CN107688873A - Metro passenger flow Forecasting Methodology based on big data analysis - Google Patents
Metro passenger flow Forecasting Methodology based on big data analysis Download PDFInfo
- Publication number
- CN107688873A CN107688873A CN201710757135.6A CN201710757135A CN107688873A CN 107688873 A CN107688873 A CN 107688873A CN 201710757135 A CN201710757135 A CN 201710757135A CN 107688873 A CN107688873 A CN 107688873A
- Authority
- CN
- China
- Prior art keywords
- passenger flow
- data
- daily
- flow data
- timesharing
- 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
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000007405 data analysis Methods 0.000 title claims abstract description 16
- 238000013500 data storage Methods 0.000 claims abstract description 11
- 238000013499 data model Methods 0.000 claims description 8
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 claims description 3
- 230000001932 seasonal effect Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 2
- 238000005457 optimization Methods 0.000 abstract description 3
- 238000013528 artificial neural network Methods 0.000 description 6
- 230000000306 recurrent effect Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000007935 neutral effect Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000002969 morbid Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 238000005312 nonlinear dynamic Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Entrepreneurship & Innovation (AREA)
- Biomedical Technology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of metro passenger flow Forecasting Methodology based on big data analysis, applied to the passenger flow estimation of track traffic, comprise the following steps：Passenger flow data is extracted from passenger flow data storehouse, and is conducted into big data storage system；Daily timesharing passenger flow data and/or passenger flow data accumulative daily are read from above-mentioned big data storage system；Passenger flow data accumulative according to above-mentioned daily timesharing passenger flow data and/or daily carries out passenger flow estimation modeling using RNN models, and optimizes, and obtains passenger flow estimation data；Passenger flow data accumulative according to above-mentioned daily timesharing passenger flow data and/or daily and passenger flow estimation data, Continuous optimization prediction model parameterses, improve the degree of accuracy predicted next time.The problems such as present invention solves subway passenger flow Forecasting Methodology prediction result commonly used in the prior art and differs larger with actual operation passenger flow statisticses value, and the referring to property of prediction data is poor in actual operation.
Description
Technical field
The invention belongs to the neutral net passenger flow estimation technical field under big data environment, refer specifically to for a kind of big data ring
The metro passenger flow Forecasting Methodology of recurrent neural network (RNN) optimized algorithm is based under border.
Background technology
Track traffic long-term passenger flow estimation in planning can be carried out initial stage, but due to passenger flow estimation content and predicted condition
Complexity, its passenger flow estimation result differ larger with actual operation passenger flow statisticses value, and prediction data refers in actual operation
Property is poor.
Subway passenger flow data is predicted exactly, is had to the arrangement of subway transport power, following development and construction, the planning of function
Vital effect.Therefore, Accurate Prediction subway passenger flow just becomes an important topic in metro operation management,
It is the basis of subway effective distribution of resources.
Subway passenger flow change has complexity, randomness and periodic feature.Passenger flow forecast amount problem has height
It is non-linear and uncertain, while a correlation is stronger, the conventional method of such problem mainly has forecast of regression model
Method and the machine learning method using neutral net as representative.
In regression model, simple regression is most simple and sane, but describe it is often weak during the behavior of complication system, because
This Predicting Technique based on multiple regression is more common.Multivariate regression models is usually linear, is not shown due to that may be present
The dependency relation between variable and each independent variable is write, serious morbid state occurs in the normal equation group that can cause to return, has influence on
The stability of regression equation, so the basic problem that multiple linear regression faces is to find " Optimal Regression Equation.
Neutral net (Neural Networks) is a highly complex non-linear dynamic learning system, as to multiple
Miscellaneous nonlinear system approaches device, has self study, self-organizing and generalization ability, there is very big advantage in prediction field.
Recurrent neural network (Recurrent Neural Network, RNN) is one kind of neutral net, inherits nerve
Network has the advantages that self study, adaptive, fault-tolerant in function approximation, overcomes that network, which is not restrained, convergence rate is slow asks
Topic, plus under big data environment, the data of magnanimity provide the training sample of abundance for recurrent neural network (RNN), pre-
Precision aspect is surveyed also to improve a lot.
The content of the invention
Above-mentioned the deficiencies in the prior art are directed to, it is an object of the invention to provide a kind of subway based on big data analysis
Passenger flow forecasting, to solve subway passenger flow Forecasting Methodology prediction result commonly used in the prior art and actual operation passenger flow system
The problem of evaluation difference is larger, and the referring to property of prediction data is poor in actual operation.
To reach above-mentioned purpose, a kind of metro passenger flow Forecasting Methodology based on big data analysis of the invention, applied to rail
The passenger flow estimation of road traffic, comprises the following steps：
1) passenger flow data is extracted from passenger flow data storehouse, and is conducted into big data storage system；
2) daily timesharing passenger flow data and/or passenger flow number accumulative daily are read from above-mentioned big data storage system
According to；
3) passenger flow data added up according to above-mentioned daily timesharing passenger flow data and/or daily carries out visitor using RNN models
Stream prediction modeling, and optimize, obtain passenger flow estimation data；
4) passenger flow data added up according to above-mentioned daily timesharing passenger flow data and/or daily and passenger flow estimation data, hold
Continuous optimal prediction model parameter, improves the degree of accuracy predicted next time.
Preferably, described step 3) further comprises：It is according to described daily timesharing passenger flow data and/or accumulative daily
Passenger flow data carry out the modeling of basic day passenger flow estimation.
Preferably, described step 3) further comprises：According to the timesharing passenger flow data daily and/or accumulative daily
Passenger flow data carries out all passenger flow data modelings in basis.
Preferably, described step 3) further comprises：According to the timesharing passenger flow data daily and/or accumulative daily
Passenger flow data carries out basic moon passenger flow data modeling.
Preferably, described step 3) further comprises：According to the timesharing passenger flow data daily and/or accumulative daily
Passenger flow data carries out seasonal passenger traffic data modeling.
Preferably, described step 3) further comprises：According to the timesharing passenger flow data daily and/or accumulative daily
Passenger flow data carries out road network structure passenger flow data modeling.
Preferably, described step 3) further comprises：According to the timesharing passenger flow data daily and/or accumulative daily
Passenger flow data carries out rail network structure passenger flow data modeling.
Preferably, described step 3) further comprises：According to the timesharing passenger flow data daily and/or accumulative daily
Passenger flow data generates time factor table and date factor meter.
Preferably, described step 3) further comprises：Commuter time on working day section is included in the time factor table
Passenger flow data and off-hour section passenger flow data, working day passenger flow data, nonworkdays are included in the date factor meter
Passenger flow data and special day passenger flow data.
Preferably, described step 3) further comprises：According to commuter time on the working day section passenger flow data and non-
Commuter time section passenger flow data carry out passenger flow estimation modeling, obtain commuter time on working day section passenger flow estimation data and it is non-on
Quitting time section passenger flow estimation data.
Preferably, described step 3) further comprises：According to the working day passenger flow data and nonworkdays (two-day weekend
And state determines festivals or holidays) passenger flow data carries out passenger flow estimation modeling respectively, obtain working day passenger flow estimation data and nonworkdays visitor
Flow prediction data.
Preferably, the big data storage system reads passenger flow data and the passenger flow estimation data that subway line actually occurs
Optimal prediction model parameter, the prediction model parameterses after being optimized.
Beneficial effects of the present invention：
The present invention is based on recurrent neural network (RNN) technology, has the advantages that self study, adaptive, fault-tolerant, in big data
Storage system endlessly under mass data training, establishes prediction model parameterses, and the passenger flow number predicted according to system itself
It is compared according to the passenger flow data actually occurred, Continuous optimization prediction model parameterses, improves the accuracy of passenger flow estimation data.
Brief description of the drawings
Fig. 1 is the flow chart of Forecasting Methodology of the present invention.
Fig. 2 is the Passenger flow forecast model figure of the invention based on RNN.
Fig. 3 is RNN illustratons of model.
Fig. 4 is RNN model expanded views.
Embodiment
For the ease of the understanding of those skilled in the art, the present invention is made further with reference to embodiment and accompanying drawing
Bright, the content that embodiment refers to not is limitation of the invention.
Reference picture 1, shown in Fig. 2, a kind of metro passenger flow Forecasting Methodology based on big data analysis of the invention, applied to rail
The passenger flow estimation of road traffic, comprises the following steps：
1) passenger flow data is extracted from subway ticket selling and checking system passenger flow data storehouse, and is conducted into big data storage system；
2) daily timesharing passenger flow data and/or passenger flow number accumulative daily are read from above-mentioned big data storage system
According to；
3) passenger flow data added up according to above-mentioned daily timesharing passenger flow data and/or daily carries out visitor using RNN models
Stream prediction modeling, and parameter optimization is carried out, obtain passenger flow estimation data；In the model of foundation, three layers are shared：It is input layer, hidden
Hide layer and output layer；Xt-1, Xt-2, Xt-3For three the history moment same period t-1, t-2, t-3 of input layer passenger flow data, Yt-1To be defeated
Enter a layer passenger flow data for last moment prediction, be a value of feedback in model, to improve prediction accuracy.YtFor output layer
T passenger flow estimation value.
4) passenger flow data added up according to above-mentioned daily timesharing passenger flow data and/or daily and passenger flow estimation data, hold
Continuous optimal prediction model parameter, improves the degree of accuracy predicted next time.
In methods described, basic day is carried out according to the timesharing passenger flow data daily and/or passenger flow data accumulative daily
Passenger flow data models.
In methods described, basis week is carried out according to the timesharing passenger flow data daily and/or passenger flow data accumulative daily
Passenger flow data models.
In methods described, the basic moon is carried out according to the timesharing passenger flow data daily and/or passenger flow data accumulative daily
Passenger flow data models.
In methods described, carried out according to the timesharing passenger flow data daily and/or passenger flow data accumulative daily seasonal
Passenger flow data models.
In methods described, road network knot is carried out according to the timesharing passenger flow data daily and/or passenger flow data accumulative daily
Structure passenger flow data models.
In methods described, gauze knot is carried out according to the timesharing passenger flow data daily and/or passenger flow data accumulative daily
Structure passenger flow data models.
In methods described, according to the timesharing passenger flow data daily and/or passenger flow data accumulative daily generate the time because
Plain table and date factor meter.
In methods described, in the time factor table comprising commuter time on working day section passenger flow data and it is non-on and off duty when
Between section passenger flow data, include working day passenger flow data, nonworkdays passenger flow data and special day passenger flow in the date factor meter
Data.
In methods described, according to commuter time on the working day section passenger flow data and off-hour section passenger flow data
Passenger flow estimation modeling is carried out, obtains commuter time on working day section passenger flow estimation data and off-hour section passenger flow estimation number
According to.
In methods described, passenger flow estimation modeling is carried out according to the working day passenger flow data and nonworkdays passenger flow data,
Obtain working day passenger flow estimation data and nonworkdays passenger flow estimation data.
In methods described, passenger flow data and the passenger flow that subway line actually occurs are read according to the big data storage system
Prediction data optimal prediction model parameter, the prediction model parameterses after being optimized.
Model parameter calculation process is as follows：
Reference picture 3, it is RNN illustratons of model, and Fig. 4 is obtained after expansion.
Wherein t represents moment, XtRepresent the passenger flow data of t, StRepresent the output of t hidden layer, ytWhen representing t
Carve passenger flow forecast output.The input of hidden layer has two sources, and one is current XtInput, another is that Last status is hidden
The output S of layert-1, W, U, V are parameter.Can be by Fig. 4 representations using formula：
St=tanh (Uxt+Wst-1)
If hidden layer node number is 100, dictionary size C=8000, the dimensional information of parameter is：
xt∈R8000
yt∈R8000
st∈R100
U∈R100×8000
V∈R8000×100
W∈R100×100
Using cross entropy as loss function, if N number of sample, loss function can be written as：
Loss is cross entropy, is represented by：
WhereinFor the estimation passenger flow of t,For total passenger flow, EtLost for t, E is total losses, and W is sought to total losses
Partial derivative be：
Et can be further expressed as：
Shared, can obtained according to W weights in chain rule and RNN：
W is parameter required in model.
Concrete application approach of the present invention is a lot, and described above is only the preferred embodiment of the present invention, it is noted that for
For those skilled in the art, under the premise without departing from the principles of the invention, some improvement can also be made, this
A little improve also should be regarded as protection scope of the present invention.
Claims (10)
1. a kind of metro passenger flow Forecasting Methodology based on big data analysis, applied to the passenger flow estimation of track traffic, its feature exists
In comprising the following steps：
1）Passenger flow data is extracted from subway ticket selling and checking system passenger flow data storehouse, and is conducted into big data storage system；
2）Daily timesharing passenger flow data and/or passenger flow data accumulative daily are read from above-mentioned big data storage system；
3）Passenger flow data accumulative according to above-mentioned daily timesharing passenger flow data and/or daily is pre- using RNN models progress passenger flow
Modeling is surveyed, and is optimized, obtains passenger flow estimation data；
4）Passenger flow data accumulative according to above-mentioned daily timesharing passenger flow data and/or daily and passenger flow estimation data, continue excellent
Change prediction model parameterses, improve the degree of accuracy predicted next time.
2. the metro passenger flow Forecasting Methodology according to claim 1 based on big data analysis, it is characterised in that described step
Rapid 3）Further comprise：Passenger flow data accumulative according to described daily timesharing passenger flow data and/or daily carries out basic day visitor
Stream prediction modeling.
3. the metro passenger flow Forecasting Methodology according to claim 2 based on big data analysis, it is characterised in that described step
Rapid 3）Further comprise：The all passenger flows in basis are carried out according to the timesharing passenger flow data daily and/or passenger flow data accumulative daily
Data modeling.
4. the metro passenger flow Forecasting Methodology according to claim 3 based on big data analysis, it is characterised in that described step
Rapid 3）Further comprise：Basic moon passenger flow is carried out according to the timesharing passenger flow data daily and/or passenger flow data accumulative daily
Data modeling.
5. the metro passenger flow Forecasting Methodology according to claim 4 based on big data analysis, it is characterised in that described step
Rapid 3）Further comprise：Seasonal passenger traffic is carried out according to the timesharing passenger flow data daily and/or passenger flow data accumulative daily
Data modeling.
6. the metro passenger flow Forecasting Methodology according to claim 1 based on big data analysis, it is characterised in that described step
Rapid 3）Further comprise：Road network structure visitor is carried out according to the timesharing passenger flow data daily and/or passenger flow data accumulative daily
Flow data models.
7. the metro passenger flow Forecasting Methodology according to claim 1 based on big data analysis, it is characterised in that described step
Rapid 3）Further comprise：Rail network structure visitor is carried out according to the timesharing passenger flow data daily and/or passenger flow data accumulative daily
Flow data models.
8. the metro passenger flow Forecasting Methodology according to claim 1 based on big data analysis, it is characterised in that described step
Rapid 3）Further comprise：Time factor table is generated according to the timesharing passenger flow data daily and/or passenger flow data accumulative daily
With date factor meter.
9. the metro passenger flow Forecasting Methodology according to claim 8 based on big data analysis, it is characterised in that described step
Rapid 3）Further comprise：Commuter time on working day section passenger flow data and off-hour section are included in the time factor table
Passenger flow data, working day passenger flow data, nonworkdays passenger flow data and special day passenger flow data are included in the date factor meter.
10. the metro passenger flow Forecasting Methodology according to claim 9 based on big data analysis, it is characterised in that described
Step 3）Further comprise：Entered according to commuter time on the working day section passenger flow data and off-hour section passenger flow data
Row passenger flow estimation models, and obtains commuter time on working day section passenger flow estimation data and off-hour section passenger flow estimation number
According to.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710757135.6A CN107688873A (en) | 2017-08-29 | 2017-08-29 | Metro passenger flow Forecasting Methodology based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710757135.6A CN107688873A (en) | 2017-08-29 | 2017-08-29 | Metro passenger flow Forecasting Methodology based on big data analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107688873A true CN107688873A (en) | 2018-02-13 |
Family
ID=61155537
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710757135.6A Pending CN107688873A (en) | 2017-08-29 | 2017-08-29 | Metro passenger flow Forecasting Methodology based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107688873A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108647832A (en) * | 2018-05-18 | 2018-10-12 | 辽宁工业大学 | A kind of subway circulation interval time control algolithm based on neural network |
| CN110782060A (en) * | 2018-07-31 | 2020-02-11 | 上海宝信软件股份有限公司 | Rail transit section passenger flow short-time prediction method and system based on big data technology |
| CN110888732A (en) * | 2018-09-10 | 2020-03-17 | 中国移动通信集团黑龙江有限公司 | Resource allocation method, equipment, device and computer readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103065205A (en) * | 2012-12-26 | 2013-04-24 | 深圳先进技术研究院 | Three-dimensional intelligent transportation junction passenger flow time-space analysis and prediction system |
| CN105427002A (en) * | 2015-12-29 | 2016-03-23 | 上海仪电物联技术股份有限公司 | Logistic model-based passenger flow prediction method |
| KR101742042B1 (en) * | 2016-11-15 | 2017-05-31 | 한국과학기술정보연구원 | Apparatus and method for traffic flow prediction |
-
2017
- 2017-08-29 CN CN201710757135.6A patent/CN107688873A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103065205A (en) * | 2012-12-26 | 2013-04-24 | 深圳先进技术研究院 | Three-dimensional intelligent transportation junction passenger flow time-space analysis and prediction system |
| CN105427002A (en) * | 2015-12-29 | 2016-03-23 | 上海仪电物联技术股份有限公司 | Logistic model-based passenger flow prediction method |
| KR101742042B1 (en) * | 2016-11-15 | 2017-05-31 | 한국과학기술정보연구원 | Apparatus and method for traffic flow prediction |
Non-Patent Citations (1)
| Title |
|---|
| FLORIAN TOQU´ 等: "Forecasting Dynamic Public Transport Origin-Destination Matrices with Long-Short Term Memory Recurrent Neural Networks", 《2016 IEEE 19TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC)》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108647832A (en) * | 2018-05-18 | 2018-10-12 | 辽宁工业大学 | A kind of subway circulation interval time control algolithm based on neural network |
| CN108647832B (en) * | 2018-05-18 | 2020-08-04 | 辽宁工业大学 | Subway operation interval time control algorithm based on neural network |
| CN110782060A (en) * | 2018-07-31 | 2020-02-11 | 上海宝信软件股份有限公司 | Rail transit section passenger flow short-time prediction method and system based on big data technology |
| CN110888732A (en) * | 2018-09-10 | 2020-03-17 | 中国移动通信集团黑龙江有限公司 | Resource allocation method, equipment, device and computer readable storage medium |
| CN110888732B (en) * | 2018-09-10 | 2023-04-25 | 中国移动通信集团黑龙江有限公司 | Resource allocation method, equipment, device and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Environmentally sustainable toll design for congested road networks with uncertain demand | |
| Moretti et al. | Urban traffic flow forecasting through statistical and neural network bagging ensemble hybrid modeling | |
| Wen et al. | Polycentric urban structure and housing price in the transitional China: Evidence from Hangzhou | |
| Law | Back-propagation learning in improving the accuracy of neural network-based tourism demand forecasting | |
| Kofinas et al. | Urban water demand forecasting for the island of Skiathos | |
| Vázquez et al. | A comparison of deep learning methods for urban traffic forecasting using floating car data | |
| Algers et al. | Is it time to use activity-based urban transport models? A discussion of planning needs and modelling possibilities | |
| CN113762338B (en) | Traffic flow prediction method, equipment and medium based on multiple graph attention mechanism | |
| Agami et al. | A neural network based dynamic forecasting model for Trend Impact Analysis | |
| CN107688873A (en) | Metro passenger flow Forecasting Methodology based on big data analysis | |
| Molinero-Parejo et al. | Combining a land parcel cellular automata (LP-CA) model with participatory approaches in the simulation of disruptive future scenarios of urban land use change | |
| Durango-Cohen et al. | Maintenance optimization for transportation systems with demand responsiveness | |
| Gao et al. | An agent-based simulation system for evaluating gridding urban management strategies | |
| CN114492978A (en) | Time-space sequence prediction method and device based on multi-layer attention mechanism | |
| Zhao et al. | LandSys II: Agent-based land use–forecast model with artificial neural networks and multiagent model | |
| Jin et al. | A literature review on the space of flows | |
| Abaza | Simplified Markovian-based pavement management model for sustainable long-term rehabilitation planning | |
| Wu et al. | A BP Neural Network‐Based GIS‐Data‐Driven Automated Valuation Framework for Benchmark Land Price | |
| Ning et al. | Probabilistic short-term power load forecasting based on B-SCN | |
| Wang | A Hybrid Wavelet Transform Based Short‐Term Wind Speed Forecasting Approach | |
| CN116934380A (en) | E-commerce material supply and demand combined prediction method under abnormal event | |
| Lakshmanan et al. | Knowledge Economy in the Megalopolis: Interactions of innovations in transport, information, production and organizations | |
| Marković et al. | Planning dial-a-ride services: Statistical and meta-modeling approach | |
| Goumas et al. | Modeling and forecasting of tourist arrivals in crete using statistical models and models of computational intelligence: A comparative study | |
| Li et al. | Forecasting method for urban rail transit ridership at station level using back propagation neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180213 |
|
| RJ01 | Rejection of invention patent application after publication |