الفهرس Only 14 pages are availabe for public view
 |  | from | 129 |  |  |
| | | from | 129 | | |
Abstract
Cancer classification based on molecular level investigation has gained the interest of research papers as it provides a systematic, accurate and objective diagnosis. Several recent researches have been studying the problem of cancer classification using data mining methods, machine learning algorithms and statistical methods to reach an efficient analysis for gene expression profiles. Studying the characteristics of thousands of genes simultaneously offered a deep insight into cancer classification problem. Microarray technology introduced an abundant amount of data ready to be explored. It has been applied in wide range of applications such as drug discovery, cancer prediction and diagnosis. It has enriched the study of gene expressions in such a way that scientists are now able to understand the function of genes and the interaction between genes in normal and abnormal conditions. That is done by monitoring the behavior of gene expression profiles under different conditions. This Thesis investigates several classification algorithms and their suitability to the biological domain. For applications that suffer from the high dimensionality, different feature selection methods are considered for illustration and analysis. Moreover, an effective ensemble system is proposed. In addition, Experiments are carried out against three well-known benchmark gene expression datasets. The proposed ensemble system is assessed and compared with related work performance. The motivation beyond using ensemble classifiers is that ensemble classifiers increase not only the performance of the classification, but also the confidence of the results as results are less dependent on peculiarities of a single training set. The results indicate significant improvements in classification accuracy and the credibility of the proposed system