CN113160593A - Mountain road driving safety early warning method based on edge cloud cooperation - Google Patents
Mountain road driving safety early warning method based on edge cloud cooperation Download PDFInfo
- Publication number
- CN113160593A CN113160593A CN202110062817.1A CN202110062817A CN113160593A CN 113160593 A CN113160593 A CN 113160593A CN 202110062817 A CN202110062817 A CN 202110062817A CN 113160593 A CN113160593 A CN 113160593A
- Authority
- CN
- China
- Prior art keywords
- risk
- road section
- road
- indexes
- driving
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000012502 risk assessment Methods 0.000 claims abstract description 80
- 238000013210 evaluation model Methods 0.000 claims abstract description 15
- 238000013528 artificial neural network Methods 0.000 claims description 50
- 238000012549 training Methods 0.000 claims description 29
- 238000012360 testing method Methods 0.000 claims description 13
- 238000011156 evaluation Methods 0.000 claims description 9
- 230000002411 adverse Effects 0.000 claims description 2
- 238000003062 neural network model Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Atmospheric Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a mountain road driving safety early warning method based on edge cloud cooperation, which comprises the following steps of: dividing a road into a plurality of road section intervals, and acquiring position data, historical accident data and historical risk index data of each road section interval; according to the position data, the historical accident data and the historical risk index data, a road section driving risk assessment model of each road section interval is constructed; acquiring real-time position information and real-time risk index data of a vehicle; acquiring a road section driving risk evaluation model of the current road section according to the real-time position information; inputting the real-time risk index data into a road section driving risk evaluation model of the current road section to obtain a real-time driving risk accident rate; generating an early warning instruction according to the real-time driving risk accident rate; according to the method and the system, the mountain road risk source is fully considered, the risk data of the driver and the vehicle are considered, a closed-loop mountain road risk assessment system is formed, and the operability is high.
Description
Technical Field
The invention relates to the technical field of road traffic safety, in particular to a mountain road driving safety early warning method based on edge cloud cooperation.
Background
The mountain highway has more high-risk road sections due to the influence of landforms such as vertical and horizontal mountains, dense river distribution and the like. The road has complex shape, more long and large bridges and tunnels, frequent transition of roadbed-bridge-tunnel, steep curve of slope, complex setting of overpass, variable climate, easy occurrence of secondary accident, and the possibility of accident occurrence is higher than that of common road when a driver drives on the road in a mountain area.
At present, a driver mostly browses a map, searches places, inquires driving/bus lines, updates road conditions in real time and other functions through various navigation APPs, safety prompts of the driver are few due to the navigation APPs, voice broadcast in the aspect of road traffic safety is rarely involved, and the early warning effect on driving risks of mountainous roads is very limited; many scholars have a certain research foundation in the aspect of highway driving early warning, can provide a certain theoretical foundation for a highway early warning method, but do not embed the characteristics of mountain roads into an early warning system, and do not analyze mountain road risk sources from a traffic closed-loop system of 'human-vehicle-road-environment', so that a complete, effective and accurate voice early warning and broadcasting system for mountain road driving safety is not formed; the general early warning system cannot judge dynamic risk factors in real time, vehicles running on a highway in a mountainous area are influenced by static risk factors such as road alignment and fixed structures, and also influenced by dynamic risk factors such as group fog and emergency, and the real-time performance is difficult to guarantee; in addition, the general early warning system does not consider the driver information and the type and structure of the vehicle when setting the voice broadcast, only has simple early warning information such as 'you have overspeed and please notice deceleration', does not consider the operability of the driver on the early warning information due to age, driving habits and the like, does not consider different types of vehicles and driving conditions of the vehicles to reasonably set voice prompt, and reduces the recognition degree and the operability of the early warning system.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a mountain road driving safety early warning method based on edge cloud cooperation.
The technical means adopted by the invention is as follows:
a mountain road driving safety early warning method based on edge cloud cooperation comprises the following steps:
dividing a road into a plurality of road section intervals, and acquiring position data, historical accident data and historical risk index data of each road section interval;
according to the position data, the historical accident data and the historical risk index data, a road section driving risk assessment model of each road section interval is constructed;
acquiring real-time position information and real-time risk index data of a vehicle;
acquiring a road section driving risk evaluation model of the current road section according to the real-time position information;
inputting the real-time risk index data into a road section driving risk evaluation model of the current road section to obtain a real-time driving risk accident rate;
and generating an early warning instruction according to the real-time driving risk accident rate.
Further, the acquiring of the historical risk indicator data of each road section specifically includes:
determining a risk assessment index;
acquiring historical risk index data of each road section interval according to the risk assessment index;
the risk assessment indexes comprise primary risk assessment indexes and secondary risk assessment indexes, the primary risk assessment indexes are road condition indexes, driving environment indexes, driver indexes and vehicle indexes, and each primary risk assessment index comprises a plurality of secondary risk assessment indexes.
Further, after determining the risk assessment index, the method further includes:
and dividing each risk evaluation index into four risk levels according to the risk levels, wherein the four risk levels correspond to four risk values respectively.
Further, according to the position data, the historical accident data and the historical risk index data, a road section driving risk assessment model of each road section interval is constructed, and the method specifically comprises the following steps:
respectively inputting historical accident data and historical risk index data of each road section interval into a neural network training model for training to obtain a road section driving risk evaluation model of each road section interval, wherein the road section driving risk evaluation model is used for evaluating the driving risk accident rate of the corresponding road section interval;
and storing the road section driving risk evaluation model in the cloud platform according to the position information of each road section interval.
Further, before the historical accident data and the historical risk index data of each road section are respectively input into the neural network training model for training, the method further includes:
classifying historical risk index data corresponding to the risk assessment index according to the risk value;
respectively inputting historical accident data and classified historical risk index data of each road section interval into a geographic detector to obtain an importance value of a risk evaluation index of each road section interval;
according to the importance value, ranking the importance of the risk assessment indexes of each road section interval;
taking a preset number of risk assessment indexes with larger importance in the importance ranking of each road section interval as the road section risk assessment indexes of the road section interval;
acquiring a training sample and a test sample of each road section interval according to the road section risk assessment indexes;
and respectively inputting the historical accident data and the training samples of each road section interval into a neural network training model for training to obtain a road section driving risk assessment model of each road section interval.
Further, the secondary indexes under the road condition indexes respectively comprise a flat curve radius, a vertical curve radius, a longitudinal slope gradient, a longitudinal slope length, a lane width, the number of lanes, a road surface condition, a road shoulder width, a road test facility, a traffic structure, a bridge condition, a tunnel condition, an interchange condition and an adverse combination condition; the secondary indexes under the driving environment indexes respectively comprise: visibility, weather conditions, and traffic volume; the secondary indexes under the driver indexes respectively comprise the age of the driver, the driving age of the driver, the sex of the driver, the vision of the driver and the driving habit of the driver; the secondary indexes under the vehicle indexes respectively comprise the type of the vehicle, the performance of the vehicle, the running time and the speed of the vehicle.
Further, the neural network is a BP neural network, a GA-BP neural network and a PSO-BP neural network.
Further, inputting historical accident data and training samples of each road section interval into a BP neural network, a GA-BP neural network and a PSO-BP neural network respectively for training to obtain a BP neural network prediction model, a GA-BP neural network prediction model and a PSO-BP neural network prediction model of each road section interval respectively;
and respectively inputting the test samples into a BP neural network prediction model, a GA-BP neural network prediction model and a PSO-BP neural network prediction model for testing to respectively obtain the error value of each neural network prediction model, and selecting the prediction model with the minimum error value as the optimal prediction model of the road section interval.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the invention, the road is divided into a plurality of road section intervals, the historical risk index data of each road section interval is respectively obtained, the road section driving risk evaluation model is constructed, the driving risk accident rate of the corresponding road section can be evaluated by using the road section driving risk evaluation model, the environmental road condition characteristics of each road section interval can be fully considered during evaluation, and the evaluation accuracy is higher.
2. When the risk assessment indexes are set, the first-level risk assessment indexes are set from the four aspects of people, vehicles, roads and environments, mountain highway risk sources are fully considered, meanwhile, driver and vehicle risk data are considered, a closed-loop mountain highway risk assessment system is formed, and the operability is high.
Detailed Description
The invention is further described below with reference to specific examples:
a mountain road driving safety early warning method based on edge cloud cooperation comprises the following steps:
and S1, determining a risk evaluation index, wherein the risk evaluation index is used for evaluating the driving risk. The risk assessment indexes comprise primary risk assessment indexes and secondary risk assessment indexes, the primary risk assessment indexes are road condition indexes, driving environment indexes, driver indexes and vehicle indexes, and each primary risk assessment index comprises a plurality of secondary risk assessment indexes. When the risk assessment indexes are set, the first-level risk assessment indexes are set from the four aspects of people, vehicles, roads and environments, mountain highway risk sources are fully considered, and a closed-loop mountain highway risk assessment system is formed.
The secondary indexes under the road condition indexes respectively comprise one or more of a flat curve radius, a vertical curve radius, a longitudinal slope gradient, a longitudinal slope length, lane width, lane number, road surface condition, road shoulder width, road testing facilities, traffic structures, bridge condition, tunnel condition, interchange condition and unfavorable combination condition; the secondary indexes under the driving environment indexes respectively comprise: one or more of visibility, weather conditions, and traffic volume; the secondary indexes under the driver indexes respectively comprise one or more of the age of the driver, the driving age of the driver, the sex of the driver, the vision of the driver and the driving habits of the driver; the secondary indicators under the vehicle indicator respectively include one or more of a vehicle type, a vehicle performance and travel time, and a vehicle speed.
And S2, dividing each risk assessment index into four risk levels according to the risk levels, wherein the four risk levels correspond to four risk values respectively.
The four risk levels are respectively safe, safer, more dangerous and dangerous, the four risk values are respectively 0, 1, 2 and 3, the four risk levels respectively correspond to the four risk values, i.e. the risk value 0 corresponds to the safety of the risk level, the risk value 1 corresponds to the safer of the risk level, the risk value 2 corresponds to the more dangerous of the risk level, and the risk value 3 corresponds to the danger of the risk level.
The risk evaluation indexes comprise both type quantity indexes and numerical quantity indexes, when the risk value of each risk index is determined, the type quantity indexes manually determine the risk value of the risk index according to the property of the type quantity indexes, and the numerical quantity indexes determine the risk value of the risk index according to actual data of the numerical quantity indexes. The risk value corresponding to each risk assessment index is shown in the following table:
TABLE 1 Risk assessment index grading
And S3, dividing the road into a plurality of road section intervals, and acquiring the position data, the historical accident data and the historical risk index data of each road section interval.
When the road section is divided, the road section is divided by adopting a fixed length method or/and an indefinite length method, wherein the fixed length method is used for dividing according to a fixed length, and the indefinite length method is used for dividing according to any length. By constructing the road section driving risk assessment model according to the road section intervals, the influence of the risk index data of each road section interval on the driving risk accident rate can be fully considered, and the accuracy of risk assessment is improved.
In acquiring the historical risk index data, the historical risk index data of each link section is acquired according to the risk assessment index determined in step S1.
And S4, constructing a road section driving risk assessment model of each road section according to the position data, the historical accident data and the historical risk index data, wherein the road section driving risk assessment model is used for assessing the driving risk accident rate of the corresponding road section.
In step S4, a road section driving risk assessment model for each road section is constructed according to the set data, the historical accident data, and the historical risk index data, and the method specifically includes:
and S41, classifying the historical risk index data corresponding to the risk assessment index according to the risk value.
And S42, respectively inputting the historical accident data of each road section and the classified historical risk index data into a geographic detector, and obtaining the importance value of the risk assessment index of each road section.
Specifically, historical accident data of each road section and classified historical risk index data are respectively input into a factor detection module of a geographic detector, and q values of all secondary risk assessment indexes are detected quantitatively, wherein the accident data comprise accident grades; the q value represents the influence of the risk assessment index on the accident grade, namely the importance of the risk assessment index; the value range of the q value is [0, -1], and the larger the q value is, the stronger the interpretation of the risk assessment index on the accident grade is, and the weaker the interpretation is; q is 1, the risk assessment index completely controls the occurrence of the accident grade, and the more important the risk assessment index is, the higher the importance of the risk assessment index is; q is 0, which indicates that the occurrence of the accident grade is irrelevant to the risk assessment index, and the importance is low.
And S43, sorting the importance of the risk assessment indexes of each road section interval according to the importance value.
And S44, taking the preset number of risk assessment indexes with larger importance in the importance sequence of each road section interval as the road section risk assessment indexes of the road section interval. Because people, vehicles, roads and environments of each road section interval are different, the road section risk assessment indexes selected by each road section interval have certain difference, the influence of the risk assessment indexes of each road section interval on the accident rate can be fully considered by taking the road section interval as a unit, and the model prediction accuracy is improved.
The number of the selected risk assessment indexes can be selected according to actual conditions, indexes with low importance are abandoned, and the operation rate is improved on the premise of ensuring accuracy.
S45, obtaining a training sample and a test sample of each road section interval according to the road section risk assessment indexes, wherein the training sample and the test sample can adopt a formula 1: a ratio of 1.
And S46, respectively inputting the historical accident data and the training samples of each road section interval into the neural network training model for training to obtain a road section driving risk assessment model of each road section interval, wherein the road section driving risk assessment model is used for assessing the driving risk accident rate of the corresponding road section interval. The historical accident data comprises the historical accident number and the accident grade, and only the historical accident number can be used for training during training.
The neural network is BP neural network, GA-BP neural network and PSO-BP neural network. Respectively inputting historical accident data and training samples of each road section interval into a BP neural network, a GA-BP neural network and a PSO-BP neural network for training to respectively obtain a BP neural network prediction model, a GA-BP neural network prediction model and a PSO-BP neural network prediction model of each road section interval;
and respectively inputting the test samples into a BP neural network prediction model, a GA-BP neural network prediction model and a PSO-BP neural network prediction model for testing to respectively obtain the error value of each neural network prediction model, and selecting the prediction model with the minimum error value as the optimal prediction model of the road section interval.
Specifically, the error value is one or more of a Mean Absolute Error (MAE), a Root Mean Square Error (RMSE), and a mean absolute percentage error.
More specifically:
the Mean Absolute Error (MAE) is:
wherein, yiIn order to realize the actual traffic risk accident rate,
in order to predict the driving risk accident rate, n is the total number of samples.
Root Mean Square Error (RMSE) is:
wherein, yiIn order to realize the actual traffic risk accident rate,
in order to predict the driving risk accident rate, n is the total number of samples.
Mean Absolute Percent Error (MAPE) is:
wherein, yiIn order to realize the actual traffic risk accident rate,
in order to predict the driving risk accident rate, n is the total number of samples.
Taking the minimum value of the sum of the average absolute error, the root mean square error and the average absolute percentage error of the driving risk assessment model of each road section as follows:
M＝min{MAEi+RMSEi+MAPEi}(i＝1,2,3)
wherein M represents a value at which the sum of errors is minimum, MAEiRepresenting the mean absolute error of the ith neural network model; RMSEiRepresenting the root mean square error of the ith neural network model; MAPEiThe mean absolute percentage error of the ith neural network model is expressed.
The minimum value of M represents that the prediction effect of the neural network is optimal.
And S47, storing the road section driving risk assessment model in the cloud platform according to the position information of each road section interval.
And S5, acquiring real-time position information and real-time risk index data of the vehicle.
Specifically, a driving information acquisition module, a weather condition module and a GPS module can be installed on the vehicle, the driving information acquisition module acquires current driver indexes, such as a driver, the vehicle and the like, and vehicle indexes, the GPS module acquires real-time position information of the vehicle in real time, road condition index data are acquired according to the position information, and the weather condition module acquires driving environment index data in real time. And carrying out normalization processing on the acquired real-time risk index data.
And S6, acquiring a road section driving risk assessment model of the current road section according to the real-time position information. And sending the real-time position information of the vehicle to a cloud platform, and acquiring a road section driving risk assessment model corresponding to the real-time position information.
And S7, inputting the real-time risk index data into the road section driving risk evaluation model of the current road section to obtain the real-time driving risk accident rate.
And S8, generating an early warning instruction according to the real-time driving risk accident rate.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention and not for limiting the technical solutions, and although the present invention has been described in detail by referring to the preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions to the technical solutions of the present invention can be made without departing from the spirit and scope of the technical solutions, and all the modifications and equivalent substitutions should be covered by the claims of the present invention.
Claims (8)
1. A mountain road driving safety early warning method based on edge cloud cooperation is characterized by comprising the following steps:
dividing a road into a plurality of road section intervals, and acquiring position data, historical accident data and historical risk index data of each road section interval;
according to the position data, the historical accident data and the historical risk index data, a road section driving risk assessment model of each road section interval is constructed;
acquiring real-time position information and real-time risk index data of a vehicle;
acquiring a road section driving risk evaluation model of the current road section according to the real-time position information;
inputting the real-time risk index data into a road section driving risk evaluation model of the current road section to obtain a real-time driving risk accident rate;
and generating an early warning instruction according to the real-time driving risk accident rate.
2. The mountain road driving safety early warning method based on edge cloud cooperation as claimed in claim 1, wherein the obtaining of historical risk index data of each road section specifically comprises:
determining a risk assessment index;
acquiring historical risk index data of each road section interval according to the risk assessment index;
the risk assessment indexes comprise primary risk assessment indexes and secondary risk assessment indexes, the primary risk assessment indexes are road condition indexes, driving environment indexes, driver indexes and vehicle indexes, and each primary risk assessment index comprises a plurality of secondary risk assessment indexes.
3. The mountain road driving safety early warning method based on edge cloud coordination as claimed in claim 2, wherein after determining the risk assessment index, the method further comprises:
and dividing each risk evaluation index into four risk levels according to the risk levels, wherein the four risk levels correspond to four risk values respectively.
4. The mountain road driving safety early warning method based on edge cloud cooperation as claimed in claim 3, wherein the step of constructing a road section driving risk assessment model of each road section according to the position data, the historical accident data and the historical risk index data specifically comprises the steps of:
respectively inputting historical accident data and historical risk index data of each road section interval into a neural network training model for training to obtain a road section driving risk evaluation model of each road section interval, wherein the road section driving risk evaluation model is used for evaluating the driving risk accident rate of the corresponding road section interval;
and storing the road section driving risk evaluation model in the cloud platform according to the position information of each road section interval.
5. The mountain road driving safety early warning method based on edge cloud cooperation as claimed in claim 4, wherein before inputting the historical accident data and the historical risk index data of each road section into the neural network training model for training, the method further comprises:
classifying historical risk index data corresponding to the risk assessment index according to the risk value;
respectively inputting historical accident data and classified historical risk index data of each road section interval into a geographic detector to obtain an importance value of a risk evaluation index of each road section interval;
according to the importance value, ranking the importance of the risk assessment indexes of each road section interval;
taking a preset number of risk assessment indexes with larger importance in the importance ranking of each road section interval as the road section risk assessment indexes of the road section interval;
acquiring a training sample and a test sample of each road section interval according to the road section risk assessment indexes;
and respectively inputting the historical accident data and the training samples of each road section interval into a neural network training model for training to obtain a road section driving risk assessment model of each road section interval.
6. The mountain road driving safety early warning method based on edge cloud coordination as claimed in claim 2,
the secondary indexes under the road condition indexes respectively comprise a flat curve radius, a vertical curve radius, a longitudinal slope gradient, a longitudinal slope length, a lane width, the number of lanes, a road surface condition, a road shoulder width, a road test facility, a traffic structure, a bridge condition, a tunnel condition, an interchange condition and an adverse combination condition; the secondary indexes under the driving environment indexes respectively comprise: visibility, weather conditions, and traffic volume; the secondary indexes under the driver indexes respectively comprise the age of the driver, the driving age of the driver, the sex of the driver, the vision of the driver and the driving habit of the driver; the secondary indexes under the vehicle indexes respectively comprise the type of the vehicle, the performance of the vehicle, the running time and the speed of the vehicle.
7. The mountain road driving safety early warning method based on edge cloud cooperation of claim 5, wherein the neural network is a BP neural network, a GA-BP neural network and a PSO-BP neural network.
8. The mountain road driving safety early warning method based on edge cloud cooperation as claimed in claim 7, wherein historical accident data and training samples of each road section interval are respectively input into a BP neural network, a GA-BP neural network and a PSO-BP neural network for training, and a BP neural network prediction model, a GA-BP neural network prediction model and a PSO-BP neural network prediction model of each road section interval are respectively obtained;
and respectively inputting the test samples into a BP neural network prediction model, a GA-BP neural network prediction model and a PSO-BP neural network prediction model for testing to respectively obtain the error value of each neural network prediction model, and selecting the prediction model with the minimum error value as the optimal prediction model of the road section interval.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110062817.1A CN113160593A (en) | 2021-01-18 | 2021-01-18 | Mountain road driving safety early warning method based on edge cloud cooperation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110062817.1A CN113160593A (en) | 2021-01-18 | 2021-01-18 | Mountain road driving safety early warning method based on edge cloud cooperation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113160593A true CN113160593A (en) | 2021-07-23 |
Family
ID=76878413
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110062817.1A Pending CN113160593A (en) | 2021-01-18 | 2021-01-18 | Mountain road driving safety early warning method based on edge cloud cooperation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113160593A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114582126A (en) * | 2022-03-04 | 2022-06-03 | 深圳市综合交通与市政工程设计研究总院有限公司 | Intelligent management and control method and system suitable for ultra-long tunnel traffic and giving consideration to efficiency safety |
| CN114822024A (en) * | 2022-04-19 | 2022-07-29 | 哈尔滨工业大学 | Active safety guidance system for expressway agglomerate fog road section |
| CN114995164A (en) * | 2022-08-03 | 2022-09-02 | 武汉维泰信息科技有限公司 | New energy automobile safety early warning method and device based on Internet of things |
| CN115019532A (en) * | 2022-04-21 | 2022-09-06 | 东北林业大学 | Automatic identification and early warning system for potential safety hazards of roads based on passenger traffic data |
| CN115331449A (en) * | 2022-10-17 | 2022-11-11 | 四川省公路规划勘察设计研究院有限公司 | Method and device for identifying accident prone area of long and large continuous longitudinal slope section and electronic equipment |
| CN116720728A (en) * | 2023-04-26 | 2023-09-08 | 广州地铁设计研究院股份有限公司 | Risk assessment method, electronic device and storage medium |
| CN116778733A (en) * | 2022-11-26 | 2023-09-19 | 武汉广旺科技有限公司 | Highway navigation voice early warning method and system based on big data |
| CN117057605A (en) * | 2023-08-15 | 2023-11-14 | 广州地铁设计研究院股份有限公司 | Risk assessment model training method, risk assessment method and related equipment |
| CN117474344A (en) * | 2023-12-28 | 2024-01-30 | 青岛盈智科技有限公司 | Risk assessment method and system for cargo transportation process |
| CN117787699A (en) * | 2023-12-26 | 2024-03-29 | 公安部道路交通安全研究中心 | Road risk prediction method and device, computer equipment and storage medium |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102922999A (en) * | 2012-10-17 | 2013-02-13 | 重庆交通大学 | Vehicle dangerous driving state recognition device and recognition method for mountain highway |
| CN104240437A (en) * | 2013-06-19 | 2014-12-24 | 通用汽车环球科技运作有限责任公司 | Methods and apparatus for detection and reporting of vehicle operator impairment |
| CN105469641A (en) * | 2015-12-15 | 2016-04-06 | 华南理工大学 | Danger judgment device and early warning method for special line-type highway sections in mountain area |
| CN205334755U (en) * | 2015-12-15 | 2016-06-22 | 华南理工大学 | Special linear highway section of mountain area highway danger attitude discriminating gear |
| CN106228499A (en) * | 2016-07-06 | 2016-12-14 | 东南大学 | A kind of cargo security evaluation model based on people's bus or train route goods multi-risk System source |
| CN106932806A (en) * | 2017-03-22 | 2017-07-07 | 南京航空航天大学 | A kind of mountain area bend collision prevention of vehicle alarm method and system based on big-dipper satellite |
| CN107230389A (en) * | 2017-07-26 | 2017-10-03 | 山西省交通科学研究院 | A kind of mountain area winding road safety pre-warning system and method |
| CN108133317A (en) * | 2017-12-20 | 2018-06-08 | 长安大学 | A kind of mountainous area highway equals the evaluation method of vertical combination level of security |
| CN108396674A (en) * | 2018-02-01 | 2018-08-14 | 重庆交通大学 | Highway song section optical illusion speed reduction marking and its design method |
| CN109272775A (en) * | 2018-10-22 | 2019-01-25 | 华南理工大学 | A kind of expressway bend safety monitoring method for early warning, system and medium |
| CN109726942A (en) * | 2019-03-01 | 2019-05-07 | 北京汽车研究总院有限公司 | A kind of driving environment methods of risk assessment and system |
| CN109740286A (en) * | 2019-01-21 | 2019-05-10 | 北京工业大学 | A kind of Water Quality Forecasting Model of Lake construction method of hybrid optimization BP neural network |
| CN109801491A (en) * | 2019-01-18 | 2019-05-24 | 深圳壹账通智能科技有限公司 | Intelligent navigation method, device, equipment and storage medium based on risk assessment |
| CN110276370A (en) * | 2019-05-05 | 2019-09-24 | 南京理工大学 | A kind of road traffic accident risk Factor Analysis method based on random forest |
| CN110443468A (en) * | 2019-07-18 | 2019-11-12 | 天津大学 | A kind of more measurement evaluation methods of mountain flood fragility |
| CN110569554A (en) * | 2019-08-13 | 2019-12-13 | 成都垣景科技有限公司 | Landslide susceptibility evaluation method based on spatial logistic regression and geographic detector |
| CN110796859A (en) * | 2019-10-28 | 2020-02-14 | 长安大学 | Real-time traffic state identification and accident risk early warning method based on traffic flow |
| CN111126853A (en) * | 2019-12-25 | 2020-05-08 | 华北水利水电大学 | Fuzzy FMEA-based hydraulic engineering risk early warning analysis method and system |
| CN112201038A (en) * | 2020-09-28 | 2021-01-08 | 同济大学 | Road network risk assessment method based on risk of bad driving behavior of single vehicle |
-
2021
- 2021-01-18 CN CN202110062817.1A patent/CN113160593A/en active Pending
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102922999A (en) * | 2012-10-17 | 2013-02-13 | 重庆交通大学 | Vehicle dangerous driving state recognition device and recognition method for mountain highway |
| CN104240437A (en) * | 2013-06-19 | 2014-12-24 | 通用汽车环球科技运作有限责任公司 | Methods and apparatus for detection and reporting of vehicle operator impairment |
| CN105469641A (en) * | 2015-12-15 | 2016-04-06 | 华南理工大学 | Danger judgment device and early warning method for special line-type highway sections in mountain area |
| CN205334755U (en) * | 2015-12-15 | 2016-06-22 | 华南理工大学 | Special linear highway section of mountain area highway danger attitude discriminating gear |
| CN106228499A (en) * | 2016-07-06 | 2016-12-14 | 东南大学 | A kind of cargo security evaluation model based on people's bus or train route goods multi-risk System source |
| CN106932806A (en) * | 2017-03-22 | 2017-07-07 | 南京航空航天大学 | A kind of mountain area bend collision prevention of vehicle alarm method and system based on big-dipper satellite |
| CN107230389A (en) * | 2017-07-26 | 2017-10-03 | 山西省交通科学研究院 | A kind of mountain area winding road safety pre-warning system and method |
| CN108133317A (en) * | 2017-12-20 | 2018-06-08 | 长安大学 | A kind of mountainous area highway equals the evaluation method of vertical combination level of security |
| CN108396674A (en) * | 2018-02-01 | 2018-08-14 | 重庆交通大学 | Highway song section optical illusion speed reduction marking and its design method |
| CN109272775A (en) * | 2018-10-22 | 2019-01-25 | 华南理工大学 | A kind of expressway bend safety monitoring method for early warning, system and medium |
| CN109801491A (en) * | 2019-01-18 | 2019-05-24 | 深圳壹账通智能科技有限公司 | Intelligent navigation method, device, equipment and storage medium based on risk assessment |
| CN109740286A (en) * | 2019-01-21 | 2019-05-10 | 北京工业大学 | A kind of Water Quality Forecasting Model of Lake construction method of hybrid optimization BP neural network |
| CN109726942A (en) * | 2019-03-01 | 2019-05-07 | 北京汽车研究总院有限公司 | A kind of driving environment methods of risk assessment and system |
| CN110276370A (en) * | 2019-05-05 | 2019-09-24 | 南京理工大学 | A kind of road traffic accident risk Factor Analysis method based on random forest |
| CN110443468A (en) * | 2019-07-18 | 2019-11-12 | 天津大学 | A kind of more measurement evaluation methods of mountain flood fragility |
| CN110569554A (en) * | 2019-08-13 | 2019-12-13 | 成都垣景科技有限公司 | Landslide susceptibility evaluation method based on spatial logistic regression and geographic detector |
| CN110796859A (en) * | 2019-10-28 | 2020-02-14 | 长安大学 | Real-time traffic state identification and accident risk early warning method based on traffic flow |
| CN111126853A (en) * | 2019-12-25 | 2020-05-08 | 华北水利水电大学 | Fuzzy FMEA-based hydraulic engineering risk early warning analysis method and system |
| CN112201038A (en) * | 2020-09-28 | 2021-01-08 | 同济大学 | Road network risk assessment method based on risk of bad driving behavior of single vehicle |
Non-Patent Citations (1)
| Title |
|---|
| 岳淼聪: "基于FAHP与GA-BP神经网络的行车安全评价", 《2019年（第六届）全国大学生统计建模大赛优秀论文集 》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114582126A (en) * | 2022-03-04 | 2022-06-03 | 深圳市综合交通与市政工程设计研究总院有限公司 | Intelligent management and control method and system suitable for ultra-long tunnel traffic and giving consideration to efficiency safety |
| CN114822024A (en) * | 2022-04-19 | 2022-07-29 | 哈尔滨工业大学 | Active safety guidance system for expressway agglomerate fog road section |
| CN115019532A (en) * | 2022-04-21 | 2022-09-06 | 东北林业大学 | Automatic identification and early warning system for potential safety hazards of roads based on passenger traffic data |
| CN114995164B (en) * | 2022-08-03 | 2022-12-02 | 武汉维泰信息科技有限公司 | New energy automobile safety early warning method and device based on Internet of things |
| CN114995164A (en) * | 2022-08-03 | 2022-09-02 | 武汉维泰信息科技有限公司 | New energy automobile safety early warning method and device based on Internet of things |
| CN115331449B (en) * | 2022-10-17 | 2023-02-07 | 四川省公路规划勘察设计研究院有限公司 | Method and device for identifying accident-prone area of long and large continuous longitudinal slope section and electronic equipment |
| CN115331449A (en) * | 2022-10-17 | 2022-11-11 | 四川省公路规划勘察设计研究院有限公司 | Method and device for identifying accident prone area of long and large continuous longitudinal slope section and electronic equipment |
| CN116778733A (en) * | 2022-11-26 | 2023-09-19 | 武汉广旺科技有限公司 | Highway navigation voice early warning method and system based on big data |
| CN116720728A (en) * | 2023-04-26 | 2023-09-08 | 广州地铁设计研究院股份有限公司 | Risk assessment method, electronic device and storage medium |
| CN117057605A (en) * | 2023-08-15 | 2023-11-14 | 广州地铁设计研究院股份有限公司 | Risk assessment model training method, risk assessment method and related equipment |
| CN117787699A (en) * | 2023-12-26 | 2024-03-29 | 公安部道路交通安全研究中心 | Road risk prediction method and device, computer equipment and storage medium |
| CN117474344A (en) * | 2023-12-28 | 2024-01-30 | 青岛盈智科技有限公司 | Risk assessment method and system for cargo transportation process |
| CN117474344B (en) * | 2023-12-28 | 2024-03-22 | 青岛盈智科技有限公司 | Risk assessment method and system for cargo transportation process |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113160593A (en) | Mountain road driving safety early warning method based on edge cloud cooperation | |
| US10325490B2 (en) | Providing driving condition alerts using road attribute data | |
| CN102208013B (en) | Landscape coupling reference data generation system and position measuring system | |
| CN106127586A (en) | Vehicle insurance rate aid decision-making system under big data age | |
| CN104864878A (en) | Electronic map based road condition physical information drawing and inquiring method | |
| CN112734242B (en) | Availability analysis method and device of vehicle running track data, storage medium and terminal | |
| CN110428621A (en) | A kind of monitoring of Floating Car dangerous driving behavior and method for early warning based on track data | |
| CN111341101A (en) | Large-wind driving monitoring and early warning system for large-span highway bridge | |
| Krumm et al. | Risk-Aware Planning: Methods and Case Study on Safe Driving Route | |
| CN113160564A (en) | Traffic safety early warning analysis method and device and computer equipment | |
| CN113990088A (en) | Safe passing informing software system for expressway in severe weather | |
| CN111881566B (en) | Landslide displacement detection method and device based on live-action simulation | |
| Belz et al. | Analyzing the effect of driver age on operating speed and acceleration noise: on-board second-by-second driving data | |
| CN117172554A (en) | Icing disaster risk prediction method, device, equipment and storage medium | |
| CN116433027A (en) | Road network risk zoning method based on side slope geological disasters | |
| Rengarasu et al. | Effects of road geometry and cross-section variables on traffic accidents: study using homogeneous road segments | |
| CN116307699A (en) | Road hidden trouble point segment grading method, device and storage medium based on multi-source data | |
| Ambros et al. | Identification of road horizontal alignment inconsistencies–A pilot study from the Czech Republic | |
| KR102192337B1 (en) | System and Method for Evaluation of the Safety of Bridge regarding the Running Vehicles on the Bridge against Strong Wind | |
| Ekpenyong et al. | Comparative study of the road roughness measurement of roadlab pro and roadroid applicatons for IRI data collection in Nigeria | |
| Entezari et al. | A review on the impacts of connected vehicles on pavement management systems | |
| CN106897517A (en) | Line of high-speed railway gale monitoring optimizes automatic search method of arranging net | |
| Andrášik et al. | Identification of Curves and Straight Sections on Road Networks from Digital Vector Data | |
| Tola et al. | Assessment on the Impacts of Road Geometry and Route Selection on Road Safety: A Case of Mettu-Gore Road, Ethiopia | |
| Gang et al. | Cause analysis of traffic accidents based on degrees of attribute importance of rough set |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210723 |