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

Driving Behavior Recognition Method Based on Variant Algorithm of Adaptive Resonance Theory

An adaptive and behavioral technology, applied in the field of driving behavior recognition, can solve the problems of not considering the driver's influence and low recognition rate

Active Publication Date: 2019-04-05
HEFEI UNIV OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the existing technical methods can effectively realize driving behavior recognition, they mainly analyze and study the driver's behavior characteristics and behavior recognition, and do not consider the influence of the driver's individual characteristics on driving behavior recognition, resulting in a low actual recognition rate.

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
  • Driving Behavior Recognition Method Based on Variant Algorithm of Adaptive Resonance Theory
  • Driving Behavior Recognition Method Based on Variant Algorithm of Adaptive Resonance Theory
  • Driving Behavior Recognition Method Based on Variant Algorithm of Adaptive Resonance Theory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] In this example, if figure 1 As shown, a driving behavior recognition method based on adaptive resonance theory variant algorithm is carried out as follows:

[0065] Step 1. Use the on-board sensors to collect N sets of original manipulation data with a duration of T for the driver's H types of driving behavior, denoted as U H×N ; The driving behavior involved in the specific implementation process includes four types of acceleration (deceleration), steering, merging, and overtaking, that is, H=4; the value of T is the average of the driver's longest time-consuming driving behavior manipulation Duration, the unit is s; thus obtain H×N groups of original manipulation data with a duration of T;

[0066] Step 2. The nth group of raw manipulation data of the collected hth driving behavior carry out preprocessing; Represents the k-th type of manipulation action data in the n-th group of original manipulation data of the h-th type of driving behavior; and has Indicat...

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 discloses a driving behavior recognition method based on a variant algorithm of the self-adaptive resonance theory, which is carried out in the following steps: 1. Collect the driver's driving behavior manipulation data by means of a vehicle-mounted sensor, and extract the corresponding driving manipulation action after preprocessing; 2. Construct the driver's 3. Construct a driving behavior recognition method based on adaptive resonance theory variant algorithm; 4. Input all driving behavior manipulation modes into the network at one time to complete the network’s memory of all driving behaviors; 5. Input any driving behavior manipulation mode, the network The corresponding driving behavior can be identified, and it has the characteristics of online incremental self-learning. The invention can make the driving behavior recognition method better close to the individual characteristics of the driver's driving manipulation, thereby improving the recognition rate of the driving behavior.

Description

technical field [0001] The invention is a driving behavior recognition method based on a variant algorithm of adaptive resonance theory, which is used to solve the inconsistency between the traditional driving behavior recognition technology and the driver's individual characteristics, and belongs to the technical field of driving behavior recognition. Background technique [0002] The statistical results of the causes of traffic accidents show that 80%-90% of traffic accidents are caused by the driver's individual factors, while the traffic accidents caused by vehicles and environmental factors only account for 10-20%. The data fully demonstrates the core position and role of drivers in traffic accident prevention. Drivers are not only information processors and decision makers of the road traffic system, but also regulators and controllers. Whether their behavior is safe or not has a major impact on the state of the entire system . However, in the actual driving process, ...

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): G06K9/00G06N3/02
CPCG06N3/02G06V20/597
Inventor 肖献强周凌侃王家恩殷延杰
Owner HEFEI UNIV OF TECH
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