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

A Context-Aware Non-Negative Tensor Decomposition Method for Urban Dynamics Analysis

A non-negative tensor decomposition and analysis method technology, applied in the field of urban dynamic analysis, can solve problems such as the inability to analyze the long-term evolution of dynamic models and the inability to fit the interaction between models, and achieve the effect of model accuracy

Active Publication Date: 2020-06-30
BEIHANG UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The model created by the invention overcomes the problems that the existing models cannot fit the interaction between the models and cannot analyze the long-term evolution of the dynamic model, and at the same time introduces the urban context information to make the results more accurate

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 Context-Aware Non-Negative Tensor Decomposition Method for Urban Dynamics Analysis
  • A Context-Aware Non-Negative Tensor Decomposition Method for Urban Dynamics Analysis
  • A Context-Aware Non-Negative Tensor Decomposition Method for Urban Dynamics Analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0041] An embodiment of the present invention provides a method for analyzing urban dynamics based on context-aware non-negative tensor decomposition, referring to figure 1 shown, including:

[0042] S1. Divide the city to be analyzed into M regions, and divide each day into N time slices;

[0043] S2. Extract the departure place, arrival place and time information from the trajectory data related to human activities; match the de...

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 relates to an urban dynamic analysis method based on context-aware non-negative tensor decomposition, using tensor factorization as the basis of the model, which can not only discover the spatial and temporal patterns of human activities in the city, but also simulate the relationship between these patterns In addition, urban context information is introduced into the tensor factorization model to make the model more accurate; and a pipeline initialization method for analyzing tensor sequences is proposed, so that the non-negative tensor decomposition model can analyze urban dynamics long-term evolution. This method proposes a context-aware non-negative tensor factorization model (cNTF), which uses resident flow data and urban environment information to discover potential patterns of human activities in cities based on tensor Tucker decomposition. The method provided by the invention overcomes the problems that the existing models cannot fit the interaction between the models and cannot analyze the long-term evolution of the dynamic model, and at the same time introduces the urban context information to make the result more accurate.

Description

technical field [0001] The present invention relates to the field of data mining technology and the field of smart city technology, in particular to an urban dynamic analysis method based on context-aware non-negative tensor decomposition. Background technique [0002] In intelligent transportation systems (ITS) and urban computing, tensor decomposition (factorization) is an effective tool for modeling spatiotemporal data. Based on tensor decomposition, the existing space-time modeling techniques are based on the factors obtained after decomposition, trying to reveal the potential physical meaning of each mode. For example, a second-order tensor matrix is ​​used to fit urban taxi travel data, and non-negative matrix factorization (NMF) is used to dig out potential factors corresponding to the daily rhythm of residents; tensor cp decomposition is used to analyze residents' health in the earthquake in Japan Mobile phone data, discovering different human activity patterns; usi...

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): G06F17/18G06K9/62G06Q50/26
CPCG06F17/18G06Q50/26G06F18/2133
Inventor 王静远陈超熊璋
Owner BEIHANG 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