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

A traffic flow pattern recognition method based on density peak clustering algorithm

A technology of clustering algorithm and traffic mode, which is applied in the field of clustering algorithm, can solve the problems that affect the online classification of traffic flow and long calculation time, and achieve the effect of fast calculation speed, stable clustering effect and easy realization

Inactive Publication Date: 2019-01-22
HUZHOU CITY SPECIAL EQUIP INSPECTION INST
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method has strong generalization ability and overcomes the dependence on training data, but has the disadvantage of long calculation time, which affects the online classification of traffic flow

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 traffic flow pattern recognition method based on density peak clustering algorithm
  • A traffic flow pattern recognition method based on density peak clustering algorithm
  • A traffic flow pattern recognition method based on density peak clustering algorithm

Examples

Experimental program
Comparison scheme
Effect test

experiment example

[0045] Such as figure 1 As shown, the data used in the experiment is the traffic flow data of a multi-tenant office building in a building for 2 days. The data is collected from 7 o'clock to 19 o'clock, and the collection time interval is 5 minutes. 144 data are obtained in one day, and there are 288 traffic flow data points in total. .

[0046] From the clustering results of the swarm intelligence clustering algorithm, it can be seen that the first category corresponds to the mixed traffic mode in the morning off-peak period, and the cluster center coordinates are (25.21, 17.69, 3.06); the second category corresponds to the mixed traffic mode in the afternoon off-peak period. Traffic mode, the cluster center coordinates are (33.13, 31.66, 22.15); the third category corresponds to the noon traffic mode, the cluster center coordinates are (68.12, 73.50, 61.59); the fourth category corresponds to the uplink peak mode, the cluster center The coordinates are (80.86, 9.72, 6.54); ...

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 an elevator traffic pattern recognition method based on a density peak clustering algorithm. Firstly, the local density of each data point and the minimum distance from the datapoint with higher density are calculated. Then, a decision chart is drawn by the two methods, and the cluster center is selected manually. Finally, the remaining data points are categorized accordingto the category of higher density data points nearest to them. The algorithm has the following advantages: First, it inherits the advantages of density clustering algorithm, does not need to specifythe number of clusters and can cluster arbitrary shape data. Second, it can be adapted to different data sets with different densities in different clusters. Third, accommodate arbitrary metrics as distances. Fourth, the algorithm is deterministic algorithm, not iterative algorithm, and the computational load is small. Fifth, outliers and noise points can be excluded.

Description

technical field [0001] The invention relates to a clustering algorithm, in particular to an elevator traffic pattern recognition method based on a density peak clustering algorithm. Background technique [0002] The elevator group control system is an indispensable vertical transportation tool in modern high-rise buildings. A well-designed elevator group control system can not only provide passengers with high-quality services, but also increase the use value of buildings. The core of the elevator group control system is the elevator group control scheduling algorithm, and the traffic flow is an important factor affecting the performance of the elevator group control scheduling algorithm. Accurately classify the traffic flow conditions in the building, and select the appropriate elevator group control scheduling algorithm under different traffic flow conditions, which can effectively improve the service quality and various performance indicators of the elevator system. [...

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): G06K9/62
CPCG06F18/23
Inventor 陈本瑶阮利程杨轶平卞建忠施沈科俞平叶健朱绍军
Owner HUZHOU CITY SPECIAL EQUIP INSPECTION INST
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