A method for automatic assessment of vehicle following safety based on machine learning

A machine learning, safe and automatic technology, applied in the fields of instruments, computer parts, computing, etc., can solve problems such as heavy workload, complicated tracking and judgment, and achieve the effect of avoiding danger or accident

Active Publication Date: 2019-01-25
CHINA INFOMRAITON CONSULTING & DESIGNING INST CO LTD
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the traditional sense, tracking and judging the driving behavior of individual vehicles is difficult and requires a lot of work, and there is no precedent for using traditional methods

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 method for automatic assessment of vehicle following safety based on machine learning
  • A method for automatic assessment of vehicle following safety based on machine learning
  • A method for automatic assessment of vehicle following safety based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment example

[0062] An implementation case of the present invention is introduced below. The case uses all data during the operation period of about 260 kilometers of expressways under the jurisdiction of a certain expressway company from 2012 to 2014, including main road checkpoint data, toll collection data at each toll station, and meteorological data for each road section. , accident record data and other raw data, its size is about 1.2Tb.

[0063] The hardware environment for modeling research and testing in this case is CORE TM i5 CPU, memory 16Gb, system platform is Windows 10 (64~bit), development and testing software using python TM 3.4 (64bit), machine learning modeling uses python third-party library sckit-learn 0.16.0.

[0064] The specific implementation steps of the case are as follows:

[0065] Step 1, collect and prepare the required data.

[0066] Step 2, use SQL language and Python script to process raw data, and perform preprocessing analysis based on each vehic...

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 method for automatic evaluation of vehicle following safety based on machine learning, which includes collecting data, performing data cleaning on the obtained data, retaining the data that meets the requirements, standardizing and regularizing the data into the same data set D, and analyzing the data after cleaning. According to the accident records and related monitoring data, the modeling data M used for machine learning is extracted from the cleaned and regularized data, and the M set is randomly divided into two according to a given ratio. A subset of MT and ME, MT is used for model training, ME is used for model performance verification test, using supervised classification machine learning algorithm, using training data MT for modeling learning, using ME data to verify the obtained model performance, and calculating the relevant confusion matrix and model classification accuracy, record and compare each result, select an optimal model, use the optimal model to automatically evaluate all records in the data set D one by one, append the results to the data set D and output the results.

Description

technical field [0001] The invention belongs to the field of information processing of expressway operation management, and in particular relates to a machine learning-based automatic vehicle following safety evaluation method. Background technique [0002] In recent years, the role of informatization in expressway operation and management has been increasing day by day. With the improvement of informatization (a large amount of data accumulation, the improvement of machine performance, the development of data mining and other disciplines), the precise management and service based on vehicles are in the smart It came into being in the construction of expressways. Providing precise management services for individual vehicles relies on in-depth cognition of various behaviors of vehicles. However, due to the large number of management objects and complex cognition content, manual evaluation cannot be processed one by one on a vehicle-by-vehicle basis due to the huge workload. ...

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 & AuthorityPatents(China)
IPC IPC(8): G06K9/62
CPCG06F18/241G06F18/214
Inventor齐家卞加佳陈晨冒兵朱磊焦枫
OwnerCHINA INFOMRAITON CONSULTING & DESIGNING INST CO LTD