<Abstrcat>The effects of GPS signal errors on mobile robot positioning accuracy were studied and a fusion model by blending GPS and odometry data was presented.

To solve this problem, a concept which combines GPS and mobile-communication-ne twork-based MPS was adopted, and the BP neural network was used, thus constructi ng a vehicle positioning fusion model of GPS and MPS positioning information.

In this paper,according to the orbit parameters estmated from nonlinear fusion model,we present a method to assessing accuracy of orbit parameters,using Monte Carlo method,basing on separating model errors and think over its effecting on accuracy of orbit parameters.

Type fusion based on multistage neural network;

Native and non-native speech recognition based on acoustic model merging

This paper presents an approach for modeling the CMM implementation process based on model merging mechanism.

In this paper, we propose a new model merging method which can cover both American and British accents to improve the performance of pronunciation scoring with smaller model size.