Unlock instant, AI-driven research and patent intelligence for your innovation.

Bus arrival time prediction method based on deep neural network calculation

A technology of deep neural network and time prediction, applied in prediction, calculation, traffic flow detection, etc., can solve the problems of capturing long-term trends, lack of systematic extraction of real-time traffic information, and difficulty in training models

Active Publication Date: 2021-09-10
SHENZHEN URBAN TRANSPORT PLANNING CENT
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There are many defects in the method of using time series forecasting to predict the arrival time. For example, it is difficult to capture the long-term trend at the same time under the condition of limited time slice window. When the time window is too long, the calculation will increase and it is difficult to train the model. And Lack of systematic extraction of real-time traffic information
[0004] Therefore, using the method of time series analysis to predict the arrival time in the future cannot meet the needs of the existing bus stops to display the accurate arrival time in real time, and it is more used in the future travel planning to predict the bus travel in the future period of time. time forecast

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Bus arrival time prediction method based on deep neural network calculation
  • Bus arrival time prediction method based on deep neural network calculation
  • Bus arrival time prediction method based on deep neural network calculation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] refer to Figure 1-Figure 5 Illustrate this embodiment, a method for predicting bus arrival time based on deep neural network calculations, comprising the following steps:

[0047] The bus route is a fixed route driven by a public transport bus, and in the present invention, the bus route is composed of a series of GPS points composition, . GPS point is the location of the bus stop on the bus route, , and the problem that the present invention aims to solve is based on the last two sites , real-time on and last two sites , Historical traffic information to predict bus travel time between two stops on a bus route.

[0048] Step 1, preprocessing the traffic data; the specific method is: divide the bus route into a pair of road sections between the front and back stations, and extract the traffic information of each road section; the traffic information specifically includes discrete variables and continuous variables; the Discrete variables such as: ...

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

No PUM Login to View More

Abstract

The invention provides a bus arrival time prediction method based on deep neural network calculation, and belongs to the technical field of public traffic information processing. The method specifically comprises the following steps: firstly, preprocessing traffic data; secondly, extracting segmented traffic information, and obtaining road section traffic features; secondly, expanding the sample size of the traffic features of the road section; secondly, performing multi-road-section historical feature extraction and information selection on the historical driving time data of various road sections by using an attention mechanism model; secondly, inputting the selected feature vectors into a full connection layer, and training an attention mechanism model by using a mean square error as a loss function; and finally, obtaining the predicted bus arrival time. The technical problem that in the prior art, bus arrival time prediction is not accurate is solved, and the technical effect that arrival time prediction between bus stops is more real-time and accurate is achieved.

Description

technical field [0001] The present application relates to a bus arrival time prediction method, in particular to a bus arrival time prediction method based on deep neural network calculation, which belongs to the technical field of public transportation information processing. Background technique [0002] Bus arrival time prediction is one of the important components of intelligent transportation system. Accurate real-time bus arrival time prediction can help travelers choose and optimize their travel routes. In addition, accurate arrival time prediction can not only help bus managers adjust and optimize bus scheduling time under the influence of emergencies. Therefore, real-time and accurate bus arrival time prediction is one of the important ways that smart traffic can help improve urban traffic efficiency. The traditional bus arrival time prediction is to calculate the historical average operation time between bus stations by obtaining the bus operation time between ea...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G08G1/01G06Q50/30G06Q10/04
CPCG06Q10/04G08G1/0129G06Q50/40
Inventor 林涛陈振武周勇李朋王宇彭亚红张枭勇王晋云钱宇清
Owner SHENZHEN URBAN TRANSPORT PLANNING CENT