CN113313145A - Expressway traffic incident detection method based on mixed kernel correlation vector machine - Google Patents
Expressway traffic incident detection method based on mixed kernel correlation vector machine Download PDFInfo
- Publication number
- CN113313145A CN113313145A CN202110505742.XA CN202110505742A CN113313145A CN 113313145 A CN113313145 A CN 113313145A CN 202110505742 A CN202110505742 A CN 202110505742A CN 113313145 A CN113313145 A CN 113313145A
- Authority
- CN
- China
- Prior art keywords
- detector
- traffic
- kernel
- downstream
- upstream
- 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
- 238000001514 detection method Methods 0.000 title abstract description 16
- 238000011144 upstream manufacturing Methods 0.000 claims abstract description 37
- 230000006870 function Effects 0.000 claims abstract description 34
- 238000000034 method Methods 0.000 claims abstract description 16
- 241000255581 Drosophila <fruit fly, genus> Species 0.000 claims abstract description 13
- 238000005457 optimization Methods 0.000 claims abstract description 9
- 230000008859 change Effects 0.000 claims abstract description 7
- 238000012216 screening Methods 0.000 claims abstract description 6
- 238000012549 training Methods 0.000 claims abstract description 4
- 238000005259 measurement Methods 0.000 claims abstract description 3
- 241000255588 Tephritidae Species 0.000 claims description 10
- 230000006978 adaptation Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method for detecting an expressway traffic incident based on a hybrid kernel correlation vector machine, which comprises the steps of constructing an expressway traffic incident detection initial variable set according to the change characteristics of upstream and downstream traffic flow parameters of a traffic incident; learning minority sample information by adopting a conditional generation type confrontation network, generating minority supplementary samples by a training generator, and balancing data distribution; screening out key variables by adopting variable importance measurement of an XGboost algorithm; establishing a combined kernel function based on a local Gaussian kernel and a global polynomial kernel; training a multi-core correlation vector machine model by taking key variables as input; and optimizing parameters of the drosophila through an improved drosophila optimization algorithm to obtain an optimal model. The invention improves the detection rate of traffic events, timely detects the traffic events on the expressway, strives for time for road emergency rescue, reduces casualties and property loss of the events, and simultaneously provides technical support for early warning of road traffic safety risks.
Description
Technical Field
The invention belongs to the technical field of traffic safety, and particularly relates to a method for detecting an expressway traffic incident.
Background
According to the statistics of the world health organization, about 130 thousands of people die of road traffic accidents every year around the world, and other tens of millions of people are injured in different degrees. Road traffic accidents have become a significant public nuisance in human society, as have traffic safety issues. Studies have shown that secondary accidents cause much greater severity than primary accidents, with 600% increase in risk compared to primary accidents. The longer the event processing time, the greater the probability of causing a secondary accident. Therefore, how to accurately and efficiently detect and identify road traffic events in as short a time as possible is an important point of research in the traffic field.
Currently, although there are many scholars who propose methods for detecting traffic events, there are many shortcomings to be improved. For example, the detection time of the detection model is longer; the detection model performs poorly in unbalanced datasets; the detection rate of the detection model is low; on the other hand, a general traffic event detection framework is also lacking.
Disclosure of Invention
In order to solve the technical problems mentioned in the background art, the invention provides a method for detecting an expressway traffic incident based on a hybrid kernel correlation vector machine.
In order to achieve the technical purpose, the technical scheme of the invention is as follows:
a method for detecting an expressway traffic incident based on a hybrid kernel correlation vector machine comprises the following steps:
(1) acquiring upstream and downstream traffic flow parameter data of the expressway traffic detector, and analyzing the obvious change of the traffic flow parameters caused by traffic events;
(2) analyzing the change trend of the upstream and downstream traffic flow parameters of the event site by using the data acquired in the step (1), and constructing an initial variable set according to the measured values of the upstream and downstream traffic flow parameters and the basic mathematical operation combination of the parameters;
(3) learning minority sample information by adopting a conditional generation type confrontation network, generating minority supplementary samples by a training generator, and balancing data distribution;
(4) based on the initial variable set, screening out key variables by adopting variable importance measurement of an XGboost algorithm;
(5) establishing a mixed kernel correlation vector machine model based on a local Gaussian kernel and a global polynomial kernel;
(6) and optimizing the parameters of the mixed kernel correlation vector machine model by adopting an improved drosophila optimization algorithm, and detecting the expressway traffic incident by using the optimized model.
Further, in the step (1), the collected traffic flow parameters include traffic flow, traffic speed and traffic occupancy.
Further, in step (2), the constructed initial variable set includes the following variables:
the traffic flow of the upstream detector, the speed of the upstream detector, the occupancy of the upstream detector, the traffic flow of the downstream detector, the speed of the downstream detector, the occupancy of the downstream detector, the ratio of the traffic flow of the upstream detector to the occupancy, the ratio of the traffic flow of the upstream detector to the speed, the ratio of the speed of the upstream detector to the occupancy, the ratio of the traffic flow of the downstream detector to the speed, the ratio of the speed of the downstream detector to the occupancy, the ratio of the speed of the upstream detector to the historical speed average of the detector, the ratio of the occupancy of the upstream detector to the historical occupancy of the upstream detector, the ratio of the flow of the upstream detector to the historical flow of the detector, the ratio of the speed of the downstream detector to the historical speed average of the downstream detector, the ratio of the historical speed of the downstream detector to the historical speed average of the detector, the historical speed of the downstream detector, the historical speed of the detector, the historical speed of the downstream detector, the historical speed of the detector, the historical speed of the detector, the traffic of the traffic, The ratio of the occupancy of the downstream detector to the historical occupancy of the detector, the ratio of the flow of the downstream detector to the historical flow of the detector, the flow difference between adjacent detectors upstream and downstream, the velocity difference between adjacent detectors upstream and downstream, and the occupancy difference between adjacent detectors upstream and downstream.
Further, in step (3), the conditional generation countermeasure network has the following expression:
in the above formula, V (D, G) is the objective function, G is the generator, D is the discriminator, x is the real data set, y is the classification label, λ is the noise,
the representation satisfies the mathematical expectations of the true data distribution,
indicating that the mathematical expectation of the original noise distribution is satisfied.
Further, in step (4), based on the initial variable set data, calculating feature importance by using an XGboost algorithm and sequencing; and then deleting the features with the minimum importance each time, recalculating the classification accuracy of the XGboost algorithm by using the remaining features, successively iterating until all the features are searched, and finally sorting through the feature importance to screen out the key variables.
Further, in step (5), the mixed kernel-correlation vector machine model is as follows:
in the above formula, y (x; w) is the model output, Kj(x,xi) Is a basic kernel function including Gaussian kernel function and polynomial kernel function, K (x, x)i) For combined kernel functions, M is the number of basic kernel functions, αjIs a weight coefficient of the basic kernel function, wiAs model weight, w0For model initial weights, N is the number of samples.
Further, in step (6), the improved drosophila optimization algorithm is as follows:
(a) initializing model parameters and setting maximum iteration number KmaxSetting the population scale and the number of subgroups, and initializing the positions of the drosophila populations;
(b) according to the smell of the individual drosophila, independently assigning values to each group; substituting the decision variable value into the fitness function so as to calculate the fitness value of each individual fruit fly at the position;
(c) finding out the fruit flies with the optimal adaptation value in each subgroup;
(d) judging whether the fitness of each subgroup is better than the previous iterative fitness, if so, updating the optimal fitness value of each subgroup, and flying towards the position independently by using vision;
(e) updating the global optimal fitness and the optimal position;
(f) performing a joint local search;
(g) if the current iteration number K is more than or equal to KmaxIf yes, stopping searching; otherwise, returning to the step (b).
Adopt the beneficial effect that above-mentioned technical scheme brought:
1. according to the invention, by analyzing the change characteristics of upstream and downstream traffic flow parameters of the road traffic detector and constructing the variable set in a traffic parameter multi-combination mode, the event data and the non-accident data are easy to distinguish, the later-stage traffic event detection is facilitated, and the event detection rate is improved.
2. The invention adopts a conditional generation type countermeasure network (CGAN), has a very flexible design framework on the basis of the GAN, can integrate various loss functions into a CGAN model, and directly samples and deduces aiming at different tasks, thereby improving the application efficiency of the GAN. Therefore, the detection rate of the model can be improved by processing the unbalanced data set by using a conditional generation countermeasure network.
3. The invention screens the characteristics of the data set, selects the important variable to input into the model, and can reduce the detection time of the model.
4. The invention adopts the correlation vector machine model of the mixed kernel, and solves the limitation that the multi-dimensional data of the single kernel function has irregular distribution because the characteristics of the sample data contain information with different structures or the sample size is relatively large.
5. The invention adopts an improved drosophila optimization algorithm, can improve the speed of searching global optimal parameters, and thus reduces the detection time of the model.
Drawings
FIG. 1 is an overall flow chart of the present invention;
FIG. 2 is a flow chart of variable screening according to the present invention;
FIG. 3 is a flow chart of a hybrid kernel-based correlation vector machine according to the present invention;
FIG. 4 is a flow chart of an improved drosophila optimization algorithm in the present invention.
Detailed Description
The technical scheme of the invention is explained in detail in the following with the accompanying drawings.
The invention designs a method for detecting an expressway traffic incident based on a hybrid kernel correlation vector machine, which can be divided into the following six parts as shown in figure 1:
(1) and (6) data acquisition. The present invention takes highway traffic detector data as an example. When the traffic flow is in a normal traffic state, the changes of three basic traffic parameters of the traffic flow, the speed and the occupancy of the highway are relatively stable; when a traffic incident occurs on a road segment, traffic parameters collected by the upstream and downstream detectors change significantly. Therefore, the method respectively collects the traffic parameters of the accident upstream and downstream detectors, namely the traffic flow, the traffic speed and the traffic occupancy.
(2) And constructing a variable set. Through analysis of a large amount of data of the high-speed coil detectors, not only three basic traffic parameters of flow, speed and occupancy rate can be obviously changed in the occurrence period of the traffic incident, but also the combination of different traffic parameters and the combination of traffic parameters of an upstream detector and a downstream detector show strong sensitivity to the occurrence of the traffic incident. Thus, the invention constructs traffic variable types as shown in table 1.
TABLE 1 traffic incident detection data variable set
(3) And (4) unbalanced data processing. Because the traffic event data is unbalanced data, a conditional generative countermeasure network (CGAN) is utilized, the distribution of real samples is learned to enable the generated samples to be closer to the real samples, and finally the aim of balancing the data set is achieved. The raw data set can be processed by the following calculation method. The calculation formula is as follows:
in the above formula, V (D, G) is the objective function, G is the generator, D is the discriminator, x is the real data set, y is the classification label, λ is the noise,
the representation satisfies the mathematical expectations of the true data distribution,
indicating that the mathematical expectation of the original noise distribution is satisfied.
(4) And (4) feature screening. Screening variable characteristics by using an XGboost algorithm, calculating the importance of the characteristics by using the XGboost algorithm based on initial variable set data, and sequencing; and then deleting the features with the minimum importance each time, recalculating the classification accuracy of the XGboost algorithm by using the remaining features, successively iterating until all the features are searched, and finally sorting through the feature importance to screen out the key variables. As shown in fig. 2.
(5) And constructing a mixed kernel correlation vector machine model. A gaussian kernel function is a typical local kernel that has an effect on a small range of sample points near a sample point; the polynomial kernel function is a global kernel function and can consider the influence of data far away from a sample point on the test of the sample point, so that the model can be ensured to have both global fitting capacity and local fitting capacity by establishing a combined kernel function based on a local Gaussian kernel and a global polynomial kernel. The model building process is described in detail with reference to fig. 3. The following formula is a combination method of a gaussian kernel function, a polynomial kernel function and a mixed kernel function:
in the above formula, KjIs a basic kernel function (Gaussian kernel function or polynomial kernel function), M is the number of the basic kernel functions, alphajK is the mixing kernel function.
The mixed kernel-correlation vector machine model can be represented by the following formula:
in the above formula, wiAs model weight, w0For model initial weights, N is the number of samples.
(6) Optimizing model parameters based on an optimization algorithm for improving the fruit flies. The fruit fly optimization algorithm is divided into a plurality of subgroups from the group, the fitness function is directly controlled by a decision variable, the fruit fly algorithm is optimized in the aspect of reducing the search radius by using odor, and the parameters of the mixed kernel correlation vector machine are optimized to obtain a performance optimal model. Please refer to fig. 4.
S1 first initializes the model parameters and sets the maximum iteration number KmaxSetting the population scale and the number of subgroups, and initializing the positions of the drosophila populations;
s2 assigning a value to each group independently according to the smell of the fruit fly individual; substituting the decision variable value into the fitness function so as to calculate the fitness value of each individual fruit fly at the position;
s3 finding out the fruit flies with the optimal fitness value in each subgroup;
s4 determining whether the fitness of each subgroup is better than the previous iterative fitness, and if so, updating the optimal fitness value for each subgroup, and each subgroup will fly towards the location using vision independently at this time;
s5, updating the global optimal fitness and the optimal position;
s6 by performing a federated local search;
s7 if the current iteration number K is more than or equal to KmaxStopping searching; otherwise, S2 is continued.
The embodiments are only for illustrating the technical idea of the present invention, and the technical idea of the present invention is not limited thereto, and any modifications made on the basis of the technical scheme according to the technical idea of the present invention fall within the scope of the present invention.
Claims (7)
1. A method for detecting an expressway traffic incident based on a hybrid kernel correlation vector machine is characterized by comprising the following steps:
(1) acquiring upstream and downstream traffic flow parameter data of the expressway traffic detector, and analyzing the obvious change of the traffic flow parameters caused by traffic events;
(2) analyzing the change trend of the upstream and downstream traffic flow parameters of the event site by using the data acquired in the step (1), and constructing an initial variable set according to the measured values of the upstream and downstream traffic flow parameters and the basic mathematical operation combination of the parameters;
(3) learning minority sample information by adopting a conditional generation type confrontation network, generating minority supplementary samples by a training generator, and balancing data distribution;
(4) based on the initial variable set, screening out key variables by adopting variable importance measurement of an XGboost algorithm;
(5) establishing a mixed kernel correlation vector machine model based on a local Gaussian kernel and a global polynomial kernel;
(6) and optimizing the parameters of the mixed kernel correlation vector machine model by adopting an improved drosophila optimization algorithm, and detecting the expressway traffic incident by using the optimized model.
2. The method for detecting expressway traffic events based on hybrid kernel-correlation vector machine according to claim 1, wherein in step (1), the collected traffic flow parameters comprise traffic flow, traffic speed and traffic occupancy.
3. The method for detecting expressway traffic events based on hybrid kernel-correlation vector machine according to claim 2, wherein in step (2), the constructed initial variable set comprises the following variables:
the traffic flow of the upstream detector, the speed of the upstream detector, the occupancy of the upstream detector, the traffic flow of the downstream detector, the speed of the downstream detector, the occupancy of the downstream detector, the ratio of the traffic flow of the upstream detector to the occupancy, the ratio of the traffic flow of the upstream detector to the speed, the ratio of the speed of the upstream detector to the occupancy, the ratio of the traffic flow of the downstream detector to the speed, the ratio of the speed of the downstream detector to the occupancy, the ratio of the speed of the upstream detector to the historical speed average of the detector, the ratio of the occupancy of the upstream detector to the historical occupancy of the upstream detector, the ratio of the flow of the upstream detector to the historical flow of the detector, the ratio of the speed of the downstream detector to the historical speed average of the downstream detector, the ratio of the historical speed of the downstream detector to the historical speed average of the detector, the historical speed of the downstream detector, the historical speed of the detector, the historical speed of the downstream detector, the historical speed of the detector, the historical speed of the detector, the traffic of the traffic, The ratio of the occupancy of the downstream detector to the historical occupancy of the detector, the ratio of the flow of the downstream detector to the historical flow of the detector, the flow difference between adjacent detectors upstream and downstream, the velocity difference between adjacent detectors upstream and downstream, and the occupancy difference between adjacent detectors upstream and downstream.
4. The method for detecting an expressway traffic event based on a hybrid kernel-correlation vector machine according to claim 1, wherein in step (3), the expression of the conditional generation countermeasure network is as follows:
in the above formula, V (D, G) is the objective function, G is the generator, D is the discriminator, x is the real data set, y is the classification label, λ is the noise,
the representation satisfies the mathematical expectations of the true data distribution,
indicating that the mathematical expectation of the original noise distribution is satisfied.
5. The method for detecting the expressway traffic events based on the hybrid kernel-correlation vector machine according to claim 1, wherein in the step (4), feature importance is calculated and ranked by using an XGboost algorithm based on initial variable set data; and then deleting the features with the minimum importance each time, recalculating the classification accuracy of the XGboost algorithm by using the remaining features, successively iterating until all the features are searched, and finally sorting through the feature importance to screen out the key variables.
6. The hybrid kernel-correlation vector machine-based expressway traffic event detecting method according to claim 1, wherein in step (5), the hybrid kernel-correlation vector machine model is as follows:
in the above formula, y (x; w) is the model output, Kj(x,xi) Is a basic kernel function including a Gaussian kernel function and a polynomial kernel function, K (x, x)i) For combined kernel functions, M is the number of basic kernel functions, αjIs a weight coefficient of the basic kernel function, wiAs model weight, w0For model initial weights, N is the number of samples.
7. The method for detecting expressway traffic events based on hybrid kernel-correlation vector machine according to claim 1, wherein in step (6), the improved drosophila optimization algorithm is as follows:
(a) initializing model parameters and setting maximum iteration number KmaxSetting the population sizeAnd the number of subgroups, initializing the positions of the drosophila populations;
(b) according to the smell of the individual drosophila, independently assigning values to each group; substituting the decision variable value into the fitness function so as to calculate the fitness value of each individual fruit fly at the position;
(c) finding out the fruit flies with the optimal adaptation value in each subgroup;
(d) judging whether the fitness of each subgroup is better than the previous iterative fitness, if so, updating the optimal fitness value of each subgroup, and flying towards the position independently by using vision;
(e) updating the global optimal fitness and the optimal position;
(f) performing a joint local search;
(g) if the current iteration number K is more than or equal to KmaxIf yes, stopping searching; otherwise, returning to the step (b).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110505742.XA CN113313145B (en) | 2021-05-10 | 2021-05-10 | Expressway traffic event detection method based on mixed kernel correlation vector machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110505742.XA CN113313145B (en) | 2021-05-10 | 2021-05-10 | Expressway traffic event detection method based on mixed kernel correlation vector machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113313145A true CN113313145A (en) | 2021-08-27 |
| CN113313145B CN113313145B (en) | 2024-03-15 |
Family
ID=77372817
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110505742.XA Active CN113313145B (en) | 2021-05-10 | 2021-05-10 | Expressway traffic event detection method based on mixed kernel correlation vector machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113313145B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113806338A (en) * | 2021-11-18 | 2021-12-17 | 深圳索信达数据技术有限公司 | Data discrimination method and system based on data sample imaging |
| CN114446052A (en) * | 2022-01-17 | 2022-05-06 | 东南大学 | Multi-source data multi-stage fusion-based highway incident detection method and device |
| CN115035722A (en) * | 2022-06-20 | 2022-09-09 | 浙江嘉兴数字城市实验室有限公司 | Road safety risk prediction method based on combination of spatio-temporal features and social media |
| CN115311844A (en) * | 2022-06-22 | 2022-11-08 | 东南大学 | Highway traffic state estimation method based on self-supervision learning support vector machine |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102682601A (en) * | 2012-05-04 | 2012-09-19 | 南京大学 | Expressway traffic incident detection method based on optimized support vector machine (SVM) |
| US20140011484A1 (en) * | 2012-07-09 | 2014-01-09 | Sheng-Ying YEN | Method and system for estimating traffic information by using integration of location update events and call events |
| CN104091216A (en) * | 2014-07-29 | 2014-10-08 | 吉林大学 | Traffic information predication method based on fruit fly optimization least-squares support vector machine |
| CN106971548A (en) * | 2017-05-18 | 2017-07-21 | 福州大学 | The Short-time Traffic Flow Forecasting Methods of optimizable multi-core adaptive SVMs |
-
2021
- 2021-05-10 CN CN202110505742.XA patent/CN113313145B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102682601A (en) * | 2012-05-04 | 2012-09-19 | 南京大学 | Expressway traffic incident detection method based on optimized support vector machine (SVM) |
| US20140011484A1 (en) * | 2012-07-09 | 2014-01-09 | Sheng-Ying YEN | Method and system for estimating traffic information by using integration of location update events and call events |
| CN104091216A (en) * | 2014-07-29 | 2014-10-08 | 吉林大学 | Traffic information predication method based on fruit fly optimization least-squares support vector machine |
| CN106971548A (en) * | 2017-05-18 | 2017-07-21 | 福州大学 | The Short-time Traffic Flow Forecasting Methods of optimizable multi-core adaptive SVMs |
Non-Patent Citations (1)
| Title |
|---|
| 林浩 等: "支持向量机在智能交通***中的研究应用综述", 计算机科学与探索, 1 April 2020 (2020-04-01), pages 901 - 917 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113806338A (en) * | 2021-11-18 | 2021-12-17 | 深圳索信达数据技术有限公司 | Data discrimination method and system based on data sample imaging |
| CN114446052A (en) * | 2022-01-17 | 2022-05-06 | 东南大学 | Multi-source data multi-stage fusion-based highway incident detection method and device |
| CN114446052B (en) * | 2022-01-17 | 2023-05-30 | 东南大学 | Expressway event detection method and device based on multi-level fusion of multi-source data |
| CN115035722A (en) * | 2022-06-20 | 2022-09-09 | 浙江嘉兴数字城市实验室有限公司 | Road safety risk prediction method based on combination of spatio-temporal features and social media |
| CN115035722B (en) * | 2022-06-20 | 2024-04-05 | 浙江嘉兴数字城市实验室有限公司 | Road safety risk prediction method based on combination of space-time characteristics and social media |
| CN115311844A (en) * | 2022-06-22 | 2022-11-08 | 东南大学 | Highway traffic state estimation method based on self-supervision learning support vector machine |
| CN115311844B (en) * | 2022-06-22 | 2023-05-16 | 东南大学 | Expressway traffic state estimation method based on self-supervision learning support vector machine |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113313145B (en) | 2024-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113313145A (en) | Expressway traffic incident detection method based on mixed kernel correlation vector machine | |
| CN105117602B (en) | A kind of metering device running status method for early warning | |
| CN112506990B (en) | Hydrological data anomaly detection method based on spatiotemporal information | |
| CN107103332A (en) | A kind of Method Using Relevance Vector Machine sorting technique towards large-scale dataset | |
| CN107677472A (en) | The bearing state noise diagnostics algorithm that network-oriented Variable Selection merges with Characteristic Entropy | |
| CN106021771A (en) | Method and device for diagnosing faults | |
| CN112541532B (en) | Target detection method based on dense connection structure | |
| CN111680875B (en) | Unmanned aerial vehicle state risk fuzzy comprehensive evaluation method based on probability baseline model | |
| CN112735097A (en) | Regional landslide early warning method and system | |
| CN101271625A (en) | Method for detecting freeway traffic event by integration supporting vector machine | |
| CN107025468A (en) | Highway congestion recognition methods based on PCA GA SVM algorithms | |
| CN103278326A (en) | Method for diagnosing faults of wind generating set gear case | |
| CN112131731B (en) | Urban growth cellular simulation method based on spatial feature vector filtering | |
| CN111179592B (en) | Urban traffic prediction method and system based on spatio-temporal data flow fusion analysis | |
| CN114971301A (en) | Ecological interference risk identification and evaluation method based on automatic parameter adjustment optimization model | |
| CN110738232A (en) | grid voltage out-of-limit cause diagnosis method based on data mining technology | |
| CN113887908A (en) | Bridge risk assessment method considering subjective and objective cross fusion weight | |
| CN107507421A (en) | Method for rapidly judging traffic state and device | |
| CN110674858A (en) | Traffic jam detection method based on space-time association and big data mining | |
| CN113191585A (en) | Typhoon disaster risk assessment method for power transmission line | |
| CN112734154A (en) | Multi-factor public opinion risk assessment method based on fuzzy number similarity | |
| CN111678880A (en) | Satellite remote sensing identification method and system for stratospheric ozone invading lower layer in troposphere | |
| CN111144637A (en) | Regional power grid geological disaster forecasting model construction method based on machine learning | |
| CN114266289A (en) | Complex equipment health state assessment method | |
| CN115033591A (en) | Intelligent detection method and system for electricity charge data abnormity, storage medium and computer equipment |
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 |