Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Method for Bus Travel Time Prediction Based on Sparse GPS Data

A GPS data and travel time technology, applied in forecasting, data processing applications, traffic flow detection, etc., can solve the problem of low reliability of bus travel time prediction, achieve fast travel services, improve error accuracy, and have good application prospects. Effect

Active Publication Date: 2022-01-28
JILIN UNIV
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem that the reliability of bus travel time prediction is low due to the sparse characteristics of bus data at the present stage, and propose a bus travel time prediction method based on sparse GPS data

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
  • A Method for Bus Travel Time Prediction Based on Sparse GPS Data
  • A Method for Bus Travel Time Prediction Based on Sparse GPS Data
  • A Method for Bus Travel Time Prediction Based on Sparse GPS Data

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0020] Specific implementation mode one: combine figure 1 Illustrate this embodiment, the concrete process of a kind of bus travel time prediction method based on sparse GPS data in this embodiment is:

[0021] Step 1. After receiving the original GPS data uploaded by the public transport vehicle, carry out normalized preprocessing to the original GPS data of the public transport, and integrate the data after normalized preprocessing into a two-dimensional space-time velocity matrix (as described in step 2 model input);

[0022] Step 2. Construct a generative confrontation network based on traffic flow prior rules to generate traffic conditions that fit the actual bus line;

[0023] Step 3. Based on the model-free adaptive driving method, the bus travel time is predicted online.

specific Embodiment approach 2

[0024] Specific embodiment two: the difference between this embodiment and the specific embodiment one is that after receiving the original GPS data uploaded by the public transport vehicle in the step one, normalization preprocessing is carried out to the original GPS data of the public transport, and normalized The preprocessed data are integrated into a two-dimensional space-time velocity matrix (as the input of the model described in step 2); the specific process is as follows:

[0025] Step 11, after receiving the original GPS data uploaded by the bus vehicle, normalize the original GPS data of the bus and preprocess it; the process is:

[0026] 1) After receiving the original GPS data uploaded by the bus, the data whose speed exceeds the maximum speed limit of the bus (50km / h) is regarded as an abnormal value and deleted;

[0027] 2) In order to avoid the interference of different magnitudes of original data on network learning, normalize the original GPS data uploaded b...

specific Embodiment approach 3

[0034] Specific embodiment three: the difference between this embodiment and specific embodiment one or two is that in the step two, a generative confrontation network based on traffic flow prior rules is constructed to generate a traffic state of a bus line that fits the reality; the specific process is:

[0035] The present invention uses the bus speed as an index to measure the traffic state of the bus line. After receiving the processed bus GPS data, it is necessary to generate the state of the empty value position in the speed matrix, so as to obtain the complete bus traffic status and provide it to step 3 for bus Travel time forecast. In conventional data generation algorithms, an encoding-decoding structure is often used to extract and restore data features, so as to obtain the generated results. However, the gradual feature restoration process will lead to the continuous accumulation of errors, which will affect the accuracy of the output results. The present inventio...

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

A bus travel time prediction method based on sparse GPS data, the invention relates to a bus travel time prediction method based on sparse GPS data. The purpose of the present invention is to solve the problem of low credibility of bus travel time prediction due to the sparse nature of bus data at the present stage. The specific process of a bus travel time prediction method based on sparse GPS data is as follows: Step 1. After receiving the original GPS data uploaded by the bus vehicle, the original GPS data of the bus is normalized and preprocessed, and the normalized preprocessed Integrate the data into a two-dimensional space-time velocity matrix; Step 2: Construct a generative confrontation network based on the traffic flow prior rules to generate the actual traffic status of the bus line; Step 3: Based on the model-free adaptive driving method, online prediction of the bus schedule time. The invention is used in the technical field of public transportation information processing.

Description

technical field [0001] The invention relates to the technical field of public transport information processing, and more specifically, the invention relates to a method for predicting bus travel time based on sparse GPS data. Background technique [0002] In recent years, under the guidance of the public transportation priority strategy, the construction of urban intelligent public transportation travel system has achieved remarkable development. However, the concentrated arrival of buses caused by road network traffic congestion or the phenomenon that they cannot arrive for a long time is becoming more and more serious, causing residents to choose other travel modes due to the decline in the quality of bus travel. The lack of attractiveness of public transport restricts the development of public transport. Reasonable real-time bus scheduling and reliable bus travel time estimation are important means to improve passenger travel experience. However, due to the small number...

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 Patents(China)
IPC IPC(8): G08G1/01G06N3/04G06N3/08G06Q10/04G06Q50/26
CPCG08G1/0125G08G1/0137G06N3/084G06Q10/04G06Q50/26G06N3/045
Inventor 宋现敏田婧李志慧吴丛张明业曹倩马永建冷宁张璐雨
Owner JILIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com