DocumentCode :
3538387
Title :
A fuzzy classification system based on memetic algorithm for cancer disease diagnosis
Author :
Shabgahi, A.Z. ; Abadeh, Mohammad Saniee
Author_Institution :
Fac. of Electr. & Comput. Eng., Tarbiat Modares Univ., Tehran, Iran
fYear :
2011
fDate :
14-16 Dec. 2011
Firstpage :
5
Lastpage :
10
Abstract :
Classification systems have been widely utilized in medical domain to explore patient´s data and extract a predictive model. This model helps physicians to improve their prognosis, diagnosis or treatment planning procedures. Cancer disease is one of the main research topics in the medical field. We are looking for to develop a computer system for powerful and reliable cancer diagnostic model development based on microarray data. An accurate classifier with linguistic interpretability using a small number of relevant genes is beneficial to microarray data analysis and development of inexpensive diagnostic tests. The aim of this paper is to use a Memetic (Genetic Local Search) classification system to extract a set of fuzzy rules for diagnosis of cancer disease. A new memetic algorithm has been proposed which is capable of extracting interprétable and accurate fuzzy if-then rules from cancer data. In this paper, we applied our system on 14_Tumors dataset and we´ll show that our approach is useful in cancer tumor detection based on the results.
Keywords :
cancer; cellular biophysics; fuzzy reasoning; genetics; patient diagnosis; patient treatment; tumours; cancer diagnostic model development; cancer disease diagnosis; cancer tumor detection; classification systems; fuzzy classification system; gene expression classifier; genes; genetic local search classification; memetic algorithm; memetic classification; microarray data; predictive model; treatment planning procedure; Biomedical engineering; Conferences; Cancer Disease Diagnosis; Fuzzy Classifier; Gene Expression Data; Gene Selection; Memetic Algorithm; Rule Learning;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Biomedical Engineering (ICBME), 2011 18th Iranian Conference of
Conference_Location :
Tehran
Print_ISBN :
978-1-4673-1004-8
Type :
conf
DOI :
10.1109/ICBME.2011.6168585
Filename :
6168585
Link To Document :
بازگشت