您的位置：山东大学 -> 科技期刊社 -> 《山东大学学报（工学版）》

山东大学学报(工学版) ›› 2014, Vol. 44 ›› Issue (4): 22-30.doi: 10.6040/j.issn.1672-3961.0.2014.003

• 控制科学与工程 • 上一篇    下一篇

基于改进粒子群优化神经网络的房地产市场预测

花景新1,2, 薄煜明1, 陈志敏1   

  1. 1. 南京理工大学自动化学院, 江苏 南京 210094;  2. 山东城市建设职业学院, 山东 济南 250103
  • 收稿日期:2014-01-06 修回日期:2014-07-02 发布日期:2014-01-06
  • 通讯作者: 薄煜明（1965-），男，江苏常熟人，研究员，博导，主要研究方向系统工程与智能优化算法.E-mail：byming@mail.njust.edu.cn E-mail:byming@mail.njust.edu.cn
  • 作者简介:花景新（1964-），男，山东济南人，教授，博士，主要研究方向为房地产市场研究与智能算法.E-mail：sdhuajx@163.com
  • 基金资助:
    国家自然科学基金资助项目（61104109）；教育部博士点基金资助项目（20113219110027）；江苏省自然科学基金资助项目（BK2011703）；江苏省科技支撑与自主创新基金资助项目（BE2012178）

Forecasting of real estate market based on particle swarm optimized neural network

HUA Jingxin1,2, BO Yuming1, CHEN Zhimin1   

  1. 1. School of Automation, Nanjing University of Science and Technology, Nanjing 210094, Jiangsu, China;  2. Shandong Urban Construction Vocational College, Jinan 250103, Shandong, China
  • Received:2014-01-06 Revised:2014-07-02 Published:2014-01-06

PDF (PC)

456

摘要： 针对粒子群优化算法精度不高、容易陷入局部最优、难以满足房地产市场形势需求的问题，提出一种改进粒子群优化神经网络，并应用于房地产市场预测中，该算法将混沌引入粒子群优化神经网络算法权重和阈值的初始化与更新的过程，提高了初始样本的质量，减轻了局部极值现象，提高了算法的全局搜索能力，同时设置了躲避因子，使粒子一定程度上离开偏离真实值的区域。研究结果表明，提出的改进算法可以提高粒子群优化神经网络权重和阈值的准确性。

关键词: 权重, 粒子群优化, 混沌, 阈值, 神经网络

Abstract: Particle swarm optimization (PSO) had the defects of low precision, and that were easily to be trapped in local optimization. To solve these problems, an neural network based on improved PSO was proposed for forecasting the real estate market. This algorithm introduced chaos sequence to update the weight and threshold, which could improve the quality of samples, reduce the local optimization and enhance the global searching ability. In addition, the avoid factor was set, which could make the particles be away from low likelihood area. Simulation results showed that this algorithm improved the accuracy of the weight and threshold.

Key words: threshold, particle swarm optimization, neural network, chaos, weight

中图分类号: 

  • TP273
[1] 叶艳兵,丁烈云.房地产预警指标体系设计研究[J].基建优化,2001,22(3):1-3. YE Yanbing, DING Lieyun. Design and study of real estate early warning index system[J].Optimization of Capital Construction, 2001, 22(3):1-3.
[2] 周忠学,李永江.房地产业预警预报系统影响因素的主成分分析[J].企业经济,2003(12):130-132. ZHOU Zhongxue, LI Yongjiang. Factors affecting principal component analysis of the real estate industry warning system[J].Enterprise Economy, 2003(12):130-132.
[3] 李永江.房地产业预警预报系统影响因素的聚类分析[J].经济师,2003(6):256-258. LI Yongjiang. Cluster analysis of factors affecting the real estate industrys early warning and forecasting system[J].China Economist, 2003(6):256-258.
[4] 赵黎明,贾永飞.房地产预警系统研究[J].天津大学学报:社会科学版,1999(12):277-280. ZHAO Liming, JIA Yongfei. Real estate early warning system[J].Journal of Tianjin University: Social Sciences, 1999(12):277-280.
[5] ZHOU Zhengzhu, QU Hongjian, JOYCE Bill. The study of risk warning and controlling of R&D outsourcing: based on BP neural network[J]. International Journal of Strategic Change Management, 2012, 4(3-4):250-265.
[6] LI Mingshun, CHEN Wencui. Application of BP neural network algorithm in sustainable development of highway construction projects[J]. Physics Procedia, 2012(25):1212-1217.
[7] CHEN Qian, HUANG Kama, YANG Xiaoqing, et al. A BP neural network realization in the measurement of material permittivity[J].Journal of Software, 2011, 6(6):1089-1095.
[8] 方正, 佟国峰, 徐心和. 粒子群优化粒子滤波方法[J]. 控制与决策, 2007, 22(3):273-277. FANG Zheng, TONG Guofeng, XU Xinhe. Particle swarm optimized particle filter[J]. Control and decision, 2007, 22(3):273-277.
[9] LI Ying, BAI Bendu, ZHANG Yanning. Improved particle swarm optimization algorithm for fuzzy multi-class SVM[J]. Journal of Systems Engineering and Electronics, 2010, 21(3): 509-513.
[10] YU Zhifu, LI Junwu, LIU Kai. Radar emitter recognition based on PSO-BP network[J]. AASRI Procedia, 2012(1):213-219.
[11] ZHANG W, LIU Y T. Adaptive particle swarm optimization for reactive power and voltage control in power systems[J]. Lecture Note in Computer Science, 2005:449-452.
[12] CHEN Zhimin, BO Yuming, WU Panlong, et al. A new particle filter based on organizational adjustment particle swarm optimization[J]. Applied Mathematics & Information Science, 2013, 7(1):179-186.
[13] JOE Yuichiro Wakano, CHRISTOPH Hauert. Pattern formation and chaos in spatial ecological public goodsgames[J]. Journal of Theoretical Biology, 2011, 268(1):30-38.
[14] LING S H, IU H C F, LEUNG H F, et al. Improved hybrid particle swarm optimized wavelet neural network for modeling the development of fluid dispensing for electronic packaging[J]. IEEE Trans Ind Electron, 2008, 55(9):3447-3460.
[15] RICHARDS M, VENTURA D. Choosing a starting configuration for particle swarm optimization[C]//Proc IEEE Int Joint Conf Neural Network.[S.l.]:[s.n.]: 2004(3):2309-2312.
[16] ZHU Zhiliang, ZHANG Wei, WONG Kwok. A chaos-based symmetric image encryption scheme using a bit-level permutation[J]. Information Sciences, 2011, 181(6):1171-1186.
[17] CHEN Zhimin, BO Yuming, WU Panlong, et al. A particle filter algorithm based on chaos particle swarm optimization and its application to radar target tracking[J]. Journal of Computational Information Systems, 2012, 8(7): 3081-3090.
[18] XINYU X, BAOXIN L. Adaptive rao-blackwellized particle filter and its evaluation for tracking in surveillance[J].IEEE Transactions on Image Processing, 2007,16(3):838-849.
[19] JOE Yuichiro Wakano, CHRISTOPH Hauert. Pattern formation and chaos in spatial ecological public goodsgames[J]. Journal of Theoretical Biology, 2011, 268(1):30-38.
[1] 王东晓. 具有纠缠项的分数阶五维混沌系统滑模同步的两种方法[J]. 山东大学学报(工学版), 2018, 48(5): 85-90.
[2] 沈冬冬,周风余,栗梦媛,王淑倩,郭仁和. 基于集成深度神经网络的室内无线定位[J]. 山东大学学报(工学版), 2018, 48(5): 95-102.
[3] 张璞,刘畅,王永. 基于特征融合和集成学习的建议语句分类模型[J]. 山东大学学报(工学版), 2018, 48(5): 47-54.
[4] 李广丽,刘斌,朱涛,殷依,张红斌. 基于优选典型相关分量的跨媒体检索模型[J]. 山东大学学报(工学版), 2018, 48(5): 38-46.
[5] 梁蒙蒙,周涛,夏勇,张飞飞,杨健. 基于PSO-ConvK卷积神经网络的肺部肿瘤图像识别[J]. 山东大学学报(工学版), 2018, 48(5): 77-84.
[6] 张宪红,张春蕊. 基于六维前馈神经网络模型的图像增强算法[J]. 山东大学学报(工学版), 2018, 48(4): 10-19.
[7] 孟晓玲,王建军. 一类分数阶冠状动脉系统的混沌同步控制[J]. 山东大学学报(工学版), 2018, 48(4): 55-60.
[8] 毛北行. 纠缠混沌系统的比例积分滑模同步[J]. 山东大学学报(工学版), 2018, 48(4): 50-54.
[9] 王换,周忠眉. 一种基于聚类的过抽样算法[J]. 山东大学学报(工学版), 2018, 48(3): 134-139.
[10] 赵彦霞, 王熙照. 基于SVD和DCNN的彩色图像多功能零水印算法[J]. 山东大学学报(工学版), 2018, 48(3): 25-33.
[11] 曹雅,邓赵红,王士同. 基于单调约束的径向基函数神经网络模型[J]. 山东大学学报(工学版), 2018, 48(3): 127-133.
[12] 谢志峰,吴佳萍,马利庄. 基于卷积神经网络的中文财经新闻分类方法[J]. 山东大学学报(工学版), 2018, 48(3): 34-39.
[13] 何正义,曾宪华,郭姜. 一种集成卷积神经网络和深信网的步态识别与模拟方法[J]. 山东大学学报(工学版), 2018, 48(3): 88-95.
[14] 唐乐爽,田国会,黄彬. 一种基于DSmT推理的物品融合识别算法[J]. 山东大学学报(工学版), 2018, 48(1): 50-56.
[15] 宋正强,杨辉玲,肖丹. 基于在线粒子群优化方法的IPMSM驱动电流和速度控制器[J]. 山东大学学报(工学版), 2018, 48(1): 112-116.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2018 《山东大学学报(工学版)》编辑部　
地址: 济南市山大南路27号（250100）　 电话: 0531-88366735　 E-mail: xbgxb@sdu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发