Skip to Main Content
Frequently Asked Questions
Submit an ETD
Global Search Box
Need Help?
Keyword Search
Participating Institutions
Advanced Search
School Logo
Files
File List
akron1205514796.pdf (2.39 MB)
ETD Abstract Container
Abstract Header
Application of Committee Neural Networks for Gene Expression Based Leukemia Classification
Author Info
Sewak, Mihir S.
Permalink:
http://rave.ohiolink.edu/etdc/view?acc_num=akron1205514796
Abstract Details
Year and Degree
2008, Master of Science in Engineering, University of Akron, Biomedical Engineering.
Abstract
The present study was an effort to design a Committee Neural Networks-based classification system to subcategorize leukemia cancer data. The need for automated classification arose from the limitations of the traditional techniques which are tedious,time consuming and expensive. In this study, two intelligent systems were designed that classified Leukemia cancer data into its subclasses. The first was a binary classification system that differentiated Acute Lymphoblastic Leukemia from Acute Myeloid Leukemia. The second was a ternary classification system which further considered the subclasses of Acute Lymphoblastic Leukemia. Gene expression profiles of leukemia patients were first subjected to a sequence of preprocessing steps. This resulted in filtering out approximately 95 percent of the genes. The remaining 5 percent of the informative genes were used to train a series of artificial neural networks. These networks were trained using different subsets of the preprocessed data. The networks that produced the best results were further recruited into decision making committees. The training and recruitment procedure enlists the best networks with different background information acting in parallel in a decision making process. The committee neural network systems were later evaluated using data not used in training. The systems correctly predicted the subclasses of Leukemia in 100 percent of the cases for the binary classification system and in more than 97 percent of the cases for the ternary classification system.
Committee
Narender Reddy (Advisor)
Zhong-Hui Duan (Advisor)
Pages
104 p.
Subject Headings
Bioinformatics
;
Biomedical Research
Keywords
Machine Learning
;
Neural Networks
;
Cancer
;
Leukemia
;
Committee
;
Classification
;
T Cell
;
B Cell
;
Recommended Citations
Refworks
EndNote
RIS
Mendeley
Citations
Sewak, M. S. (2008).
Application of Committee Neural Networks for Gene Expression Based Leukemia Classification
[Master's thesis, University of Akron]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=akron1205514796
APA Style (7th edition)
Sewak, Mihir.
Application of Committee Neural Networks for Gene Expression Based Leukemia Classification.
2008. University of Akron, Master's thesis.
OhioLINK Electronic Theses and Dissertations Center
, http://rave.ohiolink.edu/etdc/view?acc_num=akron1205514796.
MLA Style (8th edition)
Sewak, Mihir. "Application of Committee Neural Networks for Gene Expression Based Leukemia Classification." Master's thesis, University of Akron, 2008. http://rave.ohiolink.edu/etdc/view?acc_num=akron1205514796
Chicago Manual of Style (17th edition)
Abstract Footer
Document number:
akron1205514796
Download Count:
975
Copyright Info
© 2008, all rights reserved.
This open access ETD is published by University of Akron and OhioLINK.