CN110533905A - A kind of method of forecasting traffic flow, system and equipment - Google Patents
A kind of method of forecasting traffic flow, system and equipment Download PDFInfo
- Publication number
- CN110533905A CN110533905A CN201910595128.XA CN201910595128A CN110533905A CN 110533905 A CN110533905 A CN 110533905A CN 201910595128 A CN201910595128 A CN 201910595128A CN 110533905 A CN110533905 A CN 110533905A
- Authority
- CN
- China
- Prior art keywords
- bird
- nest position
- nest
- traffic flow
- updated
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—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
- G08G1/0125—Traffic data processing
- G08G1/0133—Traffic data processing for classifying traffic situation
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application discloses a kind of methods of forecasting traffic flow, comprising: the initial parameter of preset radial basis function neural network is determined by improved cuckoo algorithm；The freeway traffic flow data of input are pre-processed, training sample is obtained；Preset radial basis function neural network is trained using training sample, forecasting traffic flow model is obtained: traffic flow being predicted using forecasting traffic flow model.Technical solution provided herein, the initial parameter of preset radial basis function neural network is determined by improved cuckoo algorithm, then traffic flow is predicted using forecasting traffic flow model, so that obtained forecasting traffic flow model has faster convergence rate and better precision of prediction, there is very good effect in freeway traffic flow prediction.The application additionally provides the system, equipment and computer readable storage medium of a kind of forecasting traffic flow simultaneously, has above-mentioned beneficial effect.
Description
Technical field
This application involves forecasting traffic flow field, in particular to a kind of method of forecasting traffic flow, system, equipment and meter
Calculation machine readable storage medium storing program for executing.
Background technique
In recent years, highway vehicle flowrate is more and more, causes traffic problems further serious, not only causes congestion in road,
Certain threat can be also brought to people's security of the lives and property, therefore is that current social is badly in need of solution to effective control of traffic flow
Certainly the problem of.And cuckoo searching algorithm (Cuckoo Search, CS) has very strong global optimizing ability, can be good at
It applies on freeway traffic flow prediction model, but with the popularization that CS algorithm is applied, experiment shows CS algorithm in iteration mistake
Cheng Zhong cannot jump out current optimal solution due to the limitation of search capability, so that effective control of highway vehicle flowrate becomes
It is very difficult.
Therefore, how to carry out Accurate Prediction to the traffic flow of highway is that those skilled in the art need to solve at present
The technical issues of.
Summary of the invention
The purpose of the application is to provide method, system, equipment and the computer-readable storage medium of a kind of forecasting traffic flow
Matter carries out Accurate Prediction for the traffic flow to highway.
In order to solve the above technical problems, the application provides a kind of method of forecasting traffic flow, this method comprises:
The initial parameter of preset radial basis function neural network is determined by improved cuckoo algorithm；
The freeway traffic flow data of input are pre-processed, training sample is obtained；
The preset radial basis function neural network is trained using the training sample, obtains forecasting traffic flow
Model:
Traffic flow is predicted using the forecasting traffic flow model.
Optionally, the initial parameter that preset radial basis function neural network is determined by improved cuckoo algorithm,
Include:
The parameter of the radial basis function neural network is encoded；
Initialize the parameter of the improved cuckoo algorithm；
Determine the fitness function of the improved cuckoo algorithm；
The fitness value of all Bird's Nest positions is determined according to the fitness function, and true according to each fitness value
Fixed optimal Bird's Nest position；
Using Bird's Nest position described in improvement monkey hill climbing process policy update, and is determined and updated according to the fitness function
The fitness value of the Bird's Nest position afterwards；
Judge whether the fitness value of the updated Bird's Nest position is greater than the adaptation of the optimal Bird's Nest position
Angle value；
If so, being the updated Bird's Nest position by optimal Bird's Nest location updating.
Optionally, by optimal Bird's Nest location updating be the updated Bird's Nest position after, further includes:
Adaptive updates are carried out to probability is recognized；
Random number is generated, and judges whether the random number is greater than and updated described recognizes probability；
If so, changing the Bird's Nest position at random, and according to after the determining random change of the fitness function
The fitness value of Bird's Nest position；
Whether the fitness value of the Bird's Nest position after the random change of judgement is greater than the adaptation of the optimal Bird's Nest position
Angle value；
If the fitness value of the Bird's Nest position after random change is greater than the fitness value of the optimal Bird's Nest position,
It is then the Bird's Nest position after random change by optimal Bird's Nest location updating.
It is optionally, described using Bird's Nest position described in improvement monkey hill climbing process policy update, comprising:
According to i-th of Bird's Nest position xi=(xi1,xi2,…,xin) and formulaDetermine described i-th
A Bird's Nest gets over journey coefficient delta xi；Wherein, Δ xi=(Δ xi1,Δxi2,...,Δxin)；
Journey coefficient delta x is got over according to describediPass through formulaCalculate pseudo- gradient
Vector f 'ij(xi)；
According to the pseudo- gradient vector f 'ij(xi) pass through formulaCalculate updated Bird's Nest
Position yi；Wherein, yi=(yi1,yi2,...,yin)；
Judge the updated Bird's Nest position yiWhether in the reasonable scope and f (y is meti)≥f(xi)；
If so, by i-th of Bird's Nest position xiIt is updated to the updated Bird's Nest position yi；
If it is not, then keeping i-th of Bird's Nest position xiIt is constant；
Wherein, a is step-length of climbing the mountain, and χ is the random number for belonging to [0,1], and sign is sign function.
The application also provides a kind of system of forecasting traffic flow, which includes:
Determining module, for determining the initial ginseng of preset radial basis function neural network by improved cuckoo algorithm
Number；
Preprocessing module obtains training sample for pre-processing to the freeway traffic flow data of input；
Training module is obtained for being trained using the training sample to the preset radial basis function neural network
To forecasting traffic flow model:
Prediction module, for being predicted using the forecasting traffic flow model traffic flow.
Optionally, the determining module includes:
Encoding submodule is encoded for the parameter to the radial basis function neural network；
Initialization submodule, for initializing the parameter of the improved cuckoo algorithm；
First determines submodule, for determining the fitness function of the improved cuckoo algorithm；
Second determines submodule, for determining the fitness value of all Bird's Nest positions, and root according to the fitness function
Optimal Bird's Nest position is determined according to each fitness value；
First updates submodule, improves Bird's Nest position described in monkey hill climbing process policy update for using, and according to described
Fitness function determines the fitness value of the updated Bird's Nest position；
First judging submodule, for judging whether the fitness value of the updated Bird's Nest position is greater than institute
State the fitness value of optimal Bird's Nest position；
Third determines submodule, is greater than for the fitness value when the updated Bird's Nest position described optimal
It is the updated Bird's Nest position by optimal Bird's Nest location updating when the fitness value of Bird's Nest position.
Optionally, the determining module further include:
Second update submodule, for recognize probability carry out adaptive updates；
Second judgment submodule for generating random number, and judges whether the random number is greater than and updated described recognizes
Probability out；
It is random to change submodule, for when the random number be greater than it is updated it is described recognize probability when, change institute at random
Bird's Nest position is stated, and determines the fitness value of the Bird's Nest position after random change according to the fitness function；
Third judging submodule, for judging whether the fitness value of the Bird's Nest position after changing at random is greater than institute
State the fitness value of optimal Bird's Nest position；
Third updates submodule, if the fitness value for the Bird's Nest position after changing at random is greater than described optimal
Optimal Bird's Nest location updating is then the Bird's Nest position after random change by the fitness value of Bird's Nest position.
Optionally, the first update submodule includes:
Determination unit, for according to i-th of Bird's Nest position xi=(xi1,xi2,…,xin) and formula
Determine i-th of Bird's Nest gets over journey coefficient delta xi；Wherein, Δ xi=(Δ xi1,
Δxi2,...,Δxin)；
First computing unit, for getting over journey coefficient delta x according toiPass through formula
Calculate pseudo- gradient vector f 'ij(xi)；
Second computing unit, for according to the pseudo- gradient vector f 'ij(xi) pass through formula
yij=xij+a·sign(f′ij(xi)) calculate updated Bird's Nest position yi；Wherein, yi=(yi1,yi2,...,
yin)；
Judging unit, for judging the updated Bird's Nest position yiWhether in the reasonable scope and f (y is meti)≥f
(xi)；
Updating unit, for working as the updated Bird's Nest position yiIn the zone of reasonableness and meet f (yi)≥f
(xi) when, by i-th of Bird's Nest position xiIt is updated to the updated Bird's Nest position yi；
Holding unit, for working as the updated Bird's Nest position yiNot in the zone of reasonableness or it is unsatisfactory for f (yi)
≥f(xi) when, keep i-th of Bird's Nest position xiIt is constant；
Wherein, a is step-length of climbing the mountain, and χ is the random number for belonging to [0,1], and sign is sign function.
The application also provides a kind of forecasting traffic flow equipment, which includes:
Memory, for storing computer program；
Processor realizes the method for the forecasting traffic flow as described in any of the above-described when for executing the computer program
The step of.
The application also provides a kind of computer readable storage medium, and meter is stored on the computer readable storage medium
Calculation machine program, realizing the method for forecasting traffic flow as described in any of the above-described when the computer program is executed by processor
Step.
The method of forecasting traffic flow provided herein, comprising: preset radial base is determined by improved cuckoo algorithm
The initial parameter of Function Neural Network；The freeway traffic flow data of input are pre-processed, training sample is obtained；Benefit
Preset radial basis function neural network is trained with training sample, obtains forecasting traffic flow model: utilizing forecasting traffic flow
Model predicts traffic flow.
Technical solution provided herein determines preset radial Basis Function neural net by improved cuckoo algorithm
Then the initial parameter of network is trained preset radial basis function neural network using training sample, obtains forecasting traffic flow
Model finally predicts traffic flow using forecasting traffic flow model, so that obtained forecasting traffic flow model has comparatively fast
Convergence rate and better precision of prediction, freeway traffic flow prediction when have very good effect.The application also provides simultaneously
A kind of system of forecasting traffic flow, equipment and computer readable storage medium, have above-mentioned beneficial effect, no longer superfluous herein
It states.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, below will to embodiment or
Attached drawing needed to be used in the description of the prior art is briefly described, it should be apparent that, the accompanying drawings in the following description is only
Embodiments herein for those of ordinary skill in the art without creative efforts, can be with
Other attached drawings are obtained according to the attached drawing of offer.
Fig. 1 is a kind of flow chart of the method for forecasting traffic flow provided by the embodiment of the present application；
Fig. 2 is a kind of process of practical manifestation mode of S101 in a kind of method of forecasting traffic flow provided by Fig. 1
Figure；
Fig. 3 is the process of another practical manifestation mode of S101 in a kind of method of forecasting traffic flow provided by Fig. 1
Figure；
Fig. 4 is a kind of structure chart of the system of forecasting traffic flow provided by the embodiment of the present application；
Fig. 5 is the structure chart of the system of another kind forecasting traffic flow provided by the embodiment of the present application；
Fig. 6 is a kind of structure chart of forecasting traffic flow equipment provided by the embodiment of the present application.
Specific embodiment
The core of the application is to provide method, system, equipment and the computer-readable storage medium of a kind of forecasting traffic flow
Matter carries out Accurate Prediction for the traffic flow to highway.
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
In attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is
Some embodiments of the present application, instead of all the embodiments.Based on the embodiment in the application, ordinary skill people
Member's every other embodiment obtained without making creative work, shall fall in the protection scope of this application.
Referring to FIG. 1, Fig. 1 is a kind of flow chart of the method for forecasting traffic flow provided by the embodiment of the present application.
It specifically comprises the following steps:
S101: the initial parameter of preset radial basis function neural network is determined by improved cuckoo algorithm；
Cuckoo searching algorithm is a kind of novel meta-heuristic searching algorithm, and thought is based primarily upon two strategies: cuckoo
The brood parasitism and Lai Wei fly mechanics of bird.It searches for obtain an optimal bird's nest by way of random walk to hatch certainly
Oneself bird egg, this mode can achieve a kind of efficient optimizing mode, and major advantage is that parameter is few, easy to operate, Yi Shi
Now, random search path is excellent and optimizing ability is strong etc., however, experiment shows CS algorithm in an iterative process, due to search capability
Limitation, current optimal solution cannot be jumped out so that effective control of highway vehicle flowrate becomes very difficult, therefore the application
A kind of method of forecasting traffic flow is provided, for solving the above problems；
Radial basis function (Radial Basis Function, RBF) neural network is that have uniquely most preferably to approach (to overcome
Local minimum problem), the feed-forward type neural networks of the superperformances such as succinct, the study fast convergence rate of training, be proved at present
RBF can approach the nonlinear network of arbitrary continuation with arbitrary accuracy, be widely used in function approximation, speech recognition, mode knowledge
Not, the fields such as image procossing, automatic control and fault diagnosis, the application determine preset radial by improved cuckoo algorithm
The initial parameter of basis function neural network reduces the training time of radial basis function neural network, to improve to highway
The accuracy of forecasting traffic flow；
Optionally, preset radial basis function neural network mentioned herein, is specifically as follows:
Wherein, x1,x2,...,xnFor input variable, n is input layer number, ykj((k=1,2 ..., n, j=1,
2 ..., m) it is the corresponding output of k-th of input sample；wij(i=1,2...M, j=1,2 ..., m) it is that hidden layer extremely exports
The weight of layer；M is the dimension of output vector；M is node in hidden layer.φ(xk,ci) (k=1,2 ..., n, i=1,2,
... M) indicate radial basis function (using Gaussian function), such as formula:
Wherein, σiFor the standard deviation of Gaussian function；xkFor k-th of input sample；ciFor Basis Function Center；||xk-ci| | it is
The Euclidean distance of sample and center；
By radial basis function neural network input variable x1,x2,...,xnHighway before being defined as continuously in N days is handed over
Through-flow historical data；The output variable y of radial basis function neural network is defined as the highway in the N+1 days to be measured to hand over
Through-flow data.
S102: the freeway traffic flow data of input are pre-processed, training sample is obtained；
Optionally, the freeway traffic flow data mentioned herein to input pre-process, and obtain training sample,
It is specifically as follows:
History freeway traffic flow data are divided into rainstorm weather, two class of normal weather according to weather pattern, will be predicted
Freeway traffic flow historical data is as input under rainstorm weather in N days before day is continuous, and the N+1 days rainstorm weathers are at a high speed
Highway communication flow data is as output, until first N days training samples all complete by training；
According to formulaThe highway of input is handed over
Through-flow data are normalized；
Wherein, xikFor the freeway traffic flow magnitude at k-th of time point of i-th day freeway traffic flow, xmaxWith
xminThe respectively maximum value and minimum value of freeway traffic flow data, by xikValue insinuate [xnew min,xnew max]
In region, wherein xnew maxWith xnew minThe maximum value and minimum value of data after respectively handling.
S103: preset radial basis function neural network is trained using training sample, obtains forecasting traffic flow mould
Type；
It is mentioned herein, preset radial basis function neural network is trained using training sample, it is pre- to obtain traffic flow
The meaning for surveying model is, is predicted using the forecasting traffic flow model that training obtains freeway traffic flow, is mentioned
The speed and accuracy of height prediction.
S104: traffic flow is predicted using forecasting traffic flow model.
Based on the above-mentioned technical proposal, the method for a kind of forecasting traffic flow provided herein, passes through improved cuckoo
Algorithm determines the initial parameter of preset radial basis function neural network, then using training sample to preset radial basic function mind
It is trained through network, obtains forecasting traffic flow model, finally traffic flow is predicted using forecasting traffic flow model, is made
The forecasting traffic flow model that must be obtained has faster convergence rate and better precision of prediction, pre- in freeway traffic flow
There is very good effect when survey.
It is directed to the step S101 of an embodiment, wherein described determine by improved cuckoo algorithm is preset
The initial parameter of radial basis function neural network, is illustrated below with reference to Fig. 2.
Referring to FIG. 2, a kind of practical manifestation side of the Fig. 2 for S101 in a kind of method of forecasting traffic flow provided by Fig. 1
The flow chart of formula.
Itself specifically includes the following steps:
S201: the parameter of radial basis function neural network is encoded；
S202: the parameter of improved cuckoo algorithm is initialized；
Optionally, the parameter of the improved cuckoo algorithm of initialization mentioned herein, is specifically as follows:
Initialization improves cuckoo algorithm parameter: Bird's Nest the number nest, fitness function f (X) of other type birds, X=
(x1,x2…,xi)TWherein i=1,2 ..., nest, monkey climb the mountain minimum step amin, maximum step-length amax, other type birds maximums
Recognize probability P max, minimum recognizes probability P min, the error ε of permission, the maximum number of iterations tmax of algorithm.
S203: the fitness function of improved cuckoo algorithm is determined；
Optionally, mentioned herein, it is specifically as follows:
According to formulaCalculate fitness；
Wherein, average valueMeet formula
S204: the fitness value of all Bird's Nest positions is determined according to fitness function, and is determined most according to each fitness value
Excellent Bird's Nest position；
S205: it using improving monkey hill climbing process policy update Bird's Nest position, and is determined according to fitness function updated
The fitness value of Bird's Nest position；
Optionally, mentioned herein, using monkey hill climbing process policy update Bird's Nest position is improved, it is specifically as follows:
According to i-th of Bird's Nest position xi=(xi1,xi2,…,xin) and formulaDetermine i-th of bird
Nest gets over journey coefficient delta xi；Wherein, Δ xi=(Δ xi1,Δxi2,...,Δxin)；
According to getting over journey coefficient delta xiPass through formulaCalculate pseudo- gradient vector
f′ij(xi)；
According to pseudo- gradient vector f 'ij(xi) pass through formulaCalculate updated Bird's Nest position
yi；Wherein, yi=(yi1,yi2,...,yin)；
Judge updated Bird's Nest position yiWhether in the reasonable scope and f (y is meti)≥f(xi)；
If so, by i-th of Bird's Nest position xiIt is updated to updated Bird's Nest position yi；
If it is not, then keeping i-th of Bird's Nest position xiIt is constant；
Wherein, a is step-length of climbing the mountain, and χ is the random number for belonging to [0,1], gets over journey coefficient delta xiFor climbing for i-th Bird's Nest
Process factor, f 'ij(xi) it is pseudo- gradient vector, sig n is sign function, yiFor updated Bird's Nest position.
S206: judge whether the fitness value of updated Bird's Nest position is greater than the fitness value of optimal Bird's Nest position；
If so, entering step S207；
Optionally, when the fitness value of updated Bird's Nest position is less than or equal to the fitness value of optimal Bird's Nest position
When, then keep optimal Bird's Nest position constant.
S207: optimal Bird's Nest location updating is updated Bird's Nest position.
It is directed to an embodiment, after executing the step S207, step as shown in Figure 3 can also be performed, below
It is illustrated in conjunction with Fig. 3.
Referring to FIG. 3, another practical manifestation of the Fig. 3 for S101 in a kind of method of forecasting traffic flow provided by Fig. 1
The flow chart of mode.
Itself specifically includes the following steps:
S301: adaptive updates are carried out to probability is recognized；
Optionally, mentioned herein to probability progress adaptive updates are recognized, it is specifically as follows:
According to formulaAdaptive updates are carried out to probability is recognized；
Wherein, pminProbability, p are recognized for minimummaxProbability, p are recognized for maximummin、pmaxIt is all fixed value, and 0~1
Between；
When the optimized individual of population is close to globally optimal solution, adaptively recognizing probability strategy can reduce to kind of a group hunting
Range, current preferable solution is remained into the next generation, algorithm is helped to obtain optimal solution within a short period of time.
S302: generating random number, and judges whether random number is greater than and updated recognize probability；
If so, entering step S303；
Optionally, when the random number of generation be less than or equal to it is updated recognize probability when, then can keep optimal Bird's Nest
Position is constant.
S303: it is random to change Bird's Nest position, and according to the adaptation of the Bird's Nest position after the determining random change of fitness function
Angle value；
S304: whether the fitness value of the Bird's Nest position after the random change of judgement is greater than the fitness of optimal Bird's Nest position
Value；
If so, entering step S305；
Optionally, the fitness value of Bird's Nest position after random change is less than or equal to the adaptation of optimal Bird's Nest position
When angle value, then optimal Bird's Nest position can be kept constant.
S305: being the Bird's Nest position after random change by optimal Bird's Nest location updating.
Referring to FIG. 4, Fig. 4 is a kind of structure chart of the system of forecasting traffic flow provided by the embodiment of the present application.
The system may include:
Determining module 100, for determining the initial of preset radial basis function neural network by improved cuckoo algorithm
Parameter；
Preprocessing module 200 obtains training sample for pre-processing to the freeway traffic flow data of input；
Training module 300 is handed over for being trained using training sample to preset radial basis function neural network
Through-flow prediction model:
Prediction module 400, for being predicted using forecasting traffic flow model traffic flow.
Referring to FIG. 5, Fig. 5 is the structure chart of the system of another kind forecasting traffic flow provided by the embodiment of the present application.
The determining module 100 may include:
Encoding submodule is encoded for the parameter to radial basis function neural network；
Initialization submodule, for initializing the parameter of improved cuckoo algorithm；
First determines submodule, for determining the fitness function of improved cuckoo algorithm；
Second determines submodule, for determining the fitness value of all Bird's Nest positions according to fitness function, and according to each
Fitness value determines optimal Bird's Nest position；
First updates submodule, improves monkey hill climbing process policy update Bird's Nest position for using, and according to fitness letter
Number determines the fitness value of updated Bird's Nest position；
First judging submodule, for judging whether the fitness value of updated Bird's Nest position is greater than optimal Bird's Nest position
The fitness value set；
Third determines submodule, is greater than the suitable of optimal Bird's Nest position for the fitness value when updated Bird's Nest position
It is updated Bird's Nest position by optimal Bird's Nest location updating when answering angle value.
Further, which can also include:
Second update submodule, for recognize probability carry out adaptive updates；
Second judgment submodule for generating random number, and judges whether random number is greater than and updated recognizes probability；
It is random to change submodule, for when random number be greater than it is updated recognize probability when, it is random to change Bird's Nest position,
And the fitness value of the Bird's Nest position after random change is determined according to fitness function；
Third judging submodule, for judging whether the fitness value of the Bird's Nest position after changing at random is greater than optimal bird
The fitness value of nest position；
Third updates submodule, if the fitness value for the Bird's Nest position after changing at random is greater than optimal Bird's Nest position
Fitness value, then be the Bird's Nest position after random change by optimal Bird's Nest location updating.
This first update submodule may include:
Determination unit, for according to i-th of Bird's Nest position xi=(xi1,xi2,…,xin) and formula
Determine i-th of Bird's Nest gets over journey coefficient delta xi；Wherein, Δ xi=(Δ xi1,Δ
xi2,...,Δxin)；
First computing unit gets over journey coefficient delta x for basisiPass through formula
Calculate pseudo- gradient vector f 'ij(xi)；
Second computing unit, for according to pseudo- gradient vector f 'ij(xi) pass through formula
yij=xij+a·sign(f′ij(xi)) calculate updated Bird's Nest position yi；Wherein, yi=(yi1,yi2,...,
yin)；
Judging unit, for judging updated Bird's Nest position yiWhether in the reasonable scope and f (y is meti)≥f
(xi)；
Updating unit, for working as updated Bird's Nest position yiIn the reasonable scope and meet f (yi)≥f(xi) when, it will
I-th of Bird's Nest position xiIt is updated to updated Bird's Nest position yi；
Holding unit, for working as updated Bird's Nest position yiIn the reasonable scope or f (y is not unsatisfactory for iti)≥f(xi)
When, keep i-th of Bird's Nest position xiIt is constant；
Wherein, a is step-length of climbing the mountain, and χ is the random number for belonging to [0,1], gets over journey coefficient delta xiFor climbing for i-th Bird's Nest
Process factor, f 'ij(xi) it is pseudo- gradient vector, sign is sign function, yiFor updated Bird's Nest position.
Since the embodiment of components of system as directed is corresponded to each other with the embodiment of method part, the embodiment of components of system as directed
The description of the embodiment of method part is referred to, wouldn't be repeated here.
Referring to FIG. 6, Fig. 6 is a kind of structure chart of forecasting traffic flow equipment provided by the embodiment of the present application.
The forecasting traffic flow equipment 600 can generate bigger difference because configuration or performance are different, may include one
Or more than one processor (central processing units, CPU) 622 (for example, one or more processors)
With memory 632, storage medium 630 (such as one or one of one or more storage application programs 642 or data 644
A above mass memory unit).Wherein, memory 632 and storage medium 630 can be of short duration storage or persistent storage.Storage
It may include one or more modules (diagram does not mark) in the program of storage medium 630, each module may include pair
Series of instructions operation in device.Further, central processing unit 622 can be set to communicate with storage medium 630,
The series of instructions operation in storage medium 630 is executed in forecasting traffic flow equipment 600.
Forecasting traffic flow equipment 600 can also include one or more power supplys 626, one or more are wired
Or radio network interface 650, one or more input/output interfaces 658, and/or, one or more operating systems
641, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM etc..
Step in the method for forecasting traffic flow described in above-mentioned Fig. 1 to Fig. 3 is based on the figure by forecasting traffic flow equipment
Structure shown in 6 is realized.
It is apparent to those skilled in the art that for convenience and simplicity of description, foregoing description is
System, the specific work process of device and module can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed device, device and method, it can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, module is drawn
Point, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple module or components
It can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown or
The mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, device or module it is indirect
Coupling or communication connection can be electrical property, mechanical or other forms.
Module may or may not be physically separated as illustrated by the separation member, show as module
Component may or may not be physical module, it can it is in one place, or may be distributed over multiple nets
In network module.Some or all of the modules therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
It, can also be in addition, can integrate in a processing module in each functional module in each embodiment of the application
It is that modules physically exist alone, can also be integrated in two or more modules in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.
If integrated module is realized and when sold or used as an independent product in the form of software function module,
It can store in a computer readable storage medium.Based on this understanding, the technical solution of the application substantially or
Person says that all or part of the part that contributes to existing technology or the technical solution can body in the form of software products
Reveal and, which is stored in a storage medium, including some instructions are with so that a computer is set
Standby (can be personal computer, funcall device or the network equipment etc.) executes the complete of each embodiment method of the application
Portion or part steps.And storage medium above-mentioned include: USB flash disk, mobile hard disk, read-only memory (Read-Only Memory,
ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. are various can store program
The medium of code.
Above to method, system, equipment and the computer-readable storage medium of a kind of forecasting traffic flow provided herein
Matter is described in detail.Specific examples are used herein to illustrate the principle and implementation manner of the present application, above
The explanation of embodiment is merely used to help understand the present processes and its core concept.It should be pointed out that for the art
Those of ordinary skill for, under the premise of not departing from the application principle, can also to the application carry out it is several improvement and repair
Decorations, these improvement and modification are also fallen into the protection scope of the claim of this application.
It should also be noted that, in the present specification, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or behaviour
There are any actual relationship or orders between work.Moreover, the terms "include", "comprise" or its any other change
Body is intended to non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only
It including those elements, but also including other elements that are not explicitly listed, or further include for this process, method, object
Product or the intrinsic element of equipment.In the absence of more restrictions, being wanted by what sentence "including a ..." limited
Element, it is not excluded that there is also other identical elements in the process, method, article or equipment for including element.
Claims (10)
1. a kind of method of forecasting traffic flow characterized by comprising
The initial parameter of preset radial basis function neural network is determined by improved cuckoo algorithm；
The freeway traffic flow data of input are pre-processed, training sample is obtained；
The preset radial basis function neural network is trained using the training sample, obtains forecasting traffic flow model:
Traffic flow is predicted using the forecasting traffic flow model.
2. the method according to claim 1, wherein described determine preset radial by improved cuckoo algorithm
The initial parameter of basis function neural network, comprising:
The parameter of the radial basis function neural network is encoded；
Initialize the parameter of the improved cuckoo algorithm；
Determine the fitness function of the improved cuckoo algorithm；
The fitness value of all Bird's Nest positions is determined according to the fitness function, and is determined according to each fitness value optimal
Bird's Nest position；
Using Bird's Nest position described in improvement monkey hill climbing process policy update, and updated institute is determined according to the fitness function
State the fitness value of Bird's Nest position；
Judge whether the fitness value of the updated Bird's Nest position is greater than the fitness value of the optimal Bird's Nest position；
If so, being the updated Bird's Nest position by optimal Bird's Nest location updating.
3. according to the method described in claim 2, it is characterized in that, being the updated institute by optimal Bird's Nest location updating
After stating Bird's Nest position, further includes:
Adaptive updates are carried out to probability is recognized；
Random number is generated, and judges whether the random number is greater than and updated described recognizes probability；
If so, changing the Bird's Nest position at random, and the Bird's Nest after random change is determined according to the fitness function
The fitness value of position；
Whether the fitness value of the Bird's Nest position after the random change of judgement is greater than the fitness value of the optimal Bird's Nest position；
If the fitness value of the Bird's Nest position after random change is greater than the fitness value of the optimal Bird's Nest position, will most
Excellent Bird's Nest location updating is the Bird's Nest position after random change.
4. according to the method described in claim 2, it is characterized in that, described using bird described in improvement monkey hill climbing process policy update
Nest position, comprising:
According to i-th of Bird's Nest position xi=(xi1,xi2,…,xin) and formulaDetermine i-th of bird
Nest gets over journey coefficient delta xi；Wherein, Δ xi=(Δ xi1,Δxi2,...,Δxin)；
Journey coefficient delta x is got over according to describediPass through formulaCalculate pseudo- gradient vector f 'ij
(xi)；
According to the pseudo- gradient vector f 'ij(xi) pass through formula yij=xij+a·sign(f’ij(xi)) calculate it is described updated
Bird's Nest position yi；Wherein, yi=(yi1,yi2,...,yin)；
Judge the updated Bird's Nest position yiWhether in the reasonable scope and f (y is meti)≥f(xi)；
If so, by i-th of Bird's Nest position xiIt is updated to updated Bird's Nest position yi；
If it is not, then keeping i-th of Bird's Nest position xiIt is constant；
Wherein, a is step-length of climbing the mountain, and χ is the random number for belonging to [0,1], and sign is sign function.
5. a kind of system of forecasting traffic flow characterized by comprising
Determining module, for determining the initial parameter of preset radial basis function neural network by improved cuckoo algorithm；
Preprocessing module obtains training sample for pre-processing to the freeway traffic flow data of input；
Training module is handed over for being trained using the training sample to the preset radial basis function neural network
Through-flow prediction model:
Prediction module, for being predicted using the forecasting traffic flow model traffic flow.
6. system according to claim 5, which is characterized in that the determining module includes:
Encoding submodule is encoded for the parameter to the radial basis function neural network；
Initialization submodule, for initializing the parameter of the improved cuckoo algorithm；
First determines submodule, for determining the fitness function of the improved cuckoo algorithm；
Second determines submodule, for determining the fitness value of all Bird's Nest positions according to the fitness function, and according to each
The fitness value determines optimal Bird's Nest position；
First updates submodule, improves Bird's Nest position described in monkey hill climbing process policy update for using, and according to the adaptation
Degree function determines the fitness value of the updated Bird's Nest position；
First judging submodule, for judging it is described optimal whether the fitness value of the updated Bird's Nest position is greater than
The fitness value of Bird's Nest position；
Third determines submodule, is greater than the optimal Bird's Nest position for the fitness value when the updated Bird's Nest position
It is the updated Bird's Nest position by optimal Bird's Nest location updating when the fitness value set.
7. system according to claim 6, which is characterized in that the determining module further include:
Second update submodule, for recognize probability carry out adaptive updates；
Second judgment submodule, for generating random number, and judge the random number whether be greater than it is updated it is described recognize it is general
Rate；
It is random to change submodule, for when the random number be greater than it is updated it is described recognize probability when, change the bird at random
Nest position, and according to the fitness value of the Bird's Nest position after the determining random change of the fitness function；
Third judging submodule, for judging it is described optimal whether the fitness value of the Bird's Nest position after changing at random is greater than
The fitness value of Bird's Nest position；
Third updates submodule, if the fitness value for the Bird's Nest position after changing at random is greater than the optimal Bird's Nest position
Optimal Bird's Nest location updating is then the Bird's Nest position after random change by the fitness value set.
8. system according to claim 6, which is characterized in that described first, which updates submodule, includes:
Determination unit, for according to i-th of Bird's Nest position xi=(xi1,xi2,…,xin) and formula
Determine i-th of Bird's Nest gets over journey coefficient delta xi；Wherein, Δ xi=(Δ xi1,Δ
xi2,...,Δxin)；
First computing unit, for getting over journey coefficient delta x according toiPass through formula
Calculate pseudo- gradient vector f 'ij(xi)；
Second computing unit, for according to the pseudo- gradient vector f 'ij(xi) pass through formula
yij=xij+a·sign(f’ij(xi)) calculate updated Bird's Nest position yi；Wherein, yi=(yi1,yi2,...,yin)；
Judging unit, for judging the updated Bird's Nest position yiWhether in the reasonable scope and f (y is meti)≥f(xi)；
Updating unit, for working as the updated Bird's Nest position yiIn the zone of reasonableness and meet f (yi)≥f(xi) when,
By i-th of Bird's Nest position xiIt is updated to the updated Bird's Nest position yi；
Holding unit, for working as the updated Bird's Nest position yiNot in the zone of reasonableness or it is unsatisfactory for f (yi)≥f
(xi) when, keep i-th of Bird's Nest position xiIt is constant；
Wherein, a is step-length of climbing the mountain, and χ is the random number for belonging to [0,1], and sign is sign function.
9. a kind of forecasting traffic flow equipment characterized by comprising
Memory, for storing computer program；
Processor realizes the side of the forecasting traffic flow as described in any one of Claims 1-4 when for executing the computer program
The step of method.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes the method for the forecasting traffic flow as described in any one of Claims 1-4 when the computer program is executed by processor
The step of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910595128.XA CN110533905B (en) | 2019-07-03 | 2019-07-03 | Traffic flow prediction method, system and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910595128.XA CN110533905B (en) | 2019-07-03 | 2019-07-03 | Traffic flow prediction method, system and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110533905A true CN110533905A (en) | 2019-12-03 |
| CN110533905B CN110533905B (en) | 2022-02-15 |
Family
ID=68659645
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910595128.XA Active CN110533905B (en) | 2019-07-03 | 2019-07-03 | Traffic flow prediction method, system and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110533905B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111932875A (en) * | 2020-07-29 | 2020-11-13 | 太原理工大学 | Intersection group key path identification method based on improved cuckoo search algorithm |
| CN112907953A (en) * | 2021-01-27 | 2021-06-04 | 吉林大学 | Bus travel time prediction method based on sparse GPS data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104299033A (en) * | 2014-09-24 | 2015-01-21 | 上海电力学院 | Magnetic flux leakage defect reconstruction method based on cuckoo searching and particle filter hybrid algorithm |
| CN106127295A (en) * | 2016-06-21 | 2016-11-16 | 湘潭大学 | A kind of Optimal Design of Pressure Vessel method based on self adaptation cuckoo Yu fireworks hybrid algorithm |
| CN107018103A (en) * | 2017-04-07 | 2017-08-04 | 淮南职业技术学院 | A kind of small echo norm blind balance method based on the group's optimization of adaptive step monkey |
| CN107864507A (en) * | 2017-11-22 | 2018-03-30 | 哈尔滨工程大学 | Cognitive ratio power control method based on quantum monkey group hunting mechanism |
| CN109637121A (en) * | 2018-06-05 | 2019-04-16 | 南京理工大学 | A kind of road traffic congestion prediction technique in short-term based on CS-SVR algorithm |
| CN109671272A (en) * | 2018-12-29 | 2019-04-23 | 广东工业大学 | A kind of freeway traffic flow prediction technique |
-
2019
- 2019-07-03 CN CN201910595128.XA patent/CN110533905B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104299033A (en) * | 2014-09-24 | 2015-01-21 | 上海电力学院 | Magnetic flux leakage defect reconstruction method based on cuckoo searching and particle filter hybrid algorithm |
| CN106127295A (en) * | 2016-06-21 | 2016-11-16 | 湘潭大学 | A kind of Optimal Design of Pressure Vessel method based on self adaptation cuckoo Yu fireworks hybrid algorithm |
| CN107018103A (en) * | 2017-04-07 | 2017-08-04 | 淮南职业技术学院 | A kind of small echo norm blind balance method based on the group's optimization of adaptive step monkey |
| CN107864507A (en) * | 2017-11-22 | 2018-03-30 | 哈尔滨工程大学 | Cognitive ratio power control method based on quantum monkey group hunting mechanism |
| CN109637121A (en) * | 2018-06-05 | 2019-04-16 | 南京理工大学 | A kind of road traffic congestion prediction technique in short-term based on CS-SVR algorithm |
| CN109671272A (en) * | 2018-12-29 | 2019-04-23 | 广东工业大学 | A kind of freeway traffic flow prediction technique |
Non-Patent Citations (1)
| Title |
|---|
| 乐冰 等: "节假日高速公路短时交通流预测", 《东莞理工学院学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111932875A (en) * | 2020-07-29 | 2020-11-13 | 太原理工大学 | Intersection group key path identification method based on improved cuckoo search algorithm |
| CN112907953A (en) * | 2021-01-27 | 2021-06-04 | 吉林大学 | Bus travel time prediction method based on sparse GPS data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110533905B (en) | 2022-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shao et al. | Traffic flow prediction with long short-term memory networks (LSTMs) | |
| CN104636354B (en) | A kind of position interest points clustering method and relevant apparatus | |
| CN109711544A (en) | Method, apparatus, electronic equipment and the computer storage medium of model compression | |
| CN107102989A (en) | A kind of entity disambiguation method based on term vector, convolutional neural networks | |
| CN109376913A (en) | The prediction technique and device of precipitation | |
| CN105654729A (en) | Short-term traffic flow prediction method based on convolutional neural network | |
| CN102819663B (en) | Method for forecasting ship wake based on optimized support vector regression parameter | |
| AU6135700A (en) | Degree of outlier calculation device, and probability density estimation device and histogram calculation device for use therein | |
| CN111008690B (en) | Method and device for learning neural network with self-adaptive learning rate | |
| CN113269252A (en) | Power electronic circuit fault diagnosis method for optimizing ELM based on improved sparrow search algorithm | |
| CN107886157A (en) | A kind of new bat optimized algorithm system | |
| CN110533905A (en) | A kind of method of forecasting traffic flow, system and equipment | |
| CN109816177A (en) | A kind of Load aggregation quotient short-term load forecasting method, device and equipment | |
| CN107423762A (en) | Semi-supervised fingerprinting localization algorithm based on manifold regularization | |
| CN113240068A (en) | RBF neural network optimization method based on improved ant lion algorithm | |
| CN112766603A (en) | Traffic flow prediction method, system, computer device and storage medium | |
| CN116015967B (en) | Industrial Internet intrusion detection method based on improved whale algorithm optimization DELM | |
| CN114461931A (en) | User trajectory prediction method and system based on multi-relation fusion analysis | |
| Vernieuwe et al. | Comparison of clustering algorithms in the identification of Takagi–Sugeno models: A hydrological case study | |
| Balasubramaniam et al. | R-TOSS: A framework for real-time object detection using semi-structured pruning | |
| CN113821025A (en) | Mobile robot path planning method for optimizing heuristic function through neural network | |
| CN112068088A (en) | Radar radiation source threat assessment method based on optimized BP neural network | |
| CN108280548A (en) | Intelligent processing method based on network transmission | |
| CN110110690B (en) | Target pedestrian tracking method, device, equipment and storage medium | |
| CN111276138B (en) | Method and device for processing voice signal in voice wake-up system |
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 |