CN108492560A - A kind of Road Detection device missing data complementing method and device - Google Patents
A kind of Road Detection device missing data complementing method and device Download PDFInfo
- Publication number
- CN108492560A CN108492560A CN201810293819.XA CN201810293819A CN108492560A CN 108492560 A CN108492560 A CN 108492560A CN 201810293819 A CN201810293819 A CN 201810293819A CN 108492560 A CN108492560 A CN 108492560A
- Authority
- CN
- China
- Prior art keywords
- function
- data
- many variables
- missing
- parameter
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 34
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000012795 verification Methods 0.000 claims abstract description 20
- 238000012549 training Methods 0.000 claims abstract description 19
- 238000000605 extraction Methods 0.000 claims abstract description 8
- 230000001419 dependent effect Effects 0.000 claims abstract description 7
- 238000003556 assay Methods 0.000 claims abstract description 3
- 230000000875 corresponding effect Effects 0.000 claims description 18
- 238000012217 deletion Methods 0.000 claims description 10
- 230000037430 deletion Effects 0.000 claims description 10
- 230000002596 correlated effect Effects 0.000 claims description 9
- 239000012141 concentrate Substances 0.000 claims description 4
- 238000006467 substitution reaction Methods 0.000 claims description 4
- 238000013075 data extraction Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000007423 decrease Effects 0.000 claims description 2
- 241000208340 Araliaceae Species 0.000 claims 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims 1
- 235000003140 Panax quinquefolius Nutrition 0.000 claims 1
- 235000008434 ginseng Nutrition 0.000 claims 1
- 238000007689 inspection Methods 0.000 claims 1
- 238000011156 evaluation Methods 0.000 abstract 1
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000002805 secondary assay Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000008717 functional decline Effects 0.000 description 1
Classifications
-
- 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
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G06Q50/40—
Abstract
The invention discloses a kind of Road Detection device missing data complementing methods and device, this method to include：Road Detection device gathered data is analyzed, extraction by the motor vehicle average speed of detector section, each assay intervals by motor vehicle flow and roadway occupancy；It using traffic flow theory as foundation, is fitted using the function of many variables, using speed as dependent variable, flow, occupation rate are that independent variable establishes several function of many variables forms；The function of many variables are fitted based on training set, determine that the most optimized parameter keeps actual value and the root-mean-square error of match value minimum；The evaluation index judged as fitting function quality of root-mean-square error using on verification collection, finally using optimal function and its corresponding the most optimized parameter, missing data progress completion caused by because of the equipment the problems such as.Detector missing data complementing method provided by the invention has easy to implement, easy to operate, the features such as applicability is high, can improve detector gathered data quality, so as to improve road management, promote road traffic efficiency.
Description
Technical field
The present invention relates to freeway traffic information collections, belong to freeway traffic technical field, and in particular to a kind of
Road Detection device missing data complementing method and device.
Background technology
With the continuous development of world economy, transportation business, especially highway transportation have also obtained considerable
Development.Especially for decades recently, the features such as highway is fast, efficient, safe with its worldwide obtains
Swift and violent development greatly strengthens the economic link between area, accelerates the socio-economic development of countries in the world, area.
Traffic data collection is the basis of highway operation and supervision, and accurate highway traffic data supports traffic administration
Person formulates effective administrative decision.
However, due to detection device aging, transmission line failure, environment is bad for detection, equipment debugging and improper use etc.
Reason so that there is various quality problems for the collected dynamic traffic data of detector.How to existing detection
Device data are analyzed, and then the completion missing data of precise and high efficiency, have important engineering significance.
Invention content
Goal of the invention：For problems of the prior art, the present invention provides a kind of Road Detection device missing data benefit
Full method and device carries out completion to the section detector data classifying type of missing, is supplied to the complete high speed of traffic administration person
Highway communication data, to formulate rational management strategy, Improving Expressway net overall operation efficiency.
Technical solution：For achieving the above object, the present invention adopts the following technical scheme that：
A kind of Road Detection device missing data complementing method, includes the following steps：
(1) Road Detection device gathered data is analyzed, extraction by detector section motor vehicle average speed, every
Secondary assay intervals by motor vehicle flow and roadway occupancy；
(2) data type clearly lacked, and find out the data position of each missing；
(3) leave out the data of missing from initial data, and the data after deletion are split, form training set and test
Card collection；
(4) relationship is positively correlated according to the ratio of speed and flow and occupation rate, addition adjusting parameter is established several for choosing
Select fitting using speed V as dependent variable, flow Q and occupation rate O are the function of many variables form of independent variable；The function of many variables established
Form includes at least： Wherein, β1,
β2,β3,β4For adjusting parameter；
(5) in training set, each function of many variables undetermined parameter is adjusted, determines that the most optimized parameter makes actual value and match value
Root-mean-square error it is minimum；
(6) it is concentrated in verification, with root-mean-square error minimum, alternatively foundation, the fitting for calculating each function of many variables miss
Difference selects optimal function of many variables form；
(7) apply optimal function and its corresponding the most optimized parameter, by the corresponding independent variable of detector missing data substitute into
Row calculates, and estimated data is calculated to fill up the data value of missing.
Preferably, in the step (4), the function of many variables form established further includes following at least one kind of：
Preferably, in the step (5), the most optimized parameter of each function of many variables is determined, including：(5.1) it sets more
The initial parameter value of meta-function model；(5.2) error function is established using principle of least square method, constantly adjusts the parameter of model
Value；(5.3) after successive ignition and adjustment, when error function value drops in some given range, stopping iteration recording
The most optimized parameter of the model parameter as the function of many variables.
Preferably, in the step (5.2), the method for adjusting model parameter is：In training set, it is assumed that speed is scarce
Data are lost, is inputted flow Q, occupation rate O as independent variable, is brought into the function of many variables to be fitted, calculate estimating speed V ', with
Error function declines the parameter value that most fast direction constantly adjusts model as basis for estimation, to error function value is made so that estimates
Error between meter speed degree V ' and true velocity V gradually reduces.
Preferably, in the step (6), the method for choosing the optimal function of many variables is：Using the optimal of each function of many variables
Change parameter, verification, which is collected the independent variable in data, substitutes into the function of many variables, calculates the estimated value of institute's missing data type, and then calculate
Verification concentrates each function of many variables to fit estimated value and the root-mean-square error of measured value, compares each function of many variables, selects most
The corresponding functional form of small root-mean-square error.
A kind of Road Detection device missing data complementing device that another aspect of the present invention provides, including：
Data extraction module, for analyzing Road Detection device gathered data, the machine of detector section is passed through in extraction
Motor-car average speed, each assay intervals by motor vehicle flow and roadway occupancy；
Deletion mapping module, the data type for clearly lacking, and find out the data position of each missing；
Preprocessing module, the data for leaving out missing from initial data, and the data after deletion are split, shape
Collect at training set and verification；
The function of many variables build module, and for being positively correlated relationship according to the ratio of speed and flow and occupation rate, addition is adjusted
Whole parameter establish several selective fittings using speed V as dependent variable, flow Q and occupation rate O are the function of many variables shape of independent variable
Formula；The function of many variables form established includes at least：
Wherein, β1,β2,β3,β4For adjusting parameter；
Function Fitting module determines that the most optimized parameter makes for adjusting each function of many variables undetermined parameter based on training set
Actual value and the root-mean-square error of match value are minimum；
Optimal function chooses module, for based on verification collection, with root-mean-square error minimum, alternatively foundation, calculating to be each
The error of fitting of the function of many variables selects optimal function of many variables form；
And missing fills up module, for applying optimal function and its corresponding the most optimized parameter, by detector missing data
Corresponding independent variable substitution is calculated, and estimated data is calculated to fill up the data value of missing.
Preferably, the function of many variables form established in the function of many variables structure module further includes following at least one kind of：
Advantageous effect：Compared with prior art, the beneficial effects of the present invention are：
1, function of many variables fitting form provided by the invention meets the ratio of traffic flow theory medium velocity and flow and density
It being positively correlated, density and time occupancy are positively correlated, the correlation that speed and flow and the ratio of occupation rate are positively correlated,
It is possible thereby to the speed data that application has flow, the estimation of occupation rate data lacks.2, the present invention is using root-mean-square error as commenting
Price card is accurate, is fitted form to the function of many variables that each missing data collection selects error minimum, can ensure higher completion precision.
3, completion road of the invention lacks speed data, can improve freeway traffic operation information, is formulated for traffic administration person
Management strategy provides foundation, and then promotes the safety of traffic circulation, and it is horizontal to improve highway overall operation.
Description of the drawings
Fig. 1 is Road Detection device missing data completion flow chart of the present invention；
Fig. 2 is Road Detection device gathered data instance data of the present invention part sample sectional drawing；
Fig. 3 is the function of many variables error analysis result figure of present example missing data completion.
Specific implementation mode
In the following with reference to the drawings and specific embodiments, the present invention is further described.
As shown in Fig. 1, a kind of Road Detection device missing data complementing method disclosed by the embodiments of the present invention, first to adopting
Collection data are analyzed, extraction wherein useful information；Missing data is specified, the data of missing are left out from initial data, and right
Data after deletion are split, and are formed training set and are collected with verification.Then the function of many variables form of selective fitting is established, is adjusted
Each function of many variables undetermined parameter determines that the most optimized parameter keeps actual value and the root-mean-square error of match value minimum.Then it uses equal
Square error alternatively foundation, calculates the error of fitting of each function of many variables, selects optimal function of many variables form.Finally substitute into
Optimal function is calculated, and the data value of missing is filled up.Detailed step is as follows：
(1) Road Detection device gathered data is analyzed, extraction by detector section motor vehicle average speed, every
Secondary assay intervals by motor vehicle flow and roadway occupancy.First, it collects road and lays Road Detection device (with Coil Detector
Based on device and geomagnetism detecting device) acquisition data, then to the traffic of collection acquisition information carry out tentatively filter and analyze, collect
Useful information therein, section detector acquisition traffic effective information mainly include the magnitude of traffic flow, speed, roadway occupancy,
Acquisition interval is related with the type of detector, generally intermediate at 30 seconds to 300 seconds.
(2) data type clearly lacked, and find out the data position of each missing.In this step, to acquisition
Data dissected, the type of the detector data clearly lacked.In Fig. 2, it can be seen that wherein detector detection is certain
Velocity amplitude goes out active or data exception phenomenon, so the data class that this example is filled up using the average speed of wagon flow as needs
Type finds the position of speed data exception.
(3) leave out the data of missing from initial data, and the data after deletion are split, form training set and test
Card collection.In this step, the corresponding data line of the data lacked in data set is deleted, by the data in each data set sample
Substantially it is divided into two sections from centre, training set of the last period as adjusting parameter, the verification of latter section of alternatively optimal function
Set.In this example, the data line for speed missing or exception occur is deleted, is broken it into two, a part is as training
Collection, another part collect as verification.
(4) function of many variables form of selective fitting is established.According to traffic flow theory, the ratio of speed and flow and density
Directly proportional, vehicle density and time occupancy are directly proportional, therefore the ratio of speed and flow and occupation rate is positively correlated relationship.This
In example, the existing accurate data of detector is flow Q and occupation rate O, and missing data to be supplemented is speed parameter V.Therefore, with
V (speed) is dependent variable, and Q (flow), O (occupation rate) are independent variable, and β i are undetermined parameter, establish 7 function of many variables forms and make
For fitting function.This 7 fitting functions are respectively：
First functional form
Second functional form
Third functional form
4th functional form
5th functional form
6th functional form
7th functional form
Above-mentioned 7 kinds of functional forms are to be examined through great amount of samples, the higher functional form of matching degree, wherein fourth, fifth,
Six functional form universalities are best, in practical operation, all or part of function can be selected to be screened for fitting.
(5) in training set, undetermined parameter is adjusted to each function of many variables, determines the most optimized parameter.In this step, each
Function of many variables fitting mainly includes the following steps that：
Step (5.1) sets initial parameter value.
Step (5.2) establishes error function using principle of least square method, constantly adjusts the parameter value of model.
Step (5.3) is after successive ignition and adjustment, when error function value drops in some given range, stops
Iteration, at this time the most optimized parameter of the record cast parameter as the function of many variables.
The respective optimal undetermined parameter of 7 fitting functions is finally determined using above-mentioned steps.
Specifically, the initial value for setting undetermined parameter β i in each function first, each during training is gathered detect
Flow Q, the occupation rate O of device data are brought into as independent variable in this 7 fitting functions, are obtained estimating speed V ', are utilized minimum
Two, which multiply principle, establishes the standard whether error function optimizes as parameter, is constantly adjusted to making error function value decline most fast direction
The parameter value of integral mould eventually finds keep estimating speed V ' and true velocity V mean errors in each training set minimum optimal
Undetermined parameter β i values.
(6) root-mean-square error minimum alternatively foundation is used, the error of fitting of each function of many variables is calculated, selects optimal more
Meta-function form.Using root-mean-square error as function of many variables selection gist in this step, root-mean-square error is that selected data is square
The arithmetic square root of error, also known as standard error.Its fundamental formular is as follows, wherein observedtIndicate actually detected value,
predictedtIndicate that calculated estimated value, N are total sample number.
Verification set is taken out, concentrates flow Q, the occupation rate O of each strip detector acquisition to be inputted as independent variable verification,
It brings into each fitting function, estimating speed V ' is calculated using its optimal undetermined parameter.Calculate estimating speed V ' and verification
Concentrate the root-mean-square error and record of true velocity V.
The root-mean-square error for comparing 7 fitting functions calculated estimating speed V ' and true velocity V is selected wherein minimum
Missing completion function of the corresponding fitting function of error as the data, the corresponding optimal undetermined parameter β i of the function are optimal
Change parameter.
(7) apply optimal function and its corresponding the most optimized parameter, by the corresponding independent variable of detector missing data substitute into
Row calculates, and estimated data is calculated to fill up the data value of missing.In this example, adopted with the corresponding detector of missing speed data
Flow Q, the occupation rate O collected inputs the function as independent variable, finds out estimating speed value, to fill up the missing speed left out
Value.From the figure 3, it may be seen that the root-mean-square error that selected data is gone out with the 4th function of many variables form calculus, minimum error values are
8.21%, the missing completion function using the function as the data finally fills up precision 90% or more.
Road Detection device missing data complementing device disclosed in another embodiment of the present invention, including：Data extraction module is used
It is analyzed in Road Detection device gathered data, extraction is passed through between the motor vehicle average speed of detector section, each detection
Every by motor vehicle flow and roadway occupancy；Deletion mapping module, the data type for clearly lacking, and find out each
The data position of item missing；Preprocessing module, the data for leaving out missing from initial data, and to the number after deletion
According to being split, forms training set and collect with verification；
The function of many variables build module, and for being positively correlated relationship according to the ratio of speed and flow and occupation rate, addition is adjusted
Whole parameter establish several selective fittings using speed V as dependent variable, flow Q and occupation rate O are the function of many variables shape of independent variable
Formula；The function of many variables form established includes at least： Function
Fitting module determines that the most optimized parameter makes actual value and fitting for adjusting each function of many variables undetermined parameter based on training set
The root-mean-square error of value is minimum；Optimal function choose module, for based on verification collection with root-mean-square error minimum alternatively according to
According to calculating the error of fitting of each function of many variables, select optimal function of many variables form；And missing fills up module, for applying
The corresponding independent variable substitution of detector missing data is calculated, is calculated by optimal function and its corresponding the most optimized parameter
Estimated data fills up the data value of missing.
Above-mentioned Road Detection device missing data complementing device embodiment can be used for executing above-mentioned Road Detection device missing number
According to complementing method embodiment, technical principle, it is solved the technical issues of and generation technique effect it is similar, the road of foregoing description
The specific work process of circuit detector missing data completion and related explanation can refer to aforementioned Road Detection device missing data and mend
Corresponding process in full embodiment of the method, details are not described herein.
It will be understood by those skilled in the art that can carry out adaptively changing and it to the module in embodiment
Be arranged in the one or more systems different from the embodiment.Can in embodiment module or unit or component combine
At a module or unit or component, and it can be divided into multiple submodule or subelement or sub-component in addition.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
It for member, without departing from the principle of the present invention, can also make several improvements, these improvement also should be regarded as the present invention's
Protection domain.
Claims (7)
1. a kind of Road Detection device missing data complementing method, it is characterised in that：This method comprises the following steps：
(1) Road Detection device gathered data is analyzed, extraction is by the motor vehicle average speed of detector section, every time inspection
Survey motor vehicle flow and roadway occupancy that interval passes through；
(2) data type clearly lacked, and find out the data position of each missing；
(3) leave out the data of missing from initial data, and the data after deletion are split, form training set and verification
Collection；
(4) relationship is positively correlated according to the ratio of speed and flow and occupation rate, addition adjusting parameter is established several selective quasi-
Close using speed V as dependent variable, flow Q and occupation rate O are the function of many variables form of independent variable；The function of many variables form established
It includes at least： Wherein, β1,β2,
β3,β4For adjusting parameter；
(5) in training set, each function of many variables undetermined parameter is adjusted, determines that the most optimized parameter makes the equal of actual value and match value
Square error is minimum；
(6) it is concentrated in verification, with root-mean-square error minimum alternatively foundation, calculates the error of fitting of each function of many variables, selected
Go out optimal function of many variables form；
(7) optimal function and its corresponding the most optimized parameter are applied, the corresponding independent variable substitution of detector missing data is counted
It calculates, estimated data is calculated to fill up the data value of missing.
2. a kind of Road Detection device missing data complementing method according to claim 1, it is characterised in that：The step
(4) in, the function of many variables form established further includes following at least one kind of：
3. a kind of Road Detection device missing data complementing method according to claim 1, it is characterised in that：The step
(5) in, the most optimized parameter of each function of many variables is determined, including：(5.1) initial parameter value of function of many variables model is set；
(5.2) error function is established using principle of least square method, constantly adjusts the parameter value of model；(5.3) pass through successive ignition and
After adjustment, when error function value drops in some given range, stopping iteration, record cast parameter is as the function of many variables
The most optimized parameter.
4. a kind of Road Detection device missing data complementing method according to claim 3, it is characterised in that：The step
(5.2) in, the method for adjusting model parameter is：In training set, it is assumed that speed is missing data, and flow Q, occupation rate O are made
It is inputted for independent variable, brings into the function of many variables to be fitted, calculate estimating speed V ', using error function as basis for estimation, to
Error function value is set to decline the parameter value that most fast direction constantly adjusts model so that between estimating speed V ' and true velocity V
Error gradually reduce.
5. a kind of Road Detection device missing data complementing method according to claim 1, it is characterised in that：The step
(6) in, the method for choosing the optimal function of many variables is：Using the most optimized parameter of each function of many variables, verification is collected into oneself in data
Variable substitutes into the function of many variables, calculates the estimated value of institute's missing data type, and then calculates verification and concentrate the fitting of each function of many variables
Go out estimated value and the root-mean-square error of measured value, compare each function of many variables, selects the minimum corresponding function of root-mean-square error
Form.
6. a kind of Road Detection device missing data complementing device, which is characterized in that including：
Data extraction module, for analyzing Road Detection device gathered data, the motor vehicle of detector section is passed through in extraction
Average speed, each assay intervals by motor vehicle flow and roadway occupancy；
Deletion mapping module, the data type for clearly lacking, and find out the data position of each missing；
Preprocessing module, the data for leaving out missing from initial data, and the data after deletion are split, form instruction
Practice collection with verification to collect；
The function of many variables build module, for being positively correlated relationship, addition adjustment ginseng according to the ratio of speed and flow and occupation rate
Number establish several selective fittings using speed V as dependent variable, flow Q and occupation rate O are the function of many variables form of independent variable；Institute
The function of many variables form of foundation includes at least： Its
In, β1,β2,β3,β4For adjusting parameter；
Function Fitting module determines that the most optimized parameter makes reality for adjusting each function of many variables undetermined parameter based on training set
Value and the root-mean-square error of match value are minimum；
Optimal function chooses module, for based on verification collection, with root-mean-square error minimum, alternatively foundation, calculating to be each polynary
The error of fitting of function selects optimal function of many variables form；
And missing fills up module, and for applying optimal function and its corresponding the most optimized parameter, detector missing data is corresponded to
Independent variable substitution calculated, estimated data is calculated to fill up the data value of missing.
7. a kind of Road Detection device missing data complementing device according to claim 6, which is characterized in that the polynary letter
The function of many variables form established in number structure module further includes following at least one kind of：
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810293819.XA CN108492560A (en) | 2018-04-04 | 2018-04-04 | A kind of Road Detection device missing data complementing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810293819.XA CN108492560A (en) | 2018-04-04 | 2018-04-04 | A kind of Road Detection device missing data complementing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108492560A true CN108492560A (en) | 2018-09-04 |
Family
ID=63317926
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810293819.XA Pending CN108492560A (en) | 2018-04-04 | 2018-04-04 | A kind of Road Detection device missing data complementing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108492560A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109584553A (en) * | 2018-11-29 | 2019-04-05 | 中电海康集团有限公司 | A kind of section degree of association missing complementing method based on space time information |
| CN109710659A (en) * | 2018-12-16 | 2019-05-03 | 苏州城方信息技术有限公司 | The complementing method of detector missing data based on temporal correlation |
| CN110490419A (en) * | 2019-07-19 | 2019-11-22 | 珠海市岭南大数据研究院 | Processing method, device, computer equipment and the storage medium of Bus information data |
| CN113377508A (en) * | 2021-05-28 | 2021-09-10 | 张燕 | Mass data rapid transmission method |
| CN113782128A (en) * | 2021-08-09 | 2021-12-10 | 中国中医科学院中医临床基础医学研究所 | Missing data fitting method and device and computer equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6236932B1 (en) * | 1996-12-16 | 2001-05-22 | Mannesmann Ag | Process for completing and/or verifying data concerning the state of a road network; traffic information centre |
| CN103971520A (en) * | 2014-04-17 | 2014-08-06 | 浙江大学 | Traffic flow data recovery method based on space-time correlation |
| CN106781457A (en) * | 2016-11-29 | 2017-05-31 | 东南大学 | A kind of freeway traffic flow parameter correction method based on multi-source fusion data |
| CN107193876A (en) * | 2017-04-21 | 2017-09-22 | 美林数据技术股份有限公司 | A kind of missing data complementing method based on arest neighbors KNN algorithms |
-
2018
- 2018-04-04 CN CN201810293819.XA patent/CN108492560A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6236932B1 (en) * | 1996-12-16 | 2001-05-22 | Mannesmann Ag | Process for completing and/or verifying data concerning the state of a road network; traffic information centre |
| CN103971520A (en) * | 2014-04-17 | 2014-08-06 | 浙江大学 | Traffic flow data recovery method based on space-time correlation |
| CN106781457A (en) * | 2016-11-29 | 2017-05-31 | 东南大学 | A kind of freeway traffic flow parameter correction method based on multi-source fusion data |
| CN107193876A (en) * | 2017-04-21 | 2017-09-22 | 美林数据技术股份有限公司 | A kind of missing data complementing method based on arest neighbors KNN algorithms |
Non-Patent Citations (1)
| Title |
|---|
| 金盛: "环形线圈检测器交通数据预处理方法研究", 《中国优秀硕士学位论文全文数据库·工程科技Ⅱ辑》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109584553A (en) * | 2018-11-29 | 2019-04-05 | 中电海康集团有限公司 | A kind of section degree of association missing complementing method based on space time information |
| CN109710659A (en) * | 2018-12-16 | 2019-05-03 | 苏州城方信息技术有限公司 | The complementing method of detector missing data based on temporal correlation |
| CN109710659B (en) * | 2018-12-16 | 2022-11-25 | 苏州城方信息技术有限公司 | Method for filling detector missing data based on space-time correlation |
| CN110490419A (en) * | 2019-07-19 | 2019-11-22 | 珠海市岭南大数据研究院 | Processing method, device, computer equipment and the storage medium of Bus information data |
| CN113377508A (en) * | 2021-05-28 | 2021-09-10 | 张燕 | Mass data rapid transmission method |
| CN113377508B (en) * | 2021-05-28 | 2023-08-22 | 张燕 | Mass data rapid transmission method |
| CN113782128A (en) * | 2021-08-09 | 2021-12-10 | 中国中医科学院中医临床基础医学研究所 | Missing data fitting method and device and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108492560A (en) | A kind of Road Detection device missing data complementing method and device | |
| CN107943880B (en) | Geological disaster susceptibility improvement and evaluation method based on analytic hierarchy process | |
| CN103021193B (en) | Green wave coordination control method for artery facing to running speed section | |
| CN102087788B (en) | Method for estimating traffic state parameter based on confidence of speed of float car | |
| CN107948166A (en) | Traffic anomaly detection method and device based on deep learning | |
| CN106649709B (en) | Vehicle stopping behavior pattern prediction and evaluation method based on data mining | |
| CN108647805B (en) | Comprehensive testing method for critical rainfall of mountain torrent disasters | |
| CN104574968B (en) | Determining method for threshold traffic state parameter | |
| CN113470362B (en) | Urban road traffic jam space-time accurate discrimination method based on SVR-DEA model | |
| CN102789545A (en) | Method for predicating remaining life of turbine engine based on degradation model matching | |
| CN104750830B (en) | The cycle method for digging of time series data | |
| CN101783074A (en) | Method and system for real-time distinguishing traffic flow state of urban road | |
| CN106056903B (en) | The detection method in the road congestion region based on GPS data | |
| CN106898142A (en) | A kind of path forms time reliability degree calculation method of consideration section correlation | |
| CN106297285A (en) | Freeway traffic running status fuzzy synthetic appraisement method based on changeable weight | |
| CN106781486A (en) | Traffic behavior evaluation method based on floating car data | |
| CN104252556B (en) | A kind of river classification system | |
| Lu et al. | Estimating traffic speed with single inductive loop event data | |
| CN110232334A (en) | A kind of steel construction corrosion recognition methods based on convolutional neural networks | |
| CN100481153C (en) | Method for automatically inspecting highway traffic event based on offset minimum binary theory | |
| CN106529765A (en) | Performance evaluation method and device for collection operation | |
| CN106526149A (en) | Method for predicting pavement performance on basis of transport durations and traffic volumes | |
| CN106157616A (en) | A kind of magnitude of traffic flow short-term prediction device | |
| CN106934184A (en) | A kind of Digit Control Machine Tool load Extrapolation method based on the extension of time domain load | |
| CN102436742A (en) | Method and device for evaluating traffic information service level of floating vehicle system |
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: 20180904 |
|
| RJ01 | Rejection of invention patent application after publication |