关键词: 智能交通系统, 车辆定位, 神经网络, 融合模型

Abstract:  Signals are prone to be lost in big cities when using traditional GPS．To solve this problem‚a concept which combines GPS and mobile-communication-network-based MPS was adopted‚and the BP neural network was used‚thus constructing a vehicle positioning fusion model of GPS and MPS positioning information．By utilizing the momentum method as well as the self-adaptive adjusting strategy of learning rate‚the slow convergence speed of BP algorithm and the local minimal point were solved．
Training results with126items of research data on the network indicate that the model is consistent with GPS both in direction and in trend and is independent upon the traditional GPS model．So the model can efficiently be applied in maintaining the positioning continuity and precision with lower cost．

Key words: intelligent transportation system, vehicle positioning, neural network, fusion model