论文信息 - A Covering Algorithm Based on Competition

A Covering Algorithm Based on Competition

Abstract In covering algorithm, the order of learning samples is random, but experiments show that the learning sequence has significant impact on the network performance. This paper proposes a new algorithm which is covering algorithm based on competition (CAC). In this algorithm, sphere neighborhoods can be adjusted gradually, the ill-suited sphere neighborhoods will be removed and the whole neural network will performs more stable. Finally the algorithm is applied to a widely used database. The experiment results show that it can effectively decrease the number of rejected samples, reduce the number of sphere domains and improve the recognition accuracy.

[1] Ennio Cascetta,et al. Transportation Systems Engineering: Theory and Methods , 2001 .

[2] Bo Zhang,et al. A geometrical representation of McCulloch-Pitts neural model and its applications , 1999, IEEE Trans. Neural Networks.

[3] Andrea Papola,et al. A JOINT MODE-TRANSIT SERVICE CHOICE MODEL INCORPORATING THE EFFECT OF REGIONAL TRANSPORT SERVICE TIMETABLES , 2003 .

[4] Giulio Erberto Cantarella,et al. Multilayer Feedforward Networks for Transportation Mode Choice Analysis: An Analysis and a Comparison with Random Utility Models , 2005 .

[5] Di Wang,et al. Fast Constructive-Covering Algorithm for neural networks and its implement in classification , 2008, Appl. Soft Comput..

[6] Carlos F. Daganzo,et al. Multinomial Probit: The Theory and its Application to Demand Forecasting. , 1980 .

[7] Liang Gao,et al. Covering Algorithm Based on Neighborhood Search and its Applications , 2007, Third International Conference on Natural Computation (ICNC 2007).