CN108776650A - A kind of non-motorized lane service level evaluation method based on mixed Gauss model - Google Patents
A kind of non-motorized lane service level evaluation method based on mixed Gauss model Download PDFInfo
- Publication number
- CN108776650A CN108776650A CN201810570404.2A CN201810570404A CN108776650A CN 108776650 A CN108776650 A CN 108776650A CN 201810570404 A CN201810570404 A CN 201810570404A CN 108776650 A CN108776650 A CN 108776650A
- Authority
- CN
- China
- Prior art keywords
- service level
- motorized lane
- bicyclist
- parameter
- model
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- 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
Abstract
The invention discloses a kind of, and the non-motorized lane service level evaluation method based on mixed Gauss model belongs to traffic programme technical field suitable for there is physically-isolated non-motorized lane.Non-motorized lane service level is an index for being supplied to bicyclist's service of riding fine or not for measuring non-motorized lane.Due to being compared with motor vehicle, non-motor vehicle bicyclist can more intuitively experience external environment.Therefore bicyclist is experienced as the important evidence of service level deciding grade and level.Since the impression of people has prodigious fluctuation, the method for soft classification to be more bonded with actual conditions.The basic ideas of the present invention are that the probability of some traffic flow running rate corresponding with service hierarchical level is judged by establishing mixed Gauss model, to establish service level evaluation system.The present invention utilizes the characteristic of the soft classification of mixed Gauss model so that the impression of evaluation result and bicyclist are more close to have the planning of physically-isolated non-motorized lane, construction and management to provide theories integration.
Description
Technical field
The present invention is a kind of evaluation method for being directed to and having physically-isolated non-motor vehicle service level, using mixed Gaussian mould
Type, it is contemplated that the fluctuation of bicyclist's impression establishes soft disaggregated model.The evaluation method can serve non-motorized lane present situation
Evaluation, planning, design and management, belong to traffic programme field.
Background technology
With the continuous social and economic development, the living standard of resident is greatly improved, car quantity
Rapid development.Traffic congestion and the environmental pollution in city are also exacerbated as a result,.Currently, Manpower Transportation part city at home
City is quickly grown.From public bicycles, electric bicycle to shared bicycle, the development form of non-motor vehicle is continuously available innovation,
Increasingly consequence is also taken up in resident's go off daily.Due to non-motor vehicle environmental protection, convenient advantage, in middle short distance
Separating out has prodigious advantage in row, supplement and Vehicle emission as urban transportation together constitute entire city dweller
Trip network.And non-motorized lane as car lane as a part for urban road network, carry Urban Traffic
Critical function.Since non-motor vehicle does not have shell to isolate bicyclist and external environment, environment of riding rides to non-motor vehicle
The influence bigger of person.It is current less for the research of non-motor vehicle service level both at home and abroad, and most of researchs are with bicyclist's
Experience the evaluation as service level, but the model established uses bounds, does not consider that bicyclist's impression has fluctuation.Cause
This, it is necessary to it is directed to the operation characteristic of Manpower Transportation stream, corresponding evaluation index is chosen, using the method for soft classification to non-
The service level of car lane carries out quantization modulation, to for the planning, construction and management of non-motorized lane provide it is certain according to
According to.
Invention content
In view of the above-mentioned deficiencies in the prior art, it is an object of the present invention to provide a kind of non-motor vehicle based on mixed Gauss model
Road service level evaluation method, due to the particularity for traffic problems, the present invention establishes non-machine using mixed linear model
Motor-car road service level evaluation system, since non-automotive vehicle does not have fixed track, by considering non-machine under different in width
The difference of motor-car traffic flow modes so that the appraisement system of foundation can be suitable for the non-motorized lane of different in width.
This approach includes the following steps：
(1) section Manpower Transportation stream parameter, including flow, density, speed, overtake other vehicles time rate, electric bicycle are acquired
Ratio, masculinity proportion parameter；
(2) while the video based on the first visual angle of bicyclist is shot, records Manpower Transportation stream operating status, and is adopted
The traffic flow parameter of collection corresponds；
(3) non-motorized lane service level is artificially divided into N number of grade, a score value is corresponded to per grade；Using riding
The mode of person's marking, collects grade scoring of the different bicyclists to video clip, and takes its average value obtaining as each segment
Point；
(4) screening by significance analysis to traffic flow parameter selects significantly correlated traffic flow parameter as evaluation
Index；
(5) mixed Gauss model is used, considers the fluctuation of bicyclist's impression, the service corresponding to each traffic flow modes
Hierarchical level existing probability relationship, establishes service level evaluation system.
Step (1) acquires section Manpower Transportation stream parameter
C11, the basic information for investigating non-motorized lane, obtain width, the isolated form of non-motorized lane；
C12, statistics road section traffic volume stream information
Wherein, because it is the statistical value under unit width that non-automotive vehicle, which does not have fixed track, flow,.Statistics
The speed of wagon flow and each non-motor vehicle in certain period of time obtains non-motor vehicle in the flow q and the period of unit width
Average speed data v, density information k is obtained by the relationship q=kv of three parameter of traffic flow；Time rate of overtaking other vehicles passes through following formula
It calculates
Wherein,
r：It overtakes other vehicles time rate；
P：The number of overtaking other vehicles occurred in statistical interval；
Q：In statistical interval by vehicle number；
In addition, also needing other telecommunication flow informations in acquisition section, such as：Electric bicycle ratio, masculinity proportion, are all made of people
Work counting statistics.
The video of step (2) while shooting based on the first visual angle of bicyclist, including
C21, video is acquired using driving research mode naturally.Naturally drive research refer in its natural state (it is noiseless,
No experimenter occurs, under drive routine state) it is observed using data collecting system, tool of the record bicyclist in ride
The operating status of gymnastics work and surrounding traffic stream.Any requirement is not done to bicyclist's riding during video acquisition, is ridden
Passerby rides according to custom of usually riding.Video acquisition uses head mounted image-sensing machine, and first for simulating bicyclist regards
Angle.
It is (i.e. same non-that c22, arrangement data make each video clip and the traffic flow parameter under its recording status correspond
Video clip in the car lane same period should be corresponding with the traffic flow parameter of acquisition).
Step (3) service level is classified and video clip marking includes
C31, the qualitative description of different brackets non-motorized lane service level are following (service level is divided into five grades
For)：
A：It is very good.Vehicle is in freestream conditions, rides comfortable noiseless, can be horizontal with self-selected speed and passing behavior
It can arbitrarily be adjusted to position；
B：It is good.Bicycle is freely ridden substantially.Little interference between vehicle is ridden still comfortable, and speed can change but slightly
Constraint.Electric bicycle can keep fair speed to travel, and space of overtaking other vehicles is larger, there is certain passing behavior；
C：Generally.Bicycle flow is stable, and cycle track can meet basic demand of riding.Often have between vehicle dry
It disturbs, speed is limited, and electric bicycle traveling in part is hindered by standard bicycle, and bicycle comfort level reduces；
D：It is bad.Bicycle flow astable operation.Wagon flow is intensive, and bicycle interferes with each other more, and electric bicycle needs continuous
Changing Lane is simultaneously frequently overtaken other vehicles；
E：Difference.It rides limited or congestion occurs, cycling speed is remarkably decreased, it is difficult to passing behavior occurs, wagon flow
It is whole to move ahead.
And it defines each grade of service level and corresponds to score value and be：
A——0-0.2
B——0.2-0.4
C——0.4-0.6
D——0.6-0.8
E——0.8-1.0。
C32, random the first visual angle for inviting bicyclist to watch acquired record Manpower Transportation stream operation conditions regard
Frequently, and it is allowed to be given a mark according to the traffic flow operation conditions that the subjective feeling of itself records each video clip.Later
Take the mean value of each video clip score as the score value corresponding to the segment.It calculates as follows
Wherein,
i：Video clip is numbered；
j：Tested bicyclist's number；
n：Tested bicyclist's summation；
Leveli：Ranking score corresponding to video clip i；
sij：Tested marking of the bicyclist j to video clip i
Step (4) screening and assessment index includes
Using the score of all video clips as dependent variable, the section Manpower Transportation stream parameter conduct of step c1 acquisitions
Independent variable carries out significance analysis using spss softwares, selects significantly correlated parameter as evaluation index.
Step (5) establishes non-motorized lane service level evaluation system using mixed Gauss model
C51, the influence to eliminate in dimension, evaluation index sample data are normalized, formula is as follows
Wherein,
x：Sample data original value；
x'：Value after sample data normalization；
min：Sample data minimum value；
max：Sample data maximum value.
Each grade of service level corresponds to score value and is：
A——0-0.2
B——0.2-0.4
C——0.4-0.6
D——0.6-0.8
E——0.8-1.0
C52, the fluctuation for considering bicyclist's impression, establish non-motorized lane service level evaluation model.
The gauss hybrid models of foundation are a kind of clustering methods of probabilistic type, belong to production model, it is assumed that all
Data sample is generated by the multivariate Gaussian distribution of some given parameters, multivariate Gaussian distribution probability density function
Form is
Wherein, n is the number of evaluation index, x=(x1,x2,…,xn)TIt is the vector that n evaluation index is constituted, μ=
(μ1,μ2,…,μn)TIt is the mean vector of multivariate Gaussian distribution, μnIt is the mean value of n-th of evaluation index, ∑ is covariance matrix.
Because service level is divided into N number of grade, the mixed Gauss model of foundation is to be distributed by N number of multivariate Gaussian
The mixed distribution being combined into, probability density function can be expressed as
Wherein, wiThe weight (being obtained by parameter Estimation) being distributed in mixed model for i-th of multivariate Gaussian, and have
The parameter Estimation of mixed Gauss model can be carried out by EM algorithms, be one kind by E steps (asking expectation) and M steps
(maximization) carries out the optimization process of continuous iteration.
Beneficial effects of the present invention：The present invention is based on mixed Gauss models, have established physically-isolated non-motorized lane
Service level evaluation system, using the impression of bicyclist as evaluation criterion, it is contemplated that the fluctuation of bicyclist's impression, using soft point
The method of class so that evaluation result is more bonded with practical.
Description of the drawings
Fig. 1 is the flow diagram of the method for the present invention.
Specific implementation mode
The present invention will be described in detail below in conjunction with the accompanying drawings, as shown in Figure 1, the present invention is as follows：
Step (1) acquires section Manpower Transportation stream parameter
C11, the basic information for investigating non-motorized lane, obtain width, the isolated form of non-motorized lane；
C12, statistics road section traffic volume stream information
Wherein, because it is the statistical value under unit width that non-automotive vehicle, which does not have fixed track, flow,.Statistics
The speed of wagon flow and each non-motor vehicle in certain period of time obtains non-motor vehicle in the flow q and the period of unit width
Average speed data v, density information k is obtained by the relationship q=kv of three parameter of traffic flow；Time rate of overtaking other vehicles passes through following formula
It calculates
Wherein,
r：It overtakes other vehicles time rate；
P：The number of overtaking other vehicles occurred in statistical interval；
Q：In statistical interval by vehicle number；
In addition, also needing other telecommunication flow informations in acquisition section, such as：Electric bicycle ratio, masculinity proportion, are all made of people
Work counting statistics.
The video of step (2) while shooting based on the first visual angle of bicyclist, including
C21, video is acquired using driving research mode naturally.Naturally drive research refer in its natural state (it is noiseless,
No experimenter occurs, under drive routine state) it is observed using data collecting system, tool of the record bicyclist in ride
The operating status of gymnastics work and surrounding traffic stream.Any requirement is not done to bicyclist's riding during video acquisition, is ridden
Passerby rides according to custom of usually riding.Video acquisition uses head mounted image-sensing machine, and first for simulating bicyclist regards
Angle.
It is (i.e. same non-that c22, arrangement data make each video clip and the traffic flow parameter under its recording status correspond
Video clip in the car lane same period should be corresponding with the traffic flow parameter of acquisition).
Step (3) service level is classified and video clip marking includes
C31, the qualitative description of different brackets non-motorized lane service level are following (service level is divided into five grades
For)：
A：It is very good.Vehicle is in freestream conditions, rides comfortable noiseless, can be horizontal with self-selected speed and passing behavior
It can arbitrarily be adjusted to position；
B：It is good.Bicycle is freely ridden substantially.Little interference between vehicle is ridden still comfortable, and speed can change but slightly
Constraint.Electric bicycle can keep fair speed to travel, and space of overtaking other vehicles is larger, there is certain passing behavior；
C：Generally.Bicycle flow is stable, and cycle track can meet basic demand of riding.Often have between vehicle dry
It disturbs, speed is limited, and electric bicycle traveling in part is hindered by standard bicycle, and bicycle comfort level reduces；
D：It is bad.Bicycle flow astable operation.Wagon flow is intensive, and bicycle interferes with each other more, and electric bicycle needs continuous
Changing Lane is simultaneously frequently overtaken other vehicles；
E：Difference.It rides limited or congestion occurs, cycling speed is remarkably decreased, it is difficult to passing behavior occurs, wagon flow
It is whole to move ahead.
And it defines each grade of service level and corresponds to score value and be：
A——0-0.2
B——0.2-0.4
C——0.4-0.6
D——0.6-0.8
E——0.8-1.0。
C32, random the first visual angle for inviting bicyclist to watch acquired record Manpower Transportation stream operation conditions regard
Frequently, and it is allowed to be given a mark according to the traffic flow operation conditions that the subjective feeling of itself records each video clip.Later
Take the mean value of each video clip score as the score value corresponding to the segment.It calculates as follows
Wherein,
i：Video clip is numbered；
j：Tested bicyclist's number；
n：Tested bicyclist's summation；
Leveli：Ranking score corresponding to video clip i；
sij：Tested marking of the bicyclist j to video clip i
Step (4) screening and assessment index includes
Using the score of all video clips as dependent variable, the section Manpower Transportation stream parameter conduct of step c1 acquisitions
Independent variable carries out significance analysis using spss softwares, selects significantly correlated parameter as evaluation index.
Step (5) establishes non-motorized lane service level evaluation system using mixed Gauss model：
It is first the influence eliminated in dimension, evaluation index sample data is normalized, formula is as follows
Wherein,
x：Sample data original value；
x'：Value after sample data normalization；
min：Sample data minimum value；
max：Sample data maximum value.
Each grade of service level corresponds to score value and is：
A——0-0.2
B——0.2-0.4
C——0.4-0.6
D——0.6-0.8
E——0.8-1.0
The fluctuation for considering bicyclist's impression, establishes non-motorized lane service level evaluation model.
The gauss hybrid models of foundation are a kind of clustering methods of probabilistic type, belong to production model, it is assumed that all
Data sample is generated by the multivariate Gaussian distribution of some given parameters, multivariate Gaussian distribution probability density function
Form is
Wherein, n is the number of evaluation index, x=(x1,x2,…,xn)TIt is the vector that n evaluation index is constituted, μ=
(μ1,μ2,…,μn)TIt is the mean vector of multivariate Gaussian distribution, ∑ is covariance matrix.
Because service level is divided into 5 grades, the mixed Gauss model of foundation is to be distributed by 5 multivariate Gaussians
The mixed distribution being combined into, probability density function can be expressed as
Wherein, wiIt is distributed in the weight in mixed model for i-th of multivariate Gaussian, and is had
The parameter Estimation of mixed Gauss model can be carried out by EM algorithms, be one kind by E steps (asking expectation) and M steps
(maximization) carries out the optimization process of continuous iteration.
Claims (4)
1. a kind of non-motorized lane service level evaluation method based on mixed Gauss model, which is characterized in that include following step
Suddenly：
(1) acquire section Manpower Transportation stream parameter, including flow, density, speed, time rate of overtaking other vehicles, electric bicycle ratio,
Masculinity proportion parameter；
(2) while the video based on the first visual angle of bicyclist is shot, records Manpower Transportation stream operating status, and acquired
Traffic flow parameter corresponds；
(3) non-motorized lane service level is artificially divided into N number of grade, a score value is corresponded to per grade；It is beaten using bicyclist
The mode divided, collects grade scoring of the different bicyclists to video clip, and take its average value as the score of each segment；
(4) screening by significance analysis to traffic flow parameter selects significantly correlated traffic flow parameter as evaluation index；
(5) mixed Gauss model is used, considers the fluctuation of bicyclist's impression, the service level corresponding to each traffic flow modes
Grade existing probability relationship, establishes service level evaluation model.
2. the non-motorized lane service level evaluation method according to claim 1 based on mixed Gauss model, feature
It is, step (1) is specially：The width information with physically-isolated non-motor vehicle road segment segment is acquired, certain period of time is counted
The speed of interior wagon flow and each non-motor vehicle obtains the average speed of non-motor vehicle in the flow q and the period of unit width
Data v obtains density information k by the relationship q=kv of three parameter of traffic flow；Time rate of overtaking other vehicles is calculated by the following formula
Wherein,
r：It overtakes other vehicles time rate；
P：The number of overtaking other vehicles occurred in statistical interval；
Q：In statistical interval by vehicle number；
Electric bicycle ratio, male to female ratio are counted by artificial counting.
3. the non-motorized lane service level evaluation method according to claim 1 based on mixed linear model, feature
It is, step (4) is specially：Using the score of all video clips as dependent variable, the section non-motor vehicle of step (1) acquisition is handed over
Through-flow parameter carries out significance analysis as independent variable, using spss softwares, selects significantly correlated parameter as evaluation index.
4. the non-motorized lane service level evaluation method according to claim 1 based on mixed linear model, feature
It is, step (5) is specially：
1., evaluation index sample data is normalized, formula is as follows
Wherein,
x：Sample data original value；
x'：Value after sample data normalization；
min：Sample data minimum value；
max：Sample data maximum value；
2., consider bicyclist impression fluctuation, establish non-motorized lane service level evaluation model：
The form of multivariate Gaussian distribution probability density function is
Wherein, n is the number of evaluation index, x=(x1,x2,…,xn)TIt is the vector that n evaluation index is constituted, μ=(μ1,
μ2,…,μn)TIt is the mean vector of multivariate Gaussian distribution, μnIt is the mean value of n-th of evaluation index, ∑ is covariance matrix；
Because service level is divided into N number of grade, the mixed Gauss model of foundation is by N number of multivariate Gaussian distributed combination
At mixed distribution, probability density function can be expressed as
Wherein, wiIt is distributed in the weight in mixed model for i-th of multivariate Gaussian, and is had
The parameter Estimation of model is carried out by EM algorithms, obtains non-motorized lane service level evaluation model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810570404.2A CN108776650A (en) | 2018-06-05 | 2018-06-05 | A kind of non-motorized lane service level evaluation method based on mixed Gauss model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810570404.2A CN108776650A (en) | 2018-06-05 | 2018-06-05 | A kind of non-motorized lane service level evaluation method based on mixed Gauss model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108776650A true CN108776650A (en) | 2018-11-09 |
Family
ID=64024544
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810570404.2A Pending CN108776650A (en) | 2018-06-05 | 2018-06-05 | A kind of non-motorized lane service level evaluation method based on mixed Gauss model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108776650A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110634288A (en) * | 2019-08-30 | 2019-12-31 | 上海电科智能系统股份有限公司 | Multi-dimensional urban traffic abnormal event identification method based on ternary Gaussian mixture model |
| CN111708986A (en) * | 2020-05-29 | 2020-09-25 | 四川旷谷信息工程有限公司 | Pipe gallery state parameter measuring method |
| CN112132376A (en) * | 2020-07-14 | 2020-12-25 | 同济大学 | Non-motor vehicle riding quality evaluation method |
| CN114187766A (en) * | 2021-11-08 | 2022-03-15 | 航天科工广信智能技术有限公司 | Road service level evaluation method based on saturation rate |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101604479A (en) * | 2009-07-14 | 2009-12-16 | 北京交通大学 | The evaluation method of service level of plane signal intersection under mixed traffic environment |
| CN101710448A (en) * | 2009-12-29 | 2010-05-19 | 浙江工业大学 | Road traffic state detecting device based on omnibearing computer vision |
| CN103646533A (en) * | 2013-11-22 | 2014-03-19 | 江苏大学 | A traffic accident modeling and control method based on sparse multi-output regression |
| CN106651083A (en) * | 2016-06-29 | 2017-05-10 | 东南大学 | Pedestrian-non-motor vehicle isolation facility arrangement method for urban road segment |
| CN107564287A (en) * | 2017-09-20 | 2018-01-09 | 北京工业大学 | A kind of method for building up of signalized intersections crossing mixed traffic flow degree of order evaluation model |
-
2018
- 2018-06-05 CN CN201810570404.2A patent/CN108776650A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101604479A (en) * | 2009-07-14 | 2009-12-16 | 北京交通大学 | The evaluation method of service level of plane signal intersection under mixed traffic environment |
| CN101710448A (en) * | 2009-12-29 | 2010-05-19 | 浙江工业大学 | Road traffic state detecting device based on omnibearing computer vision |
| CN103646533A (en) * | 2013-11-22 | 2014-03-19 | 江苏大学 | A traffic accident modeling and control method based on sparse multi-output regression |
| CN106651083A (en) * | 2016-06-29 | 2017-05-10 | 东南大学 | Pedestrian-non-motor vehicle isolation facility arrangement method for urban road segment |
| CN107564287A (en) * | 2017-09-20 | 2018-01-09 | 北京工业大学 | A kind of method for building up of signalized intersections crossing mixed traffic flow degree of order evaluation model |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110634288A (en) * | 2019-08-30 | 2019-12-31 | 上海电科智能系统股份有限公司 | Multi-dimensional urban traffic abnormal event identification method based on ternary Gaussian mixture model |
| CN110634288B (en) * | 2019-08-30 | 2022-06-21 | 上海电科智能系统股份有限公司 | Multi-dimensional urban traffic abnormal event identification method based on ternary Gaussian mixture model |
| CN111708986A (en) * | 2020-05-29 | 2020-09-25 | 四川旷谷信息工程有限公司 | Pipe gallery state parameter measuring method |
| CN112132376A (en) * | 2020-07-14 | 2020-12-25 | 同济大学 | Non-motor vehicle riding quality evaluation method |
| CN112132376B (en) * | 2020-07-14 | 2023-02-07 | 同济大学 | Non-motor vehicle riding quality evaluation method |
| CN114187766A (en) * | 2021-11-08 | 2022-03-15 | 航天科工广信智能技术有限公司 | Road service level evaluation method based on saturation rate |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108776650A (en) | A kind of non-motorized lane service level evaluation method based on mixed Gauss model | |
| CN105745131B (en) | Travel controlling system, server, car-mounted device | |
| CN108806021A (en) | Electric vehicle target road section energy consumption prediction technique based on physical model and roadway characteristic parameter | |
| CN105355049B (en) | A kind of highway evaluation of running status method based on macroscopical parent map | |
| CN109085790A (en) | A kind of underground traffic passenger guiding system based on smart city | |
| CN107564313A (en) | Highway traffic congestion notice system and forecasting methods | |
| CN110298579A (en) | A kind of construction method of new energy passenger car urban operating condition | |
| CN109272746B (en) | MFD estimation method based on BP neural network data fusion | |
| CN108777066A (en) | A kind of non-motorized lane service level evaluation method based on mixed linear model | |
| CN107248284A (en) | Real-time traffic evaluation method based on Multi-source Information Fusion | |
| CN109035787B (en) | Method for identifying vehicle category by using mobile communication data | |
| CN109087507A (en) | A kind of road traffic signal single-point control Benefit Evaluation Method | |
| CN108805335B (en) | Public bicycle scheduling method | |
| Oh et al. | Real-time inductive-signature-based level of service for signalized intersections | |
| CN116823534B (en) | Intelligent service virtual man system for text travel industry based on multi-mode large model | |
| CN114187766A (en) | Road service level evaluation method based on saturation rate | |
| CN109405962B (en) | Road traffic noise frequency spectrum calculation method | |
| CN103794046B (en) | Determine the system of method, device and the demonstration driving range of driving range | |
| CN106991811A (en) | Expressway exit ring road upstream trackside road information Optimization Design based on drive simulation experiment porch | |
| CN113450564B (en) | Intersection passing method based on NARX neural network and C-V2X technology | |
| CN110716527A (en) | Vehicle energy consumption analysis method and analysis system based on kinematic segments | |
| CN109190871A (en) | A kind of non-motorized lane Service level of road section measuring method based on VR technology | |
| CN107622309B (en) | Road congestion detection method based on VANETs and improved D-S evidence theory | |
| CN114639202B (en) | Campus shared electric bicycle management system and method based on Internet | |
| CN112959966B (en) | Vehicle-mounted multimedia regulation and control method, system, equipment and computer storage medium based on internet trip and user habit deep learning |
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 |
Application publication date: 20181109 |
|
| RJ01 | Rejection of invention patent application after publication |