CN111192454B - Traffic abnormity identification method and system based on travel time evolution and storage medium - Google Patents
Traffic abnormity identification method and system based on travel time evolution and storage medium Download PDFInfo
- Publication number
- CN111192454B CN111192454B CN202010015303.6A CN202010015303A CN111192454B CN 111192454 B CN111192454 B CN 111192454B CN 202010015303 A CN202010015303 A CN 202010015303A CN 111192454 B CN111192454 B CN 111192454B
- Authority
- CN
- China
- Prior art keywords
- travel time
- weighted moving
- moving average
- distribution model
- control
- 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
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
Abstract
The invention discloses a traffic anomaly identification method, a system and a storage medium based on travel time evolution. According to the method, floating car data are utilized, and meanwhile, an index weighted moving average map is generated by constructing a travel time distribution model and calculating an index weighted moving average, so that the dynamic evolution process of the traffic state of a single road section or the whole system can be identified, abnormal traffic events in a traffic network can be effectively identified, and the identification accuracy is greatly improved. The invention can be widely applied to the traffic field.
Description
Technical Field
The invention relates to the technical field of traffic anomaly event identification, in particular to a traffic anomaly identification method and system based on travel time evolution and a storage medium.
Background
The efficient and stable operation of the traffic system not only meets the travel demands of travelers and ensures the travel efficiency of the travelers, but also can drive the development of each industry to a certain extent and stimulate the urban economy. However, in practical conditions, the traffic system may have problems such as low efficiency, serious congestion, etc., which may be caused by internal problems of the traffic system, such as defects in the design of the wire network and unreasonable management and control measures, or may be caused by external disturbances, such as traffic accidents, extreme weather, road reconstruction, or major gathering activities. These problems often reduce the operating efficiency of the road traffic network and increase the travel cost of users, so that accurately identifying short-term or long-term abnormal traffic events in the road traffic network has great significance for traffic managers to make corresponding traffic management measures in time to reduce the influence of the abnormal traffic events on the whole system.
At present, for an abnormal event identification method of a traffic system, selected indexes comprise section flow, density, occupancy, congestion index and the like, but the data are difficult to acquire or the coverage range is narrow, so that the overall state of the system cannot be comprehensively reflected. The travel time is an important index reflecting the state of a traffic system, and the continuous increase of the permeability of the floating car provides powerful support for data acquisition of the travel time. And the data collected by the floating car has some noises, which causes great interference and misjudgment to the identification of traffic events and traffic states. At present, the research on abnormal events mainly focuses on short-term (in-day) detection, and these methods can detect whether abnormal events occur in a short-term single scale of a road in real time, but do not catch the long-term slow evolution of a traffic system, and actually, the traffic system is a dynamic system, and the main reasons are that the trip behavior of a traveler and the road network structure are continuously changed, and the travel time of a road network or a road section is also dynamically changed. Thus, it may be difficult to identify a long-term abnormal state of the traffic system as a determination analysis index of traffic abnormality for a short-term static travel time.
Disclosure of Invention
In order to solve the above technical problems, an object of the present invention is to provide a method, a system and a storage medium for identifying traffic anomalies based on travel time evolution.
In a first aspect, an embodiment of the present invention provides a traffic anomaly identification method based on travel time evolution, including the following steps:
acquiring floating car data;
processing the floating car data to obtain travel time data;
obtaining a travel time distribution model according to the travel time data, reducing the dimension of the travel time distribution model, and solving the travel time distribution model to obtain a solved travel time distribution model;
calculating an exponential weighted moving average according to the solved travel time distribution model;
constructing a control boundary of the exponentially weighted moving average according to the exponentially weighted moving average to form an exponentially weighted moving average control chart;
and acquiring real-time travel time data, and identifying traffic abnormality according to a control boundary in the exponentially weighted moving mean control chart.
Further, the processing of the floating car data to obtain the travel time data specifically comprises the following steps:
and carrying out speed and time conversion processing on the floating car data to obtain travel time data.
Further, the step of obtaining a travel time distribution model according to the travel time data, performing dimension reduction on the travel time distribution model, and further solving the travel time distribution model to obtain a solved travel time distribution model specifically includes:
according to the travel time data, constructing and obtaining a travel time distribution model;
performing local least square processing on the travel time distribution model to obtain a mean function and a covariance function in a random process;
calculating a characteristic value and a characteristic function of the travel time distribution model through a characteristic equation;
calculating the minimum number of principal components with interpretable variation ratio of more than 95% according to the travel time distribution model;
and calculating the coefficient of the principal component function of the travel time distribution model by using a principal component analysis method according to the obtained minimum number of the principal components to obtain the solved travel time distribution model.
Further, the calculating an exponentially weighted moving average according to the solved travel time distribution model specifically includes:
obtaining travel time data of a required time period according to the solved travel time distribution model;
and calculating the exponentially weighted moving average according to the travel time data of the required time period.
Further, when the travel time data is travel time data of a single-path vehicle, the control boundary of the exponentially weighted moving average is constructed according to the exponentially weighted moving average to form an exponentially weighted moving average control map, and the step specifically includes:
calculating a travel time mean value and a travel time standard deviation according to the exponentially weighted moving mean value;
determining a control upper bound and a control lower bound according to the travel time mean value and the travel time standard deviation;
and generating and obtaining a number weighted moving average control chart according to the control upper bound and the control lower bound.
Further, when the travel time data is travel time data of a plurality of route vehicles, the control boundary of the exponentially weighted moving average is constructed according to the exponentially weighted moving average to form an exponentially weighted moving average control map, and the step specifically includes:
calculating a travel time mean value and a travel time standard deviation according to the exponentially weighted moving mean value;
determining a control upper bound and a control lower bound according to the travel time mean value and the travel time standard deviation;
calculating a control index of the travel time according to the exponentially weighted moving average;
and generating and obtaining a number weighted moving average control chart according to the control index, the control upper bound and the control lower bound.
In a second aspect, an embodiment of the present invention provides a traffic anomaly identification system based on travel time evolution, including:
the acquisition unit is used for acquiring floating car data;
the preprocessing unit is used for processing the floating car data to obtain travel time data;
the solving unit is used for obtaining a travel time distribution model according to the travel time data, reducing the dimension of the travel time distribution model and further solving the travel time distribution model to obtain a solved travel time distribution model;
the exponential weighted moving average calculating unit is used for calculating an exponential weighted moving average according to the solved travel time distribution model;
the control chart generation unit is used for constructing a control boundary of the exponentially weighted moving average value according to the exponentially weighted moving average value to form an exponentially weighted moving average control chart;
and the abnormality identification unit is used for acquiring real-time travel time data and identifying traffic abnormality according to the control boundary in the exponentially weighted moving average control chart.
Further, the solving unit specifically includes:
the model construction unit is used for constructing and obtaining a travel time distribution model according to the travel time data;
the first processing unit is used for carrying out local least square processing on the travel time distribution model to obtain a mean function and a covariance function in a random process;
the second processing unit is used for calculating a characteristic value and a characteristic function of the travel time distribution model through a characteristic equation;
the third processing unit is used for calculating the minimum number of the principal components with the interpretable variation ratio of more than 95 percent according to the travel time distribution model;
and the fourth processing unit is used for calculating the coefficient of the principal component function of the travel time distribution model by using a principal component analysis method according to the obtained minimum number of the principal components to obtain the solved travel time distribution model.
In a third aspect, an embodiment of the present invention provides a traffic anomaly identification device based on travel time evolution, including:
at least one processor;
at least one memory for storing at least one program;
when the at least one program is executed by the at least one processor, the at least one program causes the at least one processor to implement the method for identifying traffic anomalies based on travel time evolution.
In a fourth aspect, an embodiment of the present invention provides a storage medium having stored therein processor-executable instructions, where the processor-executable instructions are configured to perform the method for identifying traffic anomalies based on travel time evolution when executed by a processor.
The invention has the beneficial effects that:
according to the traffic anomaly identification method, the system, the device and the storage medium based on the travel time evolution, floating car data are utilized, meanwhile, the travel time distribution model is built, the index weighted moving average is calculated, and then the index weighted moving average control chart is generated, so that the dynamic evolution process of the traffic state of a single road section or the whole system can be identified, abnormal traffic events in a traffic network can be effectively identified, and the identification accuracy is greatly improved.
Drawings
FIG. 1 is a flow chart of the steps of a traffic anomaly identification method based on travel time evolution according to the present invention;
FIG. 2 is a block diagram of a traffic anomaly identification system based on travel time evolution in accordance with the present invention;
FIG. 3 is a schematic diagram illustrating the identification of an abnormal traffic event during a single road segment day according to one embodiment;
FIG. 4 is a schematic diagram illustrating the identification of an abnormal traffic event for a single road segment during the day, in one embodiment;
FIG. 5 is a diagram illustrating long-term abnormal traffic event recognition results for the overall traffic system in one embodiment.
Detailed Description
The invention is described in further detail below with reference to the figures and the specific embodiments. The step numbers in the following embodiments are provided only for convenience of illustration, the order between the steps is not limited at all, and the execution order of each step in the embodiments can be adapted according to the understanding of those skilled in the art. Furthermore, it should be noted that the embodiments and features of the embodiments in the present application may be arbitrarily combined with each other without conflict.
Referring to fig. 1, an embodiment of the present invention is configured to monitor a traffic system state in real time through historical floating car data, and identify an abnormal traffic event of the entire system at a road section and a road network scale, and this embodiment provides a traffic abnormality identification method based on travel time evolution, including the following steps:
and S101, acquiring floating car data.
And S102, processing the floating car data to obtain travel time data.
In the step, the floating car data collected by the floating car is the running speed of the vehicle, and the data needs to be preprocessed before noise reduction, namely, the running speed is converted into the travel time of unit distance.
S103, obtaining a travel time distribution model according to the travel time data, reducing the dimension of the travel time distribution model, and solving the travel time distribution model to obtain the solved travel time distribution model.
And S104, calculating an exponential weighted moving average value according to the solved travel time distribution model.
And S105, constructing a control boundary of the exponentially weighted moving average value according to the exponentially weighted moving average value to form an exponentially weighted moving average control chart.
And S106, acquiring real-time travel time data, and identifying traffic abnormality according to a control boundary in the exponential weighted moving average control chart.
Further as a preferred embodiment, the processing floating car data to obtain travel time data specifically includes:
and carrying out speed and time conversion processing on the floating car data to obtain travel time data.
Further as a preferred embodiment, in this embodiment, in order to approximate the time of flight stochastic process Φmn(t) this exampleAssuming that the travel time of the time interval n is the mean value sampling of the travel time of the time interval, obtaining a travel time distribution model according to the travel time data, performing dimension reduction on the travel time distribution model, and further solving the travel time distribution model to obtain a solved travel time distribution model, wherein the step specifically comprises the following steps:
and S1031, constructing and obtaining a travel time distribution model according to the travel time data.
In this embodiment, vector X is recordedmnRepresenting floating car data collected over a period of m days n, assuming that the travel time data is a compliant mean value, mumn(t), Gaussian process with variance G (t, s).
The n time period t on the m day can be estimated by combining the Karhunen-Loeve rulejObserved value X of travel time of timemn(tj)：
Wherein e ismnIs random noise, ximgRepresenting a set of obedience conditions E ([ xi ])mg) 0 and var (ξ)mg)＝λgRandom coefficient of (phi)g(tj) Is an orthonormal eigenfunction consisting of a set of basis units, tjIndicating the time of collection of the data. The equation represents the travel time for each time period as the average of the historical travel times for the same time period plus a perturbation and random noise.
S1032, local least square processing is carried out on the travel time distribution model to obtain a mean value function in a random process
Sum covariance function
S1033, calculating characteristic values of the travel time distribution model through a characteristic equation
And a characteristic function
S1034, calculating the minimum principal component number B with the interpretable variation ratio FVE more than 95% according to the travel time distribution model.
Wherein B is the number of principal components, C is the number of eigenvalues, λbIs the eigenvalue.
And S1035, calculating coefficients of the principal component functions of the travel time distribution model by a principal component analysis method according to the obtained minimum number of the principal components, and obtaining the solved travel time distribution model.
Further as a preferred embodiment, the calculating an exponentially weighted moving average according to the solved travel time distribution model specifically includes:
s1041, obtaining travel time data of a required time period according to the solved travel time distribution model;
s1042, calculating an exponential weighted moving average value according to the travel time data of the required time period.
In this embodiment, an exponentially weighted moving average may also be obtained by calculation according to historical data of the travel time, and a travel time change process in the day of the m-th day is represented as Tm(n), wherein n represents a time of day period. The daily travel time evolution process of time period n may be denoted as Tn(m), the travel time exponentially weighted moving average for time period n can be calculated as:
wherein z ismnFor an exponentially weighted moving average of n travel times of the mth day period, λ represents a weight constantAnd 0 is<The value of lambda is less than or equal to 1, T is 0.2n(m) represents the travel time of the road section on the m-th day, period n, zn0The travel time of the 1 st calendar history data of the section time period n. Iterating this can result in:
zmn＝(1-(1-λ)m)Tn(m-j)+(1-λ)mz0n
wherein T isn(m-j) represents the travel time for the n-th day on the m-j.
Further as a preferred embodiment, when the travel time data is travel time data of a single-path vehicle, the constructing a control boundary of an exponentially weighted moving average according to the exponentially weighted moving average to form an exponentially weighted moving average control map includes:
calculating a travel time mean value and a travel time standard deviation according to the exponentially weighted moving mean value;
determining a control upper bound and a control lower bound according to the travel time mean value and the travel time standard deviation;
and generating and obtaining a number weighted moving average control chart according to the control upper bound and the control lower bound.
In this embodiment, the exponentially weighted moving average set of the travel time is represented as Z ═ ZmnM is 1, …, M; n is 1, …, N, and the mean value μ of the travel time of the previous k days in the period N can be calculatedknAnd standard deviation σkn：
So the upper control bound UCL and lower control bound LCL at day k can be calculated as:
where L is the control boundary width, and a smaller/larger L is selected when the fluctuation of the travel time is smaller/larger. The upper and lower control boundaries define the allowable range of the normal state of the travel time, and if the calculated travel time index weighted moving average value is larger than the upper control boundary, the road section traffic at the moment is in the abnormal state, and meanwhile, the abnormal event data identified by the algorithm cannot be included in the historical data set for constructing the control boundary.
Further as a preferred embodiment, when the travel time data is travel time data of a plurality of route vehicles, the control boundary of the exponentially weighted moving average is constructed according to the exponentially weighted moving average to form an exponentially weighted moving average control map, which specifically includes:
calculating a travel time mean value and a travel time standard deviation according to the exponentially weighted moving mean value;
determining a control upper bound and a control lower bound according to the travel time mean value and the travel time standard deviation;
calculating a control index of the travel time according to the exponentially weighted moving average;
and generating and obtaining a number weighted moving average control chart according to the control index, the control upper bound and the control lower bound.
In this embodiment, assuming that the total number of paths in the traffic network is R,
representing the z value of the r-th path during the m-th day, period n. Note qmnZ values, Q, for all paths of the m-th day period nnSet of exponentially weighted moving means for all paths of time period n for M days, i.e.
Then the statistical index Y of the multivariable exponential weighted moving average control chart of the road network in the mth day period nmnComprises the following steps:
in the formula, sigmanIs QnCovariance matrix of (u)nThe vector of the mean z value of each segment in the time period n.
Will YmnCompared with the upper control bound, the abnormal event in the network can be quickly identified, namely when Y ismnAnd when the control threshold is larger than the upper control limit, the specified route has a traffic abnormal event. The multivariate exponentially weighted moving average control graph can continuously update the historical data set of the multivariate exponentially weighted moving average control graph and endow certain weight, can capture the change of the state of the traffic system caused by various reasons, and has higher practical value.
Referring to fig. 2, an embodiment of the present invention provides a traffic anomaly identification system based on travel time evolution, including:
the acquisition unit is used for acquiring floating car data;
the preprocessing unit is used for processing the floating car data to obtain travel time data;
the solving unit is used for obtaining a travel time distribution model according to the travel time data, reducing the dimension of the travel time distribution model and further solving the travel time distribution model to obtain a solved travel time distribution model;
the exponential weighted moving average calculating unit is used for calculating an exponential weighted moving average according to the solved travel time distribution model;
the control chart generation unit is used for constructing a control boundary of the exponentially weighted moving average value according to the exponentially weighted moving average value to form an exponentially weighted moving average control chart;
and the abnormality identification unit is used for acquiring real-time travel time data and identifying traffic abnormality according to the control boundary in the exponentially weighted moving average control chart.
Further as a preferred embodiment, the solving unit specifically includes:
the model construction unit is used for constructing and obtaining a travel time distribution model according to the travel time data;
the first processing unit is used for carrying out local least square processing on the travel time distribution model to obtain a mean function and a covariance function in a random process;
the second processing unit is used for calculating a characteristic value and a characteristic function of the travel time distribution model through a characteristic equation;
the third processing unit is used for calculating the minimum number of the principal components with the interpretable variation ratio of more than 95 percent according to the travel time distribution model;
and the fourth processing unit is used for calculating the coefficient of the principal component function of the travel time distribution model by using a principal component analysis method according to the obtained minimum number of the principal components to obtain the solved travel time distribution model.
It can be seen that the contents in the foregoing method embodiments are all applicable to this system embodiment, the functions specifically implemented by this system embodiment are the same as those in the foregoing method embodiment, and the advantageous effects achieved by this system embodiment are also the same as those achieved by the foregoing method embodiment.
The embodiment of the invention also provides a traffic anomaly recognition device based on travel time evolution, which comprises:
at least one processor;
at least one memory for storing at least one program;
when the at least one program is executed by the at least one processor, the at least one program causes the at least one processor to implement the method for identifying traffic anomalies based on travel time evolution.
It can be seen that the contents in the foregoing method embodiments are all applicable to this apparatus embodiment, the functions specifically implemented by this apparatus embodiment are the same as those in the foregoing method embodiment, and the advantageous effects achieved by this apparatus embodiment are also the same as those achieved by the foregoing method embodiment.
Furthermore, an embodiment of the present invention provides a storage medium having stored therein processor-executable instructions, wherein the processor-executable instructions, when executed by a processor, are configured to perform the method for identifying traffic anomalies based on travel time evolution.
In order to visually show the effect of the algorithm, fig. 3-5 are three experimental results, which show that the algorithm used by the invention can accurately identify the abnormal traffic events of the system from short-term in the day, long-term in the day, a single road section and the whole road network scale.
According to the invention, floating car data are utilized, and an index weighted moving average is calculated by constructing a travel time distribution model to generate an index weighted moving average control chart, so that the dynamic evolution process of the traffic state of a single road section or the whole system can be identified, abnormal traffic events in a traffic network can be effectively identified, and the identification accuracy is greatly improved.
While the preferred embodiments of the present invention have been illustrated and described, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (8)
1. A traffic anomaly identification method based on travel time evolution is characterized by comprising the following steps:
acquiring floating car data;
processing the floating car data to obtain travel time data;
according to the travel time data, constructing and obtaining a travel time distribution model;
performing local least square processing on the travel time distribution model to obtain a mean function and a covariance function in a random process;
calculating a characteristic value and a characteristic function of the travel time distribution model through a characteristic equation;
calculating the minimum number of principal components with interpretable variation ratio of more than 95% according to the travel time distribution model;
calculating the coefficient of a principal component function of the travel time distribution model by a principal component analysis method according to the obtained minimum number of principal components to obtain a solved travel time distribution model;
calculating an exponential weighted moving average according to the solved travel time distribution model;
constructing a control boundary of the exponentially weighted moving average according to the exponentially weighted moving average to form an exponentially weighted moving average control chart;
and acquiring real-time travel time data, and identifying traffic abnormality according to a control boundary in the exponentially weighted moving mean control chart.
2. The traffic anomaly identification method based on travel time evolution of claim 1, wherein: the method for processing the floating car data to obtain the travel time data comprises the following steps:
and carrying out speed and time conversion processing on the floating car data to obtain travel time data.
3. The traffic anomaly identification method based on travel time evolution of claim 1, wherein: the calculating of the exponentially weighted moving average according to the solved travel time distribution model specifically includes:
obtaining travel time data of a required time period according to the solved travel time distribution model;
and calculating the exponentially weighted moving average according to the travel time data of the required time period.
4. The traffic anomaly identification method based on travel time evolution of claim 1, wherein: when the travel time data is travel time data of a single-path vehicle, the control boundary of the exponentially weighted moving average is constructed according to the exponentially weighted moving average to form an exponentially weighted moving average control chart, and the step specifically includes:
calculating a travel time mean value and a travel time standard deviation according to the exponentially weighted moving mean value;
determining a control upper bound and a control lower bound according to the travel time mean value and the travel time standard deviation;
and generating and obtaining an exponential weighted moving average control chart according to the control upper bound and the control lower bound.
5. The traffic anomaly identification method based on travel time evolution of claim 1, wherein: when the travel time data is travel time data of a plurality of path vehicles, the control boundary of the exponentially weighted moving average is constructed according to the exponentially weighted moving average to form an exponentially weighted moving average control chart, and the step specifically includes:
calculating a travel time mean value and a travel time standard deviation according to the exponentially weighted moving mean value;
determining a control upper bound and a control lower bound according to the travel time mean value and the travel time standard deviation;
calculating a control index of the travel time according to the exponentially weighted moving average;
and generating and obtaining an index weighted moving average control chart according to the control index, the control upper bound and the control lower bound.
6. A traffic anomaly identification system based on travel time evolution, comprising:
the acquisition unit is used for acquiring floating car data;
the preprocessing unit is used for processing the floating car data to obtain travel time data;
the solving unit is used for obtaining a travel time distribution model according to the travel time data, reducing the dimension of the travel time distribution model and further solving the travel time distribution model to obtain a solved travel time distribution model;
the exponential weighted moving average calculating unit is used for calculating an exponential weighted moving average according to the solved travel time distribution model;
the control chart generation unit is used for constructing a control boundary of the exponentially weighted moving average value according to the exponentially weighted moving average value to form an exponentially weighted moving average control chart;
the abnormality identification unit is used for acquiring real-time travel time data and identifying traffic abnormality according to a control boundary in the exponentially weighted moving mean control chart;
the solving unit specifically includes:
the model construction unit is used for constructing and obtaining a travel time distribution model according to the travel time data;
the first processing unit is used for carrying out local least square processing on the travel time distribution model to obtain a mean function and a covariance function in a random process;
the second processing unit is used for calculating a characteristic value and a characteristic function of the travel time distribution model through a characteristic equation;
the third processing unit is used for calculating the minimum number of the principal components with the interpretable variation ratio of more than 95 percent according to the travel time distribution model;
and the fourth processing unit is used for calculating the coefficient of the principal component function of the travel time distribution model by using a principal component analysis method according to the obtained minimum number of the principal components to obtain the solved travel time distribution model.
7. A traffic anomaly recognition device based on travel time evolution is characterized by comprising:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement a method for identifying traffic anomalies based on travel time evolution according to any one of claims 1 to 5.
8. A storage medium having stored therein processor-executable instructions, which when executed by a processor, are configured to perform a method for identifying traffic anomalies based on travel time evolution according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010015303.6A CN111192454B (en) | 2020-01-07 | 2020-01-07 | Traffic abnormity identification method and system based on travel time evolution and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010015303.6A CN111192454B (en) | 2020-01-07 | 2020-01-07 | Traffic abnormity identification method and system based on travel time evolution and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111192454A CN111192454A (en) | 2020-05-22 |
| CN111192454B true CN111192454B (en) | 2021-06-01 |
Family
ID=70710705
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010015303.6A Active CN111192454B (en) | 2020-01-07 | 2020-01-07 | Traffic abnormity identification method and system based on travel time evolution and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111192454B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112232257B (en) * | 2020-10-26 | 2023-08-11 | 青岛海信网络科技股份有限公司 | Traffic abnormality determination method, device, equipment and medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103927872A (en) * | 2014-04-28 | 2014-07-16 | 武汉大学 | Method for predicting multi-period travel time distribution based on floating vehicle data |
| CN104700200A (en) * | 2014-12-18 | 2015-06-10 | 西安交通大学 | Multivariate product quality monitoring method oriented to digital workshop |
| CN105679025A (en) * | 2016-02-22 | 2016-06-15 | 北京航空航天大学 | Urban trunk road travel time estimation method based on variable weight mixed distribution |
| CN107424410A (en) * | 2017-07-14 | 2017-12-01 | 中南大学 | A kind of accident detection method calculated based on route travel time |
| CN107688556A (en) * | 2017-07-24 | 2018-02-13 | 中山大学 | A kind of real-time travel time computation method based on function type principal component analysis |
| WO2018122802A1 (en) * | 2016-12-30 | 2018-07-05 | 同济大学 | Multimodal road traffic anomaly detection method |
| CN109637143A (en) * | 2019-01-22 | 2019-04-16 | 江苏智通交通科技有限公司 | Improved Travel Time Reliability analysis method |
| CN110363989A (en) * | 2019-07-11 | 2019-10-22 | 汉王科技股份有限公司 | Magnitude of traffic flow detection method, device, electronic equipment and storage medium |
-
2020
- 2020-01-07 CN CN202010015303.6A patent/CN111192454B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103927872A (en) * | 2014-04-28 | 2014-07-16 | 武汉大学 | Method for predicting multi-period travel time distribution based on floating vehicle data |
| CN104700200A (en) * | 2014-12-18 | 2015-06-10 | 西安交通大学 | Multivariate product quality monitoring method oriented to digital workshop |
| CN105679025A (en) * | 2016-02-22 | 2016-06-15 | 北京航空航天大学 | Urban trunk road travel time estimation method based on variable weight mixed distribution |
| WO2018122802A1 (en) * | 2016-12-30 | 2018-07-05 | 同济大学 | Multimodal road traffic anomaly detection method |
| WO2018122806A1 (en) * | 2016-12-30 | 2018-07-05 | 同济大学 | Travel time distribtuion-based multimodal traffic anomaly detection method |
| WO2018122805A1 (en) * | 2016-12-30 | 2018-07-05 | 同济大学 | Traffic anomaly detection method based on time distribution of travels |
| CN107424410A (en) * | 2017-07-14 | 2017-12-01 | 中南大学 | A kind of accident detection method calculated based on route travel time |
| CN107688556A (en) * | 2017-07-24 | 2018-02-13 | 中山大学 | A kind of real-time travel time computation method based on function type principal component analysis |
| CN109637143A (en) * | 2019-01-22 | 2019-04-16 | 江苏智通交通科技有限公司 | Improved Travel Time Reliability analysis method |
| CN110363989A (en) * | 2019-07-11 | 2019-10-22 | 汉王科技股份有限公司 | Magnitude of traffic flow detection method, device, electronic equipment and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| Estimation of Travel Times on Signalized Arterials;Ivana Cavar 等;《Journal of Civil Engineering and Architecture》;20130930;第7卷(第9期);全文 * |
| 基于多尺度主成分分析的全网络异常检测方法;钱叶魁 等;《软件学报》;20120228(第2期);第363-373页 * |
| 基于浮动车数据的道路拥堵状态评价及宏观基本图研究;李梦琦;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20170115(第1期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111192454A (en) | 2020-05-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | A multivariate short-term traffic flow forecasting method based on wavelet analysis and seasonal time series | |
| Russo et al. | Air quality prediction using optimal neural networks with stochastic variables | |
| Gocheva-Ilieva et al. | Regression trees modeling of time series for air pollution analysis and forecasting | |
| Bendre et al. | Time series decomposition and predictive analytics using MapReduce framework | |
| Klein Entink et al. | How to statistically analyze nano exposure measurement results: using an ARIMA time series approach | |
| CN111368980A (en) | State detection method, device, equipment and storage medium | |
| CN111192454B (en) | Traffic abnormity identification method and system based on travel time evolution and storage medium | |
| CN111178377A (en) | Visual feature screening method, server and storage medium | |
| CN115409120A (en) | Data-driven-based auxiliary user electricity stealing behavior detection method | |
| CN116416884A (en) | Testing device and testing method for display module | |
| Miao et al. | Examining the impact of different periodic functions on short-term freeway travel time prediction approaches | |
| Shekarrizfard et al. | Wavelet transform-based artificial neural networks (WT-ANN) in PM 10 pollution level estimation, based on circular variables | |
| Yang et al. | Bayesian dynamic programming approach for tracking time-varying model properties in SHM | |
| Kulaglic et al. | Stock price forecast using wavelet transformations in multiple time windows and neural networks | |
| CN113033921B (en) | Bus route passenger flow prediction method based on multivariate stepwise regression analysis | |
| CN116203352A (en) | Fault early warning method, device, equipment and medium for power distribution network | |
| CN111105148B (en) | Off-job probability evaluation method, apparatus and computer readable storage medium | |
| CN115510763A (en) | Air pollutant concentration prediction method and system based on data-driven exploration | |
| Bensi et al. | Evaluation of tropical cyclone recurrence rate: factors contributing to epistemic uncertainty | |
| CN113919599A (en) | Medium-and-long-term load prediction method | |
| CN113988709A (en) | Medium-voltage distribution line fault rate analysis method and device, terminal equipment and medium | |
| Devarakonda | Time series analysis and forecasting of crime data | |
| Ito | Modeling dynamic diurnal patterns in high frequency financial data | |
| CN112270574A (en) | Method, device, equipment and medium for analyzing abnormal motion in motion execution process | |
| Silva et al. | Forecasting electric load demand through advanced statistical techniques |
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 |