CN109272760B - Online detection method for abnormal data value of SCATS system detector - Google Patents
Online detection method for abnormal data value of SCATS system detector Download PDFInfo
- Publication number
- CN109272760B CN109272760B CN201811213599.1A CN201811213599A CN109272760B CN 109272760 B CN109272760 B CN 109272760B CN 201811213599 A CN201811213599 A CN 201811213599A CN 109272760 B CN109272760 B CN 109272760B
- Authority
- CN
- China
- Prior art keywords
- data
- traffic flow
- zero
- abnormal
- 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.)
- Active
Links
Images
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
An on-line detection method for abnormal data values of a SCATS system detector comprises the following steps: (1) extracting SCATS system data from a database, and arranging according to the intersection number, the detector number and the time sequence; (2) judging zero data of the extracted road traffic flow data, classifying the zero data with continuous zero time span exceeding the time interval in the traffic flow data into abnormal data, and classifying the other data into normal data; (3) and (3) judging abnormal data of the normal data subjected to zero data judgment, and respectively carrying out traffic flow threshold value inspection, traffic flow parameter consistency inspection and traffic flow statistical rule inspection on the normal data to obtain normal data meeting the inspection standard and abnormal data not meeting the inspection standard. The invention ensures the validity and accuracy of the detection data, ensures the normal exertion of the functions of the SCATS system and improves the operation effect of the system.
Description
Technical Field
The invention belongs to the field of traffic control, and relates to an online detection method for abnormal data values of a SCATS system detector.
Background
Along with the popularization of intelligent traffic systems, urban intelligent traffic signal control systems are more and more widely applied. One of the main differences between an intelligent traffic signal control system and a conventional control system is the technical application in the real-time acquisition, transmission, processing and storage of road traffic data. With the continuous progress of data acquisition technology, the control range of a signal control system is larger and larger, the types of acquired information are more and more, and the data volume is also larger and larger. In the process of collecting, transmitting and storing road traffic information data, due to the faults of detector equipment, communication faults, software operation emergencies and the like, the road traffic data necessarily contains some error, lost and abnormal data, and the effectiveness and the accuracy of the data are influenced. If the data with quality problems are directly adopted, certain influence is certainly generated on the operation benefit of the signal control system. The data preprocessing technology identifies and repairs data with quality problems by processing the collected original data, and supplements road traffic flow parameter information which cannot be collected by a detection system, so as to ensure the validity, accuracy and integrity of the detection data of the detection system.
The Sydney Coordinated Adaptive Traffic control System (SCATS, or SCATS System) was developed by the state road Traffic bureau of new south wales in australia in the 70 th century and is one of the few advanced urban Traffic signal control systems in the world. The annular coil detector is widely applied to an urban intelligent traffic signal control system due to the advantages of mature technology, stable performance, lower cost and the like, and is the most widely applied road traffic sensor in the world at present. When a vehicle passes through a loop coil (hereinafter referred to as a coil) buried under the road surface, the magnetic field of the coil changes, and the detector calculates traffic parameters such as the flow, the saturation, the cycle start time and the cycle length of the vehicle according to the traffic parameters and uploads the traffic parameters to the central control system so as to meet the requirements of the traffic control system. The coil detector is usually buried under the road surface in front of the stop line in the direction of the intersection entrance. The SCATS information control system can dynamically adjust control parameters according to the traffic flow and the saturation detected by the coil detector. The saturation is data obtained by further processing and calculating the SCATS system according to basic data acquired by coils such as flow, headway and the like, and has a positive correlation with the flow theoretically, so that a binary relation graph of the saturation and the flow is drawn by taking the saturation and the flow as coordinate axes respectively, and an approximate linear relation is presented under a normal condition. The detection of the working condition of the coil is always performed manually as a routine work of an operation and maintenance link of the equipment, and the work content is only to check whether the detector sends back a signal and register, but cannot judge whether the coil sends back normal usable data capable of reflecting the actual traffic condition.
Coil data quality is rarely researched as a scientific problem or a technical problem, and most of the existing researches adopt a linear regression method to set a relation boundary of saturation and flow so as to judge an abnormal data point. However, such methods can only be operated manually for each coil independently, are difficult to be performed in batch automatically, and cannot be used for diagnosing more subdivided data problems by using a machine learning method.
Disclosure of Invention
The invention aims to provide an online detection method for abnormal data values of a SCATS system detector, which is used for ensuring the validity and accuracy of detection data, ensuring the normal function of the SCATS system and improving the operation effect of the system by researching a preprocessing method for the detection data of a loop coil detector arranged in front of a stop line of an entrance way of a road intersection in an SCATS intelligent traffic signal control system.
The technical scheme adopted by the invention is as follows:
an on-line detection method for abnormal data values of a SCATS system detector comprises the following steps:
(1) extracting SCATS system data from a database, and arranging according to the intersection number, the detector number and the time sequence;
(2) judging zero data of the extracted road traffic flow data, classifying the zero data with continuous zero time span exceeding time interval in the traffic flow data as abnormal data, and classifying the other zero data as normal data;
(3) and (3) judging abnormal data of the normal data subjected to zero data judgment, and respectively carrying out traffic flow threshold value inspection, traffic flow parameter consistency inspection and traffic flow statistical rule inspection on the normal data to obtain normal data meeting the inspection standard and abnormal data not meeting the inspection standard. The preprocessing of the road traffic flow data is to judge abnormal data after zero data judgment, and the abnormal data judgment needs to be carried out by traffic flow threshold value inspection, traffic flow parameter consistency inspection and traffic flow statistical rule inspection so as to ensure the validity and accuracy of the detection data, ensure the normal exertion of the SCATS system function and improve the operation effect of the system.
Further, the step of determining zero data in step (2) is as follows:
under the condition of low road traffic flow, the arrival of vehicles is random and obeys poisson distribution, and the time interval of the vehicle head is negative exponential distribution; the basic formula of poisson distribution is:
in the formula: p (k) -the probability of reaching k vehicles within the counting interval t;
λ -average arrival rate per unit time interval (vehicle/s);
t-the duration(s) of each counting interval;
e-base of natural logarithm, taking 2.71828;
as can be seen from equation (1), the probability that no vehicle arrives (k is 0) within the count interval t is
P(0)=e-λt(2)
The above formula shows that in a specific time interval t, if no vehicle arrives, the headway is at least t between the last arrival and the next arrival, i.e. P (0) is the probability that the headway is equal to or greater than t, and therefore
P(h≥t)=e-λt(3)
The probability that the headway is less than t is
P(h<t)=1-e-λt(4)
If Q represents the hourly traffic volume, λ ═ Q/3600, equation (4) can be written as
P(h<t)=1-e-Qt/3600(5)
From the formula (5)
Setting a corresponding probability threshold value p, and if the time span h that the detected road traffic data is continuously zero is greater than the calculated time interval t, preliminarily judging that the zero data of the time period is problem data; f (t) represents the judgment result of continuous zero data, as shown in formula (7):
further, the probability threshold value p and the hourly traffic flow Q should be set according to different traffic flows. Due to the randomness of traffic flow, the traffic flow conditions can be greatly different, such as the positions of intersections, early peaks, late peaks, flat peaks, and the situations of traffic jam and non-jam. Therefore, the probability threshold p and the hourly traffic flow Q are set according to various situations, and zero data are determined.
Further, the obtained time interval t is compared with the duration of the green light signal, and if the traffic flow data are zero in more than a plurality of continuous periods in a certain time period, abnormal data can be preliminarily researched and judged; in the time period, if the above conditions occur at a plurality of places, the detector can be determined to be abnormal; if the data in the time period is normal, counting the total number of zero data recorded by the detector in more than a plurality of continuous periods in one day, comparing the total data amount recorded by the detector in one day, and if the total number of the zero data amount exceeds 1/3 of the total data amount, determining that the detector is abnormal.
Further, the traffic flow threshold value check in step (3) includes:
there is a maximum value y that may occur in the road traffic flow data detected at the fixed pointmaxThe minimum value is 0, if the road traffic flow data is (0, y)max) The data is normal data if the range exceeds ymaxThe data is anomalous.
Further, the maximum value y of the road traffic flow data detected at the fixed pointmaxAs shown in formula (8):
in the formula: q. q.ssSaturation flow rate that can occur during signals for each road, etc
PHASE-duration of green light, i.e. duration of green light display of a certain period
If the road traffic flow data detected within the green light time period T (unit is s) is at the threshold value (0, q)sT/3600) is normal data; if q is exceededsT/3600, the traffic flow data is considered to be abnormal data.
Further, the traffic flow parameter consistency check in the step (3) comprises:
①, when the detected road traffic flow and DS are both zero, the road traffic flow is normal data, if the two are not zero, the detected road traffic flow is considered as abnormal data;
② setting a maximum threshold value of DS, if the detected road traffic flow is between 0 and the maximum threshold value, the road traffic flow is normal data, if the detected road traffic flow exceeds the maximum threshold value, the detected road traffic flow is considered abnormal data;
the system comprises a plurality of lanes, wherein each lane comprises a DS (green- (unused green) ]/green (9) green, the display time length of a green light in a certain period, and the unused green is the time which is more than or less than the standard vehicle distance of each lane; DS is "saturation" used for SCATS, which is the ratio of the green time used by the traffic to the green display time, and takes the value of a percentage of the molecular value.
Further, the traffic flow statistical rule test in the step (3) comprises:
① formula (9) and traffic flow statistical rule show that the safety minimum value of the average time of standard inter-vehicle distance
In the formula: PHASE-duration of green light, i.e. duration of green light display of a certain period
DS-degree of saturation
VOLUME-traffic flow detected during green light
ThMean time, T, representing standard inter-vehicle distancehThere is a safety minimum if ThIf the detected road traffic flow is less than the safety minimum value, the detected road traffic flow is considered as abnormal data, and if T is less than the safety minimum valuehGreater than the safety minimumIf so, the detected road traffic flow is considered as normal data;
② if the difference between the traffic flow data of a small value of one lane detected by the detector of the same phase of the entrance lane of the same intersection and the traffic flow data of a large value of the other lane exceeds a certain value at the same time, determining that the road traffic flow of the small value is abnormal data, and if the difference between the traffic flow data of the road detected by the detector of the same phase of the entrance lane of the same intersection does not exceed the limited value at the same time, determining that the road traffic flow of the small value is normal data.
Further, the SCATS system data comprises an intersection number, a detector number, a date, a period starting time, a green light duration, a saturation and a flow.
The invention has the beneficial effects that: by researching the preprocessing method of the detection data of the annular coil detector arranged in front of the stop line of the road intersection entrance in the SCATS intelligent traffic signal control system, the validity and the accuracy of the detection data are ensured, the normal function of the SCATS system is ensured, and the operation effect of the system is improved.
Drawings
FIG. 1 is a schematic flow chart of the present invention.
Detailed Description
The present invention is further illustrated by the following examples, which are not intended to limit the invention to these embodiments. It will be appreciated by those skilled in the art that the present invention encompasses all alternatives, modifications and equivalents as may be included within the scope of the claims.
Referring to fig. 1, abnormal value detection is performed by taking SCATS signal control system data of a certain urban road intersection as an example.
An on-line detection method for abnormal data values of a SCATS system detector comprises the following steps:
1. data ordering
(1) And extracting original SCATS data detected by the coil from a database, wherein the SCATS system data comprises an intersection number, a detector number, a date, a period starting moment, a green light duration, a saturation and a flow rate, and the data are sequentially sequenced according to the intersection number, the detector number and the date time. The specific sequence is shown in table 1:
TABLE 1
(2) And reading the sequenced data into a program.
2. Judging zero data of the extracted road traffic flow data, classifying the zero data with continuous zero time span exceeding the time interval in the traffic flow data into abnormal data, and classifying the other data into normal data; the method comprises the following specific steps:
(1) according to basic knowledge of road traffic flow operation, under the condition of low road traffic flow, the arrival of vehicles is random and obeys poisson distribution, and the time interval of the vehicle head is negative exponential distribution. The basic formula of poisson distribution is:
in the formula: p (k) -the probability of reaching k vehicles within the counting interval t;
λ -average arrival rate per unit time interval (vehicle/s);
t-the duration(s) of each counting interval;
e-base of natural logarithm, 2.71828.
As can be seen from equation (1), the probability that no vehicle arrives (k is 0) within the count interval t is
P(0)=e-λt(2)
The above formula shows that in a specific time interval t, if no vehicle arrives, the headway is at least t between the last arrival and the next arrival, i.e. P (0) is the probability that the headway is equal to or greater than t, and therefore
P(h≥t)=e-λt(3)
The probability that the headway is less than t is
P(h<t)=1-e-λt(4)
If Q represents the hourly traffic volume, λ ═ Q/3600, equation (4) can be written as
P(h<t)=1-e-Qt/3600(5)
By the above analysis, the probability of at least one vehicle arriving within the time interval t can be obtained. And determining a proper probability threshold value according to specific conditions in the daytime and at night to obtain a corresponding time interval t, and if the recorded traffic data continuously become zero and the time span exceeds t, preliminarily studying and judging the data as abnormal data to serve as an abnormal data screening criterion when the road traffic data is zero.
(2) And judging zero data:
from the formula (5)
Due to the randomness of traffic flow, there are great differences in different traffic flow states, such as positions of intersections, early peaks, late peaks, flat peaks, and traffic jam and non-jam situations, so corresponding probability thresholds should be set according to various situations to discriminate zero data. If the time span h of the detected traffic data continuously being zero is larger than t, the zero data can be preliminarily determined to be problem data; f (t) represents the judgment result of continuous zero data, as shown in formula (7):
specific examples are as follows:
setting the probability threshold p to be 0.9, taking the average peak hour traffic quantity Q of the corresponding urban road to be 400/h (the value is the smaller value in the average peak hour traffic quantity data of a plurality of detectors), and calculating to obtain the time intervalThe traffic quantity Q corresponding to the urban road low peak hour is 100/h (the smaller value in the low peak hour traffic data of a plurality of detectors is taken here)) The time interval t is 37.8(s). Compared with the duration of the green light signal, the urban road intersection lane should have the vehicle to pass during each green light period when the traffic is high or low, and should have the vehicle to pass during the green light periods of two continuous signal periods when the traffic is low. The result is a theoretical calculation value, and the specific value is determined according to the position of the intersection and the specific road traffic condition. We use three continuous periods as standard, if the traffic flow data is zero in more than three continuous periods, we can preliminarily study and judge it as abnormal data. Taking 7 to 22 points as a time period, and if the traffic flow data in the time period are zero in more than three continuous periods, judging the data to be abnormal data; if the above conditions occur at 3 or more times during this period, it is determined that the detector is abnormal. If the data in the time period is normal, counting the total number of zero data recorded in more than three continuous periods in one day by the detector, comparing the total data amount recorded in one day by the detector, and if the total data amount of the zero data amount exceeds 1/3 of the total data amount, determining that the detector is abnormal. As shown in table 2, for an example of detecting a certain abnormal zero data:
TABLE 2
Here, the traffic flow detected in the period from 12 to 13 is continuously zero, and it is obvious that the detector is abnormal.
3. And (3) judging abnormal data of the normal data subjected to zero data judgment, and respectively carrying out traffic flow threshold value inspection, traffic flow parameter consistency inspection and traffic flow statistical rule inspection on the normal data to obtain normal data meeting the inspection standard and abnormal data not meeting the inspection standard. The method comprises the following specific steps:
(1) and road traffic flow threshold value inspection:
road traffic flow data detected at a fixed location-due to limited road traffic capacityGenerally not exceeding a possible maximum value ymaxAnd the minimum value is 0, and the data screening can be considered to exceed (0, y)max) The range data is anomalous data.
In the formula: q. q.ssSaturation flow rate that can occur during signals for each road, etc
PHASE-duration of green light, i.e. duration of green light display of a certain period
Setting the saturation flow rate q that can occur during each lane green signals2000, in veh/h. Therefore, a threshold range of (0, q) for the detected flow rate within the green light time period T (in s) can be definedsT/3600). If the detected data exceeds the range, the detected data is considered as abnormal data. Specifically, as shown in table 3:
TABLE 3
The threshold range of the detected flow in the first data green light time length T is (0, 18); the threshold range of the detected flow within the second green light time period T is (0, 14); the threshold range of the detected flow rate in the third green light time period T is (0, 15). These are obviously anomalous data.
(2) And checking the consistency of road traffic flow parameters:
one of the data recorded by the SCATS system is 'saturation' DS
DS=[green-(unused green)]/green (9)
green: green light display duration in a certain period, unused green: a time greater or less than the standard inter-vehicle distance for each lane. The "saturation" (DS) used in the cats is a ratio of a green light time used by the traffic flow to a green light display time. The value is the molecular value of the percentage.
①, when the detected traffic flow is zero, the DS should also be zero, and conversely when the DS is zero, the detected traffic flow should also be zero, when the detected traffic flow and the DS are both zero, the traffic flow is normal data, if they are not both zero, the detected data is considered abnormal data, as shown in Table 4:
TABLE 4
The saturation DS and the flow data in the table are not zero at the same time, and are abnormal data.
② DS has a range, the threshold value range of DS is (0,200), if the detected road traffic flow saturation is between 0 and 200, the road traffic flow is normal data, if it exceeds 200, the time summation less than the standard vehicle distance of the lane is equal to the green light time, that is, the green light time is doubled by the ultra-high efficiency utilization, which is obviously unreasonable, the detected data can be considered as abnormal data, as shown in Table 5:
TABLE 5
The saturation DS value in the table exceeds 200, and the data is abnormal data.
(3) And checking a road traffic flow statistical rule:
① formula (8) and traffic flow statistical rule show that the safety minimum value of the average time of standard inter-vehicle distance
In the formula: PHASE-duration of green light, i.e. duration of green light display of a certain period
DS-degree of saturation
VOLUME-traffic flow detected during green light
ThMean time, T, representing standard inter-vehicle distancehIf there is a safety minimum (if less than the value, the distance between the vehicles is considered to be too small and unsafe), T is takenh1s, if Th<1, then it is considered asThe detected road traffic flow data is abnormal data if Th>And 1, considering the detected road traffic flow data as normal data. Specifically, as shown in table 6:
TABLE 6
Data T in the tablehThe value is less than 1, and the data can be judged as abnormal data.
② if the data detected by one of the detectors is zero and the data detected by the other or two detectors is large at the same time, if the difference exceeds 20, it can be determined that the zero data does not match the actual data, and the data of the road traffic flow is determined to be abnormal data. for example, if the data recorded by the three lanes are d1, d2 and d3, respectively, if d1 is zero, if | d1-d2| >20 or | d1-d3| >20, it can be determined that d1 is abnormal data, if the difference is not more than 20, it is determined that the zero data is normal data, as shown in table 7:
TABLE 7
The detectors of the same intersection 123001 and the same entrance lane at the same time and the same phase are JC0101, JC0102 and JC0103, wherein the data of the JC0101 is 0, the data of the detector JC0102 is 21, the data exceed the threshold value 20, the data belong to abnormal data, and the data collected by the detector JC0101 are judged to be abnormal data. The same applies to the intersection 123002.
Claims (6)
1. An on-line detection method for abnormal data values of a SCATS system detector comprises the following steps:
(1) extracting SCATS system data from a database, and arranging according to the intersection number, the detector number and the time sequence;
(2) judging zero data of the road traffic flow data, classifying the zero data of which the time span continuously becomes zero exceeds a time interval in the traffic flow data into abnormal data, and classifying the other data into normal data; the steps of the zero data judgment are as follows:
under the condition of low road traffic flow, the arrival of vehicles is random and obeys poisson distribution, and the time interval of the vehicle head is negative exponential distribution; the basic formula of poisson distribution is:
in the formula: p (k) -the probability of reaching k vehicles within the counting interval t;
λ -average arrival rate per unit time interval, in units of vehicles/s;
t-the duration of each counting interval, in units of s;
e-base of natural logarithm, taking 2.71828;
as can be seen from equation (1), the probability that no vehicle arrives within the count interval t, that is, k is 0, is
P(0)=e-λt(2)
The above formula shows that in a specific time interval t, if no vehicle arrives, the headway is at least t between the last arrival and the next arrival, i.e. P (0) is the probability that the headway is equal to or greater than t, and therefore
P(h≥t)=e-λt(3)
The probability that the headway is less than t is
P(h<t)=1-e-λt(4)
If Q represents the hourly traffic volume, λ ═ Q/3600, equation (4) can be written as
P(h<t)=1-e-Qt/3600(5)
From the formula (5)
Setting a corresponding probability threshold value p and an hourly traffic volume Q, and if the time span h1 that the detected road traffic volume data are continuously zero is greater than the calculated time interval t, judging that the zero data of the time period are problem data; f (t) represents the judgment result of continuous zero data, as shown in formula (7):
(3) judging abnormal data of the normal data subjected to zero data judgment, and respectively carrying out traffic flow threshold value inspection, traffic flow parameter consistency inspection and traffic flow statistical rule inspection on the normal data to obtain normal data meeting the inspection standard and abnormal data not meeting the inspection standard; wherein the traffic flow parameter consistency check comprises:
①, when the detected road traffic flow and DS are both zero, the road traffic flow is normal data, if the two are not zero, the detected road traffic flow is considered as abnormal data;
② setting a maximum threshold value of DS, if the detected road traffic flow is between 0 and the maximum threshold value, the road traffic flow is normal data, if the detected road traffic flow exceeds the maximum threshold value, the detected road traffic flow is considered abnormal data;
the system comprises a plurality of lanes, wherein each lane comprises a DS (green- (unused green) ]/green (9) green, the display time length of a green light in a certain period, and the unused green is the time which is more than or less than the standard vehicle distance of each lane; DS is "saturation" used for SCATS, which is the ratio of green time utilized by traffic to green display time, and takes the value as a percentage molecular value;
the traffic flow statistical rule test comprises the following steps:
① formula (9) and traffic flow statistical rule show that the safety minimum value of the average time of standard inter-vehicle distance
In the formula: PHASE-duration of green light, i.e. duration of green light display of a certain period
DS-degree of saturation
VOLUME-traffic flow detected during green light
ThPresentation standardMean time between vehicles, ThThere is a safety minimum if ThIf the detected road traffic flow is less than the safety minimum value, the detected road traffic flow is considered as abnormal data, and if T is less than the safety minimum valuehIf the detected road traffic flow is larger than the safety minimum value, the detected road traffic flow is considered as normal data;
② if the difference between the traffic flow data of a small value of one lane detected by the detector of the same phase of the entrance lane of the same intersection and the traffic flow data of a large value of the other lane exceeds a certain value at the same time, determining that the road traffic flow of the small value is abnormal data, and if the difference between the road traffic flow data detected by the detector of the same phase of the entrance lane of the same intersection does not exceed a limited value at the same time, determining that the road traffic flow of the small value is normal data.
2. The method for on-line detection of abnormal values of SCATS system detector data as claimed in claim 1, wherein: the probability threshold value p and the hourly traffic volume Q are set according to different traffic flows.
3. The method for on-line detection of abnormal values of SCATS system detector data as claimed in claim 1, wherein: comparing the obtained time interval t with the duration of the green light signal, and preliminarily studying and judging the traffic flow data as abnormal data if the traffic flow data is zero more than a plurality of continuous green light signal periods in a certain time period; during the time period, if a plurality of the conditions occur, the detector can be determined to be abnormal; if the data in the time period is normal, counting the total number of zero data recorded by the detector in a day above a plurality of continuous green light signal periods, comparing the total data with the total data amount recorded by the detector in a day, and if the total data amount of zero data exceeds 1/3 of the total data amount, determining that the detector is abnormal.
4. A method for on-line detection of SCATS system detector data outliers according to any of claims 1-3, characterized by: the traffic flow threshold value inspection in the step (3) comprises the following steps:
fixed groundThere is a maximum value y that may occur in the road traffic flow data detected by the pointmaxThe minimum value is 0, if the road traffic flow data is (0, y)max) The data is normal data if the range exceeds ymaxThe data is anomalous.
5. The method for on-line detection of abnormal values of SCATS system detector data as claimed in claim 4, wherein: maximum value y of road traffic flow data detected at fixed pointmaxAs shown in formula (8):
in the formula: q. q.ssSaturation flow rate that can occur during signals for each road, etc
PHASE-duration of green light, i.e. duration of green light display of a certain period
If the road traffic flow data detected in the green light time period T is within the threshold value (0, q)sT/3600) is normal data; if q is exceededsT/3600, the traffic flow data is considered to be abnormal data.
6. The method for on-line detection of abnormal values of SCATS system detector data as claimed in claim 1, wherein: the SCATS system data comprises an intersection number, a detector number, a date, a period starting time, green light duration, saturation and 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 CN109272760A (en) | 2019-01-25 |
CN109272760B true 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) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
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 |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3984372B2 (en) * | 1998-07-21 | 2007-10-03 | 松下電器産業株式会社 | Traffic control method and apparatus |
EP1549092A1 (en) * | 2003-12-22 | 2005-06-29 | Nortel Networks Limited | Wireless data traffic statistics |
CN103903452B (en) * | 2014-03-11 | 2015-10-07 | 东南大学 | Forecasting Approach for Short-term Traffic Flow |
CN103971520B (en) * | 2014-04-17 | 2015-11-18 | 浙江大学 | A kind of traffic flow data restoration methods based on temporal 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 |
CN106971538B (en) * | 2017-04-26 | 2019-08-02 | 同济大学 | A kind of method for drafting of Regional Road Network traffic behavior macroscopic view parent map |
CN107591001B (en) * | 2017-09-07 | 2019-12-27 | 山东大学 | Expressway traffic flow data filling method and system based on online calibration |
-
2018
- 2018-10-18 CN CN201811213599.1A patent/CN109272760B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN109272760A (en) | 2019-01-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102881162B (en) | Data processing and fusion method for large-scale traffic information | |
CN109448367B (en) | Intelligent road traffic tracking management system based on big data image acquisition | |
CN109272760B (en) | Online detection method for abnormal data value of SCATS system detector | |
CN107798876B (en) | Road traffic abnormal jam judging method based on event | |
CN103258430B (en) | Road traveling time calculating and traffic road condition judging method and road traveling time calculating and traffic road condition judging device | |
CN102855760B (en) | On-line queuing length detection method based on floating vehicle data | |
CN104157156B (en) | A kind of highway Dangerous Area speed of a motor vehicle dynamic management method for early warning | |
CN104392610B (en) | Expressway based on distributed video traffic events coverage dynamic monitoring and controlling method | |
CN103150900A (en) | Traffic jam event automatic detecting method based on videos | |
CN101882374A (en) | System and method for analysis of comprehensive information on vehicle trip distribution | |
CN107170247B (en) | Method and device for determining queuing length of intersection | |
CN104408925A (en) | Array radar based intersection running state evaluation method | |
CN109147330A (en) | A kind of congestion recognition methods and device | |
CN102592451B (en) | Method for detecting road traffic incident based on double-section annular coil detector | |
CN102087788A (en) | Method for estimating traffic state parameter based on confidence of speed of float car | |
CN107918762B (en) | Rapid detection system and method for road scattered objects | |
CN113436432A (en) | Method for predicting short-term traffic risk of road section by using road side observation data | |
CN110136442A (en) | Pedestrian based on shared bicycle GPS track data occupies road Activity recognition method | |
CN106157609A (en) | The monitoring method of a kind of block status and device | |
CN103971519A (en) | System and method of using traffic conflicts for judging accident-prone sections | |
US20220319323A1 (en) | Method for identifying road risk based on networked vehicle-mounted adas | |
CN101075377A (en) | Method for automatically inspecting highway traffic event based on offset minimum binary theory | |
CN104966404A (en) | Single-point self-optimization signal control method and device based on array radars | |
CN105118310A (en) | Video-based single-point self-optimization signal control method and device | |
CN113032239A (en) | Risk prompting method and device, electronic equipment and storage medium |
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 |