CN107066501A - A kind of telemetering motor vehicle tail equipment points distributing method based on road similitude - Google Patents
A kind of telemetering motor vehicle tail equipment points distributing method based on road similitude Download PDFInfo
- Publication number
- CN107066501A CN107066501A CN201611267879.1A CN201611267879A CN107066501A CN 107066501 A CN107066501 A CN 107066501A CN 201611267879 A CN201611267879 A CN 201611267879A CN 107066501 A CN107066501 A CN 107066501A
- Authority
- CN
- China
- Prior art keywords
- sample
- class
- mrow
- road
- attribute
- 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
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000004458 analytical method Methods 0.000 claims abstract description 9
- 238000001514 detection method Methods 0.000 claims description 12
- 238000005259 measurement Methods 0.000 claims description 12
- 239000010755 BS 2869 Class G Substances 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 8
- 239000000779 smoke Substances 0.000 claims description 7
- 230000000007 visual effect Effects 0.000 claims description 7
- 244000025254 Cannabis sativa Species 0.000 claims description 6
- 238000002513 implantation Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 230000001133 acceleration Effects 0.000 claims description 4
- 239000003344 environmental pollutant Substances 0.000 claims description 4
- 231100000719 pollutant Toxicity 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 2
- 238000007417 hierarchical cluster analysis Methods 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 241001269238 Data Species 0.000 abstract description 2
- 230000007613 environmental effect Effects 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 7
- 230000008901 benefit Effects 0.000 description 4
- 230000000875 corresponding effect Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000002596 correlated effect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000004744 fabric Substances 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 238000003915 air pollution Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000005713 exacerbation Effects 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 208000023504 respiratory system disease Diseases 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000002459 sustained effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of telemetering motor vehicle tail equipment points distributing method based on road similitude.This method is using city road network motor-vehicle tail-gas as research object, the influence such as environmental factor attribute by urban road topological features and road is taken into full account, the higher attribute of wherein correlation is extracted as clustering variable, the motor-vehicle tail-gas data obtained in city road network are analyzed and handled using the method for hierarchical clustering.The present invention combines the result and the actual related request layouted of tail gas remote-measuring equipment of clustering, it is proposed that any number of tail gas remote-measuring equipment can be optimized to the algorithm of laying.The present invention therefrom obtains rule of layouting by the processing and analysis to a large amount of emission datas, or other rules be further discovered that reference is provided.
Description
Technical field
The invention belongs to the data processing field of intelligent transportation, it is related to a kind of motor-vehicle tail-gas based on road similitude distant
Measurement equipment points distributing method.
Background technology
Today's society, due to sustained and rapid development, the steady increase of people's income, national vehicles number is presented year by year
Increased trend, incident motor-vehicle tail-gas problem is also increasingly highlighted.Motor-vehicle tail-gas as urban air pollution master
Source is wanted, the exacerbation of urban atmospheric pollution is not only caused, causes taking place frequently for haze weather, also triggers city dweller's respiratory system disease
The increase of sick risk, daily life to city dweller and healthy has undesirable effect.Vehicle exhaust has become
One with the enhancement of environment between the two contradiction protruded very much is developed in city in maximization, in order to solve this problem, to machine
It is necessary that motor-car tail gas, which carries out effective detection and control,.Meanwhile, combining information technology, data communication transmission technology, electronics are passed
The intelligent transportation of sense technology, control technology and computer technology has become the inevitable development direction of future city traffic, faces
Data are analyzed and processed, found by the substantial amounts of data constantly produced in intelligent transportation system using the method for data mining
Wherein implicit rule, has become the developing important step of intelligent transportation.By being obtained to motor-vehicle tail-gas data
Take, prediction, so as to it is accurate, comprehensive, promptly control motor-vehicle tail-gas data changes, be correlation analysis work
And development strategy is formulated and provides decision-making foundation, to meet need of the administrative department to Maneuver seeker prevention and control and energy-saving and emission-reduction
Will.
Clustering is a kind of method of statistical analysis, and data are simplified by data modeling, it is therefore an objective in the base of similitude
Data are classified on plinth.Because road network topology structure, road surrounding environment etc. is similar, the emission data in each section also has
There is certain similitude.The emission data directly collected is all original and coarse, it is impossible to is effectively organized and utilized,
The motor-vehicle tail-gas data obtained in city road network are analyzed and processed using the method for clustering, help to obtain tail gas
Some valuable rules in data, for instructing sensor distributing etc. to have important practical significance.
Due to the scale that road traffic net is huge, on every road being respectively mounted remote-measuring equipment is obviously difficult to, in order to
In the case of remote-measuring equipment limited amount, by rational stationing mode, the greatest benefit of remote-measuring equipment is played, expands equipment
The scope of detection is urgent problem to be solved in engineering.Weight is assigned to the section investigated, weight considers the section
Fuzzy overall evaluation side is utilized after the key elements such as implantation of device cost, the economic value in the section region and management personnel's opinion
Method is determined, is chosen the maximum section of weight in each class and is laid remote-measuring equipment, limited resource so is focused on into high value
Part, realizes the target of maximizing the benefits.Any number of tail gas remote-measuring equipment is optimized into laying and causes sensor distributing
It is more flexible, on the one hand, to avoid the idle waste with fund of equipment, every remote-measuring equipment can be made to make the best use of everything；It is another
Aspect, exhaust information as much as possible can be obtained to greatest extent and system-wide net exhaust information is made prediction.
It is compared with existing method, more similarly entitled " a kind of city road network motor-vehicle tail-gas is distant in real time
Sense monitoring plot choosing method " (Application No. 201510214145.6), this is the achievement in advance of applicant, it uses vehicle
The single attribute whether occurred is classified to road as cluster feature and each classification results is estimated, selected most
Excellent scheme.It is disadvantageous in that the information difficulty for obtaining each car occurred on road is very big, obtained by the clustering method taken
As a result the selection of initial cluster center is possibly relied on, result may be caused to produce obvious deviation, precision of layouting is low.
The content of the invention
The technology of the present invention solves problem：In order to solve in Tail gas measuring to be laid any number of tail gas remote-measuring equipment
The problem of, the deficiencies in the prior art are overcome there is provided a kind of telemetering motor vehicle tail equipment points distributing method based on road similitude,
The correlated characteristic of motor-vehicle tail-gas data using clustering method to being obtained in city road network has carried out extraction and analysis, finally
The method that any number of tail gas remote-measuring equipment is laid in road network is proposed, is applicable with higher precision of layouting with more preferable
Property.
In order to solve the above problems, the technical solution used in the present invention is:
A kind of telemetering motor vehicle tail equipment points distributing method based on road similitude, comprises the following steps：
Step one：Sample data is simultaneously pre-processed to sample data needed for collection, and the required sample data refers to use
Tail gas remote-measuring equipment obtains every section Tail gas measuring information interior for a period of time, information of vehicle flowrate on road, day in target road network
Gas information and road relevant information；Data prediction includes data cleansing, hough transformation and data and converts three aspects；
Step 2：The sample data in step one after data prediction is handled is carried out using the method for hierarchical clustering
Clustering；Using measurement of the Euclidean distance as clustering distance, each sample is classified as a class first, every two are calculated
Similarity between individual class, that is, sample with sample measured between any two by distance；Then wherein similarity degree highest
The namely minimum sample of distance is polymerized to a class, circulating repetition similarity measurement and the merging for carrying out nearest class, and one is reduced every time
Class, finally until all samples are gathered into a class, obtains cluster result；
Step 3：Cluster result in step 2, draws Cluster tendency, the visual result that each step is clustered
It is shown on Cluster tendency；
Step 4：Weight is assigned to the section investigated, the significance level in section is represented and pays the utmost attention to degree, will be appointed
Anticipate number tail gas remote-measuring equipment correspondence respective number cluster result, found on Cluster tendency comprising class number be equal to pair
The cluster result of number is answered, the maximum section of weight in each class is chosen and lays tail gas remote-measuring equipment, finally give Arbitrary Digit
The scheme that purpose tail gas remote-measuring equipment is layouted.
In step one, sample data needed for being gathered before cluster is simultaneously pre-processed to sample data, is implemented as follows：
(1) the sample data collection before clustering, using every section in target road network as a sample, obtains each sample
This section specific Tail gas measuring information interior for a period of time, including data item have：Detection device is numbered, detection time, detection
The number-plate number, speed, vehicle acceleration, Vehicle length, CO2, CO, HC, NO concentration, smoke intensity value, capture pictures etc..
Information of vehicle flowrate on road, including data item have：Road name, time, the inhomogeneity such as station wagon, middle bus
The vehicle flowrate of type vehicle.
Weather information, including data item have：Time, city, weather conditions, temperature, humidity, wind speed, PM2.5, PM10,
AQI etc..
Road relevant information, including data item have：Geographical position id, place province, place city, place street, even
Connect mode, roadside tree and grass coverage, building average height etc..
(2) sample data preprocessing part includes data cleansing, hough transformation and data three aspects of conversion.Data are clear
Wash, be exactly, by the analysis to data, to find out missing values, deviate excessive indivedual extremums progress discard processing, due to original
Data volume is very big, and the ratio shared by this kind of data is very small, will not be very big on problem influence, so can be with carrying out discard processing.
Hough transformation, is exactly deleted and considered a problem uncorrelated, weak related or redundancy attribute, merging same alike result, due to original
Attribute is many in data, is not necessarily considered a problem to the present invention related, it is necessary to which the continuous selection to association attributes is repaiied
Change, can be only achieved relatively good Clustering Effect.Data are converted, and are exactly standardized data, and conversion is for ease of processing
Appropriate format, the need for adapting to clustering and algorithm, because the corresponding data span difference of different attribute may
Very big, in order to eliminate the influence that varying number DBMS is brought, it is necessary that data, which are standardized,.
By data prediction, present invention eliminates the bad data of interference cluster result, wherein appropriate category has been selected
Property and has carried out standardization to the corresponding data of each attribute as the attribute of sample point, is expressed as matrix form such as
Under：
Wherein n represents number of samples (the bar number of target road section), and m represents the number (association attributes for the association attributes chosen
Total vehicle flowrate after pollutant total concentration, smoke intensity value, attribute merging after merging including attribute, connected mode, roadside vegetation face
Product, building average height etc.), x represents the concrete numerical value of the attribute after standardization.
In step 2, the sample data obtained using the method for hierarchical clustering to being handled in step one carries out clustering tool
Body comprises the following steps：
(1) each sample that processing is obtained in sample in step one is classified as between a class, calculating each two class
Similarity, that is, distance to sample with sample between any two are measured.The similitude measured between sample is commonly used
Have Euclidean distance, manhatton distance and a Minkowski Distance, the present invention by repetition test using euclidean away from
From the measurement as clustering distance, Euclidean distance is as follows：
Wherein, d (i, j) represents Euclidean distance, i and the specimen number that j is i-th of sample and j-th of sample, respectively
Represent i-th section and j-th strip section, m represents that (association attributes includes the pollution after attribute merges for the association attributes number chosen
Total vehicle flowrate, connected mode, roadside tree and grass coverage, building average height after thing total concentration, smoke intensity value, attribute merging etc.),
X represents numerical value of the association attributes after standardization, xi1Represent the 1st attribute, x of i-th of samplei2Represent i-th sample
2nd attribute, ximRepresent m-th of attribute of i-th of sample, xj1Represent the 1st attribute, x of j-th of samplej2Represent j-th
2nd attribute, x of samplejmRepresent m-th of attribute of j-th of sample.
(2) the namely two minimum samples of distance of similarity degree highest in (1) are polymerized to a class, it is assumed that for sample s and
Sample t, by sample s, t merges into a new class, is designated as G1={ s, t }, the class G newly produced1Association attributes section s, t correspondences
The average of attribute represents that the attribute of that is, new class is represented byWherein, s and t be s-th sample and
The specimen number of t-th of sample, m represents the association attributes number chosen, and x represents numerical value of the association attributes after standardization,
xs1Represent the 1st attribute, x of s-th of samplesmRepresent m-th of attribute of s-th of sample, xt1Represent the 1st of t-th of sample
Attribute, xtmRepresent m-th of attribute of t-th of sample；
(3) new class and other classes can obtain the sample of a n-1 capacity together, calculate all sample point each twos in sample
Between similarity, that is, distance between any two measured.It will wherein to be polymerized to one apart from two minimum samples
Class, is designated as G2, the class G newly produced2Association attributes represented with the average of the corresponding attribute of two samples included in class.
(4) similarly, repeat the merging of similarity measurement and nearest class, reduce by a class every time, can obtain successively
New class G3, G4..., Gn-1, the number of last class is reduced to 1, and all samples are gathered into a class.
In step 3, Cluster tendency is drawn according to clustering information, abscissa is the result that cluster for the first time is represented at 1,
Abscissa is the result that second cluster is represented at 2, the like, the visual result that each step is clustered is included in cluster spectrum
It is on figure.Cluster tendency fully illustrates every a one-step process of cluster, allows and recognizes that each step is gathered from visual aspect
For the section of a class, each step cluster terminates the section included respectively in rear inhomogeneous number and these classes.
In step 4, weight w is assigned to the section investigated, weight considers the implantation of device cost in the section, set
Standby lay determines that the bigger significance level for representing section of weight is bigger and pays the utmost attention to degree more after the key elements such as complexity
It is high.Assuming that needing to carry out number for k tail gas remote-measuring equipment, the cluster knot that correspondence class number is k is found from Cluster tendency
Really, i.e. result after the n-th-k clusters, chooses the maximum section laying tail gas remote-measuring equipment of the weight of each class in this k class,
Finally give the scheme layouted to any number of tail gas remote-measuring equipment.
The advantage of the present invention compared with prior art is：
(1) in terms of the selection of attribute, obtain that the information difficulty of each car occurred on road is very big, and traffic flow is obtained
Take relatively easy (such as Floating Car method).Whether occur compared to vehicle on more single selection road, the present invention is using cluster point
The correlated characteristic of motor-vehicle tail-gas data of the analysis method to being obtained in city road network has carried out extraction and analysis, finally proposes on road
The method that any number of tail gas remote-measuring equipment is laid in net, has considered the influence of various association attributeses, improves cluster
The precision of analysis, with higher precision of layouting.
(2) secondly, selection of the cluster process independent of remote-measuring equipment number k so that with higher flexibility and suitable
The property used.
(3) finally, existing algorithm is layouted for different number of remote-measuring equipment needs to re-start clustering, and originally
The method that invention is proposed need to only carry out a clustering, just can obtain all sides of layouting of the different number remote-measuring equipments of correspondence
Case.
(4) one aspect of the present invention avoids the idle waste with fund of equipment, and every remote-measuring equipment thing can be made to use up it
With；On the other hand, exhaust information as much as possible can be obtained to greatest extent and system-wide net exhaust information is made prediction.This
Invention therefrom obtains rule of layouting by the processing and analysis to a large amount of emission datas, or other rules further hair
Reference is now provided.
Brief description of the drawings
Fig. 1 is the implementation process figure of the inventive method；
Fig. 2 is embodiment Cluster tendency schematic diagram of the present invention.
Embodiment
To make the object, technical solutions and advantages of the present invention clearer, further is made to the present invention below in conjunction with the accompanying drawings
Detailed description.The following examples are only intended to illustrate the technical solution of the present invention more clearly, and this can not be limited with this
The protection domain of invention.
Embodiment chooses Hefei City somewhere road network specific detection data interior for a period of time, and the road network includes section
Number is n=10, obtains that arbitrary number can be optimized to the side of laying for k tail gas remote-measuring equipment using clustering
Case, as shown in figure 1, it is as follows to implement process.
Step one：Sample data needed for being gathered before cluster is simultaneously pre-processed to sample data.Will be every in target road network
Bar section obtains each sample section specific Tail gas measuring information interior for a period of time as a sample, including data item
Have：Detection device is numbered, detection time, the number-plate number of detection, speed, vehicle acceleration, Vehicle length, CO2, CO, HC, NO
Concentration, smoke intensity value, capture pictures etc..Information of vehicle flowrate on road, including data item have：Road name, the time, station wagon,
The vehicle flowrate of the different type vehicle such as middle bus.Weather information, including data item have：Time, city, weather conditions, temperature
Degree, humidity, wind speed, PM2.5, PM10, AQI etc..Road relevant information, including data item have：Geographical position id, place province
Part, place city, place street, connected mode, roadside tree and grass coverage, building average height etc..
Data cleansing is carried out first, by the analysis to data, is found out missing values, is deviateed excessive indivedual extremums progress
Discard processing, this step needs to spend the more time.Then hough transformation is carried out, is deleted and considered a problem uncorrelated, weak phase
Pass or the attribute (such as temperature, humidity, wind speed, the number-plate number of detection, speed, vehicle acceleration etc.) of redundancy, merge similar category
(vehicle flowrate of the different type vehicle such as station wagon, middle bus merges into vehicle flowrate to property, and CO2, CO, HC, NO concentration are merged into
Pollutant concentration), finally have chosen wherein m=8 association attributes, (it is always dense that association attributes includes the pollutant after attribute merges
Total vehicle flowrate, connected mode, roadside tree and grass coverage, building average height after degree, smoke intensity value, attribute merging etc.).It is most laggard
Row data are converted, and the data of not commensurate, varying number level are standardized.
Step 2：The sample data obtained using the method for hierarchical clustering to being handled in step one carries out Hierarchical clustering analysis
Specifically include following steps：
(1) processing in step one is obtained into each sample in sample and is classified as a class, altogether 10 classes, calculate every two
Similarity between individual class, that is, the Euclidean distance of sample point between any two is calculated, obtain distance matrix as follows：
Wherein d represents Euclidean distance.
(2) it is d (3,6) to choose element minimum in lower triangle below diagonal, section 3 and section 6 is merged into one new
Class, is designated as G1={ 3,6 }, are recalculated using the association attributes in section 3 and section 6 and obtain new class G1Attribute.
(3) new class and other classes can obtain the sample of a n-1=9 capacity together, calculate all sample points in new samples
Distance between any two, wherein make it that apart from minimum be d (4,10), is polymerized to a class by section 4 and section 10, is designated as G2=
{ 4,10 }, the number of class is reduced to 9.Recalculated using the association attributes in section 4 and section 10 and obtain new class G2Attribute.
(4) similarly, repeat similarity measurement and the merging apart from infima species, reduce by a class every time, can be successively
Obtain new class G3, G4..., G9, when the 9th step is clustered, the number of class is reduced to 1, and all samples are gathered for a class, are gathered
Class result.Cluster result is as shown in the table：
| Cluster step number | Clustering and selection | Cluster result |
| 1 | 3,6 | 1,2,4,5,7,8,9,10, { 3,6 } |
| 2 | 4,10 | 1,2,5,7,8,9, { 3,6 }, { 4,10 } |
| 3 | 8,9 | 1,2,5,7,{8,9},{3,6},{4,10} |
| 4 | G2, G3 | 1,2,5,7,{3,6},{4,8,9,10} |
| 5 | 5, G4 | 1,2,7,{3,6},{4,5,8,9,10} |
| 6 | 7, G5 | 1,2,{3,6},{4,5,7,8,9,10} |
| 7 | 1,2 | {1,2},{3,6},{4,5,7,8,9,10} |
| 8 | G1, G7 | {1,2,3,6},{4,5,7,8,9,10} |
| 9 | G6, G8 | {1,2,3,4,5,6,7,8,9,10} |
Step 3：Cluster result in step 2 draws Cluster tendency, the visual result that each step is clustered
It is shown on Cluster tendency as shown in Figure 2.Abscissa be 1 at represents for the first time cluster result, comprising 9 classes { 1 },
{ 2 }, { 4 }, { 5 }, { 7 }, { 8 }, { 9 }, { 10 }, { 3,6 } }.Abscissa is the result that second of cluster is represented at 2, includes 8 classes
{ { 1 }, { 2 }, { 5 }, { 7 }, { 8 }, { 9 }, { 4,10 }, { 3,6 } }, the like.
Step 4：Weight is assigned to the section investigated, the significance level in section is represented and pays the utmost attention to degree, weight
Consider and determined after the key elements such as implantation of device cost, the implantation of device complexity in the section.The weight of section 1 is 4, section 2,
3,4 weights are 3, and the weight of section 5,6 is 2, and the weight of section 7,8,9,10 is 1.Assuming that needing the tail gas remote measurement by number for k=3
Implantation of device finds the knot after the cluster result that correspondence class number is 3, i.e., the 7th time cluster into the road network from Cluster tendency
Fruit is { { 1,2 }, { 3,6 }, { 4,5,7,8,9,10 } }, chooses maximum section { 1,3, the 4 } cloth of the weight of each class in this 3 classes
If tail gas remote-measuring equipment, it is cloth on the section 3 in section 1, section 4 to finally give the scheme layouted to tail gas remote-measuring equipment
Point.
The general principle and principal character of the present invention has been shown and described above.It should be understood by those skilled in the art that,
The present invention is not limited by examples detailed above, and the description in examples detailed above and specification merely illustrates the principles of the invention, and is not taking off
On the premise of from spirit and scope of the invention, various changes and modifications of the present invention are possible, and these changes and improvements are both fallen within will
Ask in the invention scope of protection.The claimed scope of the invention is by appended claims and its equivalent thereof.
Claims (5)
1. a kind of telemetering motor vehicle tail equipment points distributing method based on road similitude, it is characterised in that comprise the following steps：
Step one：Sample data is simultaneously pre-processed to sample data needed for collection, and the required sample data refers to use tail gas
Remote-measuring equipment obtains every section Tail gas measuring information interior for a period of time in target road network, information of vehicle flowrate on road, weather letter
Breath and road relevant information；Data prediction includes data cleansing, hough transformation and data and converts three aspects；
Step 2：The sample data in step one after data prediction is handled is clustered using the method for hierarchical clustering
Analysis；Using measurement of the Euclidean distance as clustering distance, each sample is classified as a class first, each two class is calculated
Between similarity, that is, distance is measured between any two for sample and sample；Then wherein similarity degree highest also
It is that the minimum sample of distance is polymerized to a class, circulating repetition similarity measurement and the merging for carrying out nearest class, reduces by a class every time, most
Afterwards until all samples are gathered into a class, cluster result is obtained；
Step 3：Cluster result in step 2, draws Cluster tendency, the display for the visual result that each step is clustered
On Cluster tendency；
Step 4：Weight is assigned to the section investigated, the significance level in section is represented and pays the utmost attention to degree, by Arbitrary Digit
The cluster result of purpose tail gas remote-measuring equipment correspondence respective number, finds on Cluster tendency and is equal to correspondence number comprising class number
Purpose cluster result, chooses the maximum section of weight in each class and lays tail gas remote-measuring equipment, finally giving will be any number of
The scheme that tail gas remote-measuring equipment is layouted.
2. the telemetering motor vehicle tail equipment points distributing method according to claim 1 based on road similitude, its feature exists
In：In step one, it is implemented as follows：
(1) the sample data collection before clustering, using every section in target road network as a sample, obtains each sample arm
Tail gas measuring information, information of vehicle flowrate on road, Weather information and road relevant information in section a period of time；Wherein：
Tail gas measuring information, including data item have：Detection device is numbered, detection time, the number-plate number of detection, speed, car
Acceleration, Vehicle length, CO2, CO, HC, NO concentration, smoke intensity value, capture pictures；
Information of vehicle flowrate on road, including data item have：Road name, time, station wagon, middle bus different type vehicle
Vehicle flowrate；
Weather information, including data item have：Time, city, weather conditions, temperature, humidity, wind speed, PM2.5, PM10, AQI；
Road relevant information, including data item have：Geographical position id, place province, place city, place street, connection side
Formula, roadside tree and grass coverage, building average height；
(2) sample data preprocessing part includes data cleansing, hough transformation and data three aspects of conversion；Data cleansing, just
It is, by the analysis to data, to find out missing values, deviate excessive indivedual extremums progress discard processing；Hough transformation, is deleted
To considered a problem uncorrelated, weak related or redundancy attribute, merge same alike result, while the constantly selection to association attributes
Modify, to reach required Clustering Effect；Data are converted, and the data after hough transformation are standardized, and are turned
The appropriate format for being easy to processing is turned to, the need for adapting to clustering.
3. the telemetering motor vehicle tail equipment points distributing method according to claim 1 based on road similitude, its feature exists
In：In the step 2, the sample data obtained using the method for hierarchical clustering to being handled in step one carries out clustering tool
Body comprises the following steps：
(1) each sample that processing is obtained in sample in step one is classified as similar between a class, calculating each two class
Degree, i.e., the distance to sample with sample between any two is measured；Similitude between measurement sample uses Euclidean distance
As the measurement of clustering distance, Euclidean distance is as follows：
<mrow>
<mi>d</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mroot>
<mrow>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mrow>
<mi>i</mi>
<mn>1</mn>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>x</mi>
<mrow>
<mi>j</mi>
<mn>1</mn>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mrow>
<mi>i</mi>
<mn>2</mn>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>x</mi>
<mrow>
<mi>j</mi>
<mn>2</mn>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<mn>...</mn>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mrow>
<mi>i</mi>
<mi>m</mi>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>x</mi>
<mrow>
<mi>j</mi>
<mi>m</mi>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
<mn>2</mn>
</mroot>
</mrow>
1
Wherein, d (i, j) represents Euclidean distance, i and the specimen number that j is i-th of sample and j-th of sample, represents respectively
I-th section and j-th strip section, m represent the association attributes number chosen, and it is total that association attributes includes the pollutant after attribute merges
Total vehicle flowrate, connected mode after concentration, smoke intensity value, attribute merging, roadside tree and grass coverage, building average height, x represent phase
Close numerical value of the attribute after standardization, xi1Represent the 1st attribute, x of i-th of samplei2Represent the 2nd category of i-th of sample
Property, ximRepresent m-th of attribute of i-th of sample, xj1Represent the 1st attribute, x of j-th of samplej2Represent the of j-th of sample
2 attributes, xjmRepresent m-th of attribute of j-th of sample；
(2) the namely two minimum samples of distance of similarity degree highest in step (1) are polymerized to a class, it is assumed that for sample s and
Sample t, by sample s, t merges into a new class, is designated as G1={ s, t }, the class G newly produced1Association attributes section s, t correspondences
The average of attribute represents that the attribute of that is, new class is expressed as
Wherein, s and t is the specimen number of s-th of sample and t-th of sample, and m represents the association attributes number chosen, and x represents phase
Close numerical value of the attribute after standardization, xs1Represent the 1st attribute, x of s-th of samplesmRepresent m-th of category of s-th of sample
Property, xt1Represent the 1st attribute, x of t-th of sampletmRepresent m-th of attribute of t-th of sample；
(3) new class and other classes obtain the sample of a n-1 capacity together, calculate in sample between all sample point each twos
Similarity, i.e., distance between any two is measured；It will wherein to be polymerized to a class apart from two minimum samples, be designated as G2,
The class G newly produced2Association attributes represented with the average of the corresponding attribute of two samples included in class；
(4) similarly, repeat the merging of similarity measurement and nearest class, reduce by a class every time, new class G is obtained successively3,
G4..., Gn-1, the number of last class is reduced to 1, and all samples are gathered into a class, obtain cluster result.
4. the telemetering motor vehicle tail equipment points distributing method according to claim 1 based on road similitude, its feature exists
In：In the step 3, Cluster tendency is drawn according to cluster process, abscissa is the result that cluster for the first time is represented at 1, horizontal
Coordinate is the result that second cluster is represented at 2, the like, the visual result that each step is clustered is included in cluster pedigree
On figure, Cluster tendency fully illustrates every a one-step process of cluster, allows and recognizes that each step is gathered from visual aspect and be
The section of one class, each step cluster terminates the section included respectively in rear inhomogeneous number and these classes.
5. the telemetering motor vehicle tail equipment points distributing method according to claim 1 based on road similitude, its feature exists
In：In the step 4, weight w is assigned to the section investigated, weight considers implantation of device cost, the equipment in the section
Lay and determined after complexity key element, the bigger significance level for representing section of weight is bigger and to pay the utmost attention to degree higher；It is false
If needing to carry out number for k tail gas remote-measuring equipment, the cluster result that correspondence class number is k is found from Cluster tendency, i.e.,
Result after n-th-k clusters, chooses the maximum section laying tail gas remote-measuring equipment of the weight of each class in this k class, finally
Obtain the scheme layouted to any number of tail gas remote-measuring equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611267879.1A CN107066501B (en) | 2016-12-31 | 2016-12-31 | motor vehicle exhaust remote measuring equipment distribution method based on road similarity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611267879.1A CN107066501B (en) | 2016-12-31 | 2016-12-31 | motor vehicle exhaust remote measuring equipment distribution method based on road similarity |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107066501A true CN107066501A (en) | 2017-08-18 |
| CN107066501B CN107066501B (en) | 2020-01-31 |
Family
ID=59623872
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611267879.1A Active CN107066501B (en) | 2016-12-31 | 2016-12-31 | motor vehicle exhaust remote measuring equipment distribution method based on road similarity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107066501B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107976514A (en) * | 2017-11-20 | 2018-05-01 | 中国科学技术大学 | A kind of remote-measuring equipment points distributing method based on the prediction of motor-vehicle tail-gas concentration distribution |
| CN109150629A (en) * | 2018-10-12 | 2019-01-04 | 中交第公路勘察设计研究院有限公司 | A kind of road network polymorphic type monitoring device combination distribution method |
| CN109508727A (en) * | 2018-04-23 | 2019-03-22 | 北京航空航天大学 | A method of similitude between the metric function based on weighted euclidean distance |
| CN111241720A (en) * | 2020-04-27 | 2020-06-05 | 北京英视睿达科技有限公司 | Modeling method and device of road raise dust model |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104835099A (en) * | 2015-04-29 | 2015-08-12 | 中国科学技术大学 | Urban road network motor vehicle exhaust real-time remote sensing monitoring base address selecting method |
| CN204945122U (en) * | 2015-09-16 | 2016-01-06 | 张世达 | A kind of Vehicular exhaust pollutant monitoring system |
| CN105259304A (en) * | 2015-09-16 | 2016-01-20 | 张世达 | On-line monitoring system and method for pollutants in vehicle tail gas |
| US20160247183A1 (en) * | 2015-02-23 | 2016-08-25 | Iogen Corporation | Pipeline arrangement for utilizing a gas comprising biomethane |
-
2016
- 2016-12-31 CN CN201611267879.1A patent/CN107066501B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160247183A1 (en) * | 2015-02-23 | 2016-08-25 | Iogen Corporation | Pipeline arrangement for utilizing a gas comprising biomethane |
| CN104835099A (en) * | 2015-04-29 | 2015-08-12 | 中国科学技术大学 | Urban road network motor vehicle exhaust real-time remote sensing monitoring base address selecting method |
| CN204945122U (en) * | 2015-09-16 | 2016-01-06 | 张世达 | A kind of Vehicular exhaust pollutant monitoring system |
| CN105259304A (en) * | 2015-09-16 | 2016-01-20 | 张世达 | On-line monitoring system and method for pollutants in vehicle tail gas |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107976514A (en) * | 2017-11-20 | 2018-05-01 | 中国科学技术大学 | A kind of remote-measuring equipment points distributing method based on the prediction of motor-vehicle tail-gas concentration distribution |
| CN109508727A (en) * | 2018-04-23 | 2019-03-22 | 北京航空航天大学 | A method of similitude between the metric function based on weighted euclidean distance |
| CN109150629A (en) * | 2018-10-12 | 2019-01-04 | 中交第公路勘察设计研究院有限公司 | A kind of road network polymorphic type monitoring device combination distribution method |
| CN109150629B (en) * | 2018-10-12 | 2021-05-14 | 中交第一公路勘察设计研究院有限公司 | Road network multi-type monitoring equipment combined layout method |
| CN111241720A (en) * | 2020-04-27 | 2020-06-05 | 北京英视睿达科技有限公司 | Modeling method and device of road raise dust model |
| CN111241720B (en) * | 2020-04-27 | 2020-07-17 | 北京英视睿达科技有限公司 | Modeling method and device of road raise dust model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107066501B (en) | 2020-01-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108109382B (en) | Congestion point, congestion line and congestion area discovery method based on composite network | |
| Nie et al. | Pavement Crack Detection based on yolo v3 | |
| CN107248283B (en) | A kind of urban area road network evaluation of running status method considering section criticality | |
| Wu et al. | Mapping building carbon emissions within local climate zones in Shanghai | |
| CN106529608B (en) | A kind of telemetering motor vehicle tail equipment complex system for arranging gravity points | |
| CN108492555A (en) | A kind of city road net traffic state evaluation method and device | |
| CN105374209B (en) | A kind of urban area road network running status characteristics information extraction method | |
| CN110232398A (en) | A kind of road network sub-area division and its appraisal procedure based on Canopy+Kmeans cluster | |
| CN108761509A (en) | A kind of traval trace and mileage prediction technique based on historical data | |
| CN106897826A (en) | A kind of street accidents risks appraisal procedure and system | |
| CN102136190A (en) | Dispatching management system and method for event emergency response of urban bus passenger transport | |
| CN107066501A (en) | A kind of telemetering motor vehicle tail equipment points distributing method based on road similitude | |
| CN106228808A (en) | City expressway travel time prediction method based on Floating Car space-time grid data | |
| CN105241524A (en) | Urban flood warning system and method based on radial basic function neural network model | |
| Zhi-Peng et al. | An improved adaptive exponential smoothing model for short-term travel time forecasting of urban arterial street | |
| Zhang et al. | How road network transformation may be associated with reduced carbon emissions: An exploratory analysis of 19 major Chinese cities | |
| CN117238126A (en) | Traffic accident risk assessment method under continuous flow road scene | |
| CN112101132B (en) | Traffic condition prediction method based on graph embedding model and metric learning | |
| CN106384507A (en) | Travel time real-time estimation method based on sparse detector | |
| CN111806443A (en) | Pure electric heavy truck unmanned energy consumption optimization method | |
| CN118364865A (en) | Method for predicting visibility of highway traffic meteorological environment in minute level and early warning system | |
| Liu et al. | An intelligent urban traffic data fusion analysis method based on improved artificial neural network | |
| CN110765900A (en) | DSSD-based automatic illegal building detection method and system | |
| Xu et al. | Research on parking Space Detection and Prediction Model based on CNN-LSTM | |
| Jiang et al. | Parametric calibration of speed–density relationships in mesoscopic traffic simulator with data mining |
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 | ||
| CP02 | Change in the address of a patent holder |
Address after: No.443 Huangshan Road, Shushan District, Hefei City, Anhui Province 230022 Patentee after: University of Science and Technology of China Address before: 230026 Jinzhai Road, Baohe District, Hefei, Anhui Province, No. 96 Patentee before: University of Science and Technology of China |
|
| CP02 | Change in the address of a patent holder |