Dissertation > Excellent graduate degree dissertation topics show

Classification Research on Chinese Medicine Syndrome of Heart Disease and Its Applications

Author: DengFeng
Tutor: XiaChunMing
School: East China University of Science and Technology
Course: Mechanical and Electronic Engineering
Keywords: Syndromes BP neural network SVM support vector machine GA genetic algorithm The PSO particle swarm optimization algorithm
CLC: TP18
Type: Master's thesis
Year: 2011
Downloads: 45
Quote: 0
Read: Download Dissertation

Abstract


TCM diagnosis is access to a multi- source information processing and integration process , the traditional Chinese medicine diagnosis often depends on the physician's subjective consciousness and experience accumulated by the limitations of the environmental factors , the lack of objective indicators , it is difficult to repeat the verification . The TCM syndrome lack of objective and quantitative and standardized , largely limits its application and development . Therefore , the use of information on scientific methods The TCM diagnostic information acquisition and processing technology research , has a very important significance . In this paper, 503 cases of Chinese medicine heart samples of four diagnostic information , to explore heart disease symptoms and syndromes dialectical analysis , research content and work as follows: the use of BP (Back Propagation) neural network learning and forecast data samples , this method to solve easy to fall into local optimal problem using genetic algorithms (GA, Genetic Algorithms) to optimize BP neural network weights and threshold values ??, to find the global optimum , and GA genetic algorithm independent variable dimensionality reduction to improve BP neural network computing speed and accuracy of classification ; important use of support vector machine (SVM, Support Vector Machine) learning and prediction of the data samples , compare grid search method , GA genetic algorithm and particle swarm optimization (PSO, Particle Swarm Optimization) two types of SVM parameter optimization results; using VB language and ACCESS database . NET - based platform , completed the integration of the four diagnostic diagnostic system . Tests proved that the use of the BP neural network and SVM SVM common heart disease five kinds of syndromes total average accuracy rate is 65.80% and 71.24% , respectively ; based GA genetic algorithm BP neural network , the average correct rate is 68.3% ; GA-SVM and PSO-SVM predicted average accuracy rate of 71.82% and 72.47% , compared to a grid search method , two evolutionary algorithms more competitive in the global optimal convergence rate , and the prediction accuracy of the PSO-SVM highest ; completed the integration of the four diagnostic diagnostic system to meet the sample collection, data management , data analysis , and user management needs , and embedded in the data analysis module BP neural network and SVM support vector machine two intelligent analysis , convenient implementation of online diagnostics .

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. Study on Correlation between TCM Syndrome Types and IFN-γ in Patients with Chronic Hepatitis B,R259
  4. Research on the Correlativity between the Common Chinese Medicine Syndromes of CHF and UA、LVMI,R259
  5. Isolated systolic hypertension in patients with cardiac ultrasound characteristics of traditional Chinese medicine dialectical correlation exploration,R544.1
  6. Municipal tourism land use planning environmental impact assessment,X820.3
  7. Integrative treatment of elderly patients with hypertension TCM syndromes and quality of life,R544.1
  8. Study on Taste Characteristic of Taste Peptide Enzymatic Production from Oyster Base on A Neural Network Method,TS254.4
  9. The Research on Evaluation of Living Status Systems of Expressway Relocated People,D523
  10. Mine Risk Information Integration and Intelligent Early Warning,X936
  11. Research of Orange Quality Classification Technology Based on Computer Vision,TP391.41
  12. Optimization Study on Gating System and Molding Process Parameters of Injection Mold Based on Simulation,TQ320.662
  13. Design of Positive Draw-back Motion of Wool Spinning Frame and Comparison of Prediction Models of Worsted Yarns Performances,TP183
  14. Study on Luohe Technical Supervision Bureau of Food Safety Early Warrning System Based on Neural Network,F203
  15. Research of Adaptive Active Noise Control Based on Neural Network,TP183
  16. Modeling and Simulation Software Design for the Glutamic Acid Fermentation,TQ922.1
  17. Research on Automatic Reading System for Digital Meters,TP391.41
  18. Research on Feature Extraction, Selection and Classification Algorithms for Pulmonary CAD,TP391.41
  19. Research on State Diagnosis on Fan Based on Factor Analysis and BP Neural Network,F426.61
  20. Analysis on Water Ecological Carrying Capacity of Jiangxi Province,TV213.4
  21. Research Offingerprint of Communication Behavior,TP311.13

CLC: > Industrial Technology > Automation technology,computer technology > Automated basic theory > Artificial intelligence theory
© 2012 www.DissertationTopic.Net  Mobile