Title :
A new approach of neural networks to time-varying database classification
Author :
Wang, Xiao-ye ; Liang, Xiu-xia ; Sun, Ji-Zhou
Author_Institution :
Dept. of Comput. Sci. & Technol., Tianjin Univ., China
Abstract :
The time-varying databases, whose data distribution are changed with time. This database is frequently observed in many application areas including manufacturing, financing, and marketing. Knowledge discovery in time-varying databases is an important subject of data mining technology. This paper presents a moving-window neural network classification algorithm that can effectively classify the time-varying databases. We derive the algorithm. The experiment demonstrates the effective of the presented algorithm.
Keywords :
data mining; neural nets; temporal databases; data mining technology; knowledge discovery; neural network; time-varying database classification; Data mining; Feedforward neural networks; Least squares methods; Machine learning; Manufacturing processes; Neural networks; Semiconductor device manufacture; Spatial databases; Sun; Training data; Neural Network; Time-varying database; classification;
Conference_Titel :
Machine Learning and Cybernetics, 2005. Proceedings of 2005 International Conference on
Conference_Location :
Guangzhou, China
Print_ISBN :
0-7803-9091-1
DOI :
10.1109/ICMLC.2005.1527282
