A Multi-step Traffic Speed Prediction Method Considering Spatial-Spatial Correlation and Contribution Difference Synergistically
A space-time correlation and contribution technology, applied in traffic flow detection, road vehicle traffic control system, traffic control system, etc.
Active Publication Date: 2021-07-06
ZHEJIANG UNIV
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The purpose of the present invention is to provide a multi-step traffic speed prediction method considering the temporal-spatial correlation and contribution difference for the deficiencies of the existing traffic speed prediction methods
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0055] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific examples.
[0056] The data used in this example is the GPS signal data of 8,000 taxis in Hangzhou for a period of four months from October 1, 2013 to January 31, 2014, a total of 123 days. GPS data includes speed values, sampling time and positions information.
[0057] Step 1: Modeling data preprocessing.
[0058] The original speed data is averaged, and the data of external factors such as weather and holidays are preprocessed.
[0059] For the original speed data, the obtained vehicle speed data is classified according to different road sections. For each road segment that needs to be analyzed, each day is divided into 24 time periods with one hour as the time interval. For the zth time interval, z=0,1,2,...,23, use the average speed of the road section within the time interval to represent the speed of the zth time interval, each moment corr...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a multi-step traffic speed prediction method that synergistically considers temporal-spatial correlation and contribution differences. The method uses an encoding-decoding network architecture based on a cyclic neural network to fully express the time-series characteristics of traffic speeds. In the coding part, the first-stage attention mechanism is introduced into the input vector composed of the speed values of the relevant road segments, so that it can adaptively learn the weight contribution of different relevant road segments at different times; in the decoding part, the second-stage attention mechanism is introduced , to adaptively learn the weight contribution of different historical moments to the current prediction moment. At the same time, considering the influence of external factors, the output of the decoder and the features of external factors are input into the fully connected neural network to obtain the final output. This method can describe the spatial-temporal correlation characteristics of traffic data in a finer-grained and differentiated manner, and can perform multi-step traffic speed prediction, which points out a new direction for the research of traffic speed prediction methods.
Description
technical field [0001] The invention belongs to the research field of traffic time series data analysis and prediction, in particular to a traffic speed prediction method based on time-space correlation and external factor characteristics and a sequence network with a two-stage attention mechanism. Background technique [0002] With the increase of the number of motor vehicles, the problem of traffic congestion is becoming more and more serious, which brings a lot of inconvenience to people's travel, also causes pollution to the environment, and even threatens people's life safety. The immediate problem with traffic congestion is increased travel time. On the other hand, the traffic congestion caused by the increase in the number of motor vehicles has increased the number of starts and stops of vehicles, and increased the waiting time on the road, resulting in an increase in vehicle exhaust emissions, causing air pollution, and seriously endangering human health. At the sam...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G08G1/01G06K9/62G06N3/04
CPCG08G1/0104G06N3/045G06F18/2411G06F18/214
Inventor 赵春晖崔紫强
Owner ZHEJIANG UNIV