RHMX: Bus arrival time prediction via mixed model

With the widespread use of information technologies such as IoT and big data in the transportation business, traditional passenger transportation has begun to transition and upgrade into intelligent transportation, providing passengers with a better riding experience. Giving precise bus arrival times is a critical link in achieving urban intelligent transportation. As a result, a mixed model-based bus arrival time prediction model (RHMX) was suggested in this work, which could dynamically forecast bus arrival time based on the input data. First, two sub-models were created: bus station stopping time prediction and interstation running time prediction. The former predicted the stopping time of a running bus at each downstream station in an iterative manner, while the latter projected its running time on each downstream road segment (stations as the break points). Using the two models, a group of time series data on interstation running time and bus station stopping time may be predicted. Following that, the time series data from the two sub-models was fused using long short-term memory (LSTM) to generate an approximate bus arrival time. Finally, using Kalman filtering, the LSTM prediction results were dynamically updated in order to eliminate the influence of aberrant data on the anticipated value and obtain a more precise bus arrival time. The experimental findings showed that the suggested model's accuracy and stability were both improved by 35% and 17%, respectively, over AutoNavi and Baidu.

Joint Geoeffectiveness and Arrival Time Prediction of CMEs by a Unified Deep Learning Framework

Fast and accurate prediction of the geoeffectiveness of coronal mass ejections (CMEs) and the arrival time of the geoeffective CMEs is urgent, to reduce the harm caused by CMEs. In this paper, we present a new deep learning framework based on time series of satellites’ optical observations that can give both the geoeffectiveness and the arrival time prediction of the CME events. It is the first time combining these two demands in a unified deep learning framework with no requirement of manually feature selection and get results immediately. The only input of the deep learning framework is the time series images from synchronized solar white-light and EUV observations. Our framework first uses the deep residual network embedded with the attention mechanism to extract feature maps for each observation image, then fuses the feature map of each image by the feature map fusion module and determines the geoeffectiveness of CME events. For the geoeffective CME events, we further predict its arrival time by the deep residual regression network based on group convolution. In order to train and evaluate our proposed framework, we collect 2400 partial-/full-halo CME events and its corresponding images from 1996 to 2018. The F1 score and Accuracy of the geoeffectiveness prediction can reach 0.270% and 75.1%, respectively, and the mean absolute error of the arrival time prediction is only 5.8 h, which are both significantly better than well-known deep learning methods and can be comparable to, or even better than, the best performance of traditional methods.