CN115223365A - Road network speed prediction and anomaly identification method based on damping Holt model - Google Patents
Road network speed prediction and anomaly identification method based on damping Holt model Download PDFInfo
- Publication number
- CN115223365A CN115223365A CN202210832141.4A CN202210832141A CN115223365A CN 115223365 A CN115223365 A CN 115223365A CN 202210832141 A CN202210832141 A CN 202210832141A CN 115223365 A CN115223365 A CN 115223365A
- Authority
- CN
- China
- Prior art keywords
- road network
- speed
- time
- data
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000013016 damping Methods 0.000 title claims abstract description 22
- 230000002159 abnormal effect Effects 0.000 claims abstract description 32
- 238000005259 measurement Methods 0.000 claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 7
- 230000007246 mechanism Effects 0.000 claims abstract description 5
- 238000009499 grossing Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 230000001186 cumulative effect Effects 0.000 claims description 2
- 238000005315 distribution function Methods 0.000 claims description 2
- 238000011156 evaluation Methods 0.000 claims description 2
- 230000004927 fusion Effects 0.000 claims description 2
- 238000013178 mathematical model Methods 0.000 claims description 2
- 238000005457 optimization Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 claims description 2
- 238000010998 test method Methods 0.000 claims description 2
- 230000002123 temporal effect Effects 0.000 claims 2
- 238000004364 calculation method Methods 0.000 claims 1
- 239000000203 mixture Substances 0.000 claims 1
- 230000005856 abnormality Effects 0.000 abstract description 8
- 230000008439 repair process Effects 0.000 abstract description 2
- 230000015572 biosynthetic process Effects 0.000 abstract 1
- 230000008859 change Effects 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000036962 time dependent Effects 0.000 description 1
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
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- 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
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
- G08G1/0141—Measuring and analyzing of parameters relative to traffic conditions for specific applications for traffic information dissemination
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a road network speed prediction and abnormality recognition method based on a damping Holt model, which comprises the following steps of (1) performing abnormality recognition and repair on problem data aiming at road network historical traffic speed data detected by geomagnetic equipment, processing abnormal values in the traffic speed data by using median of absolute value difference, and repairing missing data by using a space-time regression model; (2) Predicting road network speed measurement in a period of time in the future, establishing a model for the road network speed measurement according to historical road network speed, and predicting the road network speed measurement in the future; (3) Aiming at the difference between the real-time speed measurement and the historical road network speed caused by the traffic of the emergency road network of a certain road section in the road network traffic system, an early warning mechanism is established to realize the early warning of the preset lead, and the early warning is carried out on the abnormal emergency road network speed and a signal is sent out. The road network speed prediction and abnormality identification method provided by the invention can be used for early warning the formation of abnormal road network speed and the future development trend and making early warning with enough lead.
Description
Technical Field
The invention belongs to the field of intelligent traffic, and relates to a road network speed prediction method and an abnormality identification method.
Background
Road traffic speed is an important parameter in an intelligent traffic system, and compared with density and flow, the speed can directly reflect the congestion condition of road traffic. For a high-load urban traffic network, the abnormal speed of the road can cause large-scale aggregation of passenger flow and spread of congestion. The speed is reasonably and accurately predicted and abnormal recognition is carried out, the road network state can be effectively identified, and data feedback and theoretical support are further provided for traffic decision making.
In the prior art, the urban rail traffic flow prediction method is represented by combining a traditional time series method with deep learning, and is mainly based on the situation that original data are complete and data accuracy is high. However, the speed time sequence regularity is low in practice and is not suitable for the deep learning method, the deep learning method needs a large amount of sample training, actual samples are few, and the scale required by the deep learning training is difficult to achieve. In view of the above technical defects in the prior art, it is urgently needed to develop a new road network speed prediction method and an abnormal speed identification method.
Disclosure of Invention
The road network speed prediction and anomaly identification method based on the damping Holt model provided by the invention is used for analyzing the road network speed evolution rule in an urban traffic system, establishing a prediction and early warning mechanism, classifying, tracking and monitoring abnormal events through deviation analysis, and realizing the automation of traffic anomaly detection. And a quantitative evaluation method is adopted to provide decision support for dealing with the urban traffic abnormal events. And early warning with enough lead can be timely made by using real-time data continuously issued by a traffic monitoring system.
The technical scheme of the invention is as follows: a road network speed prediction and anomaly identification method based on a damping Holt model comprises the following steps:
the method comprises the following steps of (1) carrying out abnormity identification and repair on road network historical traffic speed data detected by geomagnetic equipment;
step (2), predicting road network speed measurement in a period of time in the future, establishing a model for the road network speed measurement according to historical road network speed, and predicting the road network speed measurement in the future;
and (3) aiming at the difference between the real-time speed measurement and the historical road network speed caused by the traffic of the emergency road network of a certain road section in the road network traffic system, establishing an early warning mechanism to realize early warning of the preset lead, early warning the abnormal emergency road network speed and sending a signal.
By adopting the technical scheme, the invention has the following beneficial effects:
1. the method provides timely and reliable express way traffic state and trend information for traffic managers, reasonably estimates and predicts the duration of traffic jam under the contingency event, and is convenient for providing effective traffic information service for the public.
2. The method provides accurate express way bottleneck information for traffic managers, and facilitates the design and implementation of long-term or short-term traffic management measures and control schemes.
3. For the traffic speed data with complex changes, the invention provides a data preprocessing method, and simultaneously uses a damping Holt model to better predict fluctuation data in the traffic speed data, particularly for abnormal speed data, the prediction trend of the abnormal speed data can change along with the change of the traffic data along with the time, and the abnormal speed data has better fitting degree and prediction capability.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a detailed flow chart of a road network speed prediction and anomaly identification method based on a damping Holt model;
FIG. 3 is a time-series comparison chart before and after pretreatment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
According to an embodiment of the present invention, as shown in fig. 1-2, a method for road network speed prediction and anomaly identification based on a damping Holt model is provided, which includes the following steps:
(1) The method specifically comprises the steps of processing abnormal values in traffic speed data by using median absolute value differences, repairing missing data in the traffic speed data by using a space-time regression model, and performing smooth noise reduction on the traffic speed data by using a moving average method;
(2) Predicting road network speed measurement in a period of time in the future, establishing a model for the road network speed measurement according to historical road network speed, and predicting the road network speed measurement in the future;
(3) The method comprises the steps that real-time speed measurement and historical road network speed are different due to the fact that the traffic of an emergency road network of a certain road section in a road network traffic system, an early warning mechanism is established to achieve early warning of preset lead, early warning is conducted on abnormal emergency road network speed, and a signal is sent out;
further, in the method for predicting and identifying the road network speed and the abnormality based on the damped Holt model, in the step (1), the historical traffic speed abnormal data is repaired, and the median of absolute difference is selected, the method uses the median of anti-outlier and the median-based absolute deviation to determine the upper limit value and the lower limit value, the outlier is detected by calculating the sum of the distances between each data and the average value, and if the value in the data set is greater than UBV or less than LBV, the sample is regarded as the outlier. Given dataset X = { X = { [ X ] 1 ，x 2 ，...，x p P is the number of data, UBV and LBV are defined as follows:
where med (X) is the median of data set X, f is a scaling factor, and after testing the values of f from 1 to 5, the value of f =2 is the best choice for the data set.
Is the median absolute deviation of the data set X,
where k is a constant scale factor whose value depends on the distribution of the data, MAD is the median of the absolute deviation of the median of the data, and k = 1/(φ) for normally distributed data -1 (3/4))＝1.4826，φ -1 Is the inverse cumulative distribution function of a normal distribution.
MAD＝med(|x i -med(X)|)
x i For one value in the data set X, med is a median function.
Further, in the method for predicting speed of road network and identifying abnormality based on damping Holt model, in the step (1), a space-time multivariate regression model is established to fill up missing data, and m road segments are set to be related to the missing road segment, so that the space regression model of the missing road segment is as follows:
v i，t ＝α 0 +α 1 v 1，t +…+α m v m，t ，
wherein ,xi，t For the traffic speed of the road section i at time t, α i (i =0,1, …, m) is a spatial correlation regression coefficient, and m represents m adjacent road segments. In addition to spatial correlation, there is also correlation of traffic speeds at different times for the same road segment, particularly for adjacent time segments. The time regression model for the missing segment is as follows:
v i，t ＝β 0 +β 1 v i，t-1 +…+β n v i，t-n ，
wherein ,vi，t Is the traffic speed, beta, of the section i at time t i (i =0,1, …, n) is a time-dependent regression coefficient, n is v i，t The nearest n timestamps adjacent to time t in (1). And (3) establishing a fusion model by combining a time regression model and a space regression model, wherein the passing speed of the missing data is obtained by fusing the following equations:
v i，t ＝λ i vt i，t +(1-λ i )vs i，t ，
wherein ,vti，t Predicted value of time regression model, vs i，t As a predictor of a spatial regression model, lambda i ∈[0，1]For parameters, the conversion is performed by the following formula:
γ 0 ＝λβ 0 +(1-λ)α 0 ，
the following model can be obtained by integrating the formula:
v i，t ＝γ 0 +γ 1 v 1，t +γ 2 v 2，t …+γ m v m，t +γ m+1 v i，t-1 +γ m+2 v i，t-2 +…+γ m+n v i，t-n ，
the multivariate regression model is divided into two parts of parameter training of the model and estimation of missing data, a least square method can be adopted to estimate a regression coefficient gamma, H data sets H > m + n +2 are selected, and the parameters are defined as:
y t，h ＝(v 1，t h ，v 2，t h ，…，v m，t h ，v i，t-1 h ，v i，t-2 h ，…，v i，t-n h )，
a data set of size H may be defined as Y = (Y) t，1 ，y t，2 ，…，y t，h ) T The data set of the adjacent nodes is defined in a matrix form:
augmented matrix Z = [ XY = [ X ] X] H*(m+n+2) Then, by the matrix cross product form, the least square method is used to estimate the estimate of the regression coefficient γ as
It is known that
The missing data can then be estimated.
Further, in the road network speed prediction and anomaly identification method based on the damping Holt model, in the step (2), the road network speed is predicted based on the damping Holt model with constraints, and the Holt model includes a prediction equation and two smoothing equations:
the prediction equation:
the horizontal equation: l t ＝αy t +(1-α)(l t-1 +b t-1 )
The trend equation: b t ＝β * (l t -l t-1 )+(1-β * )b t-1
wherein ,lt For horizontal prediction at time t, b t For the trend prediction at time t,
the predicted value at the moment t + h is obtained. Alpha is 0-1 is a horizontal smoothing parameter, beta is 0-1 * 1 is a trend smoothing parameter. For long-term prediction, the prediction using the Holt method will increase or decrease indefinitely in the future. In this case, use is made of damping parameters
To prevent predictive "run away".
The prediction equation:
the horizontal equation: l t ＝αy t +(1-α)(l t-1 +φb t-1 )
The trend equation: b t ＝β * (l t -l t-1 )+(1-β * )φb t-1
In the prediction process, the most important is the selection of the smoothing coefficient, most of the conventional methods mainly adopt experience methods for manual selection, and the prediction result is inevitably influenced only by selecting the smoothing coefficient through experience, so that the smoothing coefficient value corresponding to the optimal prediction result is searched by considering the establishment of a corresponding mathematical model, and quantitative prediction is performed. For better comparison of goodness of fit and prediction capability of the model, considering that a sum of squared errors criterion (SSE) is one of comprehensive indexes of error analysis, the SSE is used as an evaluation index of the model, and the following optimization model is established:
wherein the constraint conditions are as follows:
wherein ,α、β* Phi and h are parameters, l 0 and b0 Is an initial value, y 1 ,y 2 …,y T T is the number of time stamps for the actual speed value. And establishing the objective function, then performing parameter training according to the constraint condition, and performing prediction application of the model according to the trained parameters.
Further, according to the road network speed prediction and abnormality identification method based on the damping Holt model, an assumption test method is adopted in the step (3) to carry out early warning on abnormal speed, due to the fact that people go out and show different changes on different dates, a time series clustering algorithm based on k-means is used for clustering traffic speed time series to obtain data sets of different modes, and then the mode data set matched with the real-time speed is calculated by using the similarity to carry out abnormal speed discovery. The data set after the mode extraction is subjected to normal distribution, so that abnormal speed is identified by adopting a Laplace criterion, and a certain time stamp is set as a speed data set with the same mode as a { y } 1 ,y 2 ,y 3 ,…,y N And N is the number of the same mode data. Calculating the arithmetic mean value thereof
And standard deviation sigma, if the real-time speed v corresponding to the time stamp i Satisfies the following conditions:
and if the continuous time stamps are abnormal, the time speed of the time period is considered to be abnormal.
According to one embodiment of the invention, the following is implemented:
as the road network speed prediction and abnormality identification method based on the damping Holt model, aiming at each road section, a historical data set of nearly 3 months is selected in the embodiment, firstly, the median of absolute value difference is used for processing an abnormal value,
logic for median absolute difference processing: (1) finding out median of all data; (2) Obtaining the absolute deviation value | x of each data and the median i -med (X) |; (3) obtaining a median MAD of the absolute deviation value; finally, UBV and LBV are calculated to determine a reasonable range [ UBV, LBV]. And then repairing the missing data by using a space-time regression model, searching a road section ID adjacent to the missing road section, searching traffic speed data and historical speed data of the same-period road section according to the road section ID, and constructing an adjacent node set by using the data, wherein Nb (i), i =1,2, … and m + n. M in the model is the number of adjacent road sections and can change along with the change of the road sections. n is the number of adjacent time clusters and is determined by the correlation coefficient of the data.
Finally, the time series data after the processing obtained by performing smooth noise reduction on the data by using the moving average method is shown in fig. 3.
And then predicting the real-time sequence by using a damping Holt model, testing the model by using historical data, and evaluating the model by selecting a Mean Absolute Percentage Error (MAPE), a Mean Absolute Error (MAE) and a maximum absolute error (MaxAE), wherein the model has a good prediction effect as can be seen from the following table.
And finally, dividing historical data into data sets of different modes by using a time sequence clustering algorithm based on k-means, wherein the data sets after mode extraction are subjected to normal distribution, so that abnormal speed is identified by adopting a Lauda criterion, and a speed data set with a certain timestamp and the same mode is set as { y } 1 ,y 2 ,y 3 ,…,y N And N is the number of the same mode data. Calculating the arithmetic mean value thereof
And standard deviation sigma, if the real-time speed v corresponding to the time stamp i Satisfies the following conditions:
and if the continuous time stamps are abnormal, the time speed of the time period is considered to be abnormal.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (5)
1. A road network speed prediction and anomaly identification method based on a damping Holt model is characterized by comprising the following steps:
the method comprises the following steps of (1) carrying out abnormity identification and restoration on road network historical traffic speed data detected by geomagnetic equipment;
step (2), predicting road network speed measurement in a period of time in the future, establishing a model for the road network speed measurement according to historical road network speed, and predicting the road network speed measurement in the future;
and (3) aiming at the difference between the real-time speed measurement and the historical road network speed caused by the traffic of the emergency road network of a certain road section in the road network traffic system, establishing an early warning mechanism to realize early warning of the preset lead, early warning the abnormal emergency road network speed and sending a signal.
2. The road network speed prediction and anomaly identification method based on the damping Holt model as claimed in claim 1, characterized in that: the step (1) specifically comprises:
processing abnormal values in the traffic speed data by using the median of absolute value difference, repairing missing data in the traffic speed data by using a space-time regression model, and performing smooth noise reduction on the traffic speed data by using a moving average method;
wherein, the processing of the abnormal value in the traffic speed data by using the median of absolute value difference comprises the following steps: determining an upper value UBV and a lower value LBV using the median of anti-outliers and the absolute deviation based on the median, detecting outliers by comparing each data to the magnitudes of UBV and LBV, the sample being considered an outlier if the value in the data set is greater than UBV or less than LBV; given dataset X = { X = { [ X ] 1 ,x 2 ,…,x p P is the number of data, UBV and LBV are defined as follows:
where med (X) is the median of the data set X, and f is a ratioThe factors are such that the ratio of the number of the components,
is the median absolute deviation of the data set X,
where k is a constant scale factor whose value depends on the distribution of the data, MAD is the median of the absolute deviation of the median of the data in the data set X, and k = 1/(φ) for normally distributed data -1 (3/4))＝1.4826，φ -1 An inverse cumulative distribution function that is a normal distribution;
MAD＝med(|x i -med(X)|)
x i for a value in the data set X, med is a median function.
3. The method for road network speed prediction and anomaly identification based on damping Holt model according to claim 1, characterized in that: establishing a space-time multivariate regression model in the step (1) to fill missing data, and if m road sections are set to be adjacent to the missing road section, establishing the space regression model of the missing road section as follows:
v i,t ＝α 0 +α 1 v 1,t +…+α m v m,t ,
wherein ,vi,t For the traffic speed, α, of the section i at time t i For a spatial correlation regression coefficient, i =0,1, …, m, m represents m adjacent road segments, and besides the spatial correlation, the traffic speeds of the same road segment at different times also have correlation, and a temporal regression model of the missing road segment is established as follows:
v i,t ＝β 0 +β 1 v i,t-1 +…+β n v i,t-n ,
wherein ,vi,t Is the traffic speed, beta, of the section i at time t i I =0,1, …, n is v i,t The nearest n timestamps adjacent to the t moment in the time table are combined with a time regression model and a space regression model to establish a fusion model, and the passing speed of the missing dataObtained by fusing the following equations:
v i,t ＝λ i vt i,t +(1-λ i )vs i,t ,
wherein ,vti,t As a predictor of the temporal regression model, vs i,t As a predictor of a spatial regression model, lambda i ∈[0,1]And estimating a regression coefficient by using a least square method for the parameter, and estimating the missing data after obtaining the regression coefficient.
4. The method for road network speed prediction and anomaly identification based on damping Holt model according to claim 1, characterized in that: in the step (2), the road network speed is predicted based on the constrained damping Holt model, and the method specifically comprises the following steps:
the prediction equation:
the horizontal equation: l. the t ＝αy t +(1-α)(l t-1 +φb t-1 )
The trend equation: b is a mixture of t ＝β*(l t -l t-1 )+(1-β * )φb t-1
wherein ,lt For horizontal prediction at time t, b t For the trend prediction at time t,
the predicted value at the moment of t + h; alpha is 0-1 is a horizontal smoothing parameter, beta is 0-1 * A trend smoothing parameter of 1 or less, using a damping parameter
The 'runaway' of prediction is prevented, a corresponding mathematical model is established in consideration of selection of the smoothing coefficient in the prediction process to search for the smoothing coefficient value corresponding to the optimal prediction result, so that quantitative prediction is carried out, the error Sum of Squares (SSE) is used as the evaluation index of the model, and the following optimization model is established:
the constraint conditions are as follows:
wherein ,α、β* Phi and h are parameters, l 0 and b0 Is an initial value, y t T =1 … T, which is the actual speed value at time T, and T is the number of time stamps.
5. The method for road network speed prediction and anomaly identification based on damping Holt model according to claim 1, characterized in that: in the step (3), an assumption test method is adopted to early warn abnormal speed, as people travel on different dates and show different changes, a time sequence clustering algorithm based on k-means is used to cluster traffic speed time sequences to obtain data sets of different modes, then a mode data set matched with real-time speed is used for abnormal speed discovery by similarity calculation, the data set after mode extraction is in normal distribution, so that abnormal speed is identified by adopting a Laudea criterion, and a certain time stamp same mode speed data set is set as y 1 ,y 2 ,y 3 ,…,y N Calculating the arithmetic mean value of the number of the same pattern data by N
And standard deviation sigma, if the real-time speed v corresponding to the time stamp i Satisfies the following conditions:
and if the continuous time stamps are abnormal, the time speed of the time period is considered to be abnormal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210832141.4A CN115223365B (en) | 2022-07-15 | 2022-07-15 | Road network speed prediction and anomaly identification method based on damping Holt model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210832141.4A CN115223365B (en) | 2022-07-15 | 2022-07-15 | Road network speed prediction and anomaly identification method based on damping Holt model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115223365A true CN115223365A (en) | 2022-10-21 |
| CN115223365B CN115223365B (en) | 2023-09-29 |
Family
ID=83612747
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210832141.4A Active CN115223365B (en) | 2022-07-15 | 2022-07-15 | Road network speed prediction and anomaly identification method based on damping Holt model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115223365B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115691144A (en) * | 2023-01-03 | 2023-02-03 | 西南交通大学 | Abnormal traffic state monitoring method, device and equipment and readable storage medium |
| CN116861347A (en) * | 2023-05-22 | 2023-10-10 | 青岛海洋地质研究所 | Magnetic force abnormal data calculation method based on deep learning model |
| CN117113264A (en) * | 2023-10-24 | 2023-11-24 | 上海昊沧系统控制技术有限责任公司 | Method for detecting abnormality of dissolved oxygen meter of sewage plant on line in real time |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102890866A (en) * | 2012-09-17 | 2013-01-23 | 上海交通大学 | Traffic flow speed estimation method based on multi-core support vector regression machine |
| CN103971520A (en) * | 2014-04-17 | 2014-08-06 | 浙江大学 | Traffic flow data recovery method based on space-time correlation |
| CN104464304A (en) * | 2014-12-25 | 2015-03-25 | 北京航空航天大学 | Urban road vehicle running speed forecasting method based on road network characteristics |
| CN105225486A (en) * | 2015-10-09 | 2016-01-06 | 哈尔滨工业大学深圳研究生院 | Fill up the method and system of disappearance floating car data |
| CN105702029A (en) * | 2016-02-22 | 2016-06-22 | 北京航空航天大学 | Express way traffic state prediction method taking spatial-temporal correlation into account at different times |
| CN106599271A (en) * | 2016-12-22 | 2017-04-26 | 江苏方天电力技术有限公司 | Emission monitoring time series data abnormal value detection method for coal-fired unit |
| CN107943558A (en) * | 2017-11-21 | 2018-04-20 | 山东科技大学 | State Forecasting Model generation method based on Holter exponential smoothing |
| CN109242265A (en) * | 2018-08-15 | 2019-01-18 | 杭州电子科技大学 | Based on the smallest Urban Water Demand combination forecasting method of error sum of squares |
| CN111177128A (en) * | 2019-12-11 | 2020-05-19 | 国网天津市电力公司电力科学研究院 | Batch processing method and system for big metering data based on improved outlier detection algorithm |
| CN112085947A (en) * | 2020-07-31 | 2020-12-15 | 浙江工业大学 | Traffic jam prediction method based on deep learning and fuzzy clustering |
| CN112668125A (en) * | 2021-01-06 | 2021-04-16 | 北京信息科技大学 | Method, system, medium and device for improving evaluation precision of incomplete small arc |
| CN113159374A (en) * | 2021-03-05 | 2021-07-23 | 北京化工大学 | Data-driven urban traffic flow rate mode identification and real-time prediction early warning method |
| CN113779169A (en) * | 2021-08-31 | 2021-12-10 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Self-enhancement method of space-time data flow model |
| CN114285728A (en) * | 2021-12-27 | 2022-04-05 | 中国电信股份有限公司 | Prediction model training method, flow prediction method, device and storage medium |
-
2022
- 2022-07-15 CN CN202210832141.4A patent/CN115223365B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102890866A (en) * | 2012-09-17 | 2013-01-23 | 上海交通大学 | Traffic flow speed estimation method based on multi-core support vector regression machine |
| CN103971520A (en) * | 2014-04-17 | 2014-08-06 | 浙江大学 | Traffic flow data recovery method based on space-time correlation |
| CN104464304A (en) * | 2014-12-25 | 2015-03-25 | 北京航空航天大学 | Urban road vehicle running speed forecasting method based on road network characteristics |
| CN105225486A (en) * | 2015-10-09 | 2016-01-06 | 哈尔滨工业大学深圳研究生院 | Fill up the method and system of disappearance floating car data |
| CN105702029A (en) * | 2016-02-22 | 2016-06-22 | 北京航空航天大学 | Express way traffic state prediction method taking spatial-temporal correlation into account at different times |
| CN106599271A (en) * | 2016-12-22 | 2017-04-26 | 江苏方天电力技术有限公司 | Emission monitoring time series data abnormal value detection method for coal-fired unit |
| CN107943558A (en) * | 2017-11-21 | 2018-04-20 | 山东科技大学 | State Forecasting Model generation method based on Holter exponential smoothing |
| CN109242265A (en) * | 2018-08-15 | 2019-01-18 | 杭州电子科技大学 | Based on the smallest Urban Water Demand combination forecasting method of error sum of squares |
| CN111177128A (en) * | 2019-12-11 | 2020-05-19 | 国网天津市电力公司电力科学研究院 | Batch processing method and system for big metering data based on improved outlier detection algorithm |
| CN112085947A (en) * | 2020-07-31 | 2020-12-15 | 浙江工业大学 | Traffic jam prediction method based on deep learning and fuzzy clustering |
| CN112668125A (en) * | 2021-01-06 | 2021-04-16 | 北京信息科技大学 | Method, system, medium and device for improving evaluation precision of incomplete small arc |
| CN113159374A (en) * | 2021-03-05 | 2021-07-23 | 北京化工大学 | Data-driven urban traffic flow rate mode identification and real-time prediction early warning method |
| CN113779169A (en) * | 2021-08-31 | 2021-12-10 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Self-enhancement method of space-time data flow model |
| CN114285728A (en) * | 2021-12-27 | 2022-04-05 | 中国电信股份有限公司 | Prediction model training method, flow prediction method, device and storage medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115691144A (en) * | 2023-01-03 | 2023-02-03 | 西南交通大学 | Abnormal traffic state monitoring method, device and equipment and readable storage medium |
| CN116861347A (en) * | 2023-05-22 | 2023-10-10 | 青岛海洋地质研究所 | Magnetic force abnormal data calculation method based on deep learning model |
| CN116861347B (en) * | 2023-05-22 | 2024-06-11 | 青岛海洋地质研究所 | Magnetic force abnormal data calculation method based on deep learning model |
| CN117113264A (en) * | 2023-10-24 | 2023-11-24 | 上海昊沧系统控制技术有限责任公司 | Method for detecting abnormality of dissolved oxygen meter of sewage plant on line in real time |
| CN117113264B (en) * | 2023-10-24 | 2024-02-09 | 上海昊沧系统控制技术有限责任公司 | Method for detecting abnormality of dissolved oxygen meter of sewage plant on line in real time |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115223365B (en) | 2023-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115223365A (en) | Road network speed prediction and anomaly identification method based on damping Holt model | |
| CN109886430B (en) | Equipment health state assessment and prediction method based on industrial big data | |
| CN109923595B (en) | Urban road traffic abnormity detection method based on floating car data | |
| CN108564790B (en) | Urban short-term traffic flow prediction method based on traffic flow space-time similarity | |
| Khosravi et al. | Prediction intervals to account for uncertainties in travel time prediction | |
| Fei et al. | A bayesian dynamic linear model approach for real-time short-term freeway travel time prediction | |
| CN107610464A (en) | A kind of trajectory predictions method based on Gaussian Mixture time series models | |
| CN107742420A (en) | It is a kind of to be used for the method that road traffic flow is predicted under emergent traffic incident | |
| CN114495507B (en) | Traffic flow prediction method integrating space-time attention neural network and traffic model | |
| CN111179591B (en) | Road network traffic time sequence characteristic data quality diagnosis and restoration method | |
| Li et al. | A comparison of detrending models and multi-regime models for traffic flow prediction | |
| CN113496314B (en) | Method for predicting road traffic flow by neural network model | |
| Pan et al. | A fundamental diagram based hybrid framework for traffic flow estimation and prediction by combining a Markovian model with deep learning | |
| CN114036452A (en) | Capacity evaluation method applied to discrete production line | |
| CN116957331A (en) | Risk passenger flow range prediction method and device | |
| CN116843071A (en) | Transportation network operation index prediction method and device for intelligent port | |
| Lu et al. | Regression model evaluation for highway bridge component deterioration using national bridge inventory data | |
| Sardinha et al. | Context-aware demand prediction in bike sharing systems: Incorporating spatial, meteorological and calendrical context | |
| CN114611764A (en) | Monitoring and early warning method for enterprise industrial water abnormity in specific area | |
| Tran et al. | Few-shot time-series forecasting with application for vehicular traffic flow | |
| Sun et al. | Ada-STNet: A Dynamic AdaBoost Spatio-Temporal Network for Traffic Flow Prediction | |
| CN116523107A (en) | Urban rail transit emergency passenger travel mode analysis method and system | |
| Chen et al. | BIM-and IoT-Based Data-Driven Decision Support System for Predictive Maintenance of Building Facilities | |
| Othman et al. | A novel approach to traffic flow estimation based on floating car data and road topography: Experimental validation in Lyon, France | |
| Widhalm et al. | Robust road link speed estimates for sparse or missing probe vehicle 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 |