TY - GEN
T1 - Local outlier detection based on kernel regression
AU - Gao, Jun
AU - Hu, Weiming
AU - Li, Wei
AU - Zhang, Zhongfei
AU - Wu, Ou
PY - 2010
Y1 - 2010
N2 - Outlier detection keeps an important and attractive task of the knowledge discovery in databases. In this paper, a novel approach named Multi-scale Local Kernel Regression is proposed. It transfers the unsupervised learning of outlier detection to the classic nonparameter regression learning. Through preprocessing the original data by the basic local density-based method, it adopts the local kernel regression estimator in the multiple scale neighborhoods to determine outliers. Experiments on several real life data sets demonstrate that this approach is promising in detection performance.
AB - Outlier detection keeps an important and attractive task of the knowledge discovery in databases. In this paper, a novel approach named Multi-scale Local Kernel Regression is proposed. It transfers the unsupervised learning of outlier detection to the classic nonparameter regression learning. Through preprocessing the original data by the basic local density-based method, it adopts the local kernel regression estimator in the multiple scale neighborhoods to determine outliers. Experiments on several real life data sets demonstrate that this approach is promising in detection performance.
UR - https://www.scopus.com/pages/publications/78149482367
U2 - 10.1109/ICPR.2010.148
DO - 10.1109/ICPR.2010.148
M3 - Conference contribution
SN - 9780769541099
T3 - Proceedings - International Conference on Pattern Recognition
SP - 585
EP - 588
BT - Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010
T2 - 2010 20th International Conference on Pattern Recognition, ICPR 2010
Y2 - 23 August 2010 through 26 August 2010
ER -