Dissertation > Excellent graduate degree dissertation topics show

Study of Economic Forecasting in Harbour Engineering Project

Author: WangLin
Tutor: WangYuanZhan
School: Tianjin University
Course: Port, Coastal and Offshore Engineering
Keywords: BP neural network Genetic Algorithms Gray model multivariate linear model Combination Forecasting Random number Cargo throughput
CLC: F550
Type: Master's thesis
Year: 2003
Downloads: 333
Quote: 10
Read: Download Dissertation

Abstract


The core of the management decision-making , scientific prediction is the guarantee of the right decisions . Economic forecasts are widely used in socio-economic sectors , in planning the future development strategy or investment projects need more accurate grasp of the future economic development of the situation , the direction for decision-makers . Port project accurately predict the future development of the port throughput level , is the key to determine the port construction scale . This paper, on the basis of the basic concepts of economic forecasts , three independent economic forecasting model , and a combination forecasting model is given . The basic concept of neural networks , genetic algorithms , gray theory and linear regression analysis , the computing process the ( modeling method ) , test indicators . Proposed the improved method of the neural networks and genetic algorithms and neural network combined to improve the performance of the model . Gray model of the defect in the modeling process , the GM (1,1) model to improve the accuracy of model fitting . The most commonly used linear regression models , the modeling process is given , and focus on model checking and correction method . The three models from different angles of the relevant economic variables to predict , from the integrity of the information considered one-sidedness , the paper also gives the combination forecasting model . The paper describes in detail the optimum combination of the presence of judgment and the screening of non-negative constraints , given the constant weight combination forecasting model quadratic programming algorithm . Tianjin Port , for instance , to study the development of its cargo throughput from a different angle , each individual model fitting accuracy to BP neural network model based on genetic algorithms , multiple linear regression model , followed by the lowest of gray model accuracy . However, the combination of the three predictive model accuracy higher than all of the individual model , which also shows the combination forecasting model from multiple perspectives , consider the full range of various factors , determine the theoretical value more fit actual , even with low accuracy the models also improve the overall accuracy of the combined forecasting model .

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. Development of the on-line Training and Examination System of Army,TP311.52
  5. Designs and Applications of Fuzzy Synthetic Evaluation Models Based on Parallel Algorithms,TP18
  6. Study on Taste Characteristic of Taste Peptide Enzymatic Production from Oyster Base on A Neural Network Method,TS254.4
  7. The Research on Evaluation of Living Status Systems of Expressway Relocated People,D523
  8. Mine Risk Information Integration and Intelligent Early Warning,X936
  9. Based on Genetic Algorithm Pishihang irrigation canal water allocation marshalling model of,S274
  10. Genetic Algorithm in logistics and warehousing Optimization Research,F259.2
  11. Mining resources based on genetic algorithm optimization model of,O224
  12. Research of Orange Quality Classification Technology Based on Computer Vision,TP391.41
  13. The Research and Application of Modified Algorithms About Fuzzy Predictive Functional Control,TP273
  14. Optimization Study on Gating System and Molding Process Parameters of Injection Mold Based on Simulation,TQ320.662
  15. Study on Luohe Technical Supervision Bureau of Food Safety Early Warrning System Based on Neural Network,F203
  16. Research of Adaptive Active Noise Control Based on Neural Network,TP183
  17. Optimal Control of Emulsion System in Cold Rolling,TP273
  18. Research on the Marshalling-scheduling Model and Algorithms of Freight Trains Based on Game Theory,O225
  19. Research on Automatic Reading System for Digital Meters,TP391.41
  20. Research on Feature Extraction, Selection and Classification Algorithms for Pulmonary CAD,TP391.41
  21. Multi-directional Mutation Genetic Algorithm and Research on Neural Network Optimization,TP18

CLC: > Economic > Transportation and economic > Sea transport and economic > Waterway transport economic theory
© 2012 www.DissertationTopic.Net  Mobile