CN115547037B - Expressway traffic accident duration prediction method, system, device and medium - Google Patents
Expressway traffic accident duration prediction method, system, device and medium Download PDFInfo
- Publication number
- CN115547037B CN115547037B CN202211114003.9A CN202211114003A CN115547037B CN 115547037 B CN115547037 B CN 115547037B CN 202211114003 A CN202211114003 A CN 202211114003A CN 115547037 B CN115547037 B CN 115547037B
- Authority
- CN
- China
- Prior art keywords
- time
- duration
- accident
- traffic accident
- 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.)
- Active
Links
- 206010039203 Road traffic accident Diseases 0.000 title claims abstract description 106
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000001133 acceleration Effects 0.000 claims abstract description 48
- 230000004083 survival effect Effects 0.000 claims abstract description 41
- 238000003745 diagnosis Methods 0.000 claims abstract description 16
- 238000012360 testing method Methods 0.000 claims abstract description 16
- 230000006870 function Effects 0.000 claims description 64
- 238000009826 distribution Methods 0.000 claims description 31
- 230000006378 damage Effects 0.000 claims description 11
- 238000007476 Maximum Likelihood Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 5
- 238000001556 precipitation Methods 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 description 12
- 208000027418 Wounds and injury Diseases 0.000 description 8
- 208000014674 injury Diseases 0.000 description 8
- 230000009286 beneficial effect Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000002459 sustained effect Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000010354 integration Effects 0.000 description 3
- 230000000670 limiting effect Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000006467 substitution reaction Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000002829 reductive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
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
- G08G1/0133—Traffic data processing for classifying traffic situation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- 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
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Data Mining & Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Mathematical Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Computational Biology (AREA)
- Algebra (AREA)
- Evolutionary Biology (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method, a system, a device and a medium for predicting the duration of traffic accidents of a highway, wherein the method comprises the following steps: acquiring historical traffic data of a highway, carrying out data space-time association by taking traffic accidents as units, and constructing a data set; carrying out correlation test and collinearity diagnosis on observation factors in the data set to obtain a predicted variable of the duration of the traffic accident; establishing a time-varying acceleration failure time model facing the expressway traffic accident duration prediction according to the prediction variable, and selecting an optimal time-varying acceleration failure time model according to the AIC index; and obtaining traffic accident data for the highway traffic accident to be predicted, and obtaining a duration survival function curve according to the traffic accident data and the optimal time-varying acceleration failure time model. The invention considers time-varying factors and time-invariant factors, so that the model is closer to the actual situation, and has practical application value. The invention can be widely applied to the field of traffic safety.
Description
Technical Field
The invention relates to the field of traffic safety, in particular to a method, a system, a device and a medium for predicting the duration of an expressway traffic accident.
Background
While providing a large amount of passenger and goods transportation, the traffic accident of the expressway frequently occurs. The highway traffic accident not only causes huge casualties and property loss, but also causes serious traffic jam, and is one of the main causes of sporadic traffic jam. Wherein, the duration of the traffic accident is a key factor for judging the space-time influence range of the traffic jam. Therefore, the prediction of the duration of the highway traffic accident and the analysis of the influencing factors are important to the emergency response decision.
According to the existing expressway traffic accident duration prediction research, according to historical traffic data, a statistical regression method represented by a survival analysis model is adopted to analyze the influence of static factors such as road conditions, accident characteristics and the like on the duration, but the influence of static factors on real-time traffic conditions, weather conditions and the like is insufficient. Traffic conditions and weather conditions are important factors affecting the arrival and clearance time of rescue workers and may change drastically over time (e.g., short-term thunderstorm weather in summer in coastal areas). With the continuous improvement of traffic and meteorological information system construction, the acquisition of real-time traffic flow and meteorological data becomes easier. In the expressway traffic accident duration prediction model, the time-varying characteristics of factors such as traffic conditions and weather conditions are ignored, so that the influence of the factors on the accident duration is difficult to accurately quantify, and the accuracy of accident duration prediction is further reduced.
Disclosure of Invention
In order to solve at least one of the technical problems existing in the prior art to a certain extent, the invention aims to provide a method, a system, a device and a medium for predicting the duration of an expressway traffic accident.
The technical scheme adopted by the invention is as follows:
a highway traffic accident duration prediction method, comprising the steps of:
acquiring historical traffic data of a highway, carrying out data space-time association by taking traffic accidents as units, and constructing a data set;
Carrying out correlation test and collinearity diagnosis on observation factors in the data set to obtain a predicted variable of the duration of the traffic accident; wherein the observation factors include time-varying factors and time-invariant factors;
Establishing a time-varying acceleration failure time model facing the expressway traffic accident duration prediction according to the prediction variable, and selecting an optimal time-varying acceleration failure time model according to the AIC index;
And obtaining traffic accident data for the expressway traffic accident to be predicted, and obtaining a duration survival function curve according to the traffic accident data and the optimal time-varying acceleration failure time model to realize the prediction of the expressway traffic accident duration.
Further, the historical traffic data includes highway traffic accident data, road design data, real-time traffic flow data, and real-time weather data;
The time-varying factors include: traffic flow, traffic composition, wind speed, precipitation, visibility, air temperature and humidity in every preset time period from the occurrence of an accident to the completion of the removal of the accident;
The time-invariant factors include: the type and damage of the hit-accident vehicle, the severity of the accident casualties, the type of accident and the road conditions of the accident site.
Further, the correlation test and the collinearity diagnosis are performed on the observation factors in the data set, including:
respectively carrying out correlation test and colinear diagnosis on the time-varying factors and the time-invariant factors;
in the correlation test, if the correlation coefficient between the two factor variables meets the preset range, judging that the correlation exists between the two factor variables;
In the co-linearity diagnosis, if the tolerance is smaller than a first preset threshold value or the variance expansion factor is larger than a second preset threshold value, the co-linearity exists among the factor variables;
And eliminating the observation factors with correlation or collinearity according to the correlation test and the collinearity diagnosis result, and taking the rest observation factors as the prediction variables of the duration of the traffic accident.
Further, the establishing a time-varying acceleration failure time model facing the highway traffic accident duration prediction according to the prediction variable comprises the following steps:
Dividing the duration T i of the ith highway traffic accident into k consecutive and non-overlapping periods: [ t 0,t1]、(t1,t2]、…、(tk-1,tk ] wherein 0 = t 0<t1<t2<…<tk-1<tk＝Ti; the predicted variable remains unchanged during each period, but changes at different periods;
Let ht|x j) and X j be the set of risk functions and predicted variables, respectively, over period j, assuming the functional relationship between the risk functions and the set of predicted variables is as follows:
h(t|Xj)＝h0[t·exp(βXj)]exp(-βXj)
Wherein beta is a coefficient vector to be estimated corresponding to a prediction variable set, and h 0 ()' is a reference risk function;
On the condition that the accident duration exceeds t j-1, the probability that the accident duration exceeds t j is calculated as:
The survival probability of the accident duration exceeding t k is:
Further, the selecting the optimal time-varying acceleration failure time model according to the AIC index includes:
Performing parameter estimation on a time-varying acceleration failure time model by using a maximum likelihood method;
For the ith incident, the number likelihood function of the time-varying acceleration failure time model is:
because the reference risk function can obtain different model parameter estimation results from different distributions, model performance comparison is carried out through AIC indexes, and an optimal time-varying acceleration failure time model is selected; AIC is defined as follows:
AIC＝2(K-LL(β))
Where LL (β) is a log likelihood value when the model converges, and K is the number of parameters to be estimated in the model.
Further, the reference risk function obeys one of the following distributions: exponential distribution, weibull distribution, loglogistic distribution, gompertz distribution, and generalized Gamma distribution.
Further, for the highway traffic accident to be predicted, traffic accident data is obtained, and a duration survival function curve is obtained according to the traffic accident data and the optimal time-varying acceleration failure time model, so as to realize the prediction of the duration of the highway traffic accident, including:
Obtaining values of time-varying factors and time-varying factors in each period of the highway traffic accident for the highway traffic accident to be predicted;
Calculating the survival probability of each time point by utilizing an optimal time-varying acceleration failure time model, and drawing an accident duration survival function curve;
and determining a survival probability critical value, and when the survival probability of the accident is equal to the survival probability critical value, obtaining the corresponding time as the predicted value of the duration of the accident.
The invention adopts another technical scheme that:
a highway traffic accident duration prediction system, comprising:
the data acquisition module is used for acquiring historical traffic data of the expressway, carrying out data space-time correlation by taking traffic accidents as units, and constructing a data set;
the variable acquisition module is used for carrying out correlation test and collinearity diagnosis on the observation factors in the data set to acquire a predicted variable of the duration of the traffic accident; wherein the observation factors include time-varying factors and time-invariant factors;
the model construction module is used for establishing a time-varying acceleration failure time model facing the expressway traffic accident duration prediction according to the prediction variable, and selecting an optimal time-varying acceleration failure time model according to the AIC index;
The time prediction module is used for obtaining traffic accident data for the expressway traffic accident to be predicted, and obtaining a duration survival function curve according to the traffic accident data and the optimal time-varying acceleration failure time model to realize the prediction of the expressway traffic accident duration.
The invention adopts another technical scheme that:
an expressway traffic accident duration prediction apparatus, comprising:
At least one processor;
at least one memory for storing at least one program;
the at least one program, when executed by the at least one processor, causes the at least one processor to implement the method described above.
The invention adopts another technical scheme that:
A computer readable storage medium, in which a processor executable program is stored, which when executed by a processor is adapted to carry out the method as described above.
The beneficial effects of the invention are as follows: the invention fully considers time-varying factors and time-invariant factors, so that the model is established more accurately. In addition, a time-varying acceleration failure time model is used instead of a machine learning method, and a statistical analysis model can give out clear explanation of the influence of each variable on the duration of the accident, so that basis is provided for emergency treatment of the expressway, and the method has a relatively high application value.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following description is made with reference to the accompanying drawings of the embodiments of the present invention or the related technical solutions in the prior art, and it should be understood that the drawings in the following description are only for convenience and clarity of describing some embodiments in the technical solutions of the present invention, and other drawings may be obtained according to these drawings without the need of inventive labor for those skilled in the art.
FIG. 1 is a flow chart of steps of a method for predicting duration of an expressway traffic accident in an embodiment of the invention;
Fig. 2 is a schematic diagram of a survival function of a highway traffic accident according to the embodiment of the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the invention. The step numbers in the following embodiments are set for convenience of illustration only, and the order between the steps is not limited in any way, and the execution order of the steps in the embodiments may be adaptively adjusted according to the understanding of those skilled in the art.
In the description of the present invention, it should be understood that references to orientation descriptions such as upper, lower, front, rear, left, right, etc. are based on the orientation or positional relationship shown in the drawings, are merely for convenience of description of the present invention and to simplify the description, and do not indicate or imply that the apparatus or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus should not be construed as limiting the present invention.
In the description of the present invention, a number means one or more, a number means two or more, and greater than, less than, exceeding, etc. are understood to not include the present number, and above, below, within, etc. are understood to include the present number. The description of the first and second is for the purpose of distinguishing between technical features only and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present invention, unless explicitly defined otherwise, terms such as arrangement, installation, connection, etc. should be construed broadly and the specific meaning of the terms in the present invention can be reasonably determined by a person skilled in the art in combination with the specific contents of the technical scheme.
As shown in fig. 1, the present embodiment provides a method for predicting the duration of an expressway traffic accident, which can effectively overcome the defect that the prior art does not consider the time-varying characteristics of part of the predicted variables. The method specifically comprises the following steps:
S1, acquiring historical traffic data of the expressway, and performing data space-time correlation by taking traffic accidents as units to construct a data set.
And acquiring expressway traffic accident data, road design data, real-time traffic flow data and real-time meteorological data, preprocessing the data, and carrying out data space-time correlation by taking traffic accidents as units to construct an expressway traffic accident duration prediction data set.
The highway traffic accident data mentioned in this step mainly includes accident duration, road yield loss, accident-related vehicle type, degree of casualties, collision type, lane occupancy, workdays, accident occurrence period, road conditions (e.g., horizontal curvature, gradient, bridge, and ramp). The real-time traffic flow data comprises real-time road section traffic flow and the ratio of vehicles of each vehicle type in the real-time traffic flow. The real-time traffic flow is the traffic flow of the car converted into equivalent, and needs to be converted according to the traffic composition ratio given by the detector. The real-time weather data includes real-time wind speed, rainfall, visibility, temperature and humidity. Accident influencing factor variables can be classified into fixed variables and time-varying variables. The fixed variables refer to variables which do not change with time in the model, such as road yield loss, accident-related vehicle types, road conditions, and the like; the time-varying variable refers to a variable that changes with time in the model, and in this patent refers to an accident-influencing variable that changes every small time after an accident occurs to before the end of the clearing of the accident. Meteorological influencing factors and traffic flow data are often analyzed as time-varying variables, with the specific time interval division depending on the dataset characteristics.
In data preprocessing, the steps to be completed include data cleaning, classification variable processing and the like. Data cleaning refers to cleaning up abnormal data, which in this embodiment refers to removing missing or abnormal data for the duration of an incident, including data for the duration of an incident of 0 and for the duration of an incident of greater than 1000 minutes. In this embodiment, the classification variable processing refers to setting one of classification variables containing n items (n.gtoreq.2) to an unreferenced item, and converting the other n-1 items to virtual (dummy) variables represented by "0-1" values. Taking the classified variable of 'accident severity' as an example, the accident severity is divided into three categories of serious injury or death, light injury and no injury, the no injury is taken as a reference item, and the serious injury or death and the light injury are processed according to whether the serious injury or the death and the light injury occur or not and are converted into '0-1' variables.
The traffic flow data and the data of the accident occurrence period of the weather station data are correlated with the accident impact data, and the impact variable in the accident data is a fixed variable throughout the accident duration, but the weather data and the traffic flow data may change with time throughout the accident duration. In accident handling, it is necessary to correspond a time-varying variable with a fixed variable, the correspondence rule being dependent on the minimum time interval in the time-varying variable. Given that the time-varying variables include 10 minutes of average wind speed and 5 minutes of vehicle flow, table 1 gives examples of time-varying variable data. The example minimum interval is 5 minutes, the wind speed is a 1 in the interval of 0-5 minutes and the value of 5-10 minutes, the vehicle flow is b 1 in the interval of 0-5 minutes, and the value of b 2 in the interval of 5-10 minutes. It should be noted that the examples are for illustration only, and that the particular time-varying intervals depend on the data set.
Table 1 time-variant variable data corresponding example
S2, carrying out correlation test and collinearity diagnosis on observation factors in the data set to obtain a predicted variable of the duration of the traffic accident; wherein the observation factors include time-varying factors and time-invariant factors.
And carrying out correlation test and collinearity diagnosis on the observed factors in the data set, eliminating factors with obvious correlation or obvious collinearity with other factors, and taking the rest factors as predicted variables of the duration of the traffic accident.
The observational factors in the dataset include both time-varying factors and time-invariant factors. Wherein the time-varying factors include: traffic flow, traffic composition, wind speed, precipitation, visibility, air temperature and humidity within a short period of time (e.g., 5 minutes or 10 minutes) after the incident occurs to before the end of the incident clearance; the time-invariant factors include: culprit vehicle type and damage level, accident severity, accident type and road conditions at the accident site (e.g. horizontal curvature, grade, bridge and ramp).
The preprocessed data needs to exclude variables with significant correlation or significant collinearity before the time-varying acceleration failure time model can be input. Correlation checking and colinear diagnosis are performed on variables in the dataset. An absolute value of the correlation coefficient greater than 0.6 indicates that there is a strong correlation between the variables and possibly a collinearly relationship. In the collinearity statistic, if the tolerance is less than 0.2 or the variance expansion factor is greater than 10, then multiple collinearity is considered to exist. And according to the correlation analysis and the co-linearity test result, combining the representativeness and the importance of each factor, and eliminating the observation result with obvious correlation or obvious co-linearity with other factors.
And S3, establishing a time-varying acceleration failure time model facing the expressway traffic accident duration prediction according to the prediction variable, and selecting an optimal time-varying acceleration failure time model according to the AIC index.
The highway accident duration studied by the problem refers to the period from the time of occurrence of the traffic accident to the time when the rescue team clears the obstacle interfering with the traffic operation and the time when the road resumes the traffic.
The survival time, namely the duration of the highway accident, is represented by T, and the distribution function of T is as follows:
F(t)＝P(T≤t)＝∫0 tf(u)du
Wherein t represents the duration of the accident; f (T) represents a probability density function of the duration T of the accident.
The survival function of T is denoted by S (T), and represents the probability that an accident has not been processed until the time T, which is also called the cumulative survival probability, and the formula is:
S(t)＝1-F(t)＝P(T>t)＝∫t ∞f(u)du
the survival function corresponds to a risk function, which is denoted by h (t). h (t) represents the conditional probability that the accident is still sustained at time t+dt (dt is a very small time interval) under the condition that the accident is sustained until time t:
the slope of the risk function may reflect the dependency of the duration ending probability on the duration length. If it is As the duration of the accident is prolonged, the probability of the accident ending soon increases; if/>As the duration of the incident is extended, the probability of the incident ending soon decreases; if/>The probability of the accident duration ending is independent of the duration length.
The accelerated failure time model belongs to a full parameter model in survival analysis, and the key assumption is that when covariates of different levels are compared, the survival time accelerates or decelerates by a constant factor.
The survival function (probability of an accident remaining untreated up to time t) of the accelerated failure time model is written as:
S(t|X)＝S0[t·exp(βX)]
where X is the covariate vector affecting the duration of the incident and beta is the vector of estimated coefficients. S 0 (-) is a baseline survival function.
The risk function (the conditional probability that the accident is still sustained at the time t+dt under the condition that the accident is sustained to the time t) of the acceleration failure time model is:
h(t|X)＝h0[t·exp(βX)]exp(-βX)
Where h 0 (-) is the baseline risk function. When using the accelerated failure time model, it is generally assumed that the baseline risk function may conform to an exponential distribution, a Weibull distribution, a Loglogistic distribution, a Gompertz distribution, and a generalized Gamma distribution. The survival and risk functions corresponding to the different distributions are shown in table 2.
TABLE 2 survival and Risk function tables of different distributions
The accelerated failure time model allows discussion of the effects of time-varying variables by extending the model, assuming t i is the duration of the ith incident, which can be divided into k non-overlapping but consecutive intervals: [ t 0,t1],(t1,t2 ], …, and [ t k-1,tk ], wherein 0=t 0<t1<t2<…<tk-1<tk＝ti. Wherein the lengths of the k time intervals are not necessarily the same. These covariates remain constant during each cell time interval and change during different time intervals.
The risk function for the j-th period ((t j-1,tj],if 1<j<k;or[tj-1,tj ], if j=1, k) is:
ht|Xj)＝h0[t·exp(βXj)]exp(-βXj)
Where β is an estimated coefficient vector (including a constant, β 0),h0 ()) for the corresponding covariate vector is the baseline risk function.
Under this assumption, the probability of highway accident duration re-continuing to t j under the condition of reaching t j-1 is:
the survival function at t k is expressed as:
The model is solved using a maximum likelihood method, and for the ith incident, its log likelihood function can be written as:
The AIC index is used to reflect the fitting effect of the model. In general, the smaller the AIC value, the better the fitting effect. And calculating AIC index values of different models corresponding to different distributions, wherein the AIC index value is the best model.
The definition of the AIC index is:
AIC＝2(K-LL(β))
Where LL (β) is a log likelihood value at the time of model convergence, and K is the number of estimation parameters.
As an alternative embodiment, the Weibull distribution and Loglogistic distribution are used to estimate the risk function:
weibull distribution:
h(t)＝λp(λt)p-1
loglogistic distribution:
Where λ and p are the position parameter and the scale parameter, respectively.
Under this assumption, the probability of the highway accident duration continuing again to t j under the condition of reaching t j-1 is
The survival function at t k is expressed as:
the model is solved using a maximum likelihood method, the log likelihood function of which can be written for the ith incident
The construction of the second term of the Log likelihood function requires an indefinite integration of the function corresponding to the different distributions, the indefinite integration corresponding to the Weibull distribution being in the form of (λt) p and the indefinite integration corresponding to the Log logistic distribution being in the form of Log [1+ (λt) p ].
And (5) performing model comparison and selection through AIC values, and selecting the optimal model.
S4, for the expressway traffic accident to be predicted, traffic accident data are obtained, and a duration survival function curve is obtained according to the traffic accident data and the optimal time-varying acceleration failure time model, so that the prediction of the expressway traffic accident duration is realized.
For any highway traffic accident, the optimal time-varying acceleration failure time model is utilized to draw a duration survival function curve according to the value of the relevant factors, and the accident duration is predicted according to the duration survival function curve.
The result obtained by solving the model in the step S3 includes the shape parameter of the parameter distribution and the mean value and standard deviation of the influencing factors, and a survival function of the calibrated parameters is obtained according to the model parameter estimation result, and the value of the relevant factor is substituted into the optimal time-varying acceleration failure model to obtain a survival function curve, see fig. 2 in particular. It is generally considered that an incident has ended when the incident continues with a probability of less than 10%. The time period during which the survival probability of the accident duration was changed from 100% to 10% was recorded as the accident duration.
In summary, compared with the prior art, the method of the embodiment has the following advantages and beneficial effects:
(1) According to the method, the time-varying characteristics of the accident influencing factors are considered instead of considering the accident influencing factors as fixed variables, so that the model can be built more accurately, and the prediction accuracy is improved. The method can obtain more accurate prediction duration, also considers the influence of time-varying factors on the accident duration, so that the model is closer to the actual situation, and has practical application value.
(2) The invention uses a time-varying acceleration failure time model instead of a machine learning method, and the statistical analysis model can give out clear explanation of the influence of each variable on the duration of the accident, thereby providing basis for emergency treatment of the expressway and having stronger application value.
The embodiment also provides a highway traffic accident duration prediction system, which comprises:
the data acquisition module is used for acquiring historical traffic data of the expressway, carrying out data space-time correlation by taking traffic accidents as units, and constructing a data set;
the variable acquisition module is used for carrying out correlation test and collinearity diagnosis on the observation factors in the data set to acquire a predicted variable of the duration of the traffic accident; wherein the observation factors include time-varying factors and time-invariant factors;
the model construction module is used for establishing a time-varying acceleration failure time model facing the expressway traffic accident duration prediction according to the prediction variable, and selecting an optimal time-varying acceleration failure time model according to the AIC index;
The time prediction module is used for obtaining traffic accident data for the expressway traffic accident to be predicted, and obtaining a duration survival function curve according to the traffic accident data and the optimal time-varying acceleration failure time model to realize the prediction of the expressway traffic accident duration.
The expressway traffic accident duration prediction system provided by the embodiment of the invention can be used for executing the expressway traffic accident duration prediction method provided by the embodiment of the invention, and any combination of the embodiment of the method can be executed, so that the method has corresponding functions and beneficial effects.
The embodiment also provides a highway traffic accident duration prediction device, which comprises:
At least one processor;
at least one memory for storing at least one program;
The at least one program, when executed by the at least one processor, causes the at least one processor to implement the method illustrated in fig. 1.
The expressway traffic accident duration prediction device provided by the embodiment of the invention can be used for executing the expressway traffic accident duration prediction method provided by the embodiment of the invention, and any combination of the embodiment of the method can be executed, so that the method has corresponding functions and beneficial effects.
Embodiments of the present application also disclose a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The computer instructions may be read from a computer-readable storage medium by a processor of a computer device, and executed by the processor, to cause the computer device to perform the method shown in fig. 1.
The embodiment also provides a storage medium which stores instructions or programs for executing the highway traffic accident duration prediction method provided by the embodiment of the method, and when the instructions or programs are run, the steps can be implemented by any combination of the embodiments of the executable method, so that the method has corresponding functions and beneficial effects.
In some alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may in fact be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, the embodiments presented and described in the flowcharts of the present invention are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed, and in which sub-operations described as part of a larger operation are performed independently.
Furthermore, while the invention is described in the context of functional modules, it should be appreciated that, unless otherwise indicated, one or more of the described functions and/or features may be integrated in a single physical device and/or software module or one or more functions and/or features may be implemented in separate physical devices or software modules. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary to an understanding of the present invention. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be apparent to those skilled in the art from consideration of their attributes, functions and internal relationships. Accordingly, one of ordinary skill in the art can implement the invention as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative and are not intended to be limiting upon the scope of the invention, which is to be defined in the appended claims and their full scope of equivalents.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
In the foregoing description of the present specification, reference has been made to the terms "one embodiment/example", "another embodiment/example", "certain embodiments/examples", and the like, means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the invention, the scope of which is defined by the claims and their equivalents.
While the preferred embodiment of the present application has been described in detail, the present application is not limited to the above embodiments, and various equivalent modifications and substitutions can be made by those skilled in the art without departing from the spirit of the present application, and these equivalent modifications and substitutions are intended to be included in the scope of the present application as defined in the appended claims.
Claims (8)
1. A method for predicting the duration of an expressway traffic accident, comprising the steps of:
acquiring historical traffic data of a highway, carrying out data space-time association by taking traffic accidents as units, and constructing a data set;
Carrying out correlation test and collinearity diagnosis on observation factors in the data set to obtain a predicted variable of the duration of the traffic accident; wherein the observation factors include time-varying factors and time-invariant factors;
Establishing a time-varying acceleration failure time model facing the expressway traffic accident duration prediction according to the prediction variable, and selecting an optimal time-varying acceleration failure time model according to the AIC index;
For highway traffic accidents to be predicted, traffic accident data are obtained, and a duration survival function curve is obtained according to the traffic accident data and an optimal time-varying acceleration failure time model, so that the prediction of the duration of the highway traffic accidents is realized; the time-varying acceleration failure time model facing the highway traffic accident duration prediction is established according to the prediction variable, and the time-varying acceleration failure time model comprises the following steps:
Dividing the duration T i of the ith highway traffic accident into k consecutive and non-overlapping periods: [ t 0,t1]、(t1,t2]、…、(tk-1,tk ] wherein 0 = t 0<t1<t2<…<tk-1<tk＝Ti; the predicted variable remains unchanged during each period, but changes at different periods;
Let h (t|x j) and X j be the risk function and the set of predicted variables, respectively, over period j, assuming the functional relationship between the risk function and the set of predicted variables is as follows:
h(t|Xj)＝h0[t·exp(βXj)]exp(-βXj)
Wherein beta is a coefficient vector to be estimated corresponding to a prediction variable set, and h 0 ()' is a reference risk function;
On the condition that the accident duration exceeds t j-1, the probability that the accident duration exceeds t j is calculated as:
The survival probability of the accident duration exceeding t k is:
the selecting the optimal time-varying acceleration failure time model according to the AIC index comprises the following steps:
Performing parameter estimation on a time-varying acceleration failure time model by using a maximum likelihood method;
For the ith incident, the number likelihood function of the time-varying acceleration failure time model is:
because the reference risk function can obtain different model parameter estimation results from different distributions, model performance comparison is carried out through AIC indexes, and an optimal time-varying acceleration failure time model is selected; AIC is defined as follows:
AIC＝2(K-LL(β))
Where LL (β) is a log likelihood value when the model converges, and K is the number of parameters to be estimated in the model.
2. The method of claim 1, wherein the historical traffic data includes highway traffic accident data, real-time traffic flow data, and real-time weather data;
The time-varying factors include: traffic flow, traffic composition, wind speed, precipitation, visibility, air temperature and humidity in every preset time period from the occurrence of an accident to the completion of the removal of the accident;
The time-invariant factors include: the type and damage of the hit-accident vehicle, the severity of the accident casualties, the type of accident and the road conditions of the accident site.
3. The method for predicting duration of an expressway traffic accident, according to claim 2, wherein said correlation and co-linearity diagnosing of the observers in the data set comprises:
respectively carrying out correlation test and colinear diagnosis on the time-varying factors and the time-invariant factors;
in the correlation test, if the correlation coefficient between the two factor variables meets the preset range, judging that the correlation exists between the two factor variables;
In the co-linearity diagnosis, if the tolerance is smaller than a first preset threshold value or the variance expansion factor is larger than a second preset threshold value, the co-linearity exists among the factor variables;
And eliminating the observation factors with correlation or collinearity according to the correlation test and the collinearity diagnosis result, and taking the rest observation factors as the prediction variables of the duration of the traffic accident.
4. The method of claim 1, wherein the reference risk function is subject to one of the following distributions: exponential distribution, weibull distribution, loglogistic distribution, gompertz distribution, and generalized Gamma distribution.
5. The method for predicting the duration of an expressway traffic accident according to claim 1, wherein the steps of obtaining traffic accident data for an expressway traffic accident to be predicted, obtaining a duration survival function curve according to the traffic accident data and an optimal time-varying acceleration failure time model, and predicting the duration of the expressway traffic accident comprise:
Obtaining values of time-varying factors and time-varying factors in each period of the highway traffic accident for the highway traffic accident to be predicted;
Calculating the survival probability of each time point by utilizing an optimal time-varying acceleration failure time model, and drawing an accident duration survival function curve;
and determining a survival probability critical value, and when the survival probability of the accident is equal to the survival probability critical value, obtaining the corresponding time as the predicted value of the duration of the accident.
6. A highway traffic accident duration prediction system, comprising:
the data acquisition module is used for acquiring historical traffic data of the expressway, carrying out data space-time correlation by taking traffic accidents as units, and constructing a data set;
the variable acquisition module is used for carrying out correlation test and collinearity diagnosis on the observation factors in the data set to acquire a predicted variable of the duration of the traffic accident; wherein the observation factors include time-varying factors and time-invariant factors;
the model construction module is used for establishing a time-varying acceleration failure time model facing the expressway traffic accident duration prediction according to the prediction variable, and selecting an optimal time-varying acceleration failure time model according to the AIC index;
The time prediction module is used for obtaining traffic accident data for the expressway traffic accident to be predicted, obtaining a duration survival function curve according to the traffic accident data and the optimal time-varying acceleration failure time model, and realizing the prediction of the expressway traffic accident duration;
the time-varying acceleration failure time model facing the highway traffic accident duration prediction is established according to the prediction variable, and the time-varying acceleration failure time model comprises the following steps:
Dividing the duration T i of the ith highway traffic accident into k consecutive and non-overlapping periods: [ t 0,t1]、(t1,t2]、…、(tk-1,tk ] wherein 0 = t 0＜t1＜t2＜…＜tk-1＜tk＝Ti; the predicted variable remains unchanged during each period, but changes between different periods;
Let h (t|x j) and X j be the risk function and the set of predicted variables, respectively, over period j, assuming the functional relationship between the risk function and the set of predicted variables is as follows:
h(t|Xj)＝h0[t·exp(βXj)]exp(-βXj)
Wherein beta is a coefficient vector to be estimated corresponding to a prediction variable set, and h 0 ()' is a reference risk function;
On the condition that the accident duration exceeds t j-1, the probability that the accident duration exceeds t j is calculated as:
The survival probability of the accident duration exceeding t k is:
the selecting the optimal time-varying acceleration failure time model according to the AIC index comprises the following steps:
Performing parameter estimation on a time-varying acceleration failure time model by using a maximum likelihood method;
For the ith incident, the number likelihood function of the time-varying acceleration failure time model is:
because the reference risk function can obtain different model parameter estimation results from different distributions, model performance comparison is carried out through AIC indexes, and an optimal time-varying acceleration failure time model is selected; AIC is defined as follows:
AIC＝2(K-LL(β))
Where LL (β) is a log likelihood value when the model converges, and K is the number of parameters to be estimated in the model.
7. A highway traffic accident duration prediction apparatus, comprising:
At least one processor;
at least one memory for storing at least one program;
the at least one program, when executed by the at least one processor, causes the at least one processor to implement the method of any one of claims 1-5.
8. A computer readable storage medium, in which a processor executable program is stored, characterized in that the processor executable program is for performing the method according to any of claims 1-5 when being executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211114003.9A CN115547037B (en) | 2022-09-14 | 2022-09-14 | Expressway traffic accident duration prediction method, system, device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211114003.9A CN115547037B (en) | 2022-09-14 | 2022-09-14 | Expressway traffic accident duration prediction method, system, device and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115547037A CN115547037A (en) | 2022-12-30 |
| CN115547037B true CN115547037B (en) | 2024-05-28 |
Family
ID=84728385
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211114003.9A Active CN115547037B (en) | 2022-09-14 | 2022-09-14 | Expressway traffic accident duration prediction method, system, device and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115547037B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109671266A (en) * | 2018-11-26 | 2019-04-23 | 北京交通大学 | Based on the pilot accident's dynamic early-warning method for accelerating failure risk model |
| CN110223533A (en) * | 2019-06-19 | 2019-09-10 | 同济大学 | A kind of resident parking facilities' forecasting method of the night based on survival analysis |
| CN112837533A (en) * | 2021-01-08 | 2021-05-25 | 合肥工业大学 | Highway accident frequency prediction method considering risk factor time-varying characteristics |
| KR102422235B1 (en) * | 2022-05-26 | 2022-07-15 | (주)에스엔테크 | System for intelligently notifying traffic jam in tunnel |
-
2022
- 2022-09-14 CN CN202211114003.9A patent/CN115547037B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109671266A (en) * | 2018-11-26 | 2019-04-23 | 北京交通大学 | Based on the pilot accident's dynamic early-warning method for accelerating failure risk model |
| CN110223533A (en) * | 2019-06-19 | 2019-09-10 | 同济大学 | A kind of resident parking facilities' forecasting method of the night based on survival analysis |
| CN112837533A (en) * | 2021-01-08 | 2021-05-25 | 合肥工业大学 | Highway accident frequency prediction method considering risk factor time-varying characteristics |
| KR102422235B1 (en) * | 2022-05-26 | 2022-07-15 | (주)에스엔테크 | System for intelligently notifying traffic jam in tunnel |
Non-Patent Citations (2)
| Title |
|---|
| A Deep Learning Approach to the Citywide Traffic Accident Risk Prediction;Honglei Ren 等;《 2018 21st International Conference on Intelligent Transportation Systems (ITSC)》;20181209;全文 * |
| 区域高速路网交通事故影响区划分及交通诱导;金书鑫;王建军;徐嫚谷;长安大学学报(自然科学版);20170315(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115547037A (en) | 2022-12-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110288096B (en) | Prediction model training method, prediction model training device, prediction model prediction method, prediction model prediction device, electronic equipment and storage medium | |
| KR101617349B1 (en) | Diagnostic system and method for the analysis of driving behavior | |
| CN107153914B (en) | System and method for evaluating automobile operation risk | |
| CN110849807B (en) | Monitoring method and system suitable for road visibility based on deep learning | |
| CN110588658B (en) | Method for detecting risk level of driver based on comprehensive model | |
| CN113091872B (en) | Method and device for diagnosing fault sensor | |
| CN112634614B (en) | Long downhill traffic incident real-time detection method, device and storage medium | |
| CN111126868B (en) | Road traffic accident occurrence risk determination method and system | |
| CN110473085B (en) | Vehicle risk discrimination method and device | |
| CN106910334B (en) | Method and device for predicting road section conditions based on big data | |
| CN111582589A (en) | Car rental insurance prediction method, device, equipment and storage medium | |
| CN115547037B (en) | Expressway traffic accident duration prediction method, system, device and medium | |
| CN115565373B (en) | Expressway tunnel accident real-time risk prediction method, device, equipment and medium | |
| CN110705628B (en) | Method for detecting risk level of driver based on hidden Markov model | |
| Watanabe et al. | A method for the estimation of coexisting risk-inducing factors in traffic scenarios | |
| CN111832834B (en) | Airport pavement service performance prediction method and device and electronic equipment | |
| CN115963344A (en) | Fault detection method and device, electronic equipment and storage medium | |
| CN115034451A (en) | Short-term early warning method for highway dense fog low visibility Logistic regression | |
| CN114565155A (en) | Road safety testing method and device, electronic equipment and storage medium | |
| CN114004268A (en) | Online diagnosis method and device for traction system fault | |
| CN117408855B (en) | Reservoir engineering safety management method, system, storage medium and computer equipment | |
| CN115345247B (en) | Model training and highway axle load determining method, device, equipment and medium | |
| CN117629637B (en) | Aeroengine bearing fault diagnosis method and diagnosis system | |
| CN112162911B (en) | Abnormal business operation behavior detection method, device, equipment and readable storage medium | |
| CN117711207A (en) | Method and system for early warning collision of meeting vehicles at curve intersection |
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 |