An urban traffic speed fusion method based on principle component analysis and neural network

Real-time traffic speed is an important element for Intelligent Transportation Systems (ITS). Getting accurate road speed is very important for transportation service and management systems. Floating car system based on traces of GPS positions is an effective way to gather accurate real-time traffic speed information of a road network. But sometimes the real-time traffic speed information may get lost unexpectedly due to device faults or storage problems. In engineering practice, the historical speed is used to make up the missing real-time speed, but this method cannot estimate the missing speed accurately. Until now, to the best of our knowledge, there is no research on dealing with the missing floating car speed data. In this paper, we propose a novel urban speed fusion method based on principle component analysis (PCA) and neural network (NN) to fuse the speeds of correlated road sections to get the missing speed of the target road section. The floating car data of the Hangzhou city were used to test our method. The experimental results demonstrate that our method outperforms other methods.