Binary Offset Carrier(BOC) has been chosen as one of modulation methods in the future Global Navigation Satellite Systems(GNSS). Even though BOC signals can bring several advantages such as better track performance an...Binary Offset Carrier(BOC) has been chosen as one of modulation methods in the future Global Navigation Satellite Systems(GNSS). Even though BOC signals can bring several advantages such as better track performance and higher positioning accuracy, there is a drawback that the autocorrelation functions have multiple side-peaks if BOC modulation is adopted. This characteristic will lead to false acquisition and the tracking loop will be locked in false phase point. The proposed Correlation Combination Ambiguity Removing Technology(CCART) cancelled all the side-peaks of the sine-phased BOC(kn,n) signals completely by making use of two kinds of correlation functions. Two kinds of sub-correlation functions were combined separately and then final correlation function without side-peaks was acquired. The simulation results are given and compared with other techniques. It is shown that acquisition will not be degraded with the increase of k.展开更多
Vehicle trajectory modeling is an important foundation for urban intelligent services. Trajectory prediction of cars is a hot topic. A model including convolutional neural network(CNN) and long short-term memory(LSTM)...Vehicle trajectory modeling is an important foundation for urban intelligent services. Trajectory prediction of cars is a hot topic. A model including convolutional neural network(CNN) and long short-term memory(LSTM) was proposed, which is named trajectory-CNN-LSTM(TCL). CNN can extract the spatial features of the trajectory in the input image. Besides, LSTM can extract the time-series features of the input trajectory. After that, the model uses fully connected layers to merge the two features for the final predicting. The experiments on the Porto dataset of The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases(ECML-PKDD) show that the average prediction error of TCL is reduced by 0.15 km, 0.42 km, and 0.39 km compared to the trajectory-convolution(T-CONV), multi-layer perceptron(MLP), and recurrent neural network(RNN) model, respectively.展开更多
基金supported in part by National Natural Science Foundation of China under Grant No.61372110National High Technology Research and Development Program of China (863 Program) under Grant No. 2012AA120802
文摘Binary Offset Carrier(BOC) has been chosen as one of modulation methods in the future Global Navigation Satellite Systems(GNSS). Even though BOC signals can bring several advantages such as better track performance and higher positioning accuracy, there is a drawback that the autocorrelation functions have multiple side-peaks if BOC modulation is adopted. This characteristic will lead to false acquisition and the tracking loop will be locked in false phase point. The proposed Correlation Combination Ambiguity Removing Technology(CCART) cancelled all the side-peaks of the sine-phased BOC(kn,n) signals completely by making use of two kinds of correlation functions. Two kinds of sub-correlation functions were combined separately and then final correlation function without side-peaks was acquired. The simulation results are given and compared with other techniques. It is shown that acquisition will not be degraded with the increase of k.
基金supported by the National Key Research and Development Program of China (2017YFB0503700)the Fundamental Research Funds for the Central Universities (2019PTB-010)。
文摘Vehicle trajectory modeling is an important foundation for urban intelligent services. Trajectory prediction of cars is a hot topic. A model including convolutional neural network(CNN) and long short-term memory(LSTM) was proposed, which is named trajectory-CNN-LSTM(TCL). CNN can extract the spatial features of the trajectory in the input image. Besides, LSTM can extract the time-series features of the input trajectory. After that, the model uses fully connected layers to merge the two features for the final predicting. The experiments on the Porto dataset of The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases(ECML-PKDD) show that the average prediction error of TCL is reduced by 0.15 km, 0.42 km, and 0.39 km compared to the trajectory-convolution(T-CONV), multi-layer perceptron(MLP), and recurrent neural network(RNN) model, respectively.