DocumentCode :
2891352
Title :
Multi-class Joint Rule Extraction and Feature Selection for Biological Data
Author :
Liu, Sheng ; Patel, Ronak Y. ; Daga, Pankaj R. ; Liu, Haining ; Fu, Gang ; Doerksen, Robert ; Chen, Yixin ; Wilkins, Dawn
Author_Institution :
Dept. of Comput. & Inf. Sci., Univ. of Mississippi, Oxford, MS, USA
fYear :
2011
fDate :
12-15 Nov. 2011
Firstpage :
476
Lastpage :
481
Abstract :
There are a vast number of biology related research problems involving a combination of multiple sources of data to achieve a better understanding of the underlying problems. It is important to select and interpret the most important information from these sources. Thus it will be beneficial to have a good algorithm to simultaneously extract rules and select features for better interpretation of the predictive model. We propose an efficient algorithm, Joint Rule Extraction and Feature Selection (JRF), based on 1-norm regularized random forests. JRF simultaneously extracts a small number of rules generated by random forests and selects important features. We applied JRF to several drug activity prediction and microarray data sets. JRF is capable of producing performance comparable with state-of-the-art prediction algorithms using a small number of decision rules. Some of the decision rules are biologically significant.
Keywords :
biology computing; data handling; learning (artificial intelligence); 1-norm regularized random forest; biological data; decision rules; drug activity prediction; microarray data set; multiclass joint rule extraction and feature selection algorithm; Accuracy; Data mining; Encoding; Feature extraction; Prediction algorithms; Radio frequency; Support vector machines; Feature selection; Multi-Class; Random forests; Rule extraction;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Bioinformatics and Biomedicine (BIBM), 2011 IEEE International Conference on
Conference_Location :
Atlanta, GA
Print_ISBN :
978-1-4577-1799-4
Type :
conf
DOI :
10.1109/BIBM.2011.82
Filename :
6120488
Link To Document :
بازگشت