Spatio-Temporal Hashing Multi-Graph Convolutional Network for Service-level Passenger Flow Forecasting in Bus Transit Systems

2021 ◽  
pp. 1-1
Author(s):  
Dan Luo ◽  
Dong Zhao ◽  
Qixue Ke ◽  
Xiaoyong You ◽  
Liang Liu ◽  
...  
Keyword(s):  
Service Level ◽  
Convolutional Network ◽  
Transit Systems ◽  
Bus Transit ◽  
Passenger Flow ◽  
Spatio Temporal

A Real-Time Passenger Flow Estimation and Prediction Method for Urban Bus Transit Systems

2017 ◽  
Vol 18 (11) ◽  
pp. 3168-3178 ◽  
Author(s):  
Jun Zhang ◽  
Dayong Shen ◽  
Lai Tu ◽  
Fan Zhang ◽  
Chengzhong Xu ◽  
...  
Keyword(s):  
Real Time ◽  
Prediction Method ◽  
Transit Systems ◽  
Flow Estimation ◽  
Bus Transit ◽  
Estimation And Prediction ◽  
Passenger Flow ◽  
Urban Bus

scholarly journals Investigating spatio-temporal mobility patterns and changes in metro usage under the impact of COVID-19 using Taipei Metro smart card data

2021 ◽  
Author(s):  
Christian Martin Mützel ◽  
Joachim Scheiner
Keyword(s):  
Smart Card ◽  
Public Transit ◽  
Mobility Patterns ◽  
Transit Planning ◽  
Transit Systems ◽  
Passenger Flow ◽  
Smart Card Data ◽  
Depth Analysis ◽  
Spatio Temporal ◽  
The Impact

AbstractModern public transit systems are often run with automated fare collection (AFC) systems in combination with smart cards. These systems passively collect massive amounts of detailed spatio-temporal trip data, thus opening up new possibilities for public transit planning and management as well as providing new insights for urban planners. We use smart card trip data from Taipei, Taiwan, to perform an in-depth analysis of spatio-temporal station-to-station metro trip patterns for a whole week divided into several time slices. Based on simple linear regression and line graphs, days of the week and times of the day with similar temporal passenger flow patterns are identified. We visualize magnitudes of passenger flow based on actual geography. By comparing flows for January to March 2019 and for January to March 2020, we look at changes in metro trips under the impact of the coronavirus pandemic (COVID-19) that caused a state of emergency around the globe in 2020. Our results show that metro usage under the impact of COVID-19 has not declined uniformly, but instead is both spatially and temporally highly heterogeneous.

MGSTCN: A Multi-Graph Spatio-Temporal Convolutional Network for Metro Passenger Flow Prediction

2021 ◽  
Author(s):  
Jiahao Yang ◽  
Tong Liu ◽  
Chengfan Li ◽  
Weiqin Tong ◽  
Yanmin Zhu ◽  
...  
Keyword(s):  
Convolutional Network ◽  
Passenger Flow ◽  
Flow Prediction ◽  
Spatio Temporal

scholarly journals FetNet: a recurrent convolutional network for occlusion identification in fetoscopic videos

2020 ◽  
Vol 15 (5) ◽  
pp. 791-801 ◽  
Author(s):  
Sophia Bano ◽  
Francisco Vasconcelos ◽  
Emmanuel Vander Poorten ◽  
Tom Vercauteren ◽  
Sebastien Ourselin ◽  
...  
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Laser Photocoagulation ◽  
Short Term Memory ◽  
Total Duration ◽  
Frame Rate ◽  
Superior Performance ◽  
Computer Assisted ◽  
Convolutional Network ◽  
Spatio Temporal

Abstract Purpose Fetoscopic laser photocoagulation is a minimally invasive surgery for the treatment of twin-to-twin transfusion syndrome (TTTS). By using a lens/fibre-optic scope, inserted into the amniotic cavity, the abnormal placental vascular anastomoses are identified and ablated to regulate blood flow to both fetuses. Limited field-of-view, occlusions due to fetus presence and low visibility make it difficult to identify all vascular anastomoses. Automatic computer-assisted techniques may provide better understanding of the anatomical structure during surgery for risk-free laser photocoagulation and may facilitate in improving mosaics from fetoscopic videos. Methods We propose FetNet, a combined convolutional neural network (CNN) and long short-term memory (LSTM) recurrent neural network architecture for the spatio-temporal identification of fetoscopic events. We adapt an existing CNN architecture for spatial feature extraction and integrated it with the LSTM network for end-to-end spatio-temporal inference. We introduce differential learning rates during the model training to effectively utilising the pre-trained CNN weights. This may support computer-assisted interventions (CAI) during fetoscopic laser photocoagulation. Results We perform quantitative evaluation of our method using 7 in vivo fetoscopic videos captured from different human TTTS cases. The total duration of these videos was 5551 s (138,780 frames). To test the robustness of the proposed approach, we perform 7-fold cross-validation where each video is treated as a hold-out or test set and training is performed using the remaining videos. Conclusion FetNet achieved superior performance compared to the existing CNN-based methods and provided improved inference because of the spatio-temporal information modelling. Online testing of FetNet, using a Tesla V100-DGXS-32GB GPU, achieved a frame rate of 114 fps. These results show that our method could potentially provide a real-time solution for CAI and automating occlusion and photocoagulation identification during fetoscopic procedures.

Based on spatio-temporal graph convolution networks with residual connection for intelligence behavior recognition

2021 ◽  
pp. 002072092199660
Author(s):  
Yinong Zhang ◽  
Shanshan Guan ◽  
Cheng Xu ◽  
Hongzhe Liu
Keyword(s):  
Human Behavior ◽  
Behavior Recognition ◽  
Convolutional Network ◽  
Skeleton Model ◽  
Basic Technology ◽  
Temporal Model ◽  
Temporal Graph ◽  
Spatio Temporal ◽  
Human Behavior Recognition ◽  
Behavior Characteristics

In the era of intelligent education, human behavior recognition based on computer vision is an important branch of pattern recognition. Human behavior recognition is a basic technology in the fields of intelligent monitoring and human-computer interaction in education. The dynamic changes of human skeleton provide important information for the recognition of educational behavior. Traditional methods usually use manual information to label or traverse rules only, resulting in limited representation capabilities and poor generalization performance of the model. In this paper, a kind of dynamic skeleton model with residual is adopted—a spatio-temporal graph convolutional network based on residual connections, which not only overcomes the limitations of previous methods, but also can learn the spatio-temporal model from the skeleton data. In the big bone NTU-RGB + D dataset, the network model not only improved the representation ability of human behavior characteristics, but also improved the generalization ability, and achieved better recognition effect than the existing model. In addition, this paper also compares the results of behavior recognition on subsets of different joint points, and finds that spatial structure division have better effects.

Sign in / Sign up

Export Citation Format

Share Document