[1]FU Chun-yan,GE Mao-song.A data stream classification methods adaptive to concept drift[J].CAAI Transactions on Intelligent Systems,2007,2(4):86-91.
Copy

A data stream classification methods adaptive to concept drift

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 2 Number of periods: 2007 4 Page number: 86-91 Column: 学术论文—机器学习 Public date: 2007-08-25
Title:
A data stream classification methods adaptive to concept drift
Author(s):
FU Chun-yan;  GE Mao-song
Commonality Teaching Department of Computer, Jiamusi University, Jiamus i 154007，China
Keywords:
data streams;  classification;  concept drifting;  onli n e learning;  decision tree
CLC:
TP311.13
DOI:
-
Abstract:
At present, most classification methods for data streams are developed with the assumption of steady data distribution. However, the data collected fr om the real world will change over a period of time in the underlying concepts ( known as concept drifting). This lowers the predictive precision of a classifica tion model. This paper proposes a classification algorithm that can identify and adapt to occurrences of concept drifting according to the characteristics of the data stream. Experiments show that the proposed algorithm dynamically adjusts the size of the training window and the number of new examples during model rec onstruction according to the current rate of concept drifting.
References:
［1］QUINLAN J R. Induction on decision trees［J］. Machine Learning,1986,13(1 ):81-106.
［2］QUINLAN J R.C4.5:programs for machine learning［M］.San Mateo:Morgan Kaufma nn, 1993.
［3］BREIMAN L,FRIEDMAN J,OLSHEN R,et al.Classification and regression tr ees monterey［M］.Belmont:Wadsworth International Group, 1984.
［4］HELMBOLD D P, LONG P M. Tracking drifting concepts by minimizing disagreem ents［J］. Machine Learning, 1994,21(14):27-45.
［5］WANG H, FAN W, YU P,HAN J.Mining conceptdrifting data streams using ensem bl e classifiers［A］.The 9th ACM International Conference on Knowledge Discove ry and Data Mining (SIGKDD’s03)［C］.New York: ACM Press, 2003.
［6］GANTI V, GEHRKE J, RAMAKRISHNAN R. Mining data streams under block evolut ion［A］. SIGKDD’s02［C］. New York: ACM Press,2002.
［7］WIDMER G,KUBAT M.Learning in the presence of concept drift and hidden contexts［J］. Machine Learning, 1996,23(1):69-101.
［8］DOMINGOS P, HULTEN G. Mining highspeed data streams［A］. In Pro ceeding s o f th e Association for Computing Machinery Sixth International Conference on Knowledg e Discovery and Data Mining［C］. New York: ACM Press, 2000.
［9］PAPADIMITRIOU S, FALOUTSOS C, BROCKWELL A. Adaptive, handsoff stre am mi ning［A］. Proceedings of the 29th International Conference on Very Large Dat a Bases(V LDB’s03)［C］. Berlin:Springer Press, 2003.
［10］AGGARWAL C, HAN J, WANG J, YU P S. On demand classification of data streams ［A］. Proc 2004 Int Conf on Knowledge Discovery and Data Mining［C］. New York: ACM Press, 2004
［11】LAST M. Online classification of nonstationary data  streams［J］.Intelli gent Data Analysis,2002,6(2):129-147.
［12］DING Q, DING Q, PERRIZO W. Decision tree classification of spatia l data s tr eams using peano count trees［A］. Proceedings of the ACM Symposium on Applied C omputing［C］. New York: ACM Press, 2002.
［13］GABER M M,KRISHNASWAMY S, ZASLAVSKY A.Onboard mining of data streams in se nsor networks［M］.Springer Verlag,2003
 ［14］MEHTA M, AGRAWAL R, RISSANEN J. SLIQ: A fast scalable classifier for data m ining［A］. Proc 1996 Int Conf Extending Database Technology (EDBT’s96)［C ］. Springer Press, 1996.
［15］SHAFER J, AGRAWAL R, MEHTA M. SPRINT: A fast scalable parallel classifier f or data mining［A］. Proc 1996 Int Conf Very Large Data Bases (VLDB’s96)［ C］. Springer Press, 1996.
［16］MITCHELL T M.Machine learning［M］.New York:McGrawHill, 1997.
Similar References:

Memo

-

Last Update: 2009-05-07

Copyright © CAAI Transactions on Intelligent Systems