CN114267184B - Multivariate behavior data mining method - Google Patents
Multivariate behavior data mining method Download PDFInfo
- Publication number
- CN114267184B CN114267184B CN202111645060.5A CN202111645060A CN114267184B CN 114267184 B CN114267184 B CN 114267184B CN 202111645060 A CN202111645060 A CN 202111645060A CN 114267184 B CN114267184 B CN 114267184B
- Authority
- CN
- China
- Prior art keywords
- traffic
- data
- time
- information
- toll station
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Traffic Control Systems (AREA)
- Devices For Checking Fares Or Tickets At Control Points (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a multi-element behavior data mining method, in particular to the technical field of road administration, aiming at integrating multi-element data and behavior data of drivers thereof through a data service cluster established by each toll station, it combines nature, road condition and human factor, and matches with time scale, so that it can predict traffic flow state of different road sections in future for a period of time, the prediction of the time scale can be obtained by the average value of the flow of the historical dates in different time periods, the probability of the occurrence of the blockage can be accurately predicted, the corresponding historical data characteristics which are accordant are retrieved by synchronously matching the detected information, and the processing method is obtained, the efficient treatment measures in the historical scheme are integrated, early warning can be realized, and corresponding suggested measures can be arranged, so that the problem of poor prediction effect caused by only considering the time characteristic of traffic compared with the traditional traffic prediction model is solved.
Description
Technical Field
The invention relates to the technical field of road information, in particular to a multivariate behavior data mining method.
Background
With the rapid development of information technology, people's behaviors are increasingly recorded in related computer systems. Such as security trading systems, credit card consumption systems, and medical care systems, among others. Due to the pace of people's day-to-day life, data recording by many computer systems is also performed day-to-day, and therefore such daily behavioral data of each person forms a behavioral data set. By mining the behavior data set, various behavior modes, phenomena and laws of people can be revealed.
The highway belongs to a high-grade highway, and can adapt to a highway which has an average day and night passenger car traffic volume of more than 25000 vehicles, is specially used for cars to drive at a high speed in a lane and controls the entrance and the exit of the cars. Although the names of the highways are different in all countries, the highways are specially designed to have more than 4 lanes, drive in two-way separation, completely control the entrances and exits and completely adopt the grade crossing.
With the continuous development of the current informatization, the electronization and informatization degrees of various industries are higher and higher, as a highway department, the congestion at high speed becomes a normal state in some areas, and for the current highway, the problem of long-time continuity and passing resistance is caused due to insufficient preparation work because the area is usually dredged after being blocked is caused.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a multivariate behavior data mining method, and the technical problems to be solved by the invention are as follows: the congestion at a high speed becomes a normal state in some areas, the reason of the congestion is diversified, and the congestion serving as individual driving behavior data has a high variable, so that the current traditional traffic prediction model only considers the time characteristic of the traffic, and further the prediction effect is poor, and the effect of making a decision in advance cannot be effectively achieved.
In order to achieve the purpose, the invention provides the following technical scheme: a multivariate behavior data mining method comprises the following steps:
s1, establishing a data service cluster according to the entrance and exit toll stations of the full-length highway section, and acquiring the quantity of vehicles entering and exiting each toll station and the information of vehicle types.
And S2, detecting the state information of the whole highway section, acquiring visibility, ground humidity and weather information, and uploading the information to a data service cluster.
And S3, establishing a road section traffic state real-time monitoring network based on the data service cluster lower layer, and acquiring data of the passing speed and the density of the vehicles.
S4, the safe passing speed among all areas of the whole road section is estimated through the weather and road section information acquired through S2, and the optimal passing accommodation capacity of the expressway in the current time period is synchronously predicted in real time.
And S5, acquiring the actual traffic volume between the road sections according to the vehicle access information of each toll station.
And S6, comparing the actual traffic volume with the optimal traffic accommodation volume to obtain a real-time ratio, and controlling the vehicles corresponding to the toll stations to enter according to the real-time ratio.
S7, comprehensively evaluating the daily average traffic quantity of each toll station, distinguishing concentrated traffic time periods, and establishing average traffic thermodynamic diagrams of each toll station at different time periods.
And S8, predicting the traffic flow data of each toll station in a future period of time according to the average traffic data of each toll station in different periods of time and by combining the average traffic of the historical traffic numerical value of the corresponding date.
And S9, according to the cooperation of the future traffic flow data of each toll station in the data service cluster and the highway whole-road state information and real-time ratio, making an advance judgment on the subsequent highway pressure and reminding.
And S10, backing up year-round data to the data service cluster in real time, detecting historical state similar items by combining the access of future weather forecast data, making early response warning, and extracting optimal treatment measures.
As a further scheme of the invention: the vehicle entering mode of the toll station corresponding to the real-time ratio control is that the ratio of the actual traffic volume A to the optimal traffic capacity B is A: B, when A is larger than B, the entrance of the toll station in the detection road section is limited, when A is smaller than B, the entrance of the toll station is not limited, and when A is larger than B, the entrance of the large-scale truck is limited.
As a further scheme of the invention: the traffic state real-time monitoring network is provided with a detection station at an interval of 10km, and the detection station is provided with integrated equipment with functions of vehicle speed, vehicle type, passing number per minute, visibility and weather detection.
As a further scheme of the invention: the forecast of the traffic data of each toll station in the step S8 for a period of time in the future comprises the following formula;
estimating the total flow on the same day:
K＝[(M 1 /At 1 +M 2 /At 2 +...+M n /At n )/i+(L 1 /Bt 1 +L 2 /Bt 2 +...+L n /Bt n )/i]/2；
flow estimation in a specific time period on the day:
K＝[(M n /At n )/i+(L n /Bt n )/i]/2；
wherein: at is the current time period, M is the number of traffic flows in the current time period, L is the number of historical traffic flows, Bt is the historical time period, i is the number of traffic flows in the historical time period, and K is the predicted value of the future traffic flow.
As a further scheme of the invention: and in the process of backing up year-round data to the data service cluster in real time in the S10, extracting the features of the data, wherein the feature extraction variables comprise: date information, weather information, congestion length, congestion section, and traffic flow data information.
As a further scheme of the invention: the average passing thermodynamic diagram of each toll station at different time intervals in the step S7 is established in such a manner that the corresponding station data of the full-range toll station of the expressway are respectively rendered into colors with different depths according to the number of passing vehicles in different time intervals all day by each toll station.
As a further scheme of the invention: the calculation method of the optimal passing accommodation amount comprises the following steps:
Q＝[(e*s)/z]；
wherein: s is average speed per hour, e is the number of parallel vehicles, Q is the capacity, z is the overall vehicle occupancy distance, and z is u 1 +u 2 +u 3 、u 1 Is the average length u of the car body 2 Average braking distance, u, of the vehicle 3 The distance is safe.
As a further scheme of the invention: the whole road section state information comprises maintenance road section construction information of the expressway, the whole road condition of the expressway and speed limit information of each area.
The invention has the beneficial effects that:
the invention integrates diversified data and behavior data of drivers by a data service cluster established by each toll station, controls the vehicle entering state of the toll stations of corresponding sections in real time according to the actual ratio by matching with the comparison between the optimal traffic capacity and the actual traffic volume of a road, can accurately control the traffic flow of congested sections, combines natural, road conditions and human factors, is matched with time scales to predict the traffic flow state of different sections in the future, can predict the prediction of the time scales by the average value of historical date and traffic flow of different time periods, can accurately predict the probability of occurrence of congestion, synchronously matches with the detected information, retrieves the corresponding historical data characteristics and obtains the processing method thereof, integrates the efficient measures in the historical scheme, can realize early warning and arrange corresponding recommended measures in advance, the method solves the problem that the prediction effect is poor due to the fact that only the time characteristic of the traffic volume is considered in comparison with the traditional traffic volume prediction model.
Drawings
FIG. 1 is a block diagram of an overview flow of the present invention;
FIG. 2 is a schematic diagram of an average curve model of the present invention when the vehicle is driven away from the high speed.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1:
a multivariate behavior data mining method comprises the following steps:
s1, establishing a data service cluster according to the entrance and exit toll stations of the full-length highway section, and acquiring the quantity of vehicles entering and exiting each toll station and the information of vehicle types.
And S2, detecting the state information of the whole highway section, acquiring visibility, ground humidity and weather information, and uploading the information to a data service cluster.
And S3, establishing a road section traffic state real-time monitoring network based on the data service cluster lower layer, and acquiring data of the passing speed and the density of the vehicles.
S4, the safe passing speed among all areas of the whole road section is estimated through the weather and road section information acquired through S2, and the optimal passing accommodation capacity of the expressway in the current time period is synchronously predicted in real time.
And S5, acquiring the actual traffic volume between the road sections according to the vehicle access information of each toll station.
And S6, comparing the actual traffic volume with the optimal traffic accommodation volume to obtain a real-time ratio, and controlling the vehicles corresponding to the toll stations to enter according to the real-time ratio.
S7, comprehensively evaluating the daily average traffic quantity of each toll station, distinguishing concentrated traffic time periods, and establishing average traffic thermodynamic diagrams of each toll station at different time periods.
And S8, predicting the traffic flow data of each toll station in a future period of time according to the average traffic data of each toll station in different periods of time and by combining the average traffic of the historical traffic numerical value of the corresponding date.
And S9, according to the cooperation of the future traffic flow data of each toll station in the data service cluster and the highway whole-road state information and real-time ratio, making an advance judgment on the subsequent highway pressure and reminding.
And S10, backing up year-round data to the data service cluster in real time, detecting historical state similar items by combining the access of future weather forecast data, making early response warning, and extracting optimal treatment measures.
The vehicle entering mode of the toll station corresponding to the real-time ratio control is that the ratio of the actual traffic volume A to the optimal traffic capacity B is A: B, when A > B, the vehicle enters the toll station in the detection road section in a limited mode, when A < B, the vehicle enters the toll station in an unlimited mode, and when A is equal to B, the vehicle enters the toll station in a limited mode. The real-time ratio is adopted to control the vehicles corresponding to the toll stations to enter, so that the vehicles can be controlled and adjusted more systematically and pertinently, and a good relieving effect can be achieved on the congestion road sections of the expressway.
A detection station is arranged at an interval of 10km in a traffic state real-time monitoring network, and the detection station is provided with integrated equipment with functions of vehicle speed, vehicle type, passing number per minute, visibility and weather detection. The integrated collection of various information is carried out by adopting a detection station mode, so that the construction of the whole system is more convenient, and meanwhile, the correlation of multivariate data in the same region is better.
The forecast of the traffic data of each toll station in a future period of time in the S8 comprises the following formula;
estimating the total flow on the same day:
K＝[(M 1 /At 1 +M 2 /At 2 +...+M n /At n )/i+(L 1 /Bt 1 +L 2 /Bt 2 +...+L n /Bt n )/i]/2；
flow estimation in a specific time period on the day:
K＝[(M n /At n )/i+(L n /Bt n )/i]/2；
wherein: at is the current time period, M is the number of traffic flows in the current time period, L is the number of historical traffic flows, Bt is the historical time period, i is the number of traffic flows in the historical time period, and K is the predicted value of the future traffic flow.
In the process of backing up year-round data to the data service cluster in real time in S10, feature extraction is carried out on the data, and the feature extraction variables comprise: date information, weather information, congestion length, congestion section, and traffic flow data information. By adopting the method, the annual data are backed up to the data service cluster in real time after the characteristic extraction, so that the corresponding approximate numerical value can be accurately retrieved through the characteristic data when the historical data is detected in the follow-up process, and the storage pressure of the data server after the characteristic extraction is greatly reduced.
The average passing thermodynamic diagram of each toll station in different time periods in the step S7 is established in such a way that the corresponding station data of the full-range toll station of the expressway are respectively rendered into colors with different depths according to the number of passing vehicles in different time periods all day by each toll station. By constructing the thermodynamic diagram, vehicles can enter and exit according to corresponding road sections in different time periods, the congestion can be rapidly solved in real time, whether the congestion is relieved or continuously aggravated can be rapidly solved, and rapid decision making can be facilitated.
The optimal traffic capacity is calculated as follows:
Q＝[(e*s)/z]；
wherein: s is average speed per hour, e is the number of parallel vehicles, Q is the capacity, z is the overall vehicle occupancy distance, and z is u 1 +u 2 +u 3 、u 1 Is the average length u of the car body 2 Average braking distance, u, of the vehicle 3 The distance is safe.
The product of the maximum parallel running number and the average speed per hour is matched with the comprehensive occupied distance of the vehicles, so that the optimal vehicle interval, namely the density of the vehicles is obtained, and finally the optimal accommodating capacity can be obtained through the optimal running density according to the density and the road distance.
The sum of the length estimation values of all the vehicles passing through in a period of time is divided by the total number of the vehicles, and then the average length of the vehicle body can be obtained.
The whole road section state information comprises the construction information of the maintenance road section of the expressway, the whole road condition of the expressway and the speed limit information of each area.
Example 2:
a multivariate behavior data mining method comprises the following steps:
s1, establishing a data service cluster according to the entrance and exit toll stations of the full-length highway section, and acquiring the quantity of vehicles entering and exiting each toll station and the information of vehicle types.
And S2, detecting the state information of the whole highway section, acquiring visibility, ground humidity and weather information, and uploading the information to a data service cluster.
And S3, establishing a road section traffic state real-time monitoring network based on the data service cluster lower layer, and acquiring data of the passing speed and the density of the vehicles.
S4, the safe passing speed among all areas of the whole road section is estimated through the weather and road section information acquired through S2, and the optimal passing accommodation capacity of the expressway in the current time period is synchronously predicted in real time.
And S5, acquiring the actual traffic volume between the road sections according to the vehicle access information of each toll station.
And S6, comparing the actual traffic volume with the optimal traffic accommodation volume to obtain a real-time ratio, and controlling the vehicles corresponding to the toll stations to enter according to the real-time ratio.
And S7, predicting the traffic flow data of each toll station in a future period of time according to the average traffic data of each toll station in different periods of time and by combining the average traffic of the historical traffic numerical value of the corresponding date.
And S8, according to the cooperation of the future traffic flow data of each toll station in the data service cluster and the highway whole-road state information and real-time ratio, making an advance judgment on the subsequent highway pressure and reminding.
And S9, backing up year-round data to the data service cluster in real time, detecting historical state similar items by combining the access of future weather forecast data, making early response warning, and extracting optimal treatment measures.
Example 3:
a multivariate behavior data mining method comprises the following steps:
s1, establishing a data service cluster according to the entrance and exit toll stations of the full-length highway section, and acquiring the quantity of vehicles entering and exiting each toll station and the information of vehicle types.
And S2, detecting the state information of the whole highway section, acquiring visibility, ground humidity and weather information, and uploading the information to a data service cluster.
And S3, establishing a road section traffic state real-time monitoring network based on the data service cluster lower layer, and acquiring data of the passing speed and the density of the vehicles.
S4, the safe passing speed among all areas of the whole road section is estimated through the weather and road section information acquired through S2, and the optimal passing accommodation capacity of the expressway in the current time period is synchronously predicted in real time.
And S5, acquiring the actual traffic volume between the road sections according to the vehicle access information of each toll station.
And S6, comparing the actual traffic volume with the optimal traffic accommodation volume to obtain a real-time ratio, and controlling the vehicles corresponding to the toll stations to enter according to the real-time ratio.
S7, comprehensively evaluating the daily average traffic quantity of each toll station, distinguishing concentrated traffic time periods, and establishing average traffic thermodynamic diagrams of each toll station at different time periods.
In conclusion, the present invention: the method comprises the steps of acquiring diversified data of the highway through the established full-section traffic state real-time monitoring network, combining the influence degree of behavior data of natural and man-made factors on vehicle driving according to road condition information to obtain a relative optimal passing capacity, synchronously comparing the optimal passing capacity with the actual passing capacity according to the optimal passing capacity, controlling the vehicle entering condition of a subsequent toll station more accurately by using the real-time ratio of the optimal passing capacity, greatly preventing the high-speed passing state from being influenced, playing a good prevention and control effect, knowing the passing condition of corresponding section sections according to the real-time ratio, facilitating to perform faster reaction, preventing the further deterioration of the passing state, simultaneously combining the high-speed passing state with the variation of vehicles at different time intervals of time scale and matching and retrieving of historical data to enable the vehicle passing state of the highway to achieve more accurate future highway to be judged in advance, by mining and integrating diversified data of the highway, the future traffic condition can be judged and predicted with higher precision, advance decision can be realized for traffic management departments, upcoming problems can be strategically deployed, and the three using modes in the embodiment are independent use of internal functions, so that the use is more flexible.
According to the extracted vehicle entering and exiting data registered by the plurality of toll stations and summarizing, after the vehicle is on a high speed, the speed of the same batch of high speed is gradually increased and gradually reduced along with the reduction of the quantity along with the change of the time scale, an average state value of the vehicle leaving the high speed is obtained according to the plurality of extracted data, the average state value is combined as a data model to estimate the attenuation of the quantity of the vehicle density along with the change of the distance in a time period of the same toll station, the influence of the residual traffic flow from the upstream toll station to the downstream toll stations can be predicted, and the subsequent traffic flow pressure change can be assisted to be predicted.
The points to be finally explained are: although the present invention has been described in detail with reference to the general description and the specific embodiments, on the basis of the present invention, the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (5)
1. A multivariate behavior data mining method is characterized by comprising the following steps:
s1, establishing a data service cluster according to the entrance and exit toll stations of the full-length highway section, and acquiring the number of vehicles entering and exiting each toll station and the information of vehicle types;
s2, detecting the state information of the whole highway section, acquiring visibility, ground humidity and weather information and uploading the information to a data service cluster;
s3, establishing a traffic state real-time monitoring network of the whole road section based on the lower layer of the data service cluster, and carrying out data acquisition on the passing speed and the density of the vehicles;
s4, the safe passing speed among all areas of the whole road section is estimated through the weather and road section information obtained in S2, the optimal passing accommodation capacity of the highway in the current time period is synchronously predicted in real time, and the optimal passing accommodation capacity is calculated in the following mode:
Q＝[(e*s)/z]；
wherein: s is average speed per hour, e is the number of parallel vehicles, Q is the capacity, z is the overall vehicle occupancy distance, and z is u 1 +u 2 +u 3 、u 1 Is the average length u of the car body 2 Average braking distance, u, of the vehicle 3 A safe vehicle distance is obtained;
s5, acquiring the actual traffic volume between the road sections according to the vehicle access information of each toll station;
s6, comparing the actual traffic volume with the optimal traffic volume to obtain a real-time ratio, and controlling the vehicles corresponding to the toll stations to enter according to the real-time ratio, wherein the real-time ratio controls the vehicles corresponding to the toll stations to enter in a mode that the ratio of the actual traffic volume A to the optimal traffic volume B is A: B, when A is greater than B, the vehicles are limited to enter the toll stations in the detection road section, when A is less than B, the vehicles are not limited to enter, and when A is greater than B, the vehicles are limited to enter;
s7, comprehensively evaluating the daily average traffic quantity of each toll station, distinguishing concentrated traffic time periods, and establishing average traffic thermodynamic diagrams of each toll station at different time periods;
s8, predicting traffic flow data of each toll station in a future period of time according to the average traffic data of each toll station in different periods of time and by combining the average flow of the historical traffic numerical value of the corresponding date, wherein the prediction of the traffic flow data of each toll station in the future period of time comprises the following formula;
estimating the total flow on the same day:
K＝[(M 1 /At 1 +M 2 /At 2 +...+M n /At n )/i+(L 1 /Bt 1 +L 2 /Bt 2 +...+L n /Bt n )/i]/2；
flow estimation in a specific time period on the day:
K＝[(M n /At n )/i+(L n /Bt n )/i]/2；
wherein: at is the current time period, M is the number of traffic flows in the current time period, L is the number of historical traffic flows, Bt is the historical time period, i is the number of traffic flows in the historical time period, and K is a predicted value of future traffic flow;
s9, according to the cooperation of the future traffic flow data of each toll station in the data service cluster, the highway whole-road state information and the real-time ratio, making an advance judgment on the subsequent highway pressure and making a prompt;
and S10, backing up year-round data to the data service cluster in real time, detecting historical state similar items by combining the access of future weather forecast data, making early response warning, and extracting optimal treatment measures.
2. The multivariate behavioral data mining method according to claim 1, characterized in that: the traffic state real-time monitoring network is provided with a detection station at an interval of 10km, and the detection station is provided with integrated equipment with functions of vehicle speed, vehicle type, passing number per minute, visibility and weather detection.
3. The multivariate behavioral data mining method according to claim 1, characterized in that: and in the process of backing up year-round data to the data service cluster in real time in the S10, extracting the features of the data, wherein the feature extraction variables comprise: date information, weather information, congestion length, congestion section, and traffic flow data information.
4. The multivariate behavioral data mining method according to claim 1, characterized in that: the average passing thermodynamic diagram of each toll station at different time intervals in the step S7 is established in such a manner that the corresponding station data of the full-range toll station of the expressway are respectively rendered into colors with different depths according to the number of passing vehicles in different time intervals all day by each toll station.
5. The multivariate behavioral data mining method according to claim 1, characterized in that: the whole road section state information comprises maintenance road section construction information of the expressway, the whole road condition of the expressway and speed limit information of each area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111645060.5A CN114267184B (en) | 2021-12-29 | 2021-12-29 | Multivariate behavior data mining method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111645060.5A CN114267184B (en) | 2021-12-29 | 2021-12-29 | Multivariate behavior data mining method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114267184A CN114267184A (en) | 2022-04-01 |
| CN114267184B true CN114267184B (en) | 2022-08-02 |
Family
ID=80831543
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111645060.5A Active CN114267184B (en) | 2021-12-29 | 2021-12-29 | Multivariate behavior data mining method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114267184B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114613145B (en) * | 2022-05-12 | 2022-08-19 | 中运科技股份有限公司 | Passenger traffic flow perception early warning system and method under big data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106781457A (en) * | 2016-11-29 | 2017-05-31 | 东南大学 | A kind of freeway traffic flow parameter correction method based on multi-source fusion data |
| CN108665707A (en) * | 2018-05-24 | 2018-10-16 | 金陵科技学院 | It is a kind of prevent local traffic congestion expressway access shunting and flow cooperative control method |
| CN109064754A (en) * | 2018-10-10 | 2018-12-21 | 南京宁昱通交通科技有限公司 | A kind of expressway access shunts and flow Collaborative Control technology |
| CN112785849A (en) * | 2021-02-24 | 2021-05-11 | 山东科技大学 | Highway congestion state judgment and traffic flow control system and method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105590346B (en) * | 2016-02-18 | 2018-01-16 | 华南理工大学 | The traffic information collection of turn pike net and inducible system based on path identifying system |
-
2021
- 2021-12-29 CN CN202111645060.5A patent/CN114267184B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106781457A (en) * | 2016-11-29 | 2017-05-31 | 东南大学 | A kind of freeway traffic flow parameter correction method based on multi-source fusion data |
| CN108665707A (en) * | 2018-05-24 | 2018-10-16 | 金陵科技学院 | It is a kind of prevent local traffic congestion expressway access shunting and flow cooperative control method |
| CN109064754A (en) * | 2018-10-10 | 2018-12-21 | 南京宁昱通交通科技有限公司 | A kind of expressway access shunts and flow Collaborative Control technology |
| CN112785849A (en) * | 2021-02-24 | 2021-05-11 | 山东科技大学 | Highway congestion state judgment and traffic flow control system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114267184A (en) | 2022-04-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107742418B (en) | Automatic identification method for traffic jam state and jam point position of urban expressway | |
| CN108242149B (en) | Big data analysis method based on traffic data | |
| CN105405293B (en) | A kind of road travel time short term prediction method and system | |
| CN105913661B (en) | A kind of express highway section traffic state judging method based on charge data | |
| CN110164132B (en) | Method and system for detecting road traffic abnormity | |
| CN104933860B (en) | Bus traffic congestion delay time at stop Forecasting Methodology based on gps data | |
| EP3162651A1 (en) | Driver profiling system and method | |
| CN108647743B (en) | Driver safety portrait system | |
| CN109887283A (en) | A kind of congestion in road prediction technique, system and device based on bayonet data | |
| CN109147319B (en) | Road emergency discrimination method based on multiple traffic data indexes | |
| CN114267184B (en) | Multivariate behavior data mining method | |
| CN107909839A (en) | Vehicle safety processing method and processing device | |
| CN115240431A (en) | Real-time online simulation system and method for traffic flow of highway toll station | |
| CN106327864A (en) | Traffic flow estimation method based on network charging data of highway | |
| CN113436432A (en) | Method for predicting short-term traffic risk of road section by using road side observation data | |
| CN106601005A (en) | City intelligent traffic induction method based on RFID and WeChat platform | |
| CN114999181B (en) | Highway vehicle speed abnormality identification method based on ETC system data | |
| Cohen | Impact of a dedicated lane on the capacity and the level of service of an urban motorway | |
| CN112767684A (en) | Highway traffic jam detection method based on charging data | |
| CN110415517A (en) | A kind of accurate early warning system of congestion in road based on vehicle driving trace and method | |
| Rashidi et al. | Using automatic vehicle location data to model and identify determinants of bus bunching | |
| CN113159374A (en) | Data-driven urban traffic flow rate mode identification and real-time prediction early warning method | |
| CN107331152B (en) | Multi-target optimization method for pedestrian crossing facilities at intersection controlled by secondary parking | |
| CN113112789A (en) | Method for predicting and controlling influence of urban expressway emergency | |
| CN106910334A (en) | A kind of method and device that section situation is predicted based on big data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |