Ensemble-learning-based Cellular Automata for Urban Geosimulation
-
摘要: 集成学习通过将若干弱分类器集成以取得比单个弱分类器更好的性能，是机器学习的重要研究方向。针对常用城市地理模拟系统中元胞自动机转换规则获取算法的局限性，本文提出基于集成学习算法的元胞自动机，并将其应用于城市建设用地的动态模拟。以决策树作为弱分类器，应用集成学习算法和元胞自动机，对东莞市2001年到2005年的建设用地时空格局进行了模拟，取得了较好的模拟效果。精度评估结果表明，经集成学习后的决策树比单个决策树对城市建设用地动态的模拟精度更高，算法泛化能力更好。
-
关键词:
- 决策树
Abstract: This paper presents a new method to simulate urban dynamics based on ensemble learning, cellular automata and GIS. Ensemble learning is an important direction of the machine learning which can improve the performance than the single classifier by constructing a set of classifier and then classify the new data set by taking a weighted vote of their predictions. Many algorithms have been used to simulate the change of land use so far. However, there exists some limitations about the algorithms in the applications . For instance, the dicision trees algorithm is always confronting the problem of over-fitting, the neural network algorithm would be trapped in local optimum easily. This paper uses the dicision tree algorithm as the classifier of the ensemble learning to predict urban dynamics of Dongguan city. The result shows that the simulation of the ensemble learning is better than the decision tree.-
Keywords:
- decision tree
-
-
[1]刘小平, 黎夏, 张啸虎, 陈刚强, 李少英, 陈逸敏.人工免疫系统与嵌入规划目标的城市模拟及应用[J].地理学报, 2008, 63(8):882-894 [2]Couclelis H.Cellular worlds: a framework for modeling micro-macro dynamics[J].Environment and Planning A, 1985, 17(5):585-596 [3]White R, Engelen G.Cellular automata and fractal urban form: a cellular modelling approach to the evolution of urban land-use [J].pattersEnvironment and Planning A, 1993, 25(8):1175-1199 [4]Clarke K C, Hoppen S, Gaydos L.A self-modifying cellular automaton model of historical urbanization in the San Francisco Bay area [J].Environment and Planning B, 1997, 24(2):247-261 [5]Apostolos L.Urban sprawl simulation linking macro-scale processes to micro-dynamics through cellular automata,an application in Thessaloniki,Greece[J].Applied Geography, 2012, 34(0):146-160 [6]龙瀛, 沈振江, 毛其智, 党安荣.基于约束性方法的北京城市形态情景分析[J].地理学报, 2010, 65(6):643-655 [7]黎夏, 叶嘉安.基于神经网络的单元自动机及真实和优化的城市模拟[J].地理学报, 2002, 57(2):159-166 [8]Zhao Y, Murayama Y.A new method to model neighborhood interaction in Cellular Automata-based urban geosimulation [J].Lecture Notes in Computer Science, 2007, 4488:550-557 [9]Li X, Yeh A G-O.Data mining of cellular automata's transition rules[J].International Journal of Geographical Information Science, 2004, 18(8):723-744 [10]黎夏, 叶嘉安.知识发现及地理元胞自动机[J].中国科学：辑, 2004, 34(9):19-27 [11]黎夏, 叶嘉安.基于神经网络的元胞自动机及模拟复杂土地利用系统[J].地理研究, 2005, 24(1):19-27 [12]杨青生, 黎夏.基于支持向量机的元胞自动机及土地利用变化模拟[J].遥感学报, 2007, 10(6):836-846 [13]陈沛玲, 决策树分类算法优化研究[D].长沙：中南大学, 2007. [14]樊为民.基于遗传算法的神经网络算法研究[J].太原师范学院学报: 自然科学版, 2005, 3(4):14-17 [15]季桂树, 陈沛玲, 宋航.决策树分类算法研究综述[J].科技广场, 2007, 1:9-12 [16]张春霞, 张讲社.选择性集成学习算法综述[J].计算机学报, 2011, 34(8):1399-1410 [17]刘艳丽, 随机森林综述[D].天津: 南开大学, 2008. [18]沈学华, 周志华.和 综述[J].计算机工程与应用, 2000, 36(12):31-32 [19]方匡南, 吴见彬, 朱建平, 谢邦昌.随机森林方法研究综述[J].统计与信息论坛, 2012, 26(3):32-38 [20]丁雍, 李小霞.基于 和 结合的优化分类算法[J].微型机与应用, 2012, 30(23):46-50
[1]刘小平, 黎夏, 张啸虎, 陈刚强, 李少英, 陈逸敏.人工免疫系统与嵌入规划目标的城市模拟及应用[J].地理学报, 2008, 63(8):882-894 [2]Couclelis H.Cellular worlds: a framework for modeling micro-macro dynamics[J].Environment and Planning A, 1985, 17(5):585-596 [3]White R, Engelen G.Cellular automata and fractal urban form: a cellular modelling approach to the evolution of urban land-use [J].pattersEnvironment and Planning A, 1993, 25(8):1175-1199 [4]Clarke K C, Hoppen S, Gaydos L.A self-modifying cellular automaton model of historical urbanization in the San Francisco Bay area [J].Environment and Planning B, 1997, 24(2):247-261 [5]Apostolos L.Urban sprawl simulation linking macro-scale processes to micro-dynamics through cellular automata,an application in Thessaloniki,Greece[J].Applied Geography, 2012, 34(0):146-160 [6]龙瀛, 沈振江, 毛其智, 党安荣.基于约束性方法的北京城市形态情景分析[J].地理学报, 2010, 65(6):643-655 [7]黎夏, 叶嘉安.基于神经网络的单元自动机及真实和优化的城市模拟[J].地理学报, 2002, 57(2):159-166 [8]Zhao Y, Murayama Y.A new method to model neighborhood interaction in Cellular Automata-based urban geosimulation [J].Lecture Notes in Computer Science, 2007, 4488:550-557 [9]Li X, Yeh A G-O.Data mining of cellular automata's transition rules[J].International Journal of Geographical Information Science, 2004, 18(8):723-744 [10]黎夏, 叶嘉安.知识发现及地理元胞自动机[J].中国科学：辑, 2004, 34(9):19-27 [11]黎夏, 叶嘉安.基于神经网络的元胞自动机及模拟复杂土地利用系统[J].地理研究, 2005, 24(1):19-27 [12]杨青生, 黎夏.基于支持向量机的元胞自动机及土地利用变化模拟[J].遥感学报, 2007, 10(6):836-846 [13]陈沛玲, 决策树分类算法优化研究[D].长沙：中南大学, 2007. [14]樊为民.基于遗传算法的神经网络算法研究[J].太原师范学院学报: 自然科学版, 2005, 3(4):14-17 [15]季桂树, 陈沛玲, 宋航.决策树分类算法研究综述[J].科技广场, 2007, 1:9-12 [16]张春霞, 张讲社.选择性集成学习算法综述[J].计算机学报, 2011, 34(8):1399-1410 [17]刘艳丽, 随机森林综述[D].天津: 南开大学, 2008. [18]沈学华, 周志华.和 综述[J].计算机工程与应用, 2000, 36(12):31-32 [19]方匡南, 吴见彬, 朱建平, 谢邦昌.随机森林方法研究综述[J].统计与信息论坛, 2012, 26(3):32-38 [20]丁雍, 李小霞.基于 和 结合的优化分类算法[J].微型机与应用, 2012, 30(23):46-50
计量
- 文章访问数: 1060
- HTML全文浏览量: 128
- PDF下载量: 260
下载:
