DocumentCode :
2850707
Title :
An adaptive learning approach for noisy data streams
Author :
Chu, Fang ; Wang, Yizhou ; Zaniolo, Carlo
Author_Institution :
Dept. of Comput. Sci., California Univ., Los Angeles, CA, USA
fYear :
2004
fDate :
1-4 Nov. 2004
Firstpage :
351
Lastpage :
354
Abstract :
Two critical challenges typically associated with mining data streams are concept drift and data contamination. To address these challenges, we seek learning techniques and models that are robust to noise and can adapt to changes in timely fashion. We approach the stream-mining problem using a statistical estimation framework, and propose a fast and robust discriminative model for learning noisy data streams. We build an ensemble of classifiers to achieve timely adaptation by weighting classifiers in a way that maximizes the likelihood of the data. We further employ robust statistical techniques to alleviate the problem of noise sensitivity. Experimental results on both synthetic and real-life data sets demonstrate the effectiveness of this model learning approach.
Keywords :
data mining; learning (artificial intelligence); noise; pattern classification; statistical analysis; adaptive learning; concept drift; data contamination; noise sensitivity; noisy data streams; robust statistical techniques; statistical estimation; stream mining; Bagging; Computer science; Contamination; Data mining; Monitoring; Noise robustness; Telecommunication traffic; Traffic control; Voting; Working environment noise;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Data Mining, 2004. ICDM '04. Fourth IEEE International Conference on
Print_ISBN :
0-7695-2142-8
Type :
conf
DOI :
10.1109/ICDM.2004.10049
Filename :
1410308
Link To Document :
بازگشت