CN107451599A - A kind of traffic behavior Forecasting Methodology of the collective model based on machine learning - Google Patents
A kind of traffic behavior Forecasting Methodology of the collective model based on machine learning Download PDFInfo
- Publication number
- CN107451599A CN107451599A CN201710504173.0A CN201710504173A CN107451599A CN 107451599 A CN107451599 A CN 107451599A CN 201710504173 A CN201710504173 A CN 201710504173A CN 107451599 A CN107451599 A CN 107451599A
- Authority
- CN
- China
- Prior art keywords
- data
- traffic
- machine learning
- algorithm
- traffic behavior
- 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.)
- Pending
Links
- 238000010801 machine learning Methods 0.000 title claims abstract description 39
- 230000006399 behavior Effects 0.000 title claims abstract description 24
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 71
- 238000012545 processing Methods 0.000 claims description 16
- 238000012706 support-vector machine Methods 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 238000003064 k means clustering Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims 1
- 230000004927 fusion Effects 0.000 abstract description 4
- 230000000694 effects Effects 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of traffic behavior Forecasting Methodology of the collective model based on machine learning, belongs to traffic behavior prediction field.The present invention is actually classified based on traffic to data, it is simultaneously again innovative independently to handle traffic user type data, period data, the class data of historical data three using most rational machine learning algorithm, maintain the mutual independence of data, so as to remain transport information to greatest extent, best information service is provided for prediction；Several machine learning algorithms are combined traffic behavior are excavated and predicted by the present invention, the superposition of not exclusively several algorithms, be based on traffic theory on the basis of Intelligent Fusion platform, traffic behavior can be predicted in real time；Intelligent weighting has been carried out again, and the machine learning result of different pieces of information can be made to reach maximization after integrating.
Description
Technical field
The invention belongs to traffic behavior to predict field, and in particular to a kind of traffic row of the collective model based on machine learning
For Forecasting Methodology.
Background technology
Excavation and prediction of the single machine learning algorithm to pedestrian traffic behavior have good example, but due to traffic
Behavior is due to what multivariable determined in itself, for different types of traffic behavior be difficult it is predicted with a kind of algorithm and
Excavate, while many algorithms can not be excavated and predicted in real time.
The content of the invention
For above-mentioned technical problem present in prior art, the present invention proposes a kind of synthesis mould based on machine learning
The traffic behavior Forecasting Methodology of type, it is reasonable in design, the deficiencies in the prior art are overcome, there is good effect.
To achieve these goals, the present invention adopts the following technical scheme that：
A kind of traffic behavior Forecasting Methodology of the collective model based on machine learning, using the synthesis mould based on machine learning
The traffic behavior of type user is predicted, and is specifically comprised the following steps：
Step 1：Data input；
Step 2：Data type is classified；
It is defeated that different types of traffic data includes traffic user type data, period data, historical data and outside
Enter the data including data；
Step 3：Machine learning is carried out to different types of data；
According to traffic theory and pedestrian traffic behavior, to different types of traffic data, calculated using different machine learning
Method is excavated to traffic behavior, and is predicted according to historical record and traffic theory；
Step 4：Intelligent weighted comprehensive is carried out according to traffic historical record and current traffic condition；
Difference using different types of machine learning algorithm to the ability of processing different type traffic data, is selected optimal
Algorithm process corresponding to traffic data, have by it is adjustable weighting conformable layer to algorithms of different processing after result add
Power is integrated, with the result for being optimal；
Step 5：Export prediction result.
Preferably, in step 3, different machine learning algorithms includes K-means clustering algorithms (K-means
Clustering algorithm, K mean cluster algorithm), ANN (Artificial Neural Network, ANN
Network) algorithm, SVM (Support Vector Machine, SVMs) algorithm；Wherein, K-means clustering algorithms be used for pair
Traffic user type data are handled, and artificial neural network algorithm is used to handle period data, SVMs
Algorithm is used for historical data processing.
This method is by different types of machine learning algorithm Intelligent Fusion, wherein to the data of trend discrimination type
The algorithm that closes on of reason is the unsupervised learning clustering algorithm in machine learning, to the artificial neural network of period data processing
It is deep learning algorithm, the SVM algorithm of support vector machine for handling historical data is the sorting algorithm in supervised learning, these algorithms
It is different types of algorithm in machine learning, application scenarios and algorithm structure have very big difference；Meanwhile these algorithms institute is right
The data that should be handled spatial and temporal distributions in traffic data in itself, are structurally and functionally all very different；The intelligence of this method
It is exactly to utilize difference of different types of machine learning algorithm to the ability of processing different type traffic data that can merge, and selection is most
Traffic data corresponding to excellent algorithm process, and the result after algorithms of different processing is carried out by adjustable weighting conformable layer
Weighting is integrated, the effect for being optimal.
Advantageous effects caused by the present invention：
1st, actually data are classified based on traffic, at the same again it is innovative by traffic user type data, it is period
Data, historical data and the class data of outer input data four are independently handled using most rational machine learning algorithm, are protected
The mutual independence of data has been held, so as to remain transport information to greatest extent, best information service is provided for prediction；
2nd, the present invention, which combines several machine learning algorithms, is excavated and is predicted to traffic behavior, is not only
The superposition of several algorithms, be based on traffic theory on the basis of Intelligent Fusion platform, can to traffic behavior carry out in real time it is pre-
Survey；Intelligent weighting has been carried out again, and the machine learning result of different pieces of information can be made to reach maximization after integrating.
Brief description of the drawings
Fig. 1 is the structure platform schematic diagram that the inventive method is fused into 5 layers.
Embodiment
Below in conjunction with the accompanying drawings and embodiment is described in further detail to the present invention：
The structure composition as shown in figure 1, this patent method is of five storeys altogether, first layer is data input layer, and the second layer is data
Classification of type layer, third layer are the machine learning algorithm layers of corresponding different types of data, and the 4th layer is remembered according to traffic history
Record and current traffic condition and the intelligent weighted comprehensive layer that carries out, layer 5 is output layer.
The second layer has divided different types of traffic data, including the data of trend discrimination type, period data, history
The three big species such as data；The foundation of division is on finding that three of the above is the main of influence traffic after a large amount of transport data processings
Data, this dividing method is also to include the widest mode of data.
Third layer is according to traffic theory and pedestrian traffic behavior, to different types of traffic data, uses different machines
Device learning algorithm to traffic behavior excavate and and is predicted wherein trend discrimination class according to historical record and traffic theory
The data of type are handled by K-means clustering algorithms, and period data are handled by ANN artificial neural networks, history
Data are handled by SVM algorithm of support vector machine；
4th layer of weighting intelligent algorithm, because each machine learning algorithm has when in face of different types of data
Itself the advantages of and defect, this method propose the intelligence of the brand-new machine learning algorithm based on variety classes transport data processing
Convergence platform.Existing traffic data algorithm platform is the platform of one species machine learning algorithm, is processing one species
The machine learning algorithm of the identical type of the traffic data of type gathers together the platform of composition, such as random forests algorithm platform both
It is by same kind of algorithm integration.
This method is by different types of machine learning algorithm Intelligent Fusion, wherein to the data of trend discrimination type
The algorithm that closes on of reason is the unsupervised learning clustering algorithm in machine learning, to the artificial neural network of period data processing
It is deep learning algorithm, the SVM algorithm of support vector machine for handling historical data is the sorting algorithm in supervised learning, these algorithms
It is different types of algorithm in machine learning, application scenarios and algorithm structure have very big difference；Meanwhile these algorithms institute is right
The data that should be handled spatial and temporal distributions in traffic data in itself, are structurally and functionally all very different；The intelligence of this method
It is exactly to utilize difference of different types of machine learning algorithm to the ability of processing different type traffic data that can merge, and selection is most
Traffic data corresponding to excellent algorithm process, and the result after algorithms of different processing is carried out by adjustable weighting conformable layer
Weighting is integrated, the result for being optimal.
The inventive method creates new machine learning algorithm model, five layers of calculating processing, three kinds of different types of traffic
Data combine most suitable machine learning algorithm independent process.
Certainly, described above is not limitation of the present invention, and the present invention is also not limited to the example above, this technology neck
The variations, modifications, additions or substitutions that the technical staff in domain is made in the essential scope of the present invention, it should also belong to the present invention's
Protection domain.
Claims (2)
1. a kind of traffic behavior Forecasting Methodology of the collective model based on machine learning, it is characterised in that use and be based on engineering
The traffic behavior of the collective model user of habit is predicted, and is specifically comprised the following steps：
Step 1：Data input；
Step 2：Data type is classified；
Different types of traffic data includes traffic user type data, period data, historical data and outside input number
According to data inside；
Step 3：Machine learning is carried out to different types of data；
According to traffic theory and pedestrian traffic behavior, to different types of traffic data, different machine learning algorithms pair is used
Traffic behavior is excavated, and is predicted according to historical record and traffic theory；
Step 4：Intelligent weighted comprehensive is carried out according to traffic historical record and current traffic condition；
Difference using different types of machine learning algorithm to the ability of processing different type traffic data, selects optimal calculation
Traffic data corresponding to method processing, there is the result after adjustable weighting conformable layer is handled algorithms of different to be weighted whole
Close, with the result for being optimal；
Step 5：Export prediction result.
2. the traffic behavior Forecasting Methodology of the collective model according to claim 1 based on machine learning, it is characterised in that
In step 3, different machine learning algorithms includes K-means clustering algorithms, ANN (Artificial Neural
Network, artificial neural network) algorithm, SVM (Support Vector Machine, SVMs) algorithm；Wherein, K-
Means clustering algorithms are used to handle traffic user type data, and artificial neural network algorithm is used for period data
Handled, algorithm of support vector machine is used for historical data processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710504173.0A CN107451599A (en) | 2017-06-28 | 2017-06-28 | A kind of traffic behavior Forecasting Methodology of the collective model based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710504173.0A CN107451599A (en) | 2017-06-28 | 2017-06-28 | A kind of traffic behavior Forecasting Methodology of the collective model based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107451599A true CN107451599A (en) | 2017-12-08 |
Family
ID=60487126
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710504173.0A Pending CN107451599A (en) | 2017-06-28 | 2017-06-28 | A kind of traffic behavior Forecasting Methodology of the collective model based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107451599A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108364467A (en) * | 2018-02-12 | 2018-08-03 | 北京工业大学 | A kind of traffic information prediction technique based on modified decision Tree algorithms |
| CN108648445A (en) * | 2018-04-19 | 2018-10-12 | 浙江浙大中控信息技术有限公司 | Dynamic traffic Tendency Prediction method based on traffic big data |
| CN109670644A (en) * | 2018-12-20 | 2019-04-23 | 华北水利水电大学 | Forecasting system and method neural network based |
| CN110458325A (en) * | 2019-07-03 | 2019-11-15 | 青岛海信网络科技股份有限公司 | A kind of traffic zone passenger flow forecasting and device in short-term |
| TWI696124B (en) * | 2017-12-15 | 2020-06-11 | 香港商阿里巴巴集團服務有限公司 | Model integration method and device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102637363A (en) * | 2012-04-11 | 2012-08-15 | 天津大学 | SVM (Support Vector Machine)-based road vehicle running speed prediction method |
| CN105160866A (en) * | 2015-08-07 | 2015-12-16 | 浙江高速信息工程技术有限公司 | Traffic flow prediction method based on deep learning nerve network structure |
-
2017
- 2017-06-28 CN CN201710504173.0A patent/CN107451599A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102637363A (en) * | 2012-04-11 | 2012-08-15 | 天津大学 | SVM (Support Vector Machine)-based road vehicle running speed prediction method |
| CN105160866A (en) * | 2015-08-07 | 2015-12-16 | 浙江高速信息工程技术有限公司 | Traffic flow prediction method based on deep learning nerve network structure |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI696124B (en) * | 2017-12-15 | 2020-06-11 | 香港商阿里巴巴集團服務有限公司 | Model integration method and device |
| CN108364467A (en) * | 2018-02-12 | 2018-08-03 | 北京工业大学 | A kind of traffic information prediction technique based on modified decision Tree algorithms |
| CN108648445A (en) * | 2018-04-19 | 2018-10-12 | 浙江浙大中控信息技术有限公司 | Dynamic traffic Tendency Prediction method based on traffic big data |
| CN108648445B (en) * | 2018-04-19 | 2020-02-21 | 浙江浙大中控信息技术有限公司 | Dynamic traffic situation prediction method based on traffic big data |
| CN109670644A (en) * | 2018-12-20 | 2019-04-23 | 华北水利水电大学 | Forecasting system and method neural network based |
| CN109670644B (en) * | 2018-12-20 | 2023-04-25 | 华北水利水电大学 | Prediction system and method based on neural network |
| CN110458325A (en) * | 2019-07-03 | 2019-11-15 | 青岛海信网络科技股份有限公司 | A kind of traffic zone passenger flow forecasting and device in short-term |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107451599A (en) | A kind of traffic behavior Forecasting Methodology of the collective model based on machine learning | |
| US20220413455A1 (en) | Adaptive-learning intelligent scheduling unified computing frame and system for industrial personalized customized production | |
| Luo et al. | A hybrid multi-objective PSO–EDA algorithm for reservoir flood control operation | |
| Han et al. | Information-utilization-method-assisted multimodal multiobjective optimization and application to credit card fraud detection | |
| CN105785231B (en) | A kind of linear integer programming method of the online fault tolerance positioning of power distribution network | |
| CN104362623B (en) | Multi-target network reestablishing method for active power distribution network | |
| De Santis et al. | Genetic optimization of a fuzzy control system for energy flow management in micro-grids | |
| CN106934497A (en) | Wisdom cell power consumption real-time predicting method and device based on deep learning | |
| CN107465664A (en) | Intrusion detection method based on parallel more artificial bee colony algorithms and SVMs | |
| CN102300281B (en) | Routing method for monitoring bridge state based on wireless sensor network | |
| CN106228184A (en) | A kind of based on the blast furnace fault detection system and the method that optimize extreme learning machine | |
| CN105305442B (en) | Multiobjective Intelligent power distribution network self-healing recovery method based on quantum genetic algorithm | |
| CN108182485A (en) | A kind of power distribution network maintenance opportunity optimization method and system | |
| Zhang et al. | Intelligent systems for power system dynamic security assessment: Review and classification | |
| CN110854891A (en) | Power distribution network pre-disaster resource allocation method and system | |
| El Bourakadi et al. | Multi-agent system based sequential energy management strategy for Micro-Grid using optimal weighted regularized extreme learning machine and decision tree | |
| CN112561129B (en) | First-aid repair material allocation method based on distribution line fault information | |
| Li et al. | Intrusion detection system using improved convolution neural network | |
| Huo et al. | Flexible job shop scheduling based on digital twin and improved bacterial foraging | |
| CN107689917B (en) | Power communication network route allocation method based on non-uniform service balance | |
| Yu et al. | Multipopulation management in evolutionary algorithms and application to complex warehouse scheduling problems | |
| CN115277789B (en) | Safety protection system and method for cascade hydropower station | |
| CN116758740A (en) | Intelligent traffic efficient simulation method based on digital twin and information tree | |
| CN110414119A (en) | A kind of yard craft shellfish bit optimization method based on improvement evolution algorithmic | |
| Liu et al. | Artificial intelligence and computational intelligence: a challenge for power system engineers |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171208 |
|
| RJ01 | Rejection of invention patent application after publication |