CN110428614A - A kind of traffic congestion temperature spatio-temporal prediction method based on non-negative tensor resolution - Google Patents
A kind of traffic congestion temperature spatio-temporal prediction method based on non-negative tensor resolution Download PDFInfo
- Publication number
- CN110428614A CN110428614A CN201910625133.0A CN201910625133A CN110428614A CN 110428614 A CN110428614 A CN 110428614A CN 201910625133 A CN201910625133 A CN 201910625133A CN 110428614 A CN110428614 A CN 110428614A
- Authority
- CN
- China
- Prior art keywords
- tensor
- section
- traffic
- negative
- resolution
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of urban traffic blocking temperature spatio-temporal prediction method based on non-negative tensor resolution, comprising: consider road network topology characteristic and space-time relationship, the tensor of building characterization urban transportation space-time congestion temperature;Tensor resolution is initialized based on Algorithms of Non-Negative Matrix Factorization;Information Meter index is calculated, core tensor size is selected according to Information Meter;The tensor resolution prediction model based on receding horizon is constructed, realizes the prediction of the granularity of different time in short-term of traffic congestion temperature.Compared to traditional prediction technique, this method merges history space time information, focuses on data interdependencies, predicts accurate fixed height.
Description
Technical field
The present invention relates to intelligent transportation field more particularly to a kind of urban traffic blocking temperatures based on non-negative tensor resolution
Spatio-temporal prediction method, for predicting urban traffic blocking temperature.
Background technique
As urbanization process and motorization trip are fast-developing, urban traffic blocking increasingly sharpens, traffic congestion it is pre-
Survey is always industry concern topic and focus.Urban transportation construction in recent years is from infrastructure construction gradually to informationization simultaneously
Construction transformation, the multi-class devices such as electronic police, Floating Car provide a large amount of traffic travel time data, to portray traffic behavior
Have accumulated mass historical data.Furthermore the state evolution of traffic congestion has association in time and space correlation characteristic, is based on magnanimity
Historical data excavates the space time correlation characteristic of traffic congestion, and then carries out the space-time temperature prediction of traffic congestion, is traffic administration
Person provides control anticipation, and for traffic trip, person provides information service, has significant application value.
Summary of the invention
The purpose of the present invention is to provide a kind of urban traffic blocking temperature spatio-temporal prediction side based on non-negative tensor resolution
Method.The core concept of this method is to consider road network topology characteristic and space-time relationship, building characterization urban transportation space-time congestion heat
The tensor of degree is excavated the multi-modal relationship of space-time data using non-negative tensor resolution, adjusts the correlation model parameters of tensor resolution,
The final short-term prediction for realizing urban traffic blocking temperature.
The technical solution adopted by the present invention, a kind of urban traffic blocking temperature spatio-temporal prediction side based on non-negative tensor resolution
Method, step include:
C1, building traffic tensor, contained element and its position are determined by road network topology characteristic and space-time relationship;
C2, tensor resolution is initialized based on Algorithms of Non-Negative Matrix Factorization;
C3, Information Meter index is calculated, core tensor size is selected according to Information Meter;
C4, tensor resolution prediction model of the building based on receding horizon, when realizing the difference in short-term of traffic congestion temperature
Between granularity prediction.
Further, in step c1, traffic tensor is constructed, detailed process includes:
C11, the collected historical traffic data for being used to characterize congestion temperature is integrated: chooses I1A section, when
Number of segment I2For one day 24 hours time interval divided by division, historical date was number of days I3;The traffic data can prolong for section
Mistake, link travel speed freedom degree, section delay index, road section traffic volume congestion index one or more of them;
It c12, with target road section is l1, calculate section l1With other I1The historical traffic data vector in -1 section it is similar
Property metric, selecting the maximum section of similarity measure values is l2, calculate section l2With remaining I1The historical traffic number in -2 sections
According to the similarity measure values of vector, selecting the maximum section of similarity measure values is l3, and so on, obtain section l1, section
l2..., section lI1, wherein 1,2 ..., I1For location label;
C13, historical data and null value to be predicted are integrated into three-dimensional tensor according to three section, period, date dimensionsWith two-value tensorWherein existing historical data is 1 in B, data to be predicted are 0.
Further, the process of step c2 includes:
C21, three-dimensional tensor is subjected to tensor matrixing according to different dimensions, obtains 3 matrixes, i.e. M(1),M(2),M(3);
C22, for specified J1、J2、J3, to M(1),M(2),M(3)Non-negative Matrix Factorization is carried out, matrix is obtainedInitialization factor matrix as tensor resolution.
Further, the process of step c3 includes:
C31, to matrix M(1), PCA calculating is carried out, Principal component λ is obtainedJm;
C32, information angle value is calculated
C33, general so thatMaximum JmValue is determined as optimal core tensor size;
C34, to M(2)And M(3)It repeats the above process, obtains the core tensor size of mode-2 and mode-3.
Further, the process of the c4 of step includes:
C41, setting convergence threshold εtoi;
C42, core tensor is calculated, withAs initialization matrix, with
J1、J2、J3As core tensor size, calculate core tensor G=M ×1A(1)×2A(2)×...×NA(N);
C43, calculate error E=B* (M-G ×1A(1)×2A(2)×...×NA(N)), judgement | | E | |2/||M||2Whether it is less than
Threshold epsilontoi, it is to be transferred to c44, it is no to be transferred to c45;
C44, factor matrix is calculated using least square ALS, gradient descent method etc. With core tensor G, returns to c43 and judged;
C45, output be calculated complete tensor G ×1A(1)×2A(2)×...×NA(N);
C46, as unit of day, utilize step c3 roll update J1、J2、J3Optimal value.
Beneficial effects of the present invention: the invention proposes a kind of, and the traffic congestion temperature space-time based on non-negative tensor resolution is pre-
Survey method.Compared to traditional prediction technique, this method merges history space time information, focuses on data interdependencies, and prediction is accurate
Fixed height;Small to data index request, applicability is wide;Computational efficiency is high, can predict large-scale road network.
Detailed description of the invention
Fig. 1 is method frame figure of the invention.
Fig. 2 is tensor resolution schematic diagram of the invention.
Fig. 3 is calculating process flow chart of the invention.
Fig. 4 is conventional method and method calculated result comparison diagram of the invention.
Specific embodiment
In order to make the invention's purpose, features and advantages of the invention more obvious and easy to understand, below in conjunction with the present invention
Attached drawing in embodiment is clearly and completely described the technical solution in embodiment of the present invention, it is clear that described
Embodiment be only some embodiments of the invention, and not all embodiments.Based on the embodiment in the present invention,
Those skilled in the art's every other embodiment obtained without making creative work, belongs to the present invention
The range of protection.
With the road network congestion index data instance in certain city, change using this method predicted congestion space-time temperature.
Step 1: building traffic tensor, contained element and its position are determined by road network topology characteristic and space-time relationship.
For constructing the element of traffic tensor, including but not limited to following traffic data:
Section delay, link travel speed freedom degree, section delay index, traffic congestion index, flow, speed, saturation
Degree.
Certain city road network shares K1A section, K2A period, K3The historical traffic data on a date, 1 date contain K2It is a
Period.
Traffic tensor is constructed, I is chosen1A section, one of them is target road section, I2A period, I3The history on a date is handed over
Logical data, wherein 1≤I1≤K1, 1≤I2≤K2, 1≤I3≤K3。
I1- 1 section is connected in road network topology with target road section, adoptable choosing method:
1) radius is gradually increased as the center of circle using the midpoint of target road section and draws circle, when round range covers I1When -1 section
Stop;
2) to sort from low to high with the shortest path of target road section by several crossing numbers, I before selecting1- 1 section;
3) consider the factor that is connected, after normalized, weight is set, by calculated value size sequencing selection I1- 1 section,
Connected factor includes but is not limited to: with the shortest path of target road section by several crossing numbers, target road section midpoint with wait choose
The gap of the category of roads of linear distance, target road section and section to be chosen between road segment midpoints.
I1Side identified below can be used in the space-time relationship in -1 section and target road section, the position in traffic tensor
Method:
It is l with target road section1, calculate section l1With other I1The similarity measurements of the historical traffic data vector in -1 section
Magnitude, selecting the maximum section of similarity measure values is l2, calculate section l2With remaining I1The historical traffic data in -2 sections
The similarity measure values of vector select similarity measure values maximum for l3, and so on, obtain l1、l2、…、lI1, 1,2 ...,
I1For location label;
Wherein, similarity measure values calculating can be used method and include but is not limited to: included angle cosine, Euclidean distance, Manhattan
Distance, mahalanobis distance, comentropy, related coefficient.
In one embodiment, step 1 specifically uses:
(1) the congestion index historical data in collected section is integrated.20 sections are chosen, when congestion index
Between between be divided into 2min, one day 24 hours time interval divided by division, totally 720 when number of segment, historical date is 30 day datas.
(2) topology in section and the space-time relationship of data are analyzed.For section l1, choose in road network topology and be attached thereto
20 sections historical data, calculate separately section l1It is pressed from both sides with the similarity measurements figureofmerit of the data vector in other 20 sections
Angle cosine value chooses the maximum section l of similitudeiMarked as 2, and so on respectively label to l20;
(3) historical data and null value to be predicted are integrated into three-dimensional tensor according to three section, period, date dimensionsWith two-value tensorWherein existing historical data is 1 in B, data to be predicted are 0.
Step 2: tensor resolution being initialized based on Algorithms of Non-Negative Matrix Factorization.
(1) three-dimensional tensor is subjected to tensor matrixing according to different dimensions, obtains 3 matrixes, i.e. M(1),M(2),M(3)。
(2) for specified J1、J2、J3, to M(1),M(2),M(3)Non-negative Matrix Factorization is carried out, matrix is obtainedInitialization factor matrix as tensor resolution.
Step 3: calculating Information Meter index, core tensor size is selected according to Information Meter.
(1) to matrix M(1), PCA calculating is carried out, Principal component is obtained
(2) information angle value is calculated
(3) will so thatMaximum JmValue is determined as optimal core tensor size.
(4) to M(2)And M(3)It repeats the above process, obtains the core tensor size of mode-2 and mode-3.
Step 4: tensor resolution prediction model of the building based on receding horizon realizes the different in short-term of traffic congestion temperature
The prediction of time granularity.
(1) convergence threshold ε is settoi。
(2) core tensor is calculated, withAs initialization matrix, with
J1、J2、J3As core tensor size, calculate core tensor G=M ×1A(1)×2A(2)×...×NA(N)。
(3) calculate error E=B* (M-G ×1A(1)×2A(2)×...×NA(N)), judgement | | E | |2/||M||2Whether it is less than
Threshold epsilontoi, use least square ALS to calculate factor matrix if no With
Core tensor G.Judgement is repeated until convergence.
(4) output be calculated complete tensor G ×1A(1)×2A(2)×...×NA(N)。
(5) it as unit of day, is rolled using step (3) and updates J1、J2、J3Optimal value.
In order to embody the effect of this technology, building evaluation index characterization prediction errorWherein N is
The number to be predicted, YiFor predicted value, XiFor actual value.Calculated result is as shown in Figure 4.As can be seen from the results, compared to traditional difference
Rolling average autoregression (ARIMA) method is integrated, of the invention has lesser prediction error, while the error under different periods
Value is steady.
In the above-described embodiment, it all emphasizes particularly on different fields to the description of each embodiment, without detailed in some embodiment
The part stated may refer to the associated description of other embodiment.The above are the description of this invention, for the general of this field
Technical staff, the thought of embodiment according to the present invention, there will be changes in the specific implementation manner and application range, comprehensive
On, the contents of this specification are not to be construed as limiting the invention.
Claims (5)
1. a kind of urban traffic blocking temperature spatio-temporal prediction method based on non-negative tensor resolution, it is characterised in that this method includes
Following steps:
C1, building traffic tensor, contained element and its position are determined by road network topology characteristic and space-time relationship;
C2, tensor resolution is initialized based on Algorithms of Non-Negative Matrix Factorization;
C3, Information Meter index is calculated, core tensor size is selected according to Information Meter;
C4, tensor resolution prediction model of the building based on receding horizon, realize the different time in short-term of traffic congestion temperature
The prediction of granularity.
2. a kind of urban traffic blocking temperature spatio-temporal prediction method based on non-negative tensor resolution according to claim 1,
It is characterized by: in step c1, the building traffic tensor, detailed process includes:
C11, the collected historical traffic data for being used to characterize congestion temperature is integrated: chooses I1A section, when number of segment I2
For one day 24 hours time interval divided by division, historical date was number of days I3;The traffic data can be section delay, road
Section travel speed freedom degree, section delay index, road section traffic volume congestion index one or more of them;
It c12, with target road section is l1, calculate section l1With other I1The similarity measurements of the historical traffic data vector in -1 section
Magnitude, selecting the maximum section of similarity measure values is l2, calculate section l2With remaining I1The historical traffic data in -2 sections to
The similarity measure values of amount, selecting the maximum section of similarity measure values is l3, and so on, obtain section l1, section l2、…、
Section lI1, wherein 1,2 ..., I1For location label;
C13, historical data and null value to be predicted are integrated into three-dimensional tensor according to three section, period, date dimensions
With two-value tensorWherein existing historical data is 1 in B, data to be predicted are 0.
3. a kind of urban traffic blocking temperature spatio-temporal prediction method based on non-negative tensor resolution according to claim 1,
It is characterized by: in step c2, described that tensor resolution is initialized based on Algorithms of Non-Negative Matrix Factorization, detailed process packet
It includes;
C21, three-dimensional tensor is subjected to tensor matrixing according to different dimensions, obtains 3 matrixes, i.e. M(1),M(2),M(3);
C22, for specified J1、J2、J3, to M(1),M(2),M(3)Non-negative Matrix Factorization is carried out, matrix is obtainedInitialization factor matrix as tensor resolution.
4. a kind of urban traffic blocking temperature spatio-temporal prediction method based on non-negative tensor resolution according to claim 1,
It is characterized by: the calculating Information Meter index selects core tensor size according to Information Meter, and detailed process includes: in step c3
C31, to matrix M(1), PCA calculating is carried out, Principal component is obtained
C32, information angle value is calculated
C33, general so thatMaximum JmValue is determined as optimal core tensor size;
C34, to M(2)And M(3)It repeats the above process, obtains the core tensor size of mode-2 and mode-3.
5. a kind of urban traffic blocking temperature spatio-temporal prediction method based on non-negative tensor resolution according to claim 1,
It is characterized by: in the c4 of step, the tensor resolution prediction model of the building based on receding horizon realizes traffic congestion heat
The prediction of the granularity of different time in short-term of degree, detailed process include:
C41, setting convergence threshold εtoi;
C42, core tensor is calculated, withAs initialization matrix, with J1、
J2、J3As core tensor size, calculate core tensor G=M ×1A(1)×2A(2)×...×NA(N);
C43, calculate error E=B* (M-G ×1A(1)×2A(2)×...×NA(N)), judgement | | E | |2/||M||2Whether threshold value is less than
εtoi, it is to be transferred to c44, it is no to be transferred to c45;
C44, factor matrix is calculated using least square ALS, gradient descent method etc. With core tensor G, returns to c43 and judged;
C45, output be calculated complete tensor G ×1A(1)×2A(2)×...×NA(N);
C46, as unit of day, utilize step c3 roll update J1、J2、J3Optimal value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910625133.0A CN110428614B (en) | 2019-07-11 | 2019-07-11 | Traffic jam heat degree space-time prediction method based on non-negative tensor decomposition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910625133.0A CN110428614B (en) | 2019-07-11 | 2019-07-11 | Traffic jam heat degree space-time prediction method based on non-negative tensor decomposition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110428614A true CN110428614A (en) | 2019-11-08 |
CN110428614B CN110428614B (en) | 2021-02-05 |
Family
ID=68409217
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910625133.0A Active CN110428614B (en) | 2019-07-11 | 2019-07-11 | Traffic jam heat degree space-time prediction method based on non-negative tensor decomposition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110428614B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111768635A (en) * | 2020-04-02 | 2020-10-13 | 东南大学 | Coupling robustness tensor decomposition-based sporadic traffic congestion detection method |
CN112200705A (en) * | 2020-09-10 | 2021-01-08 | 浙江大学 | Tensor decomposition-based urban grouping identification method |
CN112967498A (en) * | 2021-02-02 | 2021-06-15 | 重庆首讯科技股份有限公司 | Short-term traffic flow prediction method based on dynamic space-time correlation characteristic optimization |
CN113256986A (en) * | 2021-06-29 | 2021-08-13 | 中移(上海)信息通信科技有限公司 | Traffic analysis method, related device and readable storage medium |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8204988B2 (en) * | 2009-09-02 | 2012-06-19 | International Business Machines Corporation | Content-based and time-evolving social network analysis |
CN105206048A (en) * | 2015-11-05 | 2015-12-30 | 北京航空航天大学 | Urban resident traffic transfer mode discovery system and method based on urban traffic OD data |
CN107992536A (en) * | 2017-11-23 | 2018-05-04 | 中山大学 | Urban transportation missing data complementing method based on tensor resolution |
CN108920887A (en) * | 2018-06-08 | 2018-11-30 | 扬州大学 | A kind of sequential organization brain network analysis method based on Non-negative Matrix Factorization |
CN109431499A (en) * | 2018-12-12 | 2019-03-08 | 杭州师范大学 | Auxiliary system and householder method are nursed by plant person family |
CN109598936A (en) * | 2018-12-18 | 2019-04-09 | 中国科学院地理科学与资源研究所 | A kind of prediction of short-term traffic volume method based on dynamic STKNN model |
CN109816984A (en) * | 2019-03-19 | 2019-05-28 | 太原理工大学 | A kind of traffic network region division and dynamic adjusting method |
CN109830102A (en) * | 2019-02-14 | 2019-05-31 | 重庆邮电大学 | A kind of short-term traffic flow forecast method towards complicated urban traffic network |
JP6635418B2 (en) * | 2016-06-07 | 2020-01-22 | 日本電信電話株式会社 | Flow rate prediction device, pattern estimation device, flow rate prediction method, pattern estimation method, and program |
-
2019
- 2019-07-11 CN CN201910625133.0A patent/CN110428614B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8204988B2 (en) * | 2009-09-02 | 2012-06-19 | International Business Machines Corporation | Content-based and time-evolving social network analysis |
CN105206048A (en) * | 2015-11-05 | 2015-12-30 | 北京航空航天大学 | Urban resident traffic transfer mode discovery system and method based on urban traffic OD data |
JP6635418B2 (en) * | 2016-06-07 | 2020-01-22 | 日本電信電話株式会社 | Flow rate prediction device, pattern estimation device, flow rate prediction method, pattern estimation method, and program |
CN107992536A (en) * | 2017-11-23 | 2018-05-04 | 中山大学 | Urban transportation missing data complementing method based on tensor resolution |
CN108920887A (en) * | 2018-06-08 | 2018-11-30 | 扬州大学 | A kind of sequential organization brain network analysis method based on Non-negative Matrix Factorization |
CN109431499A (en) * | 2018-12-12 | 2019-03-08 | 杭州师范大学 | Auxiliary system and householder method are nursed by plant person family |
CN109598936A (en) * | 2018-12-18 | 2019-04-09 | 中国科学院地理科学与资源研究所 | A kind of prediction of short-term traffic volume method based on dynamic STKNN model |
CN109830102A (en) * | 2019-02-14 | 2019-05-31 | 重庆邮电大学 | A kind of short-term traffic flow forecast method towards complicated urban traffic network |
CN109816984A (en) * | 2019-03-19 | 2019-05-28 | 太原理工大学 | A kind of traffic network region division and dynamic adjusting method |
Non-Patent Citations (2)
Title |
---|
孟侨: "基于压缩光场的虚拟视点生成研究", 《中国优秀硕士学位论文全文数据库》 * |
蔡正义: "基于大数据的城市居民出行分析建模", 《中国博士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111768635A (en) * | 2020-04-02 | 2020-10-13 | 东南大学 | Coupling robustness tensor decomposition-based sporadic traffic congestion detection method |
CN112200705A (en) * | 2020-09-10 | 2021-01-08 | 浙江大学 | Tensor decomposition-based urban grouping identification method |
CN112967498A (en) * | 2021-02-02 | 2021-06-15 | 重庆首讯科技股份有限公司 | Short-term traffic flow prediction method based on dynamic space-time correlation characteristic optimization |
CN112967498B (en) * | 2021-02-02 | 2022-05-03 | 重庆首讯科技股份有限公司 | Short-term traffic flow prediction method based on dynamic space-time correlation characteristic optimization |
CN113256986A (en) * | 2021-06-29 | 2021-08-13 | 中移(上海)信息通信科技有限公司 | Traffic analysis method, related device and readable storage medium |
WO2023273724A1 (en) * | 2021-06-29 | 2023-01-05 | 中移(上海)信息通信科技有限公司 | Traffic analysis method, related device, and readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN110428614B (en) | 2021-02-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110428614A (en) | A kind of traffic congestion temperature spatio-temporal prediction method based on non-negative tensor resolution | |
CN110766942B (en) | Traffic network congestion prediction method based on convolution long-term and short-term memory network | |
CN108470444B (en) | A kind of city area-traffic big data analysis System and method for based on genetic algorithm optimization | |
CN106912015B (en) | Personnel trip chain identification method based on mobile network data | |
CN102542818B (en) | A kind of coordination control method for traffic signal of zone boundary based on organic calculating | |
TWI465694B (en) | Safe route configuration | |
CN110164128A (en) | A kind of City-level intelligent transportation analogue system | |
CN108053080A (en) | Zone user quantity statistics value Forecasting Methodology, device, equipment and medium | |
CN109272157A (en) | A kind of freeway traffic flow parameter prediction method and system based on gate neural network | |
CN109598936B (en) | Short-term traffic prediction method based on dynamic STKNN model | |
CN110176141B (en) | Traffic cell division method and system based on POI and traffic characteristics | |
CN109948066B (en) | Interest point recommendation method based on heterogeneous information network | |
CN107194491A (en) | A kind of dynamic dispatching method based on Forecasting of Travel Time between bus passenger flow and station | |
CN108765944B (en) | Optimal traffic flow forecasting method and Congestion Toll method based on multi-path collection | |
CN108882172B (en) | Indoor moving trajectory data prediction method based on HMM model | |
CN114692984B (en) | Traffic prediction method based on multi-step coupling graph convolution network | |
CN110164129B (en) | Single-intersection multi-lane traffic flow prediction method based on GERNN | |
CN106910199A (en) | Towards the car networking mass-rent method of city space information gathering | |
CN111145544B (en) | Travel time and route prediction method based on congestion spreading dissipation model | |
CN106780266B (en) | Principal component contribution degree parameter-based accident hotspot internal characteristic analysis and driving guidance method | |
CN108280998A (en) | Short-time Traffic Flow Forecasting Methods based on historical data dynamic select | |
Chen et al. | A multiscale-grid-based stacked bidirectional GRU neural network model for predicting traffic speeds of urban expressways | |
CN114723480B (en) | Passenger flow prediction method and cargo scheduling system for rural travel | |
CN112748732B (en) | Real-time path planning method based on improved Kstar algorithm and deep learning | |
CN116010838A (en) | Vehicle track clustering method integrating density value and K-means algorithm |
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 | ||
CP01 | Change in the name or title of a patent holder |
Address after: 310012 1st floor, building 1, 223 Yile Road, Hangzhou City, Zhejiang Province Patentee after: Yinjiang Technology Co.,Ltd. Address before: 310012 1st floor, building 1, 223 Yile Road, Hangzhou City, Zhejiang Province Patentee before: ENJOYOR Co.,Ltd. |
|
CP01 | Change in the name or title of a patent holder |