Track data compression method based on LSTM prediction and smooth analysis thought

A technology of trajectory data and compression method, applied in neural learning methods, electrical digital data processing, special data processing applications, etc., can solve problems such as loss of position information

Pending Publication Date: 2021-06-08
SHANGHAI MARITIME UNIVERSITY
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This compression method reduces space overhead to a certain extent, but at the same time loses specific location information

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
  • Track data compression method based on LSTM prediction and smooth analysis thought
  • Track data compression method based on LSTM prediction and smooth analysis thought
  • Track data compression method based on LSTM prediction and smooth analysis thought

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066] based on the following Figure 1 to Figure 7 , specifically explain the preferred embodiment of the present invention.

[0067] In this embodiment, a trajectory data compression method based on LSTM prediction and smoothing analysis ideas is provided. The deep learning model is applied to the traditional trajectory compression field, and the angle error Angle-Deviation and the synchronous Euclidean distance SED error are considered at the same time. The idea of ​​smoothing analysis determines the threshold range of the compression algorithm, and compresses the trajectory data with a large amount of data.

[0068] Such as figure 1 As shown, a trajectory data compression method based on LSTM prediction and smoothing analysis ideas provided in this embodiment includes the following steps:

[0069] Step S1, performing data cleaning on the collected original trajectory data;

[0070] Step S2, making a data set format for network model input, normalizing the data after dat...

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 trajectory data compression method based on LSTM prediction and smooth analysis thoughts and a moving object trajectory data compression method based on LSTM prediction apply a deep learning model to the traditional trajectory compression field, use a neural network to predict and obtain a distance error and a direction error, and use a smooth analysis thought to determine a compression threshold. The method does not need manual setting of an error threshold value, considers the distance and the direction at the same time, fully retains important information of an original track, obtains the error and determines the error threshold value according to the characteristics of the compressed track compared with a traditional track compression algorithm, can be better suitable for track data with different characteristics; the problems that a traditional track compression algorithm is poor in compression effect, errors are manually found, and an error threshold setting experiment is tedious are solved.

Description

technical field [0001] The invention relates to a trajectory data compression method based on LSTM prediction and smoothing analysis ideas. Background technique [0002] With the popularization and application of technical equipment such as GPS, RFID, and wireless sensors, a large amount of trajectory data of moving objects has been generated, and the amount of trajectory data has skyrocketed exponentially. Extracting the rich information contained in these data has become one of the current hot research directions. one. However, the increasing amount of trajectory data has brought huge challenges to existing research and storage devices: huge data volume, increased query time, and data redundancy. Therefore, it is imperative to compress the trajectory data of moving objects. Solving these three problems can be solved by using algorithms that reduce trajectory data. The trajectory data collected by a continuously moving object is a discrete trajectory point containing posi...

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): G06F16/215G06N3/04G06N3/08
CPCG06F16/215G06N3/084G06N3/048G06N3/044G06N3/045
Inventor 陈雪松杨智应
Owner SHANGHAI MARITIME UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap