CN109272760A - A kind of online test method of SCATS system detector data outliers - Google Patents
A kind of online test method of SCATS system detector data outliers Download PDFInfo
- Publication number
- CN109272760A CN109272760A CN201811213599.1A CN201811213599A CN109272760A CN 109272760 A CN109272760 A CN 109272760A CN 201811213599 A CN201811213599 A CN 201811213599A CN 109272760 A CN109272760 A CN 109272760A
- Authority
- CN
- China
- Prior art keywords
- data
- traffic flow
- zero
- time
- road traffic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/08—Controlling traffic signals according to detected number or speed of vehicles
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
A kind of online test method of SCATS system detector data outliers, its step are as follows: (1) SCATS system data is extracted from database, and by intersection number, detector number, chronological order arrangement;(2) judgement that the road traffic flow data of extraction are carried out with zero data will continuously be that zero time span is classified as abnormal data beyond the zero data of time interval in traffic flow data, other are classified as normal data;(3) normal data after progress zero data judgement is carried out to the judgement of abnormal data, above-mentioned normal data is examined through magnitude of traffic flow threshold test, traffic flow parameter consistency check, magnitude of traffic flow statistical law respectively, meeting test stone is normal data, and not meeting test stone is abnormal data.Validity, the accuracy of present invention guarantee detection data, it is ensured that the normal performance of SCATS system function improves the operational effect of system.
Description
Technical field
The invention belongs to field of traffic control, are related to a kind of on-line checking side of SCATS system detector data outliers
Method.
Background technique
With the popularization of intelligent transportation system, city intelligent traffic signal control system is using more and more extensive.Intelligence is handed over
Messenger control system and a main distinction of traditional control system are to acquire real-time road traffic data, transmission, locate
Technical application in reason and storing process.With being constantly progressive for data acquisition technology, whistle control system control range is more next
Bigger, the information category of acquisition is more and more, and data volume is also increasing.In the acquisition of Traffic Information data, transmits and deposit
It is inevitable in highway traffic data due to detector device failure, communication failure and software operation emergency event etc. during storage
Comprising some mistakes, the data of loss and exception, validity, the accuracy of data are influenced.If directlying adopt these with quality
The data of problem will can generate certain influence to whistle control system on-road efficiency.Data Preprocessing Technology is by adopting
The initial data collected is handled, and identifies the simultaneously defective in quality data of mending tape, while supplementing detection system and failing to acquire
The road traffic flow parameter information arrived, to guarantee the validity, accuracy and integrality of detection system detection data.
The adaptive traffic control system in Sydney (Sydney Coordinated Adaptive Traffic System, letter
Claim SCATS or abbreviation SCATS system), by New South Wales,Australia road traffic office, the 1970s, research is opened
Hair is one of current several advanced urban traffic signal control systems rare in the world.Ring coil detector is due to it
The advantages that technology maturation, performance are stable, cost is relatively low, is widely used in city intelligent traffic signal control system, is mesh
Most road traffic sensors are applied on former world.When vehicle passes through loop coil (the hereinafter referred to as line that is embedded under road surface
Circle) when can cause the variation of coil magnetic field, detector calculates flow, saturation degree, Period Start Time and the length of vehicle accordingly
The traffic parameters such as degree, and it is uploaded to central control system, to meet the needs of traffic control system.Coil checker is usually embedded
Under the road surface before the Way in stop line of intersection.SCATS letter control system can be detected according to coil checker
Vehicle flowrate and saturation degree, dynamic adjust control parameter.Saturation degree is that SCATS system is acquired according to coils such as flow and time headways
Master data the data that are calculated are further processed, theoretically have positively related relationship with flow, therefore respectively with saturation
Degree and flow draw the binary crelation figure of the two as reference axis, and approximate linear relationship should be presented under normal circumstances.About line
The detection of circle operating condition is all being all the time a regular works as equipment O&M link by manually performing, action
Also being only to look at detector has no signal to pass back and registered, and can not judge coil whether pass back it is normal, be able to reflect reality
The workable data of border traffic condition.
Loop data quality is seldom studied as a problem in science or technical problem, and existing research is mostly to use
The relationship boundary of saturation degree and flow is arranged to judge exceptional data point in the method linearly returned to.However such method can only needle
Dynamic data exchange manual operations to each coil, it is difficult to which automation executes in batches, and it is even more impossible to utilize machine learning method to more
The data problem of subdivision is diagnosed.
Summary of the invention
The object of the present invention is to provide a kind of SCATS system detector data outliers online test methods, pass through research
Ring coil detector detection before being installed on intersection entrance driveway stop line in SCATS intelligent traffic signal control system
The preprocess method of data, to guarantee validity, the accuracy of detection data, it is ensured that the normal performance of SCATS system function mentions
The operational effect of high system.
The technical solution adopted by the present invention is that:
A kind of online test method of SCATS system detector data outliers, its step are as follows:
(1) SCATS system data is extracted from database, and by intersection number, detector number, chronological order
Arrangement;
(2) judgement that the road traffic flow data of extraction are carried out with zero data, will continuously be zero in traffic flow data
Time span be classified as abnormal data beyond the zero data of time interval, other are classified as normal data;
(3) judgement that the normal data after progress zero data judgement is carried out to abnormal data, above-mentioned normal data is distinguished
It is examined through magnitude of traffic flow threshold test, traffic flow parameter consistency check, magnitude of traffic flow statistical law, meets test stone
For normal data, not meeting test stone is abnormal data.The pretreatment of the data of road traffic flow of the invention be through
Abnormal data judgement is carried out after zero passage data judging again, and abnormal data judgement is needed by magnitude of traffic flow threshold test, handed over
Through-current capacity parameter consistency is examined, magnitude of traffic flow statistical law is examined, to guarantee validity, the accuracy of detection data, it is ensured that
The normal performance of SCATS system function, improves the operational effect of system.
Further, as follows the step of the judgement of zero data in step (2):
In low road traffic flow, the arrival of vehicle is random, obedience Poisson distribution, then time headway is exactly
Quantum condition entropy;Poisson distribution fundamental formular are as follows:
In formula: P (k)-reaches the probability of k vehicle in counting interval t;
λ-unit interval average arrival rate (/s);
The each counting interval duration (s) of t-;
E-natural logrithm bottom, takes 2.71828;
By formula (1) it is found that the probability for reaching (k=0) without vehicle in counting interval t is
P (0)=e-λt (2)
Above formula shows to be spaced in t in the specific time, such as reaches without vehicle, then upper train reaches between the arrival of lower train,
Time headway at least t, that is to say, that P (0) is also the probability that time headway is equal to or more than t, then
P (h >=t)=e-λt (3)
Then probability of the time headway less than t is then
P (h < t)=1-e-λt (4)
If Q indicates the volume of traffic hourly, λ=Q/3600, formula (4) can be write as
P (h < t)=1-e-Qt/3600 (5)
It can be obtained by formula (5)
Corresponding probability threshold value p is set, if the time span h that the road Traffic Volume data of detection are continuously zero is greater than meter
Obtained time interval t, then the zero data of the preliminary judgement period is problem data;With f (t) indicate to continuously be zero number
According to judging result, as shown in formula (7):
Further, the probability threshold value p and magnitude of traffic flow Q should be set according to different traffic flows per hour.Due to handing over
Through-flow randomness has very big difference under different traffic flow modes, such as the position of intersection, morning peak, evening peak, flat
The case where peak and traffic congestion and non-congestion.Therefore corresponding probability threshold value p and traffic per hour should be set according to various situations
Flow Q, differentiates zero data.
Further, by obtained time interval t and green light signals time length comparison, if the magnitude of traffic flow number in some period
According to more than multiple periods being all continuously zero, can tentatively study and judge as abnormal data;In this period, if it is above-mentioned many places or more occur
Situation, it may be determined that this detector is abnormal;If data are normal in time period, continuous multiple weeks that statistical detector records in one day
It more than the phase is all the sum of zero data, compared with the total amount of data of detector one day record, if zero data amount accounting is more than sum
According to the 1/3 of amount, it may be determined that this detector is abnormal.
Further, the magnitude of traffic flow threshold test in step (3) includes:
The maximum value y that the road traffic flow data that fixed location detects are likely to occur there are onemax, minimum value
It is 0, if road traffic flow data are (0, ymax) it is then normal data in range, if road traffic flow data are more than ymaxThen
For abnormal data.
Further, the maximum value y for the road traffic flow data that fixed location detectsmaxAs shown in formula (8):
In formula: qsThe saturation volume rate that can occur during the signals such as-every lane road
PHASE-long green light time, i.e., a certain period green light show duration
If (the road traffic flow data detected in unit s) are in threshold value (0, q by long green light time Ts* T/3600) in range
It is then normal data;If more than qs* T/3600, then it is assumed that traffic flow data is abnormal data.
Further, the traffic flow parameter consistency check in step (3) includes:
1. when the road traffic flow of detection and DS are simultaneously zero, then the road traffic flow is normal data, if two
Person is not zero simultaneously, then it is assumed that the road traffic flow of detection is abnormal data;
2. set DS a max-thresholds, if detection road traffic flow between 0 and max-thresholds, the road
The magnitude of traffic flow is normal data, if being more than max-thresholds, then it is assumed that the road traffic flow of detection is abnormal data;
Wherein DS=[green- (unused green)]/green (9)
Green: a certain period green light shows duration, unused green: greater than or less than every lane standard following distance when
Between;DS is to refer to that the green time utilized by wagon flow and green light show the ratio between time, value used in SCATS " saturation degree "
For the numerator value of percentage.
Further, the traffic flow statistics rule in step (3), which is examined, includes:
1. can be obtained by (9) formula and traffic flow statistics rule: the safe minimum of standard following distance average time
In formula: PHASE-long green light time, i.e., a certain period green light show duration
DS-saturation degree
The vehicle flowrate detected during VOLUME-green light
ThThe average time of expression standard following distance, ThThere are a safe minimums, if ThLess than the safe minimum,
The road traffic flow for then thinking detection is abnormal data, if ThGreater than the safe minimum, then it is assumed that the road traffic of detection
Flow is normal data;
2. if synchronization, wherein a certain lane of the detector of the same same phase in crossing inlet road detection compared with
When the traffic flow data of fractional value and the larger value of traffic flow data in other lanes differ by more than certain numerical value, determine
The road traffic flow of the fractional value is abnormal data;If synchronization, the detector of the same same phase in crossing inlet road
The road traffic flow data difference of detection is less than the numerical value of the restriction, determines that the road traffic flow of the fractional value is normal
Data.
Further, the SCATS system data include intersection number, detector number, the date, start time in period,
Long green light time, saturation degree, flow.
Beneficial effects of the present invention: by being installed on intersection in research SCATS intelligent traffic signal control system
The preprocess method of ring coil detector detection data before entrance driveway stop line, to guarantee validity, the standard of detection data
True property, it is ensured that the normal performance of SCATS system function improves the operational effect of system.
Detailed description of the invention
Fig. 1 is flow diagram of the invention.
Specific embodiment
Next combined with specific embodiments below invention is further explained, but does not limit the invention to these tools
Body embodiment.One skilled in the art would recognize that present invention encompasses may include in Claims scope
All alternatives, improvement project and equivalent scheme.
Rejecting outliers are carried out with the SCATS whistle control system data instance of certain urban road intersection referring to Fig. 1.
A kind of online test method of SCATS system detector data outliers, its step are as follows:
1. data sorting
(1), the original SCATS data of Coil Detector are extracted from database, the SCATS system data includes intersecting
Mouth number, detector number, date, start time in period, long green light time, saturation degree, flow, data are numbered by intersection,
Detector number, date-time successively successively sort.Specific sequence is as shown in table 1:
Table 1
(2), by the reading data to have sorted into program.
It will continuously be zero in traffic flow data 2. pair road traffic flow data extracted carry out the judgement of zero data
Time span is classified as abnormal data beyond the zero data of time interval, other are classified as normal data;Specific step is as follows:
(1), the basic knowledge run according to road traffic flow, in low road traffic flow, the arrival of vehicle is
Random, Poisson distribution is obeyed, then time headway is exactly quantum condition entropy.Poisson distribution fundamental formular are as follows:
In formula: P (k)-reaches the probability of k vehicle in counting interval t;
λ-unit interval average arrival rate (/s);
The each counting interval duration (s) of t-;
E-natural logrithm bottom, takes 2.71828.
By formula (1) it is found that the probability for reaching (k=0) without vehicle in counting interval t is
P (0)=e-λt (2)
Above formula shows to be spaced in t in the specific time, such as reaches without vehicle, then upper train reaches between the arrival of lower train,
Time headway at least t, that is to say, that P (0) is also the probability that time headway is equal to or more than t, then
P (h >=t)=e-λt (3)
Then probability of the time headway less than t is then
P (h < t)=1-e-λt (4)
If Q indicates the volume of traffic hourly, λ=Q/3600, formula (4) can be write as
P (h < t)=1-e-Qt/3600 (5)
By above-mentioned analysis, the probability that an at least vehicle reaches in time interval t can be obtained.According to daytime and night
Concrete condition determines suitable probability threshold value, obtains corresponding time interval t, if record traffic data be continuously zero when
Between span be more than t, can tentatively study and judge as abnormal data, abnormal data screening when in this, as road traffic flow data being zero
Criterion.
(2), the judgement of zero data:
It can be obtained by formula (5)
Due to the randomness of traffic flow, very big difference is had under different traffic flow modes, position, morning such as intersection
The case where peak, evening peak, flat peak and traffic congestion and non-congestion, therefore corresponding probability threshold should be set according to various situations
Value, differentiates zero data.If the time span h that the traffic data of detection is continuously zero is greater than t, can be with preliminary judgement
Zero data is problem data;It is indicated to the continuous judging result for zero data, as shown in formula (7) with f (t):
Specific example is as follows:
If probability threshold value p=0.9, the corresponding flat peak hourly traffic volume of urban road takes Q=400/h, and (value is more herein
Smaller value in the flat peak hourly traffic volume data of a detector), time interval is calculatedIt is corresponding
Urban road ebb hourly traffic volume takes Q=100/h (herein in the ebb hourly traffic volume data of the multiple detectors of value
Smaller value), obtain time interval t=37.8 (s).It is found that urban road intersection lane is being handed over compared with green light signals duration
There should be vehicle to pass through during each green light when logical peak or flat peak, in traffic ebb, continuous two signal period green lights
Period should have vehicle to pass through.Result is calculated value herein, and specific value should also position according to intersection, specific road
Traffic condition determines.We are using continuous three periods as standard, can if traffic flow data continuous three more than the period are all zero
Tentatively study and judge as abnormal data.We take at 7 points to 22 points for a period, if occurring traffic flow data company in time period
Continuous three more than the period are all zero, be can determine that as abnormal data;It, can if occurring the above above situation at 3 within this period
Determine detector exception.If data are normal in time period, statistical detector recorded in one day continuous three it is more than the period all
It is the sum of zero data, compared with the total amount of data of detector one day record, if zero data amount accounting is more than the 1/ of total amount of data
3, it may be determined that this detector is abnormal.If table 2 is to detect certain section of abnormal zero data example:
Table 2
The magnitude of traffic flow detected in 12 points to 13 periods herein is continuously zero, it is clear that is detector exception.
3. the normal data after progress zero data judgement to be carried out to the judgement of abnormal data, above-mentioned normal data is passed through respectively
Magnitude of traffic flow threshold test, traffic flow parameter consistency check, magnitude of traffic flow statistical law are examined, and meeting test stone is
Normal data, not meeting test stone is abnormal data.It is specific as follows:
(1), road traffic flow threshold test:
Since road passage capability is limited, so the road traffic flow data that fixed location detects do not exceed generally
One maximum value y being likely to occurmax, and its minimum value is 0, when data screening, can consider to be more than (0, ymax) range data
For abnormal data.
In formula: qsThe saturation volume rate that can occur during the signals such as-every lane road
PHASE-long green light time, i.e., a certain period green light show duration
The saturation volume rate q that can occur during setting every lane green light signalss=2000, unit veh/h.Therefore it can define
(threshold range of detection flows is (0, q to long green light time T in unit s)s*T/3600).If being more than this range, then it is assumed that inspection
Measured data is abnormal data.It is specific as shown in table 3:
Table 3
The threshold range of detection flows is (0,18) in first data long green light time T;Detection in Article 2 long green light time T
The threshold range of flow is (0,14);The threshold range of detection flows is (0,15) in Article 3 long green light time T.Obviously these all
For abnormal data.
(2), road traffic flow parameter consistency is examined:
Having an item data in the data of SCATS system record is " saturation degree " DS
DS=[green- (unused green)]/green (9)
Green: a certain period green light shows duration, unused green: greater than or is less than every lane standard following distance
Time." saturation degree " (DS) used in SCATS refers to that the green time utilized by wagon flow and green light show the ratio between time.
Value is the numerator value of percentage.
1. DS also should be zero when the vehicle flowrate of detection is zero;In turn when DS is zero, vehicle flowrate detected
It should be zero.When the road traffic flow of detection and DS are simultaneously zero, then the road traffic flow is normal data, if the two
It is not simultaneously zero, then it is assumed that detection data is abnormal data.It is specific as shown in table 4:
Table 4
Saturation degree DS and data on flows are not simultaneously zero in table, are abnormal data.
2. the value of DS has a range, taking the threshold range of DS is (0,200), if the road traffic flow saturation of detection
Degree is between 0 and 200, then the road traffic flow is normal data, if more than 200, it is meant that is less than lane standard following distance
Time it is cumulative and be equal to green time, that is, green time by Ultra-High Efficiency using having more one times, this is obviously unreasonable, can
Think that detection data is abnormal data.It is specific as shown in table 5:
Table 5
Saturation degree DS value is more than 200 in table, is abnormal data.
(3), road traffic flow statistical law is examined:
1. can be obtained by (8) formula and traffic flow statistics rule: the safe minimum of standard following distance average time
In formula: PHASE-long green light time, i.e., a certain period green light show duration
DS-saturation degree
The vehicle flowrate detected during VOLUME-green light
ThThe average time of expression standard following distance, ThThere is a safe minimum (if being less than the value, it is believed that vehicle spacing
It is too small, dangerous), take Th=1s, if Th< 1, then it is assumed that the road traffic flow data of detection are abnormal data, if Th> 1, then
The road traffic flow data for thinking detection are normal data.It is specific as shown in table 6:
Table 6
Data T in tablehValue can determine that less than 1 as abnormal data.
2. if synchronization, the data of the detector of the same same phase in crossing inlet road, one of detection are zero,
The data of another or another two detection are larger, when difference is more than 20, can study and judge this zero data and not conform to the actual conditions, determine the road
Road traffic flow data is abnormal data.If the data of three lanes record are respectively d1, d2, d3, it is assumed that d1 zero, if | d1-
D2 | > 20 or | d1-d3 | > 20, can determine that d1 be abnormal data.If difference is when being less than 20, to determine the zero data for normal number
According to.It is specific as shown in table 7:
Table 7
Same intersection 123001, the detector of the same same phase of entrance driveway synchronization have JC0101, JC0102,
JC0103, wherein the data of JC0101 are 0, and the data of detector JC0102 are 21, are more than threshold value 20, belong to abnormal data,
The data for determining detector JC0101 acquisition are abnormal data.Intersection 123002 is similarly.
Claims (9)
1. a kind of online test method of SCATS system detector data outliers, its step are as follows:
(1) SCATS system data is extracted from database, and by intersection number, detector number, chronological order row
Column;
(2) judgement that road traffic flow data are carried out with zero data, will continuously be zero time span in traffic flow data
Zero data beyond time interval is classified as abnormal data, other are classified as normal data;
(3) judgement that the normal data after progress zero data judgement is carried out to abnormal data, by above-mentioned normal data respectively through handing over
Through-current capacity threshold test, traffic flow parameter consistency check, magnitude of traffic flow statistical law are examined, and being positive for test stone is met
Regular data, not meeting test stone is abnormal data.
2. a kind of online test method of SCATS system detector data outliers according to claim 1, feature exist
In: the step of judgement of zero data, is as follows in step (2):
In low road traffic flow, the arrival of vehicle is random, obedience Poisson distribution, then time headway is exactly negative refers to
Number distribution;Poisson distribution fundamental formular are as follows:
In formula: P (k)-reaches the probability of k vehicle in counting interval t;
λ-unit interval average arrival rate (/s);
The each counting interval duration (s) of t-;
E-natural logrithm bottom, takes 2.71828;
By formula (1) it is found that the probability for reaching (k=0) without vehicle in counting interval t is
P (0)=e-λt (2)
Above formula shows to be spaced in t in the specific time, such as reaches without vehicle, then upper train reaches between the arrival of lower train, headstock
When away from least t, that is to say, that P (0) is also the probability that time headway is equal to or more than t, then
P (h >=t)=e-λt (3)
Then probability of the time headway less than t is then
P (h < t)=1-e-λt (4)
If Q indicates the volume of traffic hourly, λ=Q/3600, formula (4) can be write as
P (h < t)=1-e-Qt/3600 (5)
It can be obtained by formula (5)
Corresponding probability threshold value p and per hour volume of traffic Q are set, if the road Traffic Volume data of detection are continuously zero time
Span h is greater than the time interval t being calculated, then determines the zero data of the period for problem data;It is indicated with f (t) to even
Continue the judging result for zero data, as shown in formula (7):
3. a kind of online test method of SCATS system detector data outliers according to claim 2, feature exist
Volume of traffic Q is set according to different traffic flows in: the probability threshold value p and per hour.
4. a kind of online test method of SCATS system detector data outliers according to claim 2, feature exist
In: by obtained time interval t and green light signals time length comparison, if traffic flow data continuous multiple weeks in some period
More than the phase all it is zero, can tentatively studies and judges as abnormal data;In this period, if there is the above above situation in many places, it may be determined that
This detector is abnormal;If data are normal in time period, what statistical detector recorded in one day more than continuous multiple periods is all
The sum of zero data, compared with the total amount of data of detector one day record, if zero data amount accounting is more than the 1/3 of total amount of data,
It can determine this detector exception.
5. a kind of online test method of SCATS system detector data outliers described according to claim 1~one of 4,
It is characterized by: the magnitude of traffic flow threshold test in step (3) includes:
The maximum value y that the road traffic flow data that fixed location detects are likely to occur there are onemax, minimum value 0,
If road traffic flow data are (0, ymax) it is then normal data in range, if road traffic flow data are more than ymaxIt is then different
Regular data.
6. a kind of online test method of SCATS system detector data outliers according to claim 5, feature exist
In: the maximum value y for the road traffic flow data that fixed location detectsmaxAs shown in formula (8):
In formula: qsThe saturation volume rate that can occur during the signals such as-every lane road
PHASE-long green light time, i.e., a certain period green light show duration
If (the road traffic flow data detected in unit s) are in threshold value (0, q by long green light time Ts* T/3600) be then in range
Normal data;If more than qs* T/3600, then it is assumed that traffic flow data is abnormal data.
7. a kind of online test method of SCATS system detector data outliers according to claim 6, feature exist
In: the traffic flow parameter consistency check in step (3) includes:
1. then the road traffic flow is normal data, if the two is not when the road traffic flow of detection and DS are simultaneously zero
It is simultaneously zero, then it is assumed that the road traffic flow of detection is abnormal data;
2. set DS a max-thresholds, if detection road traffic flow between 0 and max-thresholds, the road traffic
Flow is normal data, if being more than max-thresholds, then it is assumed that the road traffic flow of detection is abnormal data;
Wherein DS=[green- (unused green)]/green (9)
Green: a certain period green light shows duration, unused green: greater than or less than every lane standard following distance when
Between;DS is to refer to that the green time utilized by wagon flow and green light show the ratio between time, value used in SCATS " saturation degree "
For the numerator value of percentage.
8. a kind of online test method of SCATS system detector data outliers according to claim 7, feature exist
In: the traffic flow statistics rule inspection in step (3) includes:
1. can be obtained by (9) formula and traffic flow statistics rule: the safe minimum of standard following distance average time
In formula: PHASE-long green light time, i.e., a certain period green light show duration
DS-saturation degree
The vehicle flowrate detected during VOLUME-green light
ThThe average time of expression standard following distance, ThThere are a safe minimums, if ThLess than the safe minimum, then recognize
Road traffic flow for detection is abnormal data, if ThGreater than the safe minimum, then it is assumed that the road traffic flow of detection
For normal data;
2. if synchronization, the relatively decimal in wherein a certain lane of the detector detection of the same same phase in crossing inlet road
When the traffic flow data of value and the larger value of traffic flow data in other lanes differ by more than certain numerical value, determine that this is small
The road traffic flow of numerical value is abnormal data;If synchronization, the detector of the same same phase in crossing inlet road is detected
Road traffic flow data difference be less than the numerical value of the restriction, determine the road traffic flow of the fractional value for normal number
According to.
9. a kind of online test method of SCATS system detector data outliers according to claim 1, feature exist
In: the SCATS system data includes intersection number, detector number, date, start time in period, long green light time, saturation
Degree, flow.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811213599.1A CN109272760B (en) | 2018-10-18 | 2018-10-18 | Online detection method for abnormal data value of SCATS system detector |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811213599.1A CN109272760B (en) | 2018-10-18 | 2018-10-18 | Online detection method for abnormal data value of SCATS system detector |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109272760A true CN109272760A (en) | 2019-01-25 |
CN109272760B CN109272760B (en) | 2020-05-05 |
Family
ID=65194179
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811213599.1A Active CN109272760B (en) | 2018-10-18 | 2018-10-18 | Online detection method for abnormal data value of SCATS system detector |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109272760B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110569912A (en) * | 2019-09-09 | 2019-12-13 | 自然资源部第一海洋研究所 | Method for removing singular values of observation data of sea water profile |
CN114973741A (en) * | 2022-06-17 | 2022-08-30 | 浙江大华技术股份有限公司 | Abnormal data processing method and device, storage medium and electronic device |
CN116631195A (en) * | 2023-07-20 | 2023-08-22 | 江西师范大学 | Regional abnormality detection method based on urban sub-region hot spot crossing mining |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000036096A (en) * | 1998-07-21 | 2000-02-02 | Matsushita Electric Ind Co Ltd | Traffic control method and device |
EP1549092A1 (en) * | 2003-12-22 | 2005-06-29 | Nortel Networks Limited | Wireless data traffic statistics |
CN103903452A (en) * | 2014-03-11 | 2014-07-02 | 东南大学 | Traffic flow short time predicting method |
CN103971520A (en) * | 2014-04-17 | 2014-08-06 | 浙江大学 | Traffic flow data recovery method based on space-time correlation |
CN104537847A (en) * | 2014-12-19 | 2015-04-22 | 上海物联网有限公司 | Terrestrial magnetism vehicle detection devices having mutual diagnostic function |
US20160328654A1 (en) * | 2015-05-04 | 2016-11-10 | Agt International Gmbh | Anomaly detection for context-dependent data |
CN106971538A (en) * | 2017-04-26 | 2017-07-21 | 同济大学 | A kind of method for drafting of the macroscopical parent map of Regional Road Network traffic behavior |
CN107591001A (en) * | 2017-09-07 | 2018-01-16 | 山东大学 | Expressway Traffic Flow data filling method and system based on on-line proving |
-
2018
- 2018-10-18 CN CN201811213599.1A patent/CN109272760B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000036096A (en) * | 1998-07-21 | 2000-02-02 | Matsushita Electric Ind Co Ltd | Traffic control method and device |
EP1549092A1 (en) * | 2003-12-22 | 2005-06-29 | Nortel Networks Limited | Wireless data traffic statistics |
CN103903452A (en) * | 2014-03-11 | 2014-07-02 | 东南大学 | Traffic flow short time predicting method |
CN103971520A (en) * | 2014-04-17 | 2014-08-06 | 浙江大学 | Traffic flow data recovery method based on space-time correlation |
CN104537847A (en) * | 2014-12-19 | 2015-04-22 | 上海物联网有限公司 | Terrestrial magnetism vehicle detection devices having mutual diagnostic function |
US20160328654A1 (en) * | 2015-05-04 | 2016-11-10 | Agt International Gmbh | Anomaly detection for context-dependent data |
CN106971538A (en) * | 2017-04-26 | 2017-07-21 | 同济大学 | A kind of method for drafting of the macroscopical parent map of Regional Road Network traffic behavior |
CN107591001A (en) * | 2017-09-07 | 2018-01-16 | 山东大学 | Expressway Traffic Flow data filling method and system based on on-line proving |
Non-Patent Citations (2)
Title |
---|
徐程 等: "动态交通数据异常值的实时筛选与恢复方法", 《哈尔滨工程大学学报》 * |
魏国荣: "基于SCATS的动态交通数据预处理方法研究", 《万方数据》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110569912A (en) * | 2019-09-09 | 2019-12-13 | 自然资源部第一海洋研究所 | Method for removing singular values of observation data of sea water profile |
CN110569912B (en) * | 2019-09-09 | 2022-02-01 | 自然资源部第一海洋研究所 | Method for removing singular values of observation data of sea water profile |
CN114973741A (en) * | 2022-06-17 | 2022-08-30 | 浙江大华技术股份有限公司 | Abnormal data processing method and device, storage medium and electronic device |
CN116631195A (en) * | 2023-07-20 | 2023-08-22 | 江西师范大学 | Regional abnormality detection method based on urban sub-region hot spot crossing mining |
CN116631195B (en) * | 2023-07-20 | 2023-10-13 | 江西师范大学 | Regional abnormality detection method based on urban sub-region hot spot crossing mining |
Also Published As
Publication number | Publication date |
---|---|
CN109272760B (en) | 2020-05-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108346292B (en) | Urban expressway real-time traffic index calculation method based on checkpoint data | |
CN103646542B (en) | A kind of Forecasting Methodology of Evaluating traffic impact area and device | |
CN103021176B (en) | Discriminating method based on section detector for urban traffic state | |
Wang et al. | Can single-loop detectors do the work of dual-loop detectors? | |
CN103886756B (en) | Based on the freeway network method for detecting operation state of OBU | |
CN104933860B (en) | Bus traffic congestion delay time at stop Forecasting Methodology based on gps data | |
CN104408925B (en) | Crossing evaluation of running status method based on display radar | |
CN109272760A (en) | A kind of online test method of SCATS system detector data outliers | |
CN110728842A (en) | Abnormal driving early warning method based on reasonable driving range of vehicles at intersection | |
CN110363985B (en) | Traffic data analysis method, device, storage medium and equipment | |
CN110164132B (en) | Method and system for detecting road traffic abnormity | |
CN104240499A (en) | Abnormal congestion point judgment method based on microwave data | |
Kazagli et al. | Estimation of arterial travel time from automatic number plate recognition data | |
CN105825669A (en) | System and method for identifying urban expressway traffic bottlenecks | |
CN101739825A (en) | GPS floating vehicle-based traffic data fault identification and recovery method | |
CN103903433A (en) | Real-time dynamic judgment method and device for road traffic state | |
Tak et al. | Real-time travel time prediction using multi-level k-nearest neighbor algorithm and data fusion method | |
CN101882374A (en) | System and method for analysis of comprehensive information on vehicle trip distribution | |
CN105355049A (en) | Highway running state evaluation method based on macroscopic fundamental diagram | |
CN102855760A (en) | On-line queuing length detection method based on floating vehicle data | |
CN113870570B (en) | ETC-based road network operation state method, system and storage medium | |
CN115691120A (en) | Congestion identification method and system based on highway running water data | |
CN104700630A (en) | Method and system for monitoring vehicle flow of highway | |
CN102426783B (en) | Low flow road traffic incident detection method based on vehicle tracking | |
CN113436432A (en) | Method for predicting short-term traffic risk of road section by using road side observation data |
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 | ||
CP01 | Change in the name or title of a patent holder |
Address after: 310012 1st floor, building 1, 223 Yile Road, Hangzhou City, Zhejiang Province Patentee after: Yinjiang Technology Co.,Ltd. Address before: 310012 1st floor, building 1, 223 Yile Road, Hangzhou City, Zhejiang Province Patentee before: ENJOYOR Co.,Ltd. |
|
CP01 | Change in the name or title of a patent holder |