• EI
    • CSA
    • CABI
    • 卓越期刊
    • CA
    • Scopus
    • CSCD
    • 核心期刊

基于深度置信网络的农用地基准地价评估模型

王华, 罗平, 赵志刚, 聂可

王华, 罗平, 赵志刚, 聂可. 基于深度置信网络的农用地基准地价评估模型[J]. 农业工程学报, 2018, 34(21): 263-271. DOI: 10.11975/j.issn.1002-6819.2018.21.033
引用本文: 王华, 罗平, 赵志刚, 聂可. 基于深度置信网络的农用地基准地价评估模型[J]. 农业工程学报, 2018, 34(21): 263-271. DOI: 10.11975/j.issn.1002-6819.2018.21.033
Wang Hua, Luo Ping, Zhao Zhigang, Nie Ke. Establishment of agricultural land appraisal model based on deep belief network[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2018, 34(21): 263-271. DOI: 10.11975/j.issn.1002-6819.2018.21.033
Citation: Wang Hua, Luo Ping, Zhao Zhigang, Nie Ke. Establishment of agricultural land appraisal model based on deep belief network[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2018, 34(21): 263-271. DOI: 10.11975/j.issn.1002-6819.2018.21.033

基于深度置信网络的农用地基准地价评估模型

基金项目: 国家自然科学基金项目资助(41601418);国土资源部城市土地资源监测与仿真重点实验室开放基金资助课题(KF-2016-02-014);河南省科技攻关项目资助(172102210539;162102210059)

Establishment of agricultural land appraisal model based on deep belief network

  • 摘要: 该文针对现有基准地价评估模型主观性较强及精度不够等问题,提出了一种基于深度学习思想的农用地基准地价评估方法,构建了样本特征集合与地价标签集合的深层网络结构映射关系,并以广东省普宁市农用地基准地价评估为实例,验证了模型的可行性和有效性。结果如下:1)与神经网络、支持向量机这类浅层学习模型相比,深度置信网络模型其对地价的拟合精度要高出3.61%,3.12%;2)在训练样本只有300时,深度置信网络模型对地价的拟合误差为16.43%,比神经网络、支持向量机模型的拟合精度最少要高出6.76个百分点;3)深度置信网络模型对单个样本的运算时间及内存占用比神经网络、支持向量机模型都要高,但在评估精度都达到95%左右的情况下,深度置信网络模型所需训练样本较少,支持向量机训练时间为193 s,而深度置信网络模型耗时187 s,两者耗时基本持平;4)基于DBN模型对耕地评估单元的地价测算结果,将将普宁市耕地评估单元划分为5级,然后利用面积加权法求取对应的级别基准地价范围为21.34~26.23元/m2。上述试验结果表明该方法在对样本点地价的评估精度上要优于传统的浅层方法,并且该模型计算所得普宁市耕地基准地价与耕地质量在空间分布规律上保持一致。
    Abstract: Abstract: The basic prices of agricultural land appraisal (ALA) has the extremely vital significance on establishing a complete set of agricultural land price system and smoothly carry out land assets, such as reasonable allocation of land consolidation rural land management. Existing models such as artificial neural networks, support vector machines, multivariable regression cannot build the complex function relationship fully between the affecting factors and land prices, and the above-mentioned models with shallow structure have no ability to handle a high-dimensional sample set for land appraisal. So deep learning method was firstly introduced into ALA, and a novel method for ALA based on deep belief networks (DBN) was proposed. A group of 19-dimensional original features reflecting status of land location and quality were employed as inputs, and the land prices were used as outputs of DBN model. The parameters of DBN model were firstly initialized by unsupervised learning method with no-label samples, and then fine-tuned by supervised learning method with labeled samples. The land price of each assessment unit can be calculated by using the well-trained DBN deep neural network with the input of feature vector, and the level of assessment unit can be determined by taking advantage of total value frequency distribution histogram, then the benchmark land price for each level can be calculated via the method of area weighted technique. Take the city of Puning in Guangdong province as a case study, feasibility and validity of the model was validated. The results of the present study indicate that: 1) With respect to the artificial neural networks and support vector machines models, the DBN model get better assessment accuracy with a slight increase of 3.61% and 3.12% because of it is able to take the advantage of feature extraction of deep structure, and can enhance its generation ability by a large amount of no-label land price samples; 2) The simulating error of DBN model for land price appraisal is 16.43% when the number of training samples is only 300, which is less than the artificial neural networks and support vector machines models with a least reduction of 6.76%, DBN model gets high assessment accuracy with a small amount of training samples resorting to its unsupervised learning framework, and the assessment accuracy increases with the number of no-label samples; 3) The running time and memory usage of DBN for single training sample is higher than the artificial neural networks and support vector machines models, and the running time of support vector machines model is 193 and 187 s for DBN model when the assessment accuracy reaches about 95%, both of which are equal because of the DBN model need less training samples than the SVM model; 4) The cultivated land assessment units of Puning city are divided into 5 levels based on the their land price results which are calculated based on the DBN model, and the benchmark land price of Puning city ranges from 21.34 to 26.23 yuan/m2 which are calculated based on the area weighted technique. The above experiment results indicate that the assessment accuracy of DBN model is significantly better than the models with shallow structure, and the spatial distribution pattern of benchmark land price and quality level of cultivated land for Puning city are consistent with each other. It is concluded that the method is feasible and effective in measurement and calculation on agricultural base land price.
  • [1] 邓南荣,文雅,张金前,等. 农用地估价中土地还原率和社会保障价格的探讨[J]. 农业工程学报,2008,24(增刊1):164-168.Deng Nanrong, Wen Ya, Zhang Jinqian, et al. Land capitalization rate and social security cost in the evaluation of agricultural land price[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2008, 24(Suppl.1): 164-168. (in Chinese with English abstract)
    [2] 刘跃辰,王秋兵,钱凤魁,等. 灰色模型与回归模型在农用地基准地价评估中的比较分析[J]. 农业工程学报,2010,26(增刊2):344-348.Liu Yuechen, Wang Qiubing, Qian Fengkui, et al. Comparison and analysis of gray model and regression model in basic prices appraisal of agricultural land [J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2010, 26(Suppl.2): 344-348. (in Chinese with English abstract)
    [3] 吴宇哲. 基准地价评估中算术平均方法的应用[J]. 中外房地产导报,2000(9):52-54.
    [4] 张雅杰,唐旭,祝国瑞. 城市基准地价评估回归模型分析与改进[J]. 武汉大学学报(信息科学版),2004,29(6): 551-554.Zhang Yajie, Tang Xu, Zhu Guorui. Improvement on evaluation model for base land price[J]. Geomatics and Information Science of Wuhan University, 2004, 29(6): 551-554. (in Chinese with English abstract)
    [5] 吴群,温修春,唐焱,等. 模型法在农用地基准地价评估中的应用—以江苏省泰兴市为例[J]. 资源科学,2004,26(5):68-73.Wu Qun, Wen Xiuchun, Tang Yan, et al. Application of modeling method in datum price appraisal of arable land: a case study of Taixing city in Jiangsu province[J]. Resources Science, 2004, 26(5): 68-73. (in Chinese with English abstract)
    [6] 姚慧,郑新奇,江吉星. 基于多元线性回归的宗地地价评估—以东营市为例[J]. 资源开发与市场,2006,22(3):228-229.Yao Hui, Zheng Xinqi, Jiang Jixing. Study on zone land price estimation based on regressive equation[J]. Resource Development & Market, 2006, 22(3): 228-229. (in Chinese with English abstract)
    [7] 王满银,肖瑛,汪应宏,等. 中国基准地价评估近10年研究进展[J]. 华中农业大学学报:社会科学版,2011(6): 71-75.Wang Manyin, Xiao Ying, Wang Yinghong, et al. Research progress of appraisal of benchmark land price in China in recent ten years[J]. Journal of Huazhong Agricultural University: Social Sciences Edition, 2011(6):71-75. (in Chinese with English abstract)
    [8] 方乃芳. 宗地地价模糊评估的研究[J]. 辽宁工程技术大学学报, 2005, 24(增刊1): 86-88.Fang Naifang. Research on the price of land with blurring valuation method[J]. Journal of Liaoning Technical University, 2005, 24(Suppl.1): 86-88. (in Chinese with English abstract)
    [9] Bogataj M, Suban D T, Drobne S. Regression-fuzzy approach to land valuation[J]. Central European Journal of Operations Research, 2011, 19(3): 253-265.
    [10] 胡石元,李德仁,刘耀林. 一种新的基于云模型的宗地地价评估方法[J]. 武汉大学学报(信息科学版),2008,23(9):983-985.Hu Shiyuan, Li Deren, Liu Yaolin. A new land price evaluation method based on cloud model[J]. Geomatics and Information Science of Wuhan University, 2008, 23(9): 983-985. (in Chinese with English abstract)
    [11] 刘耀林,傅佩红. Kriging空间分析法及其在地价评估中的应用[J]. 武汉大学学报(信息科学版),2004,29(6):471-474.Liu Yaolin, Fu Peihong. Kriging analysis and its application to urban base land-value evaluation[J]. Geomatics and Information Science of Wuhan University, 2004, 29(6): 471-474. (in Chinese with English abstract)
    [12] 聂艳,周勇,曾菊新. 基于Kriging的宜都市农用地基准地价评估研究[J]. 地域研究与开发,2008,27(4):94-98.Nie Yan, Zhou Yong, Zeng Juxin. Datum land value evaluation of agricultural land of Yidou city based on Kriging spatial analysis[J]. Areal Research and Development, 2008, 27(4): 94-98. (in Chinese with English abstract)
    [13] Lewis O M, Ware J A, Jenkins D. A novel neural network technique for the valuation of residential property[J]. Neural Computing & Applications, 1997, 5(4): 224-229.
    [14] 刘耀林,焦利民. 人工神经网络的基准地价评估方法研究[J]. 地球信息科学学报,2002,4(4):1-6.Liu Yaolin, Jiao Limin. Artificial neural network based method for evaluating basic land price[J]. Journal of Geo-Information Science, 2002, 4(4): 1-6. (in Chinese with English abstract)
    [15] 吴迪军,刘耀林,黄全义. 城镇基准地价评估的人工神经网络模型研究[J]. 测绘科学技术学报,2007,24(4):255-258.Wu Dijun, Liu Yaolin, Huang Quanyi. An artificial neural network appraisal model for urban base land price[J]. Journal of Geomatics Science and Technology, 2007, 24(4): 255-258. (in Chinese with English abstract)
    [16] Sampathkumar V, Santhi M H, Vanjinathan J. Forecasting the land price using statistical and neural network software[J]. Procedia Computer Science, 2015, 57: 112-121.
    [17] 赖红松,吴次芳. 基于GASA优化支持向量机的基准地价测算[J]. 中国土地科学,2008,22(8):56-61.Lai Hongsong, Wu Cifang. Measurement and calculation on base land price based on GASA-optimized support vector machine[J]. China Land Science, 2008, 22(8): 56-61. (in Chinese with English abstract)
    [18] Bengio Y. Learning deep architectures for AI[J]. Foundations and Trends in Machine Learning, 2009, 2(1): 1-127.
    [19] Golovko V A. Deep learning: An overview and main paradigms[J]. Optical Memory & Neural Networks, 2017, 26(1): 1-17.
    [20] Schmidhuber J. Deep learning in neural networks: an overview[J]. Neural Networks the Official Journal of the International Neural Network Society, 2015, 61: 85-117.
    [21] Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507.
    [22] Hinton G E, Osindero S, The Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554.
    [23] Hinton G E. Training products of experts by minimizing contrastive divergence[J]. Neural Computer, 2002, 14(8): 1771-1800.
    [24] 刘洁,李宏,高敏华. 农用地定级与基准地价评估研究—以吐鲁番市为例[J]. 中国农业资源与区划,2011,32(2):6-12.Liu Jie, Li Hong, Gao Minhua. Research on agricultural land classification and datum land price evalution[J]. Chinese Journal of Agricultural Resources and Regional Planning, 2011, 32(2): 6-12. (in Chinese with English abstract)
计量
  • 文章访问数:  1198
  • HTML全文浏览量:  0
  • PDF下载量:  632
  • 被引次数: 0
出版历程
  • 收稿日期:  2018-01-25
  • 修回日期:  2018-08-09
  • 发布日期:  2018-10-31

目录

    /

    返回文章
    返回