Dissertation > Excellent graduate degree dissertation topics show

The Traffic Forecasts Based on GM-BP Model

Author: WeiLiJun
Tutor: ZhaoGaoChang
School: Xi'an University of Science and Technology
Course: Applied Mathematics
Keywords: Grey Theory BP neural network GM (1,1) model Forecast
CLC: U491
Type: Master's thesis
Year: 2011
Downloads: 64
Quote: 1
Read: Download Dissertation

Abstract


Urban traffic congestion , frequent traffic accidents have become a social problem that can not be ignored . The basic idea of traffic forecast is based on accident statistics, analysis and processing , the cause of the accident and the development of variation , the accident has not yet occurred or is not clear in advance to make logical of the speculated judge . This paper first introduces the basic theoretical knowledge of traffic accident prediction : prediction theory gray system theory , BP neural network . Secondly , based on the advantages and disadvantages of several previously described method of road traffic accident prediction , choose gray forecasting model and BP neural network based on using a combination of GM-BP ( gray system model -BP neural networks) prediction model to forecast traffic accident . Slow speed of learning , the objective function is the lack of local minima , proposed an improved fast algorithm , using a combination of the momentum term and adaptive learning rate method to improve the learning rate for the standard BP algorithm ; in poor prediction accuracy the exponentially rapid changes in the data sequence drawback for road traffic accidents gray GM (1,1) model prediction method using unbiased GM (1,1) model for road traffic accidents forecast new methods. Finally, with examples , the improved fast algorithm and improved GM (1,1) model of the important factors of road traffic safety indicators - road traffic accidents caused direct economic losses were predicted , verify that the combination of model prediction in road traffic accidents the validity . The experimental results show better results than a single model forecast , higher precision , and increase the usefulness of the model in a road traffic accident prediction .

Related Dissertations

  1. Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
  2. Research on Visual Servo System of Mechanical ARM,TP242.6
  3. Municipal tourism land use planning environmental impact assessment,X820.3
  4. Study on Taste Characteristic of Taste Peptide Enzymatic Production from Oyster Base on A Neural Network Method,TS254.4
  5. Application of Numerical Designing Cigarette Blending Formula on Computational Intelligence,TS44
  6. The Evaluation and Forecasting Research on Uncertainty Systems Method of Student Achievement,G642.4
  7. Research on the Evaluation of Straw Resource and the Development of Scale-Up Straw Energy Utilization in Jiangsu Province,S38
  8. Study on Growth Monitoring Technique Based on Pixel Un-Mixing Method and HJ Remote Sensing Images in Paddy Rice,S511
  9. The Research of Prediction of Lean Yield with CSB Image-Meater and Pork Carcass Grading System,S828
  10. The Research on Evaluation of Living Status Systems of Expressway Relocated People,D523
  11. Research on Talents Team in Hefei-Wuhu-Bengbu Based on Independent Innovation,C964.2
  12. TV weather programs \,G222
  13. Zhaoguan Lower Coal Group water inrush prediction and control techniques,TD745
  14. Mine Risk Information Integration and Intelligent Early Warning,X936
  15. Research of Orange Quality Classification Technology Based on Computer Vision,TP391.41
  16. Research on the Feasibility of Highway Construction Project,F542
  17. Analysis of China’s Household Electrical Appliance Industry Supply Chain Integration,F426.6
  18. Analysis on Synoptic Climatology Characteristics and Forecast Methods of Fog in Hainan,P457
  19. Optimization Study on Gating System and Molding Process Parameters of Injection Mold Based on Simulation,TQ320.662
  20. Study on Luohe Technical Supervision Bureau of Food Safety Early Warrning System Based on Neural Network,F203
  21. Research of Adaptive Active Noise Control Based on Neural Network,TP183

CLC: > Transportation > Road transport > Technical management of traffic engineering and road transport > Traffic engineering and traffic management
© 2012 www.DissertationTopic.Net  Mobile