 226-231.]
[30] Krogh A, Vedelsby J. Neural network ensembles, cross validation, and active learning. Advances in Neural Information Processing Systems, 1995, (7): 231-238.
/
| 〈 |
|
〉 |