DocumentCode :
2240184
Title :
Advanced local feature selection in medical diagnostics
Author :
Puuronen, Seppo ; Tsymbal, Alexey ; Skrypnyk, Iryna
Author_Institution :
Dept. of Comput. Sci. & Inf. Syst., Jyvaskyla Univ., Finland
fYear :
2000
fDate :
2000
Firstpage :
25
Lastpage :
30
Abstract :
Current electronic data repositories contain enormous amounts of data, especially in medical domains, where data is often feature-space heterogeneous, so that different features have different importance in different sub-areas of the whole space. In this paper, we suggest a technique that searches for a strategic splitting of the feature space, identifying the best subsets of features for each instance. Our technique is based on the wrapper approach, where a classification algorithm is used as the evaluation function to differentiate between several feature subsets. We apply a recently developed technique for the dynamic integration of classifiers and use decision trees. For each test instance, we consider only those feature combinations that include features that are present in the path taken by the test instance in the decision tree. We evaluate our technique on medical data sets from the UCI machine learning repository. The experiments show that local feature selection is often advantageous in comparison with feature selection on the whole space
Keywords :
data mining; decision trees; feature extraction; learning (artificial intelligence); medical diagnostic computing; medical expert systems; medical information systems; pattern classification; UCI machine learning repository; best feature subsets; classification algorithm; decision trees; dynamic classifier integration; electronic data repositories; evaluation function; feature importance; feature-space heterogeneous data; local feature selection; medical data sets; medical diagnostics; strategic feature-space splitting; wrapper approach; Medical diagnosis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer-Based Medical Systems, 2000. CBMS 2000. Proceedings. 13th IEEE Symposium on
Conference_Location :
Houston, TX
ISSN :
1063-7125
Print_ISBN :
0-7695-0484-1
Type :
conf
DOI :
10.1109/CBMS.2000.856868
Filename :
856868
Link To Document :
بازگشت