Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 40086 (19)
- University: Sharif University of Technology
- Department: Computer Engineering
- Advisor(s): Abolhassani, Hassan
- Abstract:
- Gene expression using microarrays technology has special importance in biology studies especially in cancer researches. Using this technology we can assess expression level of several thousand genes simultaneously. One of the major applications of this technology is diseases’ diagnosis which cancers are the most important types of them. The problem in classifying microarray data is its high dimension; although number of samples hardly exceeds a hundred. This severe asymmetry and high dimensionality, results in reduction of accuracy, speed, stability and generalization of classification methods. Thus, one of the most important issues in cancer diagnosis is selection of related and useful genes. Selected genes can be used in classifiers. They also include useful information about the relation between cancer and genes which can be benefited in supplementary researches in cancer area. Since selected genes are the basis for future studies, stability of selected subset of genes becomes very essential; meaning that a gene selection method should be stable against slight changes in the input data. A stable gene selector provides assurance to use selected genes. In this dissertation, we formally define the concept of stability and present a gene selection method based on ensemble learning. Experimental results show that presented ensemble method remarkably increases its base gene selector methods. Moreover, classification accuracy using selected genes improves slightly.
- Keywords:
- Stability ; Microarray Data ; Ensemble Learning ; Cancer Diagnosis ; Gene Selection
Digital Object List-
محتواي پايان نامه - view
Bookmark