Spatio-Temporal Meta Learning for Urban Traffic Prediction

2020 ◽  
pp. 1-1
Author(s):  
Zheyi Pan ◽  
Wentao Zhang ◽  
Yuxuan Liang ◽  
Weinan Zhang ◽  
Yong Yu ◽  
...  
Keyword(s):  
Urban Traffic ◽  
Traffic Prediction ◽  
Meta Learning ◽  
Spatio Temporal

Urban Traffic Dynamics Prediction—A Continuous Spatial-temporal Meta-learning Approach

2022 ◽  
Vol 13 (2) ◽  
pp. 1-19
Author(s):  
Yingxue Zhang ◽  
Yanhua Li ◽  
Xun Zhou ◽  
Jun Luo ◽  
Zhi-Li Zhang
Keyword(s):  
Urban Traffic ◽  
Traffic Prediction ◽  
Traffic Dynamics ◽  
Transportation Management ◽  
Learning Framework ◽  
Rolling Window ◽  
Meta Learning ◽  
Testing Algorithms ◽  
Traffic Speed ◽  
Temporal Dependencies

Urban traffic status (e.g., traffic speed and volume) is highly dynamic in nature, namely, varying across space and evolving over time. Thus, predicting such traffic dynamics is of great importance to urban development and transportation management. However, it is very challenging to solve this problem due to spatial-temporal dependencies and traffic uncertainties. In this article, we solve the traffic dynamics prediction problem from Bayesian meta-learning perspective and propose a novel continuous spatial-temporal meta-learner (cST-ML), which is trained on a distribution of traffic prediction tasks segmented by historical traffic data with the goal of learning a strategy that can be quickly adapted to related but unseen traffic prediction tasks. cST-ML tackles the traffic dynamics prediction challenges by advancing the Bayesian black-box meta-learning framework through the following new points: (1) cST-ML captures the dynamics of traffic prediction tasks using variational inference, and to better capture the temporal uncertainties within tasks, cST-ML performs as a rolling window within each task; (2) cST-ML has novel designs in architecture, where CNN and LSTM are embedded to capture the spatial-temporal dependencies between traffic status and traffic-related features; (3) novel training and testing algorithms for cST-ML are designed. We also conduct experiments on two real-world traffic datasets (taxi inflow and traffic speed) to evaluate our proposed cST-ML. The experimental results verify that cST-ML can significantly improve the urban traffic prediction performance and outperform all baseline models especially when obvious traffic dynamics and temporal uncertainties are presented.

scholarly journals Spatio-Temporal Visual Analysis for Urban Traffic Characters Based on Video Surveillance Camera Data

2021 ◽  
Vol 10 (3) ◽  
pp. 177
Author(s):  
Haochen Zou ◽  
Keyan Cao ◽  
Chong Jiang
Keyword(s):  
Video Surveillance ◽  
Traffic Management ◽  
Visual Analysis ◽  
Urban Traffic ◽  
License Plate ◽  
Road Vehicle ◽  
Urban Road ◽  
Surveillance Camera ◽  
Vehicle Density ◽  
Spatio Temporal

Urban road traffic spatio-temporal characters reflect how citizens move and how goods are transported, which is crucial for trip planning, traffic management, and urban design. Video surveillance camera plays an important role in intelligent transport systems (ITS) for recognizing license plate numbers. This paper proposes a spatio-temporal visualization method to discover urban road vehicle density, city-wide regional vehicle density, and hot routes using license plate number data recorded by video surveillance cameras. To improve the accuracy of the visualization effect, during data analysis and processing, this paper utilized Internet crawler technology and adopted an outlier detection algorithm based on the Dixon detection method. In the design of the visualization map, this paper established an urban road vehicle traffic index to intuitively and quantitatively reveal the traffic operation situation of the area. To verify the feasibility of the method, an experiment in Guiyang on data from road video surveillance camera system was conducted. Multiple urban traffic spatial and temporal characters are recognized concisely and efficiently from three visualization maps. The results show the satisfactory performance of the proposed framework in terms of visual analysis, which will facilitate traffic management and operation.

MetaTP

2021 ◽  
Vol 5 (3) ◽  
pp. 1-28
Author(s):  
Weida Zhong ◽  
Qiuling Suo ◽  
Abhishek Gupta ◽  
Xiaowei Jia ◽  
Chunming Qiao ◽  
...  
Keyword(s):  
Time Series ◽  
Large Scale ◽  
Multivariate Time Series ◽  
Modern Society ◽  
Training Data ◽  
Traffic Prediction ◽  
Temporal Prediction ◽  
Reference Space ◽  
Meta Learning ◽  
Real World Datasets

With the popularity of smartphones, large-scale road sensing data is being collected to perform traffic prediction, which is an important task in modern society. Due to the nature of the roving sensors on smartphones, the collected traffic data which is in the form of multivariate time series, is often temporally sparse and unevenly distributed across regions. Moreover, different regions can have different traffic patterns, which makes it challenging to adapt models learned from regions with sufficient training data to target regions. Given that many regions may have very sparse data, it is also impossible to build individual models for each region separately. In this paper, we propose a meta-learning based framework named MetaTP to overcome these challenges. MetaTP has two key parts, i.e., basic traffic prediction network (base model) and meta-knowledge transfer. In base model, a two-layer interpolation network is employed to map original time series onto uniformly-spaced reference time points, so that temporal prediction can be effectively performed in the reference space. The meta-learning framework is employed to transfer knowledge from source regions with a large amount of data to target regions with a few data examples via fast adaptation, in order to improve model generalizability on target regions. Moreover, we use two memory networks to capture the global patterns of spatial and temporal information across regions. We evaluate the proposed framework on two real-world datasets, and experimental results show the effectiveness of the proposed framework.

MDTP

2021 ◽  
Vol 14 (8) ◽  
pp. 1289-1297
Author(s):  
Ziquan Fang ◽  
Lu Pan ◽  
Lu Chen ◽  
Yuntao Du ◽  
Yunjun Gao
Keyword(s):  
Neural Network ◽  
Short Term Memory ◽  
Temporal Dynamics ◽  
Real Life ◽  
Feature Modeling ◽  
Traffic Prediction ◽  
Interactive System ◽  
Trajectory Data ◽  
Spatio Temporal ◽  
Prediction Approach

Traffic prediction has drawn increasing attention for its ubiquitous real-life applications in traffic management, urban computing, public safety, and so on. Recently, the availability of massive trajectory data and the success of deep learning motivate a plethora of deep traffic prediction studies. However, the existing neural-network-based approaches tend to ignore the correlations between multiple types of moving objects located in the same spatio-temporal traffic area, which is suboptimal for traffic prediction analytics. In this paper, we propose a multi-source deep traffic prediction framework over spatio-temporal trajectory data, termed as MDTP. The framework includes two phases: spatio-temporal feature modeling and multi-source bridging. We present an enhanced graph convolutional network (GCN) model combined with long short-term memory network (LSTM) to capture the spatial dependencies and temporal dynamics of traffic in the feature modeling phase. In the multi-source bridging phase, we propose two methods, Sum and Concat, to connect the learned features from different trajectory data sources. Extensive experiments on two real-life datasets show that MDTP i) has superior efficiency, compared with classical time-series methods, machine learning methods, and state-of-the-art neural-network-based approaches; ii) offers a significant performance improvement over the single-source traffic prediction approach; and iii) performs traffic predictions in seconds even on tens of millions of trajectory data. we develop MDTP + , a user-friendly interactive system to demonstrate traffic prediction analysis.

scholarly journals Do Functionally Fit Elderly Community-Dwelling Subjects Have Enough Time to Safely Cross the Road?

1970 ◽  
Vol 25 (1) ◽  
pp. 55-62 ◽  
Author(s):  
Darija Rugelj ◽  
Marija Tomšič ◽  
France Sevšek
Keyword(s):  
Dual Task ◽  
Walking Speed ◽  
Community Dwelling ◽  
Urban Traffic ◽  
Gait Velocity ◽  
Dual Task Condition ◽  
Traffic Lights ◽  
The Road ◽  
Spatio Temporal ◽  
Task Conditions

Elderly people are the most vulnerable group in urban traffic and a large proportion of them are as pedestrians victims of traffic accidents. The majority of these happen while crossing the road. Crossing a busy road at an intersection with traffic lights or without them is a typical dual task condition requiring a motor task i.e. walking and a cognitive task such as monitoring traffic. The purpose of present study was to compare the walking speed and the related spatio-temporal gait variables of fallers and non-fallers in three walking conditions against the speeds required by regulations in Slovenia for safe street crossing. To assess the spatio-temporal characteristics of gait we used a 7m instrumented walkway.The general results showed that the spatio-temporal gait parameters did not differ between the two groups at the self-selected speed. But as soon as a constraint, such as fast walking speed, was imposed on the subjects the differences between the groups became evident. Fallers demonstrated a significantly slower mean gait velocity and shorter stride length while the cadence and the base of support did not differ between the two groups. In dual task conditions the difference between the two groups reached 25 percent. The fallers group gait velocity dropped to 0.99 m/s. The observed walking speed was slower than considered by the guidelines for the design of traffic light equipped road crossing.In conclusion, the results of walking speed under dual task conditions could be a useful parameter for planning of optimal pedestrian crossing in urban areas. These results will serve for the design of a population based study in Ljubljana.

Case Studies

2018 ◽  
pp. 133-155
Keyword(s):  
Temporal Variation ◽  
Conceptual Framework ◽  
Case Studies ◽  
Landscape Pattern ◽  
Urban System ◽  
Urban Traffic ◽  
Geospatial Technology ◽  
Traffic Characteristics ◽  
Working Principle ◽  
Spatio Temporal

This chapter attempts to demonstrate the utility of geospatial technology in assessing the characteristics of different aspects of the urban system. The characteristics of these urban events may differ from each other. To understand the working principle of an urban system, occurrence of different urban events need to be investigated. Therefore, this chapter explains two different urban events. That may help readers to understand the variation in different aspects of the urban system. In addition, applicability of geospatial technology is also explained in this chapter. First problem is related to assessment of urban traffic characteristics and the second problem assesses the spatio-temporal variation in landscape pattern of the study area. The first problem is explained using a conceptual framework, and the second problem is explained using quantified demonstration. Readers may find this chapter useful to understand the utility of geospatial technology in understanding different aspects of the urban system.

Sign in / Sign up

Export Citation Format

Share Document