CN106157657A - A kind of moving state identification system and method for mobile subscriber - Google Patents
A kind of moving state identification system and method for mobile subscriber Download PDFInfo
- Publication number
- CN106157657A CN106157657A CN201510175799.2A CN201510175799A CN106157657A CN 106157657 A CN106157657 A CN 106157657A CN 201510175799 A CN201510175799 A CN 201510175799A CN 106157657 A CN106157657 A CN 106157657A
- Authority
- CN
- China
- Prior art keywords
- mobile subscriber
- mobile
- traffic data
- traffic
- moving state
- 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
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses the moving state identification system and method for a kind of mobile subscriber, comprising: traffic data receiver module, for collecting the feature of mobile subscriber's motion state;Traffic data analyzing module, for identifying the motion state of mobile subscriber, distinguishes with this and predicts traffic;Analysis result output module, is used for the traffic of the motion state with each mobile subscriber of records of values and different sections of highway;Display module, for showing the real-time traffic condition in each section on the subscriber terminal in different colors, provides the optimum drive route of system recommendations.Use the present invention, special algorithm can be utilized to determine the motion state of mobile subscriber, help to analyze real time traffic data, to improve the utilization rate of real time traffic data;And can be distinguished and predict travel pattern by analyzing the mobile traffic data collected, and the traffic of transportation network is more accurately predicted.
Description
Technical field
The present invention relates to intelligent transportation and wireless location technology, particularly relate to the motion state of a kind of mobile subscriber
Identify system and method.
Background technology
In recent years, as social development traffic congestion has become global problem, Urban Efficiency is being reduced
While also cause a series of consequence, be therefore unfavorable for urbanization and motorization.
Researcher is devoted to solve traffic jam issue by providing various types of scheme always.Wherein
A scheme be by collecting effective transport information, providing it to driver to help them to make more
Reasonably drive and determine.Practice also demonstrates, and providing real-time transport information to public transport participant is to keep away
Exempt from road congestion and formulate the key factor of optimum drive route decision-making.
At present, in inland of China and the Hong Kong Special Administrative Region, some private enterprises and government organs have been had to start to going out
Passerby provides traffic data.According to investigations, the traffic department in above-mentioned area has released some and has collected traffic data
Measure, the traffic data of the variety classes vehicles can be received in different ways, but still lack
Some technology that traffic data is analyzed.Owing to traffic data generally exists in digital form, driver
Can not directly use.Show according to another investigation result, now in the world developed country or region to traffic data
Utilization rate is still very low.
Therefore, a kind of technology that can fully excavate and utilize traffic data of research is needed badly, to improve friendship in real time
The utilization rate of logical data.
Content of the invention
In view of this, present invention is primarily targeted at the moving state identification system of a kind of mobile subscriber is provided
And method, determined the motion state of mobile subscriber by special algorithm, help to analyze real time traffic data,
To improve the utilization rate of real time traffic data.
Another object of the present invention is to, by analyzing the mobile traffic data collected, distinguish and predict traffic
Pattern, and the traffic of transportation network is more accurately predicted.
For reaching above-mentioned purpose, the technical scheme is that and be achieved in that:
The moving state identification system of a kind of mobile subscriber, comprises traffic data collection module, traffic data divides
Analyse module and analysis result output module and display module;Wherein:
Described traffic data receiver module, for collecting the feature of mobile subscriber's motion state;
Described traffic data analyzing module, for identifying the motion state of mobile subscriber, distinguishes with this and predicts
Traffic;
Described analysis result output module, for the motion state of each mobile subscriber of records of values and not
Traffic with section;And,
Described display module, for showing the real-time traffic condition in each section on the subscriber terminal in different colors,
Provide the optimum drive route of system recommendations.
Wherein: the feature of described mobile subscriber's motion state, including speed, position, the time, travel direction,
Brake information.
The motion state of described mobile subscriber, including inactive state, ambulatory status and with motor vehicle motion
State.
The described state with motor vehicle motion is specifically included in low-speed machine motor-car and High speed vehicle two states.
A kind of moving state identification method of mobile subscriber, comprises the steps:
A, the step for collecting mobile traffic data;
B, utilize and be built-in with the data analysis module of SVMs mobile traffic data are analyzed, point
Distinguish the step of various mobile subscriber's classification and motion state;
C, judge that whether translational speed within the unit interval for the described mobile subscriber is more than a certain pre-set velocity value,
If so, then judge it on the car travelling;If it is not, then judge it not on the car travelling.
Wherein: farther include after step C: D's, as required conversion mobile subscriber terminal application model
Step, particularly as follows: close data analysis pattern or turn-on data analytical model.
Step D farther includes: if closing data analysis pattern, then keep current traffic condition;Otherwise,
Return step A.
The process of described collection mobile traffic data is: utilize the mobile terminal of various access to wireless communication network
Or/and the vehicles are collected user profile and the movement state information of mobile subscriber.
Described mobile terminal and the vehicles are built-in with the traffic data analyzing module of SVMs.
The described vehicles access V2V network.
Described user profile, including collect terminal and the type of vehicle data of mobile traffic data.
Described movement state information, including movement velocity, position, time, travel direction, brake and weather
Condition information.
The moving state identification system and method for mobile subscriber provided by the present invention, have the advantage that
As described above, identifying the motion state of mobile subscriber, as static, walking, in low-speed high speed
It inside vehicle, is very important to using mobile device to collect Real-time Traffic Information.By using this
Algorithm, analyst can easily choose suitable traffic data to carry out next step analysis.Therefore, this
Item invention can optimize raising traffic data and utilize.
Compared to other machines learning algorithm, the moving state identification algorithm of described mobile subscriber is due to by low-dimensional
Data are mapped to higher dimensional space, further improve algorithm classification accuracy rate, project actual measurement in accuracy rate up to
94.93%.When the moving state identification algorithm model of described mobile subscriber is trained, depend on when training sample is less
So can reach higher accuracy rate, this makes this algorithm more extensively quickly to use, and without length
Time waits collects data.The moving state identification algorithm of described mobile subscriber is calculated compared to other machines study
Method, such as neural network algorithm etc., amount of calculation is little, and the required calculating time is few, low to internal memory and hardware requirement.
Brief description
Fig. 1 is the SVMs using in the moving state identification system of embodiment of the present invention mobile subscriber
(SVM) optimal classification surface schematic diagram;
Fig. 2 is the structure composed schematic diagram of the moving state identification system of embodiment of the present invention mobile subscriber;
Fig. 3 is the schematic flow sheet of the moving state identification method of embodiment of the present invention mobile subscriber.
Detailed description of the invention
Below in conjunction with the accompanying drawings and the moving state identification system of the mobile subscriber to the present invention for the embodiments of the invention
And method is described in further detail.
The present invention, by analyzing the mobile traffic data collected, collects, in conjunction with from other approach, the data coming,
Such as position vehicle, V2V network and video monitoring from coil, GPS, thus distinguish and predict traffic
Pattern.By being used as, these results predict that some cannot gather the section of real time traffic data or prediction one
The following road conditions in the section of real time traffic data can be provided a bit.Place can be good at according to Bayesian network method
Reason, from the transport information of adjacent road, can also process incomplete data.So, we can basis
Incomplete data, are more accurately predicted out the traffic of transportation network.
Here, described V2V network is a kind of mesh network, and the node being in network is (such as automobile, intelligence
Traffic lights etc.) can launch, capture and forward signal, on that network, between automobile, transfer message mutually,
Telling what the other side oneself doing, described information includes but is not limited to speed, position, travel direction, brake
Deng.Described V2V technology uses DSRC (DSRC), and its coverage is up to 300 meters, and it is also
Can utilize the traffic outside collecting 1.5 kilometers of jumping of multiple nodes on network, this is to most drivers
For have the enough reply time.
The present invention is used for identifying the motion state of mobile subscriber, such as static, walking, in low speed or high speed
Vehicle is medium, and this is particularly important for using mobile device to collect Real-time Traffic Information.For standard
Really predicting the motion state of user, we use extension class correlation rule (CAR) algorithm to set up
Valuable rule.These rules come from the various types of real user information of covering (as speed, position,
Time, travel direction, brake etc.), can easily with key areas Knowledge Aggregation.Proposed method,
By applying these rules and considering that some are uncertain, the dynamic of intelligent transportation system (ITS) can be met
With the demand under open environment.And by identifying the motion state of mobile subscriber, such as static, walking, low
Speed, the medium situation of vehicle of high speed, use the method for the present invention, can easily choose suitable traffic number
According to carrying out next step analysis, thus can be used to improve the utilization rate of traffic data.
It is known that the active state of mobile subscriber can be divided into inactive state, ambulatory status and with motor vehicle
The state of motion (utilizes the mobile subscriber that bicycle is gone on a journey, typically can keep inactive state or walking shape
State).Therefore, it can mobile subscriber's sample of acquisition is divided into Ambulatoria and motor vehicle class.For with motor vehicle
The mobile subscriber of motion, may produce inactive state in motion process, and the generation of inactive state may
Certain impact is produced on the final transport information calculating.The reason that produce inactive state in general have as follows
Several: to arrive at the parking that parking, stand-by period of changing trains, artificial parking and traffic congestion produce.
The mobile subscriber that there is " static " state being produced by front 3 kinds of situations in motion process (is classified as
Motor vehicle disturbs class), no matter the traffic in its place section how, quiescent time length, its speed is all
(motor vehicle can be classified as less than the mobile subscriber with car motion that there is not " static " state on same section
Class) speed;And the mobile subscriber of " static " state of the 4th kind of situation generation, it is the friendship actual by road surface
Logical situation produces, and will not produce impact to final result of calculation.
As described above, mobile subscriber's movement velocity includes: speed, the motor vehicle of the mobile subscriber of Ambulatoria are done
Disturb the speed of the mobile subscriber of the speed and motor-driven car class of the mobile subscriber of class.
In order to calculate the mean velocity information in each section in road network, the present invention utilize SVMs (SVM,
Support Vector Machines) method classified, will extract from the velocity information of above-mentioned mobile subscriber
Go out the velocity information of the mobile subscriber of motor vehicle class.From analysis above, the movement of motor vehicle interference class
The average speed of user is not more than the average speed of mobile subscriber of motor vehicle class all the time, and the movement of Ambulatoria
The average speed of user is affected very little by traffic, about stable at 3~5km/h (representative value desirable 4
km/h)。
The speed of mobile subscriber is divided into 3 classes by the method that present invention application SVMs (SVM) classifies,
Judge the classification of each class further according to features described above, barycenter is Ambulatoria closest to the class of 4km/h, remaining
In 2 classes, what barycenter was little disturbs class for motor vehicle, barycenter big for motor vehicle class.Finally according to motor vehicle
The speed of the mobile subscriber of class, can calculate average speed or the average travel time in each section in road network.
The present invention uses SVMs (SVM) to carry out classifying to identify the motion state of mobile subscriber.
Here, the machine learning method that we are used is SVMs (SVM).This SVMs
It is solving small sample, is having a lot of distinctive advantage in non-linear and high dimensional pattern identification, and can push away
It is extensively applied in the other machines problems concerning study such as Function Fitting.
SVMs (SVM) method is built upon VC dimension theory and the structure risk of Statistical Learning Theory
On the basis of minimum principle, according to limited sample information in the complexity of model (i.e. to specific training sample
Study precision, Accuracy) and the learning ability ability of arbitrary sample (i.e. error-free identify) between
Seek optimum balance, to obtaining best Generalization Ability.
Fig. 1 is the SVMs used in the moving state identification system of embodiment of the present invention mobile subscriber
(SVM) optimal classification surface schematic diagram.
Described SVMs (SVM) is that the optimal classification surface in the case of linear separability develops,
Its basic thought can be illustrated by the two-dimensional case shown in figure below.
As it is shown in figure 1, C1And C2Represent two class data samples to be distinguished respectively;H presentation class liney=ω x+b;H1And H2It is parallel to H, and cross the straight line from the nearest two class samples of H;H1With H,
H2And the distance between H is just called geometry interval, and its expression formula is:
In above formula, | | ω | | represents the norm of ω;B presentation class penalties.
So-called optimal classification line, it is simply that not only correct for two class data samples can be separated, make training error rate
Minimum, but also geometry to be made interval maximum.The former ensures empirical risk minimization;And the latter is actually
Making the fiducial range in Generalization Bounds minimum, the bigger solution in geometry interval, its upper error is less.By two dimension
Space Expanding just becomes optimal classification surface to high bit space, optimal classification line.Corresponding classification problem is permissible
Change into the problem of minimizing of a belt restraining.We are described in detail in next part.
Wherein, in the moving state identification system of the mobile subscriber of the present invention, the SVMs of employing
(SVM) algorithm, it is described as follows:
Assume there be l training sample, use vector xi∈Rn, i=1,2 ..., l represents.This training sample is in this project
In be the mobile data of user.The classification of final classification, as a example by two classes, is used | yi{ 1 ,-1} represent, permissible
Represent the static of user or mobile two states.For this classification problem, with following mathematic(al) representation meter
Calculate.
Submit to:
εi>=0,1=1 ...., 1.
In formula (1), εiRepresenting relaxation factor, it allows the existence of mistake point sample;C is a positive constant,
It is referred to as penalty factor;For penalty term, introduce its purpose and be desirable at empiric risk and promote performance
Between try to achieve certain balance.It is by xiProject to a higher dimensional space.Owing to vector parameter w may have
Very high dimension, and this problem is an optimization problem with inequality constraints, can be by adding
Lagrange multiplier, construction Lagrange function solves this problem, and the asking of the most above-mentioned optimal classification surface
Solution problem is converted into the dual problem of following convex quadratic programming optimizing:
Submit to: yTα=0,0≤αi≤ C, 1=1......1,
E=in formula (2) [1 ... ,]TBeing unit vector, Q is the positive semidefinite matrix of l × l, αiFor corresponding
Lagrange multiplier, Qif≡yiyfK(xi, xf。Being kernel function, it can realize by low-dimensional
Space is to the mapping of higher dimensional space, thus solves nonlinear problem, conventional kernel function have polynomial function,
RBF and Sigmoid function etc..
In the present invention, the kernel function of employing is RBF:
exp(-δr2),
Wherein r=1/n.
It by solving model (2), with the corresponding relation between veneziano model and master mould, is calculated model
(1) the vector parameter w in meets following condition:
Final calculated optimal classification surface function is:
This is last determining function.For a new test sample, if the value of optimal classification surface function
When being negative value, test sample is incorporated in this class of y=-1, if the value of optimal classification surface function is just
During value, test sample is incorporated in this class of y=1.In corresponding project, first we collect user
Actual mobile data are as training sample, the optimum being calculated in final (4) of used model (2)
Classifying face.
In conjunction with technical scheme, y therein represents the classification belonging to mobile subscriber, i.e. static and shifting
Dynamic, xiRepresent the feature of mobile subscriber's motion state, such as speed, position, time, travel direction, brake
Deng.
By the judgement positive and negative to optimal classification surface function value, user is divided into static and mobile two classes.
Simultaneously for this class of mobile status, above-mentioned algorithm can also be passed through, be divided into Ambulatoria and motor vehicle class.
Now y represents the two classification, xiRepresent the feature of mobile subscriber's motion state, as speed, position, when
Between, travel direction, brake etc..
Fig. 2 is the structure composed schematic diagram of the moving state identification system of embodiment of the present invention mobile subscriber.As
Shown in Fig. 2, the moving state identification system of described mobile subscriber, mainly comprise traffic data collection module,
Traffic data analyzing module, analysis result output module and display module.Wherein:
Described traffic data receiver module, is used for collecting the feature of mobile subscriber's motion state, including speed,
Position, time, travel direction and brake etc.;
Described traffic data analyzing module, is used for identifying the motion state of mobile subscriber, including inactive state,
Ambulatory status, and it (is specifically included in low-speed machine motor-car and High speed vehicle two with the state of motor vehicle motion
The state of kind);Distinguish with this again and predict traffic;
Described analysis result output module, for the motion state of each mobile subscriber of records of values and not
Traffic with section;
Described display module, for showing the real-time traffic condition in each section on the subscriber terminal in different colors,
Provide the optimum drive route of system recommendations.
Fig. 3 is the schematic flow sheet of the moving state identification method of embodiment of the present invention mobile subscriber.Such as Fig. 3
Shown in, the moving state identification method of described mobile subscriber comprises the steps:
Step 31: for the step collecting mobile traffic data.
Here it is possible to utilize various mobile terminal or/and the equipment such as vehicle or the vehicles are collected mobile use
The user profile at family and movement state information.Described mobile terminal, including but not limited to can be connect by wireless
Enter the intelligent mobile communication terminal of communication network, GPS terminal, panel computer.Described vehicle, for accessing V2V
The various vehicles of network, generally refer in particular to various motor vehicle, such as car, public transport bus, goods vehicle
Deng.The data such as the terminal of described user profile, including but not limited to collection mobile traffic data and type of vehicle.
Described movement state information, including but not limited to movement velocity, position, the time, travel direction, brake and
The information such as weather conditions.
Step 32: utilize the traffic data analyzing module being built-in with SVMs (SVM) to mobile traffic
Data are analyzed, the step differentiating various mobile subscriber's classification and motion state;Then step 33.
Here, the described detailed process utilizing traffic data analyzing module to be analyzed mobile traffic data is such as
Under:
Step 33: judge whether translational speed within the unit interval for the described mobile subscriber is more than a certain default speed
Angle value, if so, then step 34;If it is not, then step 35.
Step 34: judge its travel car on, then step 36.
Step 35: judge its not travel car on, then step 36.
Step 36: the step changing mobile subscriber terminal application model as required, then step 37.
Step 37: judge whether described mobile subscriber terminal application model changes, if it is not, then return step
Rapid 31, continue to be analyzed collected mobile traffic data;If so, then step 38, exit number
According to analytical model.
Here, whether the application model of described mobile subscriber terminal changes, and divides particularly as follows: close data
Analysis pattern or turn-on data analytical model.
Step 38: keep current traffic condition.
The above, only presently preferred embodiments of the present invention, it is not intended to limit the protection model of the present invention
Enclose.
Claims (12)
1. the moving state identification system of a mobile subscriber, it is characterised in that comprise traffic data collection module, traffic data analyzing module and analysis result output module and display module;Wherein:
Described traffic data receiver module, for collecting the feature of mobile subscriber's motion state;
Described traffic data analyzing module, for identifying the motion state of mobile subscriber, distinguishes with this and predicts traffic;
Described analysis result output module, is used for the traffic of the motion state with each mobile subscriber of records of values and different sections of highway;And,
Described display module, for showing the real-time traffic condition in each section on the subscriber terminal in different colors, provides the optimum drive route of system recommendations.
2. the moving state identification system of mobile subscriber according to claim 1, it is characterised in that the feature of described mobile subscriber's motion state, including speed, position, time, travel direction, brake information.
3. the moving state identification system of mobile subscriber according to claim 1, it is characterised in that the motion state of described mobile subscriber, including inactive state, ambulatory status and the state with motor vehicle motion.
4. the moving state identification system of mobile subscriber according to claim 3, it is characterised in that the described state with motor vehicle motion is specifically included in low-speed machine motor-car and High speed vehicle two states.
5. the moving state identification method of a mobile subscriber, it is characterised in that comprise the steps:
A, the step for collecting mobile traffic data;
B, utilize and be built-in with the data analysis module of SVMs mobile traffic data are analyzed, the step differentiating various mobile subscriber's classification and motion state;
C, judge that whether translational speed within the unit interval for the described mobile subscriber is more than a certain pre-set velocity value, if so, then judge it on the car travelling;If it is not, then judge it not on the car travelling.
6. the moving state identification method of mobile subscriber according to claim 5, it is characterised in that farther include after step C:
D, the step changing mobile subscriber terminal application model as required, particularly as follows: close data analysis pattern or turn-on data analytical model.
7. the moving state identification method of mobile subscriber according to claim 6, it is characterised in that step D farther includes:
If closing data analysis pattern, then keep current traffic condition;Otherwise, step A is returned.
8. the moving state identification method of mobile subscriber according to claim 5, it is characterized in that, the process collecting mobile traffic data is: utilize the mobile terminal of various access to wireless communication network or/and the vehicles are collected user profile and the movement state information of mobile subscriber.
9. the moving state identification method of the mobile subscriber according to claim 5 or 8, it is characterised in that be built-in with the traffic data analyzing module of SVMs in described mobile terminal and the vehicles.
10. the moving state identification method of the mobile subscriber according to claim 5 or 8, it is characterised in that the described vehicles access V2V network.
The moving state identification method of 11. mobile subscribers according to claim 8, it is characterised in that described user profile, including collect terminal and the type of vehicle data of mobile traffic data.
The moving state identification method of 12. mobile subscribers according to claim 8, it is characterised in that described movement state information, including movement velocity, position, time, travel direction, brake and weather conditions information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510175799.2A CN106157657A (en) | 2015-04-14 | 2015-04-14 | A kind of moving state identification system and method for mobile subscriber |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510175799.2A CN106157657A (en) | 2015-04-14 | 2015-04-14 | A kind of moving state identification system and method for mobile subscriber |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106157657A true CN106157657A (en) | 2016-11-23 |
Family
ID=57336933
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510175799.2A Pending CN106157657A (en) | 2015-04-14 | 2015-04-14 | A kind of moving state identification system and method for mobile subscriber |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106157657A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107315519A (en) * | 2017-06-30 | 2017-11-03 | 北京奇虎科技有限公司 | OS switching methods, device and mobile terminal under driving condition |
CN107341226A (en) * | 2017-06-30 | 2017-11-10 | 北京奇虎科技有限公司 | Information displaying method, device and mobile terminal |
CN107396306A (en) * | 2017-06-30 | 2017-11-24 | 北京奇虎科技有限公司 | User Activity state identification method, device and mobile terminal based on mobile terminal |
CN110876112A (en) * | 2018-08-14 | 2020-03-10 | 中国电信股份有限公司 | Method and device for identifying high-speed user and computer readable storage medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0763807A1 (en) * | 1995-09-14 | 1997-03-19 | AT&T Corp. | Traffic information estimation and reporting system |
JPH09205378A (en) * | 1995-10-18 | 1997-08-05 | Korea Mobil Telecommun Corp | Traffic information terminal equipment and traffic information processing method |
CN1828226A (en) * | 2005-09-28 | 2006-09-06 | 佛山市顺德区瑞图万方科技有限公司 | Real-time traffic information system and its navigation method |
CN101086784A (en) * | 2006-06-06 | 2007-12-12 | 同济大学 | A system and method for traffic information publishing grid service based on PDA client |
CN101114836A (en) * | 2006-07-24 | 2008-01-30 | 同济大学 | System and method for vehicle mounted terminal to issue traffic information gridding service |
CN102663887A (en) * | 2012-04-13 | 2012-09-12 | 浙江工业大学 | Implementation system and method for cloud calculation and cloud service of road traffic information based on technology of internet of things |
CN102737510A (en) * | 2012-07-03 | 2012-10-17 | 浙江大学 | Real-time traffic condition acquisition method based on mobile intelligent terminal |
KR20140128063A (en) * | 2013-04-26 | 2014-11-05 | 한국교통연구원 | Traffic prediction system |
-
2015
- 2015-04-14 CN CN201510175799.2A patent/CN106157657A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0763807A1 (en) * | 1995-09-14 | 1997-03-19 | AT&T Corp. | Traffic information estimation and reporting system |
JPH09205378A (en) * | 1995-10-18 | 1997-08-05 | Korea Mobil Telecommun Corp | Traffic information terminal equipment and traffic information processing method |
CN1828226A (en) * | 2005-09-28 | 2006-09-06 | 佛山市顺德区瑞图万方科技有限公司 | Real-time traffic information system and its navigation method |
CN101086784A (en) * | 2006-06-06 | 2007-12-12 | 同济大学 | A system and method for traffic information publishing grid service based on PDA client |
CN101114836A (en) * | 2006-07-24 | 2008-01-30 | 同济大学 | System and method for vehicle mounted terminal to issue traffic information gridding service |
CN102663887A (en) * | 2012-04-13 | 2012-09-12 | 浙江工业大学 | Implementation system and method for cloud calculation and cloud service of road traffic information based on technology of internet of things |
CN102737510A (en) * | 2012-07-03 | 2012-10-17 | 浙江大学 | Real-time traffic condition acquisition method based on mobile intelligent terminal |
KR20140128063A (en) * | 2013-04-26 | 2014-11-05 | 한국교통연구원 | Traffic prediction system |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107315519A (en) * | 2017-06-30 | 2017-11-03 | 北京奇虎科技有限公司 | OS switching methods, device and mobile terminal under driving condition |
CN107341226A (en) * | 2017-06-30 | 2017-11-10 | 北京奇虎科技有限公司 | Information displaying method, device and mobile terminal |
CN107396306A (en) * | 2017-06-30 | 2017-11-24 | 北京奇虎科技有限公司 | User Activity state identification method, device and mobile terminal based on mobile terminal |
CN110876112A (en) * | 2018-08-14 | 2020-03-10 | 中国电信股份有限公司 | Method and device for identifying high-speed user and computer readable storage medium |
CN110876112B (en) * | 2018-08-14 | 2021-04-06 | 中国电信股份有限公司 | Method and device for identifying high-speed user and computer readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Greenberg | An analysis of traffic flow | |
Pi et al. | Visual cause analytics for traffic congestion | |
Chen et al. | Analysis of factors affecting the severity of automated vehicle crashes using XGBoost model combining POI data | |
Stipancic et al. | Surrogate safety and network screening: Modelling crash frequency using GPS travel data and latent Gaussian Spatial Models | |
Dabiri et al. | A deep convolutional neural network based approach for vehicle classification using large-scale GPS trajectory data | |
Xing et al. | Comparison of different models for evaluating vehicle collision risks at upstream diverging area of toll plaza | |
CN112700072A (en) | Traffic condition prediction method, electronic device, and storage medium | |
CN106157657A (en) | A kind of moving state identification system and method for mobile subscriber | |
CN107180534A (en) | The express highway section average speed method of estimation of support vector regression fusion | |
Patil | Applications of deep learning in traffic management: A review | |
Wang et al. | ARIMA Model and Few‐Shot Learning for Vehicle Speed Time Series Analysis and Prediction | |
Siddique et al. | State-dependent self-adaptive sampling (SAS) method for vehicle trajectory data | |
Gore et al. | Exploring credentials of Wi‐Fi sensors as a complementary transport data: an Indian experience | |
Kabir et al. | Time-Series fuel consumption prediction assessing delay impacts on energy using vehicular trajectory | |
CN116092037B (en) | Vehicle type identification method integrating track space-semantic features | |
Luo et al. | A statistical method for parking spaces occupancy detection via automotive radars | |
Rong et al. | An interdisciplinary survey on origin-destination flows modeling: Theory and techniques | |
Khan | Real-time traffic condition assessment with connected vehicles | |
Li et al. | Graph neural networks in urban intelligence | |
Xing et al. | GRU‐CNN Neural Network Method for Regional Traffic Congestion Prediction Serving Traffic Diversion Demand | |
Xu et al. | Wi‐CL: Low‐Cost WiFi‐Based Detection System for Nonmotorized Traffic Travel Mode Classification | |
Dabiri | Application of deep learning in intelligent transportation systems | |
Sun et al. | Alleviating data sparsity problems in estimated time of arrival via auxiliary metric learning | |
Yuan et al. | Driver back-tracing based on automated vehicle identification data | |
Guo et al. | Deep learning based congestion prediction using PROBE trajectory data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20161123 |