Traffic index time sequence identification method based on autoregressive differential moving average-convolutional neural network

A technology of convolutional neural network and moving average algorithm, which is applied in the field of identifying traffic index time series, can solve the problems of traffic index time series data distortion, insufficient pattern recognition ability and deformation of traffic index time series data, and achieve accurate prediction and model The effect of identifying and alleviating urban traffic pressure

Pending Publication Date: 2021-02-05
BEIJING UNIVERSITY OF CIVIL ENGINEERING AND ARCHITECTURE +1
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although both types of pattern recognition methods can obtain good classification results under specific conditions, they are affected by multi-party traffic factors, and there are certain distortions and deformations in the traffic index time series data itself. Therefore, the traditional distance-based and feature-based methods The recognition method still has some deficiencies in the pattern recognition ability of traffic index time series 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
  • Traffic index time sequence identification method based on autoregressive differential moving average-convolutional neural network
  • Traffic index time sequence identification method based on autoregressive differential moving average-convolutional neural network
  • Traffic index time sequence identification method based on autoregressive differential moving average-convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0111] The method for generating traffic index time series described in step 0000 comprises:

[0112] Step 0200: Calculate the average traffic index at each moment according to the original traffic index data set.

[0113] Step 0400: Select the first continuous time series and the second continuous time series.

[0114] Among them, the second threshold k 2 ∈(l 2 *X,l 1 *X), l 2 is a positive real number and l 2 ≥1, preferably, l 2 is 1.5.

[0115] Step 0600: According to the traffic index raw data set, the first continuous time series and the second continuous time series, divide the traffic index raw data set.

[0116] Step 0600 further comprises:

[0117] Step 0620, if the number of moments in the first continuous time series is n t , then divide the traffic index data of the i-th day into n 0 time periods, preferably, n 0 for n 2 and n t function, more preferably, Indicates rounding down.

[0118] Optional, if there are multiple first continuous time serie...

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 a traffic index time sequence identification method based on autoregressive differential moving average-convolutional neural network, and the method comprises the steps: obtaining a traffic index original data set, and generating the traffic index time sequence; converting the traffic index time sequence into a stable sequence, and fitting an autoregressive differential moving average algorithm model according to a Bayesian information criterion matrix to achieve traffic index prediction; generating a training traffic index time sequence and a test traffic index time sequence according to the traffic index original data set, extracting traffic index feature information according to the training traffic index time sequence, and obtaining an optimal convolutional neural network model, and integrating the traffic index feature information into a one-dimensional feature vector by using the optimal convolutional neural network model, determining a pattern category of the one-dimensional feature vector according to a Softmax classifier, and further identifying a category to which a test traffic index time sequence belongs.

Description

technical field [0001] The invention relates to a method for identifying traffic index time series based on autoregressive differential moving average-convolutional neural network. Background technique [0002] Traffic is the lifeblood of a city. With the rapid development of urban economy, the problem of traffic congestion is becoming more and more serious, and the more developed the economy is, the more prominent it is. In order to cope with the complex and changeable traffic conditions in the city and alleviate the urban traffic pressure, the traffic management department has issued a series of traffic laws and regulations to restrict driving regulations, and scientific research institutions have also used technologies such as the Internet of Things to assist the traffic control department in monitoring road congestion. Although various industries have achieved certain results in reducing the risk of traffic congestion in various aspects, the negative impact of traffic 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): G06Q10/06G06Q50/26G06N3/04G06N3/08
CPCG06Q10/06393G06Q50/26G06N3/08G06N3/045
Inventor 张学东卢剑张健钦徐志洁王家川石瑞轩
Owner BEIJING UNIVERSITY OF CIVIL ENGINEERING AND ARCHITECTURE
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