Dissertation > Excellent graduate degree dissertation topics show

Multi-Class Pattern Analysis on Human Brain MRI Dataset

Author: LiuMeiJie
Tutor: HuDeWen
School: National University of Defense Science and Technology
Course: Control Science and Engineering
Keywords: Resting functional magnetic resonance imaging Structural magnetic resonance imaging Principal Component Analysis Into a group of independent component analysis Support Vector Machine RVM Delete method based on support vector machine recursive feature
CLC: TP391.41
Type: Master's thesis
Year: 2011
Downloads: 37
Quote: 0
Read: Download Dissertation

Abstract


In recent years, the pattern recognition methods have been widely used in the analysis and the study of the magnetic resonance imaging data. With the deepening of the study of the problem, the magnetic resonance imaging data of multi-class problems is increasingly prominent, running mechanism of human brain and brain disease pathology research put forward higher requirements analysis for multi-class mode of pattern recognition technology to provide the applications space . Multi-class problem, this study is mainly focused magnetic resonance imaging data using pattern recognition methods to be analyzed, expect a meaningful analysis of the results. The first three groups as the research object resting fMRI data (schizophrenia patients and their healthy compatriots and normal), through a combination of principal component analysis (Principal Component Analysis, PCA) and non-linear support vector machines (Support Vector Machine, SVM) function of resting fMRI data connection matrix characteristic pattern classification research proved the genetic characteristics of the disease, and from the angle of the pattern classification. Further, in order to obtain proof of genetic characteristics in the brain region of the above three sets of data into a group of independent component analysis (Group Independent Component Analysis, Group, ICA), to obtain 20 independent component. Is characterized by a collection of all independent component, each independent component as a subset of features, using feature fusion, principal component analysis and linear support vector machine for three sets of data twenty-two classification research, consistent with the results of previous studies , i.e., from the perspective of the pattern classification proved the genetic characteristics of the disease, is more important, resulting in the genetic characteristics of the disease, a separate component of the important contribution. Finally, a three-group structure like magnetic resonance data subjects (Alzheimer's patients with mild cognitive impairment patients and normal elderly), combined with improved delete method based on support vector machine recursive feature (Recursive Feature Elimination based on Support Vector Machine, SVM-RFE) and associated vector machine (Relevance Vector Machine, RVM) pattern classification study of the experimental data. From the results of the two categories, we found that the pixel features obtained by the pattern recognition method and the statistical differences study is consistent with the results, mainly responsible for the memory function in the hippocampus and its surrounding region. In addition, exploratory study of the three-group structure like data classification problem, including the \the group with mild cognitive impairment in patients with brain structure has undergone serious changes, and shift forward Alzheimer's disease. Multi-class model by magnetic resonance data analysis, multi-class problem of magnetic resonance imaging data, we are not only a deeper understanding of the physiology and pathology results of magnetic resonance imaging data analysis from the angle of the pattern classification, the promotion of pattern recognition methods research in brain science has an important significance.

Related Dissertations

  1. Research on Automatic Detection Algorithm for Substructure Distress of Highway Pavement Based on SVM,U418.6
  2. Research on Autamatic Music Structrue Analysis,TN912.3
  3. Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
  4. Fault Diagnosis Method Based on Support Vector Machine,TP18
  5. Process Support Vector Machine and Its Application to Satellite Thermal Equilibrium Temperature Prediction,TP183
  6. Application of Improved Principal Component Analysis Algorithm in Course Construction,G642.4
  7. Research for Infrared Image Target Identification and Tracking Technology,TP391.41
  8. Study on the Road Condition Monitoring Based on Vehicular 3D Acceleration Sensor,TP274
  9. Research of Diagnosing Cucumber Diseases Based on Hyperspectral Imaging,S436.421
  10. The Impact of Tourism on Typical Vegetation in Luya Mountain Nature Reserve, Shanxi Province,S759.9
  11. Macaca mulatta palm morphological study of pattern ridge count,Q954
  12. Zhaoguan Lower Coal Group water inrush prediction and control techniques,TD745
  13. Research on Cultural Industrial Competitiveness of Chong Qing,F224
  14. The Research on Intrusion Detection System Based on Machine Learning,TP393.08
  15. Research on Improved K Neighbor Support Vector Machine Algorithm Faced Text Classification,TP391.1
  16. The Research of Prairie Road Light Environment Effects on Physiological Indicators of Drivers,U491.254
  17. Research on Face Recognition Based on AdaBoost Algorithm,TP391.41
  18. Research on Feature Extraction, Selection and Classification Algorithms for Pulmonary CAD,TP391.41
  19. Research on Subimage Selection and Mathching Method for Synthetic Aperture Radar(SAR) Target Recognition,TN957.52
  20. Research Onamethod for Human Face Recognition Based on MMTD,TP391.41
  21. Research of Facial Expression Recognition Algorithm,TP391.41

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Pattern Recognition and devices > Image recognition device
© 2012 www.DissertationTopic.Net  Mobile