CN109493566A - A kind of fatigue driving prediction technique based on GPS data - Google Patents
A kind of fatigue driving prediction technique based on GPS data Download PDFInfo
- Publication number
- CN109493566A CN109493566A CN201811550953.XA CN201811550953A CN109493566A CN 109493566 A CN109493566 A CN 109493566A CN 201811550953 A CN201811550953 A CN 201811550953A CN 109493566 A CN109493566 A CN 109493566A
- Authority
- CN
- China
- Prior art keywords
- fatigue driving
- layer
- last week
- accumulative mileage
- gps data
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/06—Alarms for ensuring the safety of persons indicating a condition of sleep, e.g. anti-dozing alarms
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Emergency Management (AREA)
- Traffic Control Systems (AREA)
Abstract
The fatigue driving prediction technique based on GPS data that the invention discloses a kind of includes the following steps: that 1. establish GPS data library;2. choosing running data from GPS data library, running data is set as several predictive variables relevant to fatigue driving, and predictive variable is standardized, as sample;Then, by that there is a situation where fatigue drivings is corresponding with each sample, sample is divided into and belongs to fatigue driving and is not belonging to fatigue driving two states;It is finally that training set and verifying are gathered by the ratio cut partition of 7:3 by sample;3. constructing the multi-layered perception neural networks containing input layer, hidden layer and output layer, the disaggregated model for predicting fatigue driving is generated;4. being predicted using model to fatigue driving whether can occur in prediction period, when that fatigue driving can occur in prediction period, driver is reminded.Early warning can be carried out to driver in advance in advance to whether fatigue driving occurs predicting.
Description
Technical field
The invention belongs to road safety fields, are related to a kind of fatigue driving prediction technique based on GPS data.
Background technique
It is analyzed according to traffic accident causation, fatigue driving is one of the main reason for leading to fatal traffic accident.According to statistics,
Because the accounting caused by fatigue driving is up to 40% or more in major traffic accidents, it can be seen that, the harm of fatigue driving bring
It is very serious, thus cause the great attention of national governments.To reduce the accident generated by fatigue driving, fatigue driving detection
Technology is researched and developed by various countries.Detection method based on physiological driver's feature is physical signs (such as EEG, EOG according to driver
Deng) judge the fatigue state of driver, although these method accuracy are high, it is not easy to be received, is easily made to driver
At extra interference, it is unfavorable for safe driving.Existing most of fatigue driving early warning are all real-time monitorings, are driven once detecting
The person's of sailing fatigue just issues warning signal prompt driver's parking rest.But the shortcomings that real-time monitoring is not shift to an earlier date to driver
The time of reaction, i.e., once detecting fatigue, driver takes measures again may be day after the fair.
Summary of the invention
It is an object of the invention to overcome the above-mentioned prior art, a kind of fatigue driving based on GPS data is provided
Whether prediction technique, can be in advance to occurring fatigue driving and predict, to carry out early warning, high degree to driver in advance
On ensure that the driving safety of driver.
In order to achieve the above objectives, the present invention is achieved by the following scheme:
A kind of fatigue driving prediction technique based on GPS data, includes the following steps:
Step 1 establishes GPS data library: vehicle is predicted from before predicted time node by vehicle-mounted GPS equipment acquisition, the
Running data in one period, as GPS data library;
Step 2, processing data: before being selected from predicted time node in GPS data library, in the second time period of setting
Running data, first time period include second time period, by the running data chosen in second time period be set as several with
The relevant predictive variable of fatigue driving, and predictive variable is standardized, as sample;Then, by second time period
Interior that there is a situation where fatigue drivings is corresponding with each sample, and sample is divided into and belongs to fatigue driving and is not belonging to fatigue driving
Two states;It is finally that training set and verifying are gathered by the ratio cut partition of 7:3 by sample;
Step 3, building and training multi-layered perception neural networks: building one contains input layer, hidden layer and output layer
Input of the set as multi-layered perception neural networks is gathered and verified to training described in step 2 by multi-layered perception neural networks, then
Multi-layered perception neural networks are trained using back-propagation algorithm, generate the disaggregated model for predicting fatigue driving;
Step 4 is predicted using the model described in step 3 to fatigue driving whether can occur in prediction period, when pre-
When fatigue driving can occur in the survey period, driver is reminded.
Preferably, in step 2, the time cycle of second time period is one week;Setting 17 is relevant to fatigue driving pre-
Survey variable, comprising: the last week accumulative mileage T1 travelled between 0am-5am, the last week travelled between 5am-9am are accumulative
Mileage T2, the last week accumulative mileage T3 travelled between 9am-5pm, the last week accumulative mileage travelled between 5pm-10pm
T4, the last week accumulative mileage T5 travelled between 10pm-12pm, the last week accumulative mileage W1 travelled on weekdays, non-
The last week accumulative mileage W2 of working day traveling is travelled in the last week accumulative mileage R1 of urban road traveling in backroad
The last week accumulative mileage R2, the last week accumulative mileage R3 travelled on a highway, speed is between 0-40km/h
The last week accumulative mileage V1, the last week accumulative mileage V2 of the speed between 40-60km/h, speed is between 60-80km/h
The last week accumulative mileage V3, speed is greater than the last week accumulative mileage V4 of 80km/h, averagely persistently driving time C1, longest
Continue total accumulative mileage M of driving time C2 and the last week.
Further, the Class I highway and Class II highway in the classification of urban road corresponding function type road quality classification, backroad
Class III highway and Class IV highway in the classification of corresponding function type road quality classification.
Further, the standardization processing method of 17 predictive variables is as follows:
The standardization processing method of total accumulative mileage M of the last week:
Wherein, M*Indicate that total accumulated distance Jing Guo standardization, M indicate total accumulative mileage of the last week, MmaxIt indicates
The maximum value of the last week total accumulative mileage M;
Averagely continue driving time C1 and longest continue the standardization processing method of driving time C2:
Wherein, C*Indicate that the lasting driving time Jing Guo standardization, C indicate to continue driving time, CmaxIt indicates to continue
The maximum value of driving time, CminIndicate the minimum value of lasting driving time;
The standardization processing method of remaining 14 predictive variable:
Wherein, X*Indicate that the predictive variable Jing Guo standardization, X indicate that predictive variable, M indicate the total accumulative of the last week
Mileage.
Preferably, in step 2, whether driver is yawned as the foundation for judging whether fatigue driving, when yawning,
It is then non-fatigue driving state when not yawning for fatigue driving state.
Preferably, each layer of multi-layered perception neural networks containing input layer, hidden layer and output layer described in step 3
Node is connected to next layer entirely, and in addition to input node, input is all multiplied by other all nodes with itself weight factor ω, then plus
Upper biasing b generates output then in conjunction with the nonlinear activation function of itself, and network structure includes the following:
Input layer: this layer is the first layer of network, the data for final step in receiving step 2;
Hidden layer: the layer can have multilayer, for learning to data, and store training result, and what this layer used swashs
Function living is Sigmoid function:
Wherein, x indicates the input from preceding layer;
Output layer: this layer is the last layer of network, for exporting as a result, the activation primitive that this layer uses is Softmax
Function:
Wherein, xiIndicate the input from preceding layer, N indicates preceding layer node total number.
Preferably, will be in prediction period, the case where actually occurring fatigue driving, is compared with prediction result, to verify
The accuracy of the multi-layered perception neural networks model.
Preferably, vehicle operation data includes license plate number, timestamp, speed, longitude and latitude and geographic position data.
Compared with prior art, the invention has the following advantages:
The present invention will travel number by choosing the running data in the second time period of setting from before predicted time node
According to several predictive variables are divided into, sample, then the feelings with generation fatigue driving in second time period are used as after standardization
Condition is corresponded to, and whether by the framework of multi-layered perception neural networks model, fatigue driving can be generated by obtaining in predicted time section
As a result, the present invention is based on historical data, can be in advance to whether fatigue driving occur predicting, thus in advance to driver
Early warning is carried out, largely ensure that the driving safety of driver.
Detailed description of the invention
Fig. 1 is multi-layered perception neural networks structural schematic diagram of the invention.
Specific embodiment
The invention will be described in further detail with reference to the accompanying drawing:
Those skilled in the art can understand that unless otherwise defined, all terms used herein (including skill
Art belongs to and scientific term) there is meaning identical with the general understanding of those of ordinary skill in fields of the present invention.Also
It should be understood that those terms such as defined in the general dictionary should be understood that have in the context of the prior art
The consistent meaning of meaning will not be explained in an idealized or overly formal meaning and unless defined as here.
The present invention is based on the realizations of the fatigue driving prediction technique of GPS data mainly to comprise the steps of:
Step 1, GPS data library is established:
Using 1 year vehicle operation data of vehicle-mounted GPS equipment acquisition as GPS data library, running data includes license plate number
Code, timestamp, speed, longitude and latitude and geographic position data.
Step 2, data are handled:
The running data for choosing the last week embodies long-term accumulated fatigue index, and the driving index of the last week is dynamic indicator,
There is the driving index of a last week daily.Firstly, export 17 is driven with fatigue according to the running data in GPS data library
Relevant predictive variable is sailed, as shown in table 1.
Table 1
Wherein, the Class I highway and Class II highway in the classification of urban road corresponding function type road quality classification, backroad pair
Answer the Class III highway and Class IV highway in the classification of functional form road quality classification.
Secondly, this 17 predictive variables are standardized,
The standardization processing method of 17 predictive variables is as follows:
The standardization processing method of total accumulative mileage M of the last week:
Wherein, M*Indicate that total accumulated distance Jing Guo standardization, M indicate total accumulative mileage of the last week, MmaxIt indicates
The maximum value of the last week total accumulative mileage M.
Averagely continue driving time C1 and longest continue the standardization processing method of driving time C2:
Wherein, C*Indicate that the lasting driving time Jing Guo standardization, C indicate to continue driving time, CmaxIt indicates to continue
The maximum value of driving time, CminIndicate the minimum value of lasting driving time.
The standardization processing method of remaining 14 predictive variable:
Wherein, X*Indicate that the predictive variable Jing Guo standardization, X indicate that predictive variable, M indicate the total accumulative of the last week
Mileage.
9930 samples are obtained after processing, the descriptive statistic of sample data is as shown in table 2;
Table 2
Then, the case where whether driver being yawned daily is corresponding with every sample, whether beats Kazakhstan according to driver
Owe judge whether driver is tired;The acquisition method yawned, using institute in the invention of Patent No. CN201710439139.X
Disclosed method.
Gather finally, being gathered and being verified sample for training by the ratio cut partition of 7:3, i.e. training sample 6951, verifies
2979, sample.
Step 3, it constructs and trains multi-layered perception neural networks:
As shown in Figure 1, one multi-layered perception neural networks knot containing input layer, one layer of hidden layer and output layer of building
Structure.
Input layer: step 2 is divided resulting training sample, verifying sample as the number of multi-layered perception neural networks by this layer
According to input;
Hidden layer: the layer can have multilayer, and hidden layer of the invention is one layer, for learning to data, and store
Training result.Wherein, H (1:1), H (1:2), H (1:3), H (1:4), H (1:5), H (1:6), H (1:7) and H (1:8) are indicated hidden
8 nodes of layer are hidden, deviation indicates the bias node of hidden layer.The activation primitive that this layer uses is Sigmoid function:
Wherein, x indicates the input from preceding layer.
Output layer: whether this layer is the last layer of network, tired for exporting driver, and wherein Y=0 is indicated not tired
Labor, Y=1 indicate fatigue, and the activation primitive that this layer uses is Softmax function:
Wherein, xiIndicate the input from preceding layer, N indicates preceding layer node total number.
By the input of training set, verifying set as multi-layered perception neural networks described in step 2, reversed pass is recycled
It broadcasts algorithm to be trained multi-layered perception neural networks, generates the disaggregated model for predicting fatigue driving.
Step 4, it is predicted using the model described in step 3 to fatigue driving whether can occur in prediction period, when pre-
When fatigue driving can occur in the survey period, driver is reminded.
In addition, will be in prediction period, the case where actually occurring fatigue driving, is compared with prediction result, to verify
State the accuracy of multi-layered perception neural networks model.
The present invention can also be applied to the identification classification work of fatigue driving prediction, develop fatigue driving forecasting system.
The above content is merely illustrative of the invention's technical idea, and this does not limit the scope of protection of the present invention, all to press
According to technical idea proposed by the present invention, any changes made on the basis of the technical scheme each falls within claims of the present invention
Protection scope within.
Claims (8)
1. a kind of fatigue driving prediction technique based on GPS data, which comprises the steps of:
Step 1 establishes GPS data library: vehicle is predicted from before predicted time node by vehicle-mounted GPS equipment acquisition, when first
Between running data in section, as GPS data library;
Step 2, processing data: the traveling before being selected from predicted time node in GPS data library, in the second time period of setting
Data, first time period include second time period, and the running data chosen in second time period is set as several and fatigue
Relevant predictive variable is driven, and predictive variable is standardized, as sample;It then, will be in second time period
It is corresponding with each sample that there is a situation where fatigue drivings, and sample is divided into and belongs to fatigue driving and is not belonging to two kinds of fatigue driving
State;It is finally that training set and verifying are gathered by the ratio cut partition of 7:3 by sample;
Step 3, building and training multi-layered perception neural networks: one multilayer containing input layer, hidden layer and output layer of building
Training described in step 2 is gathered and is verified input of the set as multi-layered perception neural networks, recycles by layered perception neural networks
Back-propagation algorithm is trained multi-layered perception neural networks, generates the disaggregated model for predicting fatigue driving;
Step 4 is predicted using the model described in step 3 to fatigue driving whether can occur in prediction period, when prediction
When fatigue driving can occur in section, driver is reminded.
2. a kind of fatigue driving prediction technique based on GPS data according to claim 1, which is characterized in that step 2
In, the time cycle of second time period is one week;Set 17 predictive variables relevant to fatigue driving, comprising: in 0am-5am
Between the last week accumulative mileage T1, the last week accumulative mileage T2 travelled between 5am-9am, between 9am-5pm that travel
The last week accumulative mileage T3 of traveling, the last week accumulative mileage T4 travelled between 5pm-10pm, the row between 10pm-12pm
The last week accumulative mileage T5 sailed, the last week accumulative mileage W1 travelled on weekdays are tired in the last week of nonworkdays traveling
Count mileage W2, urban road traveling the last week accumulative mileage R1, backroad traveling the last week accumulative mileage R2,
The last week accumulative mileage R3 of running on expressway, the last week accumulative mileage V1 of the speed between 0km/h-40km/h,
The last week accumulative mileage V2 of the speed between 40km/h-60km/h, the last week of speed between 60km/h-80km/h
Accumulative mileage V3, speed is greater than the last week accumulative mileage V4 of 80km/h, when averagely persistently driving time C1, longest persistently drive
Between C2 and the last week total accumulative mileage M.
3. a kind of fatigue driving prediction technique based on GPS data according to claim 2, which is characterized in that city road
Class I highway and Class II highway in the classification of road corresponding function type road quality classification, the classification of backroad corresponding function type road quality classification
In Class III highway and Class IV highway.
4. a kind of fatigue driving prediction technique based on GPS data according to claim 2, which is characterized in that 17 pre-
The standardization processing method for surveying variable is as follows:
The standardization processing method of total accumulative mileage M of the last week:
Wherein, M*Indicate that total accumulated distance Jing Guo standardization, M indicate total accumulative mileage of the last week, MmaxIndicate previous
The maximum value of all total accumulative mileage M;
Averagely continue driving time C1 and longest continue the standardization processing method of driving time C2:
Wherein, C*Indicate that the lasting driving time Jing Guo standardization, C indicate to continue driving time, CmaxIt indicates lasting to drive
The maximum value of time, CminIndicate the minimum value of lasting driving time;
The standardization processing method of remaining 14 predictive variable:
Wherein, X*Indicate that the predictive variable Jing Guo standardization, X indicate that predictive variable, M indicate total accumulative mileage of the last week.
5. a kind of fatigue driving prediction technique based on GPS data according to claim 1, which is characterized in that step 2
In, whether driver is yawned as the foundation for judging whether fatigue driving, when yawning, is fatigue driving state, does not beat
It is then non-fatigue driving state when yawn.
6. a kind of fatigue driving prediction technique based on GPS data according to claim 1, which is characterized in that step 3 institute
The node of each layer of the multi-layered perception neural networks containing input layer, hidden layer and output layer stated is connected to next layer entirely, removes
Outside input node, input is all multiplied by other all nodes with itself weight factor ω, along with biasing b, then in conjunction with itself
Nonlinear activation function generate output, network structure includes the following:
Input layer: this layer is the first layer of network, the data for final step in receiving step 2;
Hidden layer: the layer can have multilayer, for learning to data, and store training result, the activation letter that this layer uses
Number is Sigmoid function:
Wherein, x indicates the input from preceding layer;
Output layer: this layer is the last layer of network, for exporting as a result, the activation primitive that this layer uses is Softmax function:
Wherein, xiIndicate the input from preceding layer, N indicates preceding layer node total number.
7. a kind of fatigue driving prediction technique based on GPS data according to claim 1, which is characterized in that will be pre-
The case where surveying in the period, actually occurring fatigue driving is compared with prediction result, to verify the multi-layered perception neural networks
The accuracy of model.
8. a kind of fatigue driving prediction technique based on GPS data according to claim 1, which is characterized in that vehicle row
Sailing data includes license plate number, timestamp, speed, longitude and latitude and geographic position data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811550953.XA CN109493566B (en) | 2018-12-18 | 2018-12-18 | Fatigue driving prediction method based on GPS data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811550953.XA CN109493566B (en) | 2018-12-18 | 2018-12-18 | Fatigue driving prediction method based on GPS data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109493566A true CN109493566A (en) | 2019-03-19 |
CN109493566B CN109493566B (en) | 2020-09-08 |
Family
ID=65710642
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811550953.XA Active CN109493566B (en) | 2018-12-18 | 2018-12-18 | Fatigue driving prediction method based on GPS data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109493566B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109849929A (en) * | 2019-03-29 | 2019-06-07 | 长安大学 | A kind of changeable driveway deviation and front truck collision warning algorithm based on driver status |
CN109927730A (en) * | 2019-03-26 | 2019-06-25 | 武汉极目智能技术有限公司 | A kind of real-time fatigue driving behavior scoring system and method based on DMS system |
CN110060484A (en) * | 2019-05-16 | 2019-07-26 | 武汉理工大学 | A kind of real-time early warning system and method violating the regulations of the highway passenger transportation based on block chain |
CN110765980A (en) * | 2019-11-05 | 2020-02-07 | 中国人民解放军国防科技大学 | Abnormal driving detection method and device |
CN111161546A (en) * | 2020-04-02 | 2020-05-15 | 武汉中科通达高新技术股份有限公司 | Key vehicle checking method and system for traffic management system |
CN113034895A (en) * | 2021-02-04 | 2021-06-25 | 招商局公路网络科技控股股份有限公司 | ETC portal system, and expressway fatigue driving early warning method and device |
CN113116352A (en) * | 2021-03-24 | 2021-07-16 | 深兰科技(上海)有限公司 | Fatigue state prediction method, fatigue state prediction device, electronic equipment and storage medium |
CN114419892A (en) * | 2022-01-28 | 2022-04-29 | 公安部交通管理科学研究所 | Method for judging vehicle with traffic violation risk of fatigue driving |
CN117576917A (en) * | 2024-01-17 | 2024-02-20 | 北京华录高诚科技有限公司 | Neural network-based vehicle overtime fatigue driving prediction method and intelligent device |
CN117975665A (en) * | 2024-03-28 | 2024-05-03 | 钧捷智能(深圳)有限公司 | DMS driver fatigue grade identification system |
Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2010102299A1 (en) * | 2009-03-06 | 2010-09-10 | Nash David E | Predictive risk intelligent safety module |
CN103578227A (en) * | 2013-09-23 | 2014-02-12 | 吉林大学 | Fatigue driving detection method based on GPS positioning information |
CN104240444A (en) * | 2013-06-24 | 2014-12-24 | 博世汽车部件(苏州)有限公司 | Driving fatigue detecting and early warning method |
CN104580335A (en) * | 2013-10-29 | 2015-04-29 | 上海沐风数码科技有限公司 | 3G communication technology-based intelligent internet-of-vehicle vehicle-mounted terminal |
CN104598993A (en) * | 2015-01-14 | 2015-05-06 | 南京信息工程大学 | Blink time based driver fatigue driving prediction method |
CN105336105A (en) * | 2015-11-30 | 2016-02-17 | 宁波力芯科信息科技有限公司 | Method, intelligent device and system for preventing fatigue driving |
CN205158585U (en) * | 2015-11-30 | 2016-04-13 | 宁波力芯科信息科技有限公司 | Prevention driver fatigue's smart machine and system |
CN106095963A (en) * | 2016-06-17 | 2016-11-09 | 上海经达信息科技股份有限公司 | Vehicle drive behavior analysis big data public service platform under the Internet+epoch |
CN106570535A (en) * | 2016-11-18 | 2017-04-19 | 杭州好好开车科技有限公司 | User classification method based on adas (advanced driver assistant system) and obd (on-board diagnostic) data |
CN107563931A (en) * | 2017-08-16 | 2018-01-09 | 上海经达信息科技股份有限公司 | A kind of real-time driving behavior quality appraisal procedure of vehicle based on the Big Dipper or gps data |
CN207216839U (en) * | 2017-10-11 | 2018-04-10 | 成都大学 | A kind of automobile anti-fatigue-driving system |
CN107909037A (en) * | 2017-11-16 | 2018-04-13 | 百度在线网络技术(北京)有限公司 | Information output method and device |
WO2018121547A1 (en) * | 2016-12-27 | 2018-07-05 | 北京奇虎科技有限公司 | Gps-based drowsy driving determination method and apparatus, and smart device |
CN108364457A (en) * | 2018-01-31 | 2018-08-03 | 长安大学 | A kind of commercial car method for detecting fatigue driving based on GPS |
CN108423006A (en) * | 2018-02-02 | 2018-08-21 | 辽宁友邦网络科技有限公司 | A kind of auxiliary driving warning method and system |
CN108491859A (en) * | 2018-02-11 | 2018-09-04 | 郭静秋 | The recognition methods of driving behavior heterogeneity feature based on automatic coding machine |
-
2018
- 2018-12-18 CN CN201811550953.XA patent/CN109493566B/en active Active
Patent Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2010102299A1 (en) * | 2009-03-06 | 2010-09-10 | Nash David E | Predictive risk intelligent safety module |
CN104240444A (en) * | 2013-06-24 | 2014-12-24 | 博世汽车部件(苏州)有限公司 | Driving fatigue detecting and early warning method |
CN103578227A (en) * | 2013-09-23 | 2014-02-12 | 吉林大学 | Fatigue driving detection method based on GPS positioning information |
CN104580335A (en) * | 2013-10-29 | 2015-04-29 | 上海沐风数码科技有限公司 | 3G communication technology-based intelligent internet-of-vehicle vehicle-mounted terminal |
CN104598993A (en) * | 2015-01-14 | 2015-05-06 | 南京信息工程大学 | Blink time based driver fatigue driving prediction method |
CN105336105A (en) * | 2015-11-30 | 2016-02-17 | 宁波力芯科信息科技有限公司 | Method, intelligent device and system for preventing fatigue driving |
CN205158585U (en) * | 2015-11-30 | 2016-04-13 | 宁波力芯科信息科技有限公司 | Prevention driver fatigue's smart machine and system |
CN106095963A (en) * | 2016-06-17 | 2016-11-09 | 上海经达信息科技股份有限公司 | Vehicle drive behavior analysis big data public service platform under the Internet+epoch |
CN106570535A (en) * | 2016-11-18 | 2017-04-19 | 杭州好好开车科技有限公司 | User classification method based on adas (advanced driver assistant system) and obd (on-board diagnostic) data |
WO2018121547A1 (en) * | 2016-12-27 | 2018-07-05 | 北京奇虎科技有限公司 | Gps-based drowsy driving determination method and apparatus, and smart device |
CN107563931A (en) * | 2017-08-16 | 2018-01-09 | 上海经达信息科技股份有限公司 | A kind of real-time driving behavior quality appraisal procedure of vehicle based on the Big Dipper or gps data |
CN207216839U (en) * | 2017-10-11 | 2018-04-10 | 成都大学 | A kind of automobile anti-fatigue-driving system |
CN107909037A (en) * | 2017-11-16 | 2018-04-13 | 百度在线网络技术(北京)有限公司 | Information output method and device |
CN108364457A (en) * | 2018-01-31 | 2018-08-03 | 长安大学 | A kind of commercial car method for detecting fatigue driving based on GPS |
CN108423006A (en) * | 2018-02-02 | 2018-08-21 | 辽宁友邦网络科技有限公司 | A kind of auxiliary driving warning method and system |
CN108491859A (en) * | 2018-02-11 | 2018-09-04 | 郭静秋 | The recognition methods of driving behavior heterogeneity feature based on automatic coding machine |
Non-Patent Citations (2)
Title |
---|
楚文慧: "驾驶行为安全性评价研究综述", 《公路交通科技》 * |
牛世峰等: "神经网络与贝叶斯滤波器在换道预测中的应用", 《科学技术与工程》 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109927730A (en) * | 2019-03-26 | 2019-06-25 | 武汉极目智能技术有限公司 | A kind of real-time fatigue driving behavior scoring system and method based on DMS system |
CN109849929A (en) * | 2019-03-29 | 2019-06-07 | 长安大学 | A kind of changeable driveway deviation and front truck collision warning algorithm based on driver status |
CN110060484A (en) * | 2019-05-16 | 2019-07-26 | 武汉理工大学 | A kind of real-time early warning system and method violating the regulations of the highway passenger transportation based on block chain |
CN110060484B (en) * | 2019-05-16 | 2021-10-22 | 武汉理工大学 | Road passenger traffic violation real-time early warning system and method based on block chain |
CN110765980A (en) * | 2019-11-05 | 2020-02-07 | 中国人民解放军国防科技大学 | Abnormal driving detection method and device |
CN111161546A (en) * | 2020-04-02 | 2020-05-15 | 武汉中科通达高新技术股份有限公司 | Key vehicle checking method and system for traffic management system |
CN111161546B (en) * | 2020-04-02 | 2020-06-30 | 武汉中科通达高新技术股份有限公司 | Key vehicle checking method and system for traffic management system |
CN113034895A (en) * | 2021-02-04 | 2021-06-25 | 招商局公路网络科技控股股份有限公司 | ETC portal system, and expressway fatigue driving early warning method and device |
CN113116352A (en) * | 2021-03-24 | 2021-07-16 | 深兰科技(上海)有限公司 | Fatigue state prediction method, fatigue state prediction device, electronic equipment and storage medium |
CN114419892A (en) * | 2022-01-28 | 2022-04-29 | 公安部交通管理科学研究所 | Method for judging vehicle with traffic violation risk of fatigue driving |
CN117576917A (en) * | 2024-01-17 | 2024-02-20 | 北京华录高诚科技有限公司 | Neural network-based vehicle overtime fatigue driving prediction method and intelligent device |
CN117975665A (en) * | 2024-03-28 | 2024-05-03 | 钧捷智能(深圳)有限公司 | DMS driver fatigue grade identification system |
Also Published As
Publication number | Publication date |
---|---|
CN109493566B (en) | 2020-09-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109493566A (en) | A kind of fatigue driving prediction technique based on GPS data | |
CN102136190B (en) | Dispatching management system and method for event emergency response of urban bus passenger transport | |
CN104809554B (en) | A kind of DSS and method towards road traffic accident emergency disposal | |
CN109242251A (en) | Vehicular behavior safety detecting method, device, equipment and storage medium | |
Chen et al. | Analysis of factors affecting the severity of automated vehicle crashes using XGBoost model combining POI data | |
CN106228499A (en) | A kind of cargo security evaluation model based on people's bus or train route goods multi-risk System source | |
CN107784587A (en) | A kind of driving behavior evaluation system | |
CN104299450B (en) | Vehicle collision prewarning method based on analytic hierarchy process (AHP) and grey fuzzy | |
CN106529599A (en) | Driver ecologic driving behavior evaluation method facing event | |
CN104778834A (en) | Urban road traffic jam judging method based on vehicle GPS data | |
CN105912862B (en) | A kind of exhaust emissions quantity measuring method and air pollution analysis method and apparatus | |
CN106251661A (en) | Tunnel portal section wagon flow control method | |
CN104835099A (en) | Urban road network motor vehicle exhaust real-time remote sensing monitoring base address selecting method | |
CN108694841A (en) | A kind of intelligent vehicle passage crossroads traffic light method based on V2X technologies | |
Stojčić | Application of ANFIS model in road traffic and transportation: a literature review from 1993 to 2018 | |
Zhu et al. | An automated vehicle fuel economy benefits evaluation framework using real-world travel and traffic data | |
CN106960189A (en) | A kind of driving intention decision method based on hidden Markov model | |
CN103456167A (en) | Good driving skill parameter obtaining method based on critical areas | |
CN118025203A (en) | Automatic driving vehicle behavior prediction method and system integrating complex network and graph converter | |
Wang et al. | Causation analysis of crashes and near crashes using naturalistic driving data | |
Jiang et al. | Safe route mapping of roadways using multiple sourced data | |
Shang et al. | Analyzing the effects of road type and rainy weather on fuel consumption and emissions: A mesoscopic model based on big traffic data | |
Zhao et al. | Factors affecting traffic risks on bridge sections of freeways based on partial dependence plots | |
Zhai et al. | Comparative analysis of drive-cycles, speed limit violations, and emissions in two cities: Toronto and Beijing | |
Wei et al. | An AHP-ME-Based Vehicle Crash Prediction Model considering Driver Intention and Real-Time Traffic/Road Condition |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20230726 Address after: Room 601-19, No. 6, Lane 288, Qianfan Road, Xinqiao Town, Songjiang District, Shanghai, 201600 Patentee after: Ziyun Intelligent Technology (Shanghai) Co.,Ltd. Address before: 710064 middle section of South Second Ring Road, Beilin District, Xi'an City, Shaanxi Province Patentee before: CHANG'AN University |
|
TR01 | Transfer of patent right |