全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...
-  2018 

基于DBN与GeoCA相结合的城市动态模型构建与多方案对比研究——以成都市为例
The Construction of an Urban Dynamic Model Based on DBN in Combination with GeoCA and a Multi-Program Comparison Research——A Case Research of Chengdu

DOI: 10.13718/j.cnki.xdzk.2018.01.020

Keywords: 深度信念网络, 元胞自动机, 规则提取, 成都市
deep belief network
, cellular automaton, rule extraction, Chengdu

Full-Text   Cite this paper   Add to My Lib

Abstract:

以成都市为例,将深度信念网络与地理元胞自动机相结合构建一个整合模型,完成城市形态的演化模拟,同时采用多方案对比法检测网络深度以及用地分类的均衡性对模拟精度的影响.实验结果显示:在用地分类类型相同,隐含层含有5层网络时总体Kappa值最高;在网络隐层数目相同,分为4种用地类型时总体Kappa值最高.研究表明,基于深度信念网络与地理元胞自动机相结合的整合模型能够较好地模拟城市的演化,同时,模型的网络层深度和用地分类的均衡性都会对模拟精度产生一定影响.
Taking Chengdu as an example, an integrated model was built with DBN (deep belief network) in combination with GeoCA (geographical cellular automaton) to realize the simulation of the evolution of urban form. In addition, a multi-program comparison method was used to investigate the effect of network depth and the balance of land classification on simulation accuracy. The results showed that the total Kappa value was the highest with similar land classification and with a 5-layer network, or with the same number of hidden layers and 4 classes of land, thus suggesting that the urban dynamic model constructed based on DBN and GeoCA can well simulate the evolution of a city and that classification imbalance and network layer depth will have some impact on simulation accuracy

References

[1]  TOBLER W R. A Computer Movie Simulating Urban Growth in the Detroit Region[J]. Economic Geography, 1970, 46: 234-240. DOI:10.2307/143141
[2]  COUCLELIS H. Cellular Worlds: A Frame Work for Modeling Micro-Macro Dynamics[J]. Environment and Planning A, 1985, 17(5): 585-596. DOI:10.1068/a170585
[3]  VERBURG P H, SCHOT P, DIJST M, et al. Land-Use Change Modeling: Current Practice and Research Priorities[J]. Geo Journal, 2004, 61(4): 309-324.
[4]  WHITE R, ENGELEN G. Cellular Automata and Fractal Urban Form: A Cellular Modelling Approach to the Evolution of Urban Land-Use Patterns[J]. Environment and Planning A, 1993, 25: 1175-1199. DOI:10.1068/a251175
[5]  马世发, 何建华, 俞艳. 基于粒子群算法的城镇土地利用空间优化模型[J]. 农业工程学报, 2010, 26(9): 321-326.
[6]  杨青生, 黎夏. 基于遗传算法自动获取CA模型的参数——以东莞市城市发展模拟为例[J]. 地理研究, 2007, 26(2): 229-237.
[7]  刘小平, 黎夏, 叶嘉安, 等. 利用蚁群智能挖掘地理元胞自动机的转换规则[J]. 中国科学D辑:地球科学, 2007, 37(6): 824-834.
[8]  LIU Y, PHINN S R. Modeling Urban Development with Cellular Automata Incorporating Fuzzy-Set Approaches[J]. Computers, Environment and Urban Systems, 2003, 27(6): 637-658. DOI:10.1016/S0198-9715(02)00069-8
[9]  刘明皓, 李东鸿. ANN-CA模型改进及城市用地动态模拟[J]. 重庆邮电大学学报(自然科学版), 2014, 26(5): 720-726. DOI:10.3979/j.issn.1673-825X.2014.05.026
[10]  HINTON G E, SALAKHUTDINOV R R. Reducing the Dimensionality of Data with Neural Networks[J]. Science, 2006, 313(5786): 504-507. DOI:10.1126/science.1127647
[11]  HINTON G E, OSINDERO S, TEH Y W. A Fast Learning Algorithm for Deep Belief Nets[J]. Neural Computation, 2006, 18(7): 1527-1554. DOI:10.1162/neco.2006.18.7.1527
[12]  BENGIO Y. Learning Deep Architectures for AI[J]. Foundations and Trends in Machine Learning, 2009, 2(1): 1-127.
[13]  孙劲光, 蒋金叶, 孟祥福, 等. 深度置信网络在垃圾邮件过滤中的应用[J]. 计算机应用, 2014, 34(4): 1122-1125.
[14]  JI N N, ZHANG J S, ZHANG C X, et al. Enhancing Performance of Restricted Boltzmann Machines via Log-Sum Regularization[J]. Knowledge-Based Systems, 2014, 63(3): 82-96.
[15]  KUREMOTO T, KIMURA S, KOBAYASHI K, et al. Time Series Forecasting Using a Deep Belief Network with Restricted Boltzmann Machines[J]. Neurocomputing, 2014, 137(15): 47-56.
[16]  MANTELAS L, PRASTACOS P, HATZICHRISTOS T, et al. Using Fuzzy Cellular Automata to Access and Simulate Urban Growth[J]. Geo Journal, 2012, 77(1): 13-28.
[17]  高红丽, 涂建军, 杨乐. 城市综合承载力评价研究——以成渝经济区为例[J]. 西南大学学报(自然科学版), 2010, 32(10): 148-152.
[18]  吕薇, 刁承泰. 中国城市规模分布演变特征研究[J]. 西南大学学报(自然科学版), 2013, 35(6): 136-141.
[19]  WHITE H. Connectionist Nonparametric Regression: Multilayer Feedforward Networks Can Learn Arbitrary Mappings[J]. Neural Networks, 1990, 3(5): 535-549. DOI:10.1016/0893-6080(90)90004-5
[20]  陈达, 高升, 蔺志青. 基于受限波兹曼机的推荐算法研究[J]. 软件, 2013, 34(12): 156-159, 185.
[21]  KUNCHEVA L. A Bound on Kappa-Error Diagrams for Analysis of Classifier Ensembles[J]. IEEE Transactions on Knowledge and Data Engineering, 2013, 25(3): 494-501. DOI:10.1109/TKDE.2011.234
[22]  赵志元, 张瑞祥. 基于元胞自动机的可修复网络系统可靠性评估模型[J]. 重庆邮电大学学报(自然科学版), 2014, 26(5): 694-699. DOI:10.3979/j.issn.1673-825X.2014.05.022
[23]  BARREDO J I, KASANKO M, MCCORMICK N, et al. Modelling Dynamic Spatial Processes: Simulation of Urban Future Scenarios Through Cellular Automata[J]. Landscape and Urban Planning, 2003, 64(3): 145-160. DOI:10.1016/S0169-2046(02)00218-9
[24]  COHEN J. A Coefficient of Agreement for Nominal Scales[J]. Educational and Psychological Measurement, 1960, 20(1): 37-46. DOI:10.1177/001316446002000104
[25]  刘明皓, 王耀兴, 李东鸿. 城市土地利用动态模拟研究进展[J]. 重庆邮电大学学报(自然科学版), 2013, 25(2): 207-214. DOI:10.3979/j.issn.1673-825X.2013.02.013
[26]  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.
[27]  田旺兰, 李加升. 改进运用深度置信网络的语音端点检测方法[J]. 计算机工程与应用, 2014, 50(20): 207-210. DOI:10.3778/j.issn.1002-8331.1402-0161
[28]  吕启, 窦勇, 牛新, 等. 基于DBN模型的遥感图像分类[J]. 计算机研究与发展, 2014, 51(9): 1911-1918. DOI:10.7544/issn1000-1239.2014.20140199

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133