No abstract

No abstract

No abstract

No abstract

Travel modes are generally derived from Global Positioning System (GPS) data on the basis of either a rule-based or machine learning classification method. The rule-based classification approach is generally easy to understand, whereas the machine learning classification method has better generalization. However, studies that jointly explore both methods are limited. The present research proposes a two-stage method that aims to impute travel modes from GPS trajectory data. In the first stage, rules are employed to detect subway modes. In the second stage, a Gaussian process classifier based on sequential forward selection methods is utilized to derive the remaining travel modes. On the basis of the four selected features constituting the feature set (i.e., average speed, average acceleration, heading change, and low-speed point rate), over 97% of the samples with subway modes are correctly identified and 93.04% of segments in the walk-based balanced test subset are accurately detected. Over 92% of the car and bus samples are correctly detected for the training and test datasets. Results provide a new perspective in selecting classification methods for the detection of travel modes and other travel characteristics from GPS trajectory data. Furthermore, high differentiation is achieved between the bus and car modes without the bus transit geographic information system sources of bus networks. Therefore, reasonable extracted features contribute to the detection of travel modes, particularly between bus and car modes. INDEX TERMS Gaussian processes, classification algorithms, global positioning system.

No abstract

No abstract

For many intelligent transportation applications, traffic congestion prediction is quite essential. If traffic congestion on the road ahead can be accurately and promptly predicted, and routes can be planned reasonably based on the prediction results, traffic congestion can be effectively alleviated. Aiming at the spatio-temporal correlation and evolution characteristics of traffic flow data, the Conv-BiLSTM module comprising a convolutional neural network (CNN) and a bidirectional long short-term memory (BiLSTM) is proposed, considering the spatio-temporal features. Firstly, the obtained traffic speed data is folded according to spatio-temporal features, and a three-dimensional matrix is constructed as the input of the prediction network module. After the spatial features are extracted by the CNN, the temporal features and alignment features are extracted by the BiLSTM, followed by which the prediction results are obtained as an output. Prediction and evaluation experiments on the traffic data of the highway in Shanghai prove that the traffic congestion state predicted by this method is largely consistent with the actual state. The results demonstrate that the proposed method has a higher prediction accuracy compared with the conventional and state-of-the-art methods and is an efficient method of traffic congestion prediction.