Please use this identifier to cite or link to this item: http://hdl.handle.net/10603/4331
Title: Machine learning for data mining in medicine
Researcher: Pushparaj, M Solomon
Guide(s): Kulkarni, P J
Keywords: Computer Sciences
Upload Date: 21-Aug-2012
University: Shivaji University
Completed Date: 2008
Abstract: Data mining is a process that uses a variety of data analysis tools to discover patterns and relationships in data that may be used to make valid predictions. Classification, clustering, prediction, association, rule extraction and sequence detection are the various types of problems we can solve through data mining. Data Mining for Biological problems are one of the ten challenging problems listed out by the data mining research community. Human medical data are the most rewarding and difficult of all biological data to mine and analyze. Volume and Complexity of medical data, Physicians interpretation, sensitivity and specificity analysis, Poor mathematical characterization are the some of the points tells about the heterogeneity of medical data. In our literature survey we found the Pima Indian Diabetes data set from the medicine domain is used by the data mining researchers to test their data mining algorithms classification performance. Twenty two different machine learning methods are applied in the Pima Indian Diabetes dataset and its average standard error rate is 26.20%. The Diabetes dataset is very difficult to classify because it has lot of missing values. As per our knowledge no single Hybrid data mining method is created to reduce the error rate in the Pima Indian Diabetes data set. We created a hybrid model using the Artificial Neural Network Back propagation Algorithm and Case Base Reasoning k- Nearest Neighbor method. Our Hybrid method gives 84.16% classification performance. It is near to 7% more than the earlier method s classification performances.
Pagination: 192p.
URI: http://hdl.handle.net/10603/4331
Appears in Departments:Department of Computer Science

Files in This Item:
File Description SizeFormat 
01_title.pdfAttached File24.16 kBAdobe PDFView/Open
02_declaration.pdf24.27 kBAdobe PDFView/Open
03_certificate.pdf26.91 kBAdobe PDFView/Open
04_acknowledgements.pdf27.5 kBAdobe PDFView/Open
05_contents.pdf36.99 kBAdobe PDFView/Open
06_abstract.pdf31.46 kBAdobe PDFView/Open
07_chapter 1.pdf85.29 kBAdobe PDFView/Open
08_chapter 2.pdf129.55 kBAdobe PDFView/Open
09_chapter 3.pdf658.8 kBAdobe PDFView/Open
10_chapter 4.pdf533.46 kBAdobe PDFView/Open
11_chapter 5.pdf487.69 kBAdobe PDFView/Open
12_conclusions.pdf42.32 kBAdobe PDFView/Open
13_publications.pdf3.7 MBAdobe PDFView/Open
14_appendix.pdf284.57 kBAdobe PDFView/Open
15_references.pdf46.65 kBAdobe PDFView/Open


Items in Shodhganga are protected by copyright, with all rights reserved, unless otherwise indicated.