Dissertation > Excellent graduate degree dissertation topics show

The Application of Support Vector Machines on Medical and Bioinformatics

Author: WangYi
Tutor: WanFuYong
School: East China Normal University
Course: Operational Research and Cybernetics
Keywords: Support Vector Machine The diagnosis of breast cancer MicroRNA Cross-entropy Filter Information Biology
CLC: R318.6
Type: Master's thesis
Year: 2007
Downloads: 174
Quote: 2
Read: Download Dissertation

Abstract


The support vector machine (SVM) is a data mining of the 1990s developed a new method , it showed very good results in many areas of practical application . The main work of this paper is the successful application of SVM two . On the diagnosis of breast cancer , support vector machine classifier with good generalization . We use the asymmetric punishment of C-SVM to solve the problem of asymmetric number of positive and negative class samples ; based generalization sector with fast parameter search method , this method than simply k -fold cross- validation search parameters faster . Use the cross-entry filter feature selection , we get a better predictive accuracy . SVM other applications are prediction plant microRNA precursors . microRNAs (miRNAs) are a class of non - protein-coding small molecule RNA of about 22 bases in length , has played a very important role in the growth and development of multi-cellular organisms . In this research , we have developed a whole new SVM classifier is used to search for plants miNRA precursor . This classification model used on behalf of the precursor 12 global and sub- structure characteristics , training of 790 positive class samples and 7900 negative class samples , model half of the amount of accuracy rate is 96.43% . To test the newly discovered 53 plant miRNA precursors (n- type) and of 62,883 negative class SVM classifier accuracy of 99.85% , a sensitivity of 79.25% and 99.87% specificity . Very good specificity makes the method applied to the genome level prediction of plant miRNA genes become possible , and this method can only use a single genome sequence information to predict which species-specific miRNA genes will be found to provide a very effective tool .

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. Research and Application of Diverse Density Learning Algorithm,TP181
  5. Fault Diagnosis Method Based on Support Vector Machine,TP18
  6. Process Support Vector Machine and Its Application to Satellite Thermal Equilibrium Temperature Prediction,TP183
  7. Bioinformatics Study of Motifs Within 3’UTR Region of Stress Response Genes and Functional Related Mirnas in Rice,Q943.2
  8. Computational Identification and Characterization of Microrna Genes from Agricultural Insects,S186
  9. Identification and Analysis of miRNA and Flower Development Specific Genes in Wheat,S512.1
  10. Effect of in Ovo Leptin Administration on Hepatic Expression of Genes and Micrornas Involved in Cholesterol Metabolism in Broiler Chickens,S831
  11. Research for Infrared Image Target Identification and Tracking Technology,TP391.41
  12. Study on the Road Condition Monitoring Based on Vehicular 3D Acceleration Sensor,TP274
  13. Research of Diagnosing Cucumber Diseases Based on Hyperspectral Imaging,S436.421
  14. The Studies of Celecoxib Affecting Its Expression Profiles of microRNA Mechanisms on Human Colon Cancer Cell Line HT-29 in Vitro,R735.35
  15. Epithelial-Mesenchymal Transition (EMT) and the Expressive Effect of Emt on microRNAs in Lung Cancer A549 Cells,R734.2
  16. The Research on Intrusion Detection System Based on Machine Learning,TP393.08
  17. Research on Improved K Neighbor Support Vector Machine Algorithm Faced Text Classification,TP391.1
  18. Detection Technology of MicroRNA-21 for Non-small Cell Lung Cancer,R734.2
  19. Research on Face Recognition Based on AdaBoost Algorithm,TP391.41
  20. Research on Feature Extraction, Selection and Classification Algorithms for Pulmonary CAD,TP391.41
  21. Research on Subimage Selection and Mathching Method for Synthetic Aperture Radar(SAR) Target Recognition,TN957.52

CLC: > Medicine, health > Basic Medical > Medical science in general > Biomedical Engineering > Apparatus, equipment
© 2012 www.DissertationTopic.Net  Mobile