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

Journey time estimation method based on auxiliary supervised learning

A travel time, supervised learning technology, applied in the field of intelligent transportation, can solve problems such as loss of useful information and underutilization of trajectory data

Active Publication Date: 2018-12-18
FUDAN UNIV
View PDF20 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In this splitting process, a lot of useful information is lost
Moreover, they do not make full use of the unique intermediate supervision labels of trajectory data, that is, the timestamp information of each intermediate GPS sampling point

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
  • Journey time estimation method based on auxiliary supervised learning
  • Journey time estimation method based on auxiliary supervised learning
  • Journey time estimation method based on auxiliary supervised learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0070] The specific implementation process of the present invention will be described below in conjunction with specific examples:

[0071] like figure 1 The historical trajectories in are used for training, and the estimated figure 2 travel time in .

[0072] 1. The preprocessing stage, the feature extraction and representation stage, preprocesses the trajectory data and extracts its various features. by figure 1 For example, the specific steps are:

[0073] (1) In the urban area, fine-grained grid division is carried out, and it is divided into adjacent small areas. like figure 1 , divide the map into 5×6 grids. Map each coordinate point in the trajectory sequence to the corresponding small area to form a grid sequence, that is, g={g 1 , g 2 ,...,g 10}.

[0074] (2) For each grid, mine its characteristics in different aspects. For example, for g 1 , using a random vector and to represent spatiotemporal semantic information. which is:

[0075]

[0076] ...

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 belongs to the technical field of intelligent traffic, and specifically relates to a journey time estimation method based on an auxiliary supervised learning. The journey time estimationmethod seeks for statistical rules from massive historical trajectory data, performs an overall estimation of the time of the journey through an end-to-end deep learning model. The journey time estimation method comprises the following steps of: performing a characteristic extraction and representation stage, wherein the trajectory data is preprocessed, and temporal and spatial characteristics, driving state characteristics, short-term and long-term traffic condition characteristics of the trajectory data are extracted respectively; preforming a training and prediction stage, wherein the extracted characteristics are trained and predicted by a unified bi-directional cyclic neural network; each step of the cyclic neural network outputs the time overhead through the current small area; andthe sum of the time overheads of the small areas is the time overhead of a total path; meanwhile, a bi-directional interval loss function is introduced to constrain the intermediate time overhead. Thejourney time estimation method can estimate the journey time of a vehicle in the city efficiently and accurately, and has better effects under actual environment.

Description

technical field [0001] The invention belongs to the technical field of intelligent transportation, and in particular relates to a method for estimating travel time based on auxiliary supervised learning. Background technique [0002] Travel time estimation is an essential and important technology in the field of urban transportation, which can provide assistance for people's travel and commuting, and can also provide support for government planning decisions. But this is not a simple small problem, but will be affected by various dynamic factors, such as traffic dynamics, intersection conditions, changes in driver's driving behavior and historical periodic data evolution, etc. These factors lead to uncertainty and difficulty in estimating travel time. With the development and popularization of GPS-enabled mobile devices, a large amount of trajectory data has been continuously generated and covers every corner of the city. With these massive historical trajectory data, we c...

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
IPC IPC(8): G08G1/01G06N3/04
CPCG08G1/0129G08G1/0137G06N3/045
Inventor 孙未未章瀚元吴昊
Owner FUDAN UNIV