CN108491958A - A kind of bus passenger flow string invariant prediction technique in short-term - Google Patents
A kind of bus passenger flow string invariant prediction technique in short-term Download PDFInfo
- Publication number
- CN108491958A CN108491958A CN201810139745.4A CN201810139745A CN108491958A CN 108491958 A CN108491958 A CN 108491958A CN 201810139745 A CN201810139745 A CN 201810139745A CN 108491958 A CN108491958 A CN 108491958A
- Authority
- CN
- China
- Prior art keywords
- passenger flow
- parameter
- pfpm
- string
- prediction
- 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
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 14
- 230000002068 genetic effect Effects 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims abstract description 9
- 230000006870 function Effects 0.000 claims description 21
- 238000005457 optimization Methods 0.000 claims description 9
- 235000014676 Phragmites communis Nutrition 0.000 claims description 4
- 230000004075 alteration Effects 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 4
- 238000010353 genetic engineering Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 238000005314 correlation function Methods 0.000 claims description 2
- 238000009795 derivation Methods 0.000 claims description 2
- 238000013461 design Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 claims description 2
- 230000005481 string theory Effects 0.000 claims description 2
- 230000009466 transformation Effects 0.000 claims description 2
- 230000002035 prolonged effect Effects 0.000 claims 1
- 238000004364 calculation method Methods 0.000 abstract description 2
- 238000012545 processing Methods 0.000 abstract description 2
- 238000004088 simulation Methods 0.000 abstract description 2
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000011144 upstream manufacturing Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000002123 temporal effect 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
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Biophysics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Marketing (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Quality & Reliability (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
A kind of string invariant prediction technique of bus passenger flow in short-term, includes the following steps：The string invariant of public transport time series simulation in short-term is converted first, string invariant Passenger flow forecast model SI PFPM are derived by the invariance in short-term of bus passenger flow time series string simulated object, then assignment is optimized to each parameter in SI PFPM using genetic algorithm, finally following bus passenger flow sequence is predicted using prediction model.The method of the present invention does not need mass data sample, does not need large-scale training, and calculation amount is small, and method is simple and practicable.Real data can be directed to and carry out effective data processing, data can be utilized to realize calculating, training, prediction, assessment, a kind of accuracy height, the strong bus passenger flow prediction model in short-term of generalization ability are provided.
Description
Technical field
The invention belongs to intelligent transportation, computer and physics interleaving techniques field, it is related to a kind of bus passenger flow in short-term
String invariant prediction technique.
Background technology
With the fast development of artificial intelligence, intelligent algorithm plays more and more important in Passenger flow forecast model research
Effect can predict bus passenger flow there are many intelligent Forecasting.Liu Lijuan etc. propose a kind of based on depth
The bus rapid transit station of neural network (deep neural network, abbreviation DDN) passenger flow forecasting in short-term, input feature vector
Including certain day in one week, one day a certain hour, whether the temporal characteristics such as festivals or holidays and go out the scenes such as inbound, means of payment spy
Sign and history are averaged the passenger flows features such as passenger flow, real-time passenger flow, and these feature combined trainings are gone out to different stacking own codings
Device (stacked autoencoders, abbreviation SAE) further initializes DNN, is finally carried out to mixed model (SAE-DNN)
Instance analysis, this method provide accurate Passenger flow forecast model for the passenger flow at the 4 bus rapid transit stations in Xiamen, but for
For non-rapid bus stop, full deep learning feature can not be obtained, lacking for data is difficult to predict bus stop passenger flow.
Li Wenquan etc. establish bus passenger flow prediction model in short-term for Changchun circuit using least square method supporting vector machine, examine
Consider upstream and downstream website passenger flow, history same period passenger flow, influence of the history passenger flow three to model prediction performance, example analysis results table
Bright, after being equipped with upstream and downstream website, history same period passenger flow in multi input variable, prediction model estimated performance improves, but insufficient
Place is that there are many influence factor of passenger flow in short-term of bus station and are difficult to analyze, and the method but only considered influence passenger flow in short-term
Small part factor.Tian Qingfei etc. use fractal theory to bus passenger flow amount is predicted in short-term, pass through correlation dimension
Settling time sequential forecasting models analyze station passenger flow Time Distribution using Phase-space Reconstruction, finally with
For the circuit station of Changchun 255, time prediction has been carried out to the station volume of the flow of passengers using the time series predicting model.The model
Error it is small, it is contemplated that the trend of passenger flow time series data itself, but to influence the volume of the flow of passengers external factor measurement show slightly rough,
Only inferred from point variation of dimension.
Invention content
The invention solves the above problem of the prior art, numerous method precision of predictions it is to be improved, do not differentiate between research
It passenger flow of getting on the bus and gets off under the incomplete background of passenger flow, hands-on data information, it is short to propose that a kind of accurate method is realized
When public transport get on or off the bus the prediction of passenger flow.
String invariant prediction technique is a kind of Forecast of Nonlinear Time Series method of simulation beam string structure, need not be as artificial
Neural network will equally train a large amount of free parameter, therefore the training time is short, and required data volume is small, realize convenient and simple.It is short
When bus passenger flow prediction be public transport Real-Time Scheduling basis, accurately grasp passenger flow changing rule in the case of, ability
Accomplish scientifically and rationally to formulate operation planning, allotment people, carfare source.The randomness of passenger flow estimation and time variation make in short-term in short-term
There are significant differences with medium-term and long-term passenger flow estimation for passenger flow estimation.The observing result of the latter is big, to lose the integrality of information as generation
Valence slackens randomness, and the Correlative Influence Factors of short-term prediction are more difficult to capture and analyze so that public transport passenger flow estimation research in short-term is more
Add difficulty.And public bus network website get on or off the bus number macroscopically with Levels of Social Economic Development, bus trip proportion, bus station
The factors such as point land character, population distribution, weather are all related, these factors are not easy to quantify and update difficult, original passenger flow training
Data are difficult to reach the requirement of the prediction techniques such as neural network, support vector machines.But from microcosmic, bus passenger flow in short-term
It is apparent that data change over time rule, change in a short time it is relatively steady, using string invariant Passenger flow forecast model (string
Invariants passenger flow prediction model, abbreviation SI-PFPM) predict that bus passenger flow meets short in short-term
When bus passenger flow time series data feature.
A kind of bus passenger flow prediction technique in short-term of the present invention, steps are as follows：
(1) according to the prediction principle of bus passenger flow data characteristic and string invariant model, design SI-PFPM is to public in short-term
Passenger flow is handed over to be predicted, if bus passenger flow time series is T (k), k=1,2,3 ..., wherein k is the index of time series, T
(k) it is the corresponding passenger flow magnitudes of index k, volume of the flow of passengers unit is number, and this time sequence is done following conversion：
In formula：T (t) indicates that corresponding passenger flow magnitude, that is, current index value is the passenger flow magnitude corresponding to t, T as k=t
(t+h) indicate that corresponding passenger flow magnitude indicates to lag the passenger flow magnitude of h sequence apart from current index value t as k=t+h,
Formula (1) indicates the change rate of the volume of the flow of passengers between two sequences.
(2) it is based on string theory, single-ended point is defined and opens string model:
In formula：Subscript (1) refers to that endpoint quantity is 1, lsRefer to chord length, variable h is indicated by chord length lsThe additional dimension of limitation
Degree extends, this model should meet reed profit Cray boundary condition：
T(1)(t, h)=0 (3)
(3) it in order to embody influence of the rare events to bus passenger flow, introduces power rate Q model and deformation process is carried out to master mould：
In formula：Q is power rate parameter, and the definition of single-ended string reflects T-sequence in lsOn linear trend, introduce both-end point
Open string T(2)(t, h) indicates T-sequence nonlinear trend：
This model should meet reed profit Cray boundary condition：
T(2)(t, 0)=T(2)(t,ls)=0 (6)
(4) the string invariant defined in SI-PFPM is the immovable characteristic in string transformation, and it is system to define constant duration set
A kind of form of correlation function during meter is learned：
In formula：K=ls-lpr, lprFor prediction step, ls>lpr, η1∈ (- 1,1), η2∈ (- 1,1) is homotopy parameter, ls,
lpr, Q, η1, η2This five parameters need to optimize assignment with the difference of prediction object, and weight W (h) is piecewise function：
Wherein：
(5) string object is simulated in passenger flow time series data and find invariant, and the stage after being predicted using invariant
Passenger flow time sequential value, anticipation function derive following invariant by formula (7)：
R(t0, k) and=R (t0+lpr, k) and k=ls-lpr (10)
In order to concisely indicate derivation result, auxiliary variable A is introduced1(k, t), A2(k, t), A3(k, t), A4(k,
T), A5(k,t)：
Derive predicted value：
In formula：lprIndicate prediction step, t ' ,=t0+lpr-ls, it is obtained from this formula：T ' ＜ t0, can be with according to formula (12)
Pass through the passenger flow data sequence before T (t ') and the l after optimal design-asides, lpr, Q, η1, η2This five parameter prediction t0+lprRope
Draw corresponding passenger flow value；Time interior prediction short at time series interval SI-PFPM is better, thus to prediction step into
Row parameter setting carries out single step loop iteration prediction, even l to passenger flowpr=1；It finally needs to l in SI-PFPMs,Q,η1,η24
A parameter is trained, and is sought and is taken best parameter group；
(6) .SI-PFPM parameter optimizations：
It needs to be determined that the coding mode of parameter, initial population number, crossing-over rate, variation in genetic algorithm optimization parametric procedure
Rate constructs fitness function, setting end condition according to SI-PFPM Parametric optimization problems, is used in SI-PFPM parameter optimizations
Steps are as follows for the specific implementation of genetic algorithm：
1) SI-PFPM parameter sets and parameter area are set, one group of SI-PFPM parameter is randomly generated, using binary coding
Mode encodes SI-PFPM parameters, determines initial population size, aberration rate, crossing-over rate；
2) determine that fitness function is average relative error function：
In formula：N is the quantity of training set volume of the flow of passengers time series；AtThe practical volume of the flow of passengers；FtFor passenger flow forecast amount, to target
Function sets desired value；
3) fitness function value is calculated, end condition is set：Fitness function value reaches desired value or iterations reach
To maximum value；If reaching end condition, the SI-PFPM parameter values exported at this time are combined as optimal parameter；If not reaching eventually
Only condition is intersected using wheel disc algorithm eliminative mechanism, and the genetic manipulations such as variation handle Current generation group, under generation
Generation group；
4) circulate operation step (3), until reaching desired value or iterations reach maximum value.
It is an advantage of the invention that：Nonlinear Time Series can be predicted, a large amount of free parameter need not be trained,
Only 4 parameters need to be set, calculation amount is small, and method is simple and practicable, can be directed to real data and carry out effective data processing, pass through
The precision of prediction higher of SI-PFPM after genetic algorithm optimization, generalization ability are stronger.
Description of the drawings
Fig. 1 is the constant prediction model parameters optimized flow chart of the string of bus passenger flow in short-term of the present invention:Start directly to write setting
Genetic algorithm parameter value.
Specific implementation mode
Below in conjunction with attached drawing and real data, the specific implementation mode that further illustrates the present invention.
This example carries out exemplary application with the passenger flow investigation of one, China megalopolis public bus network and operation data.Under
Face is passengers quantity statistical form of getting on the bus on a bus typical working day.
(1) it is training set by first 16 of data extraction in table, l is trained using genetic algorithms,Q,η1,η2This four parameters
Value, genetic algorithm flow chart attached drawing 1.It is followed the steps below in conjunction with flow chart：
1) SI-PFPM parameter sets and parameter area are set, one group of SI-PFPM parameter is randomly generated, using binary coding
Mode encodes SI-PFPM parameters, determines initial population size, aberration rate, crossing-over rate.
2) determine that fitness function is average relative error function：
In formula：N is the quantity of training set volume of the flow of passengers time series；AtThe practical volume of the flow of passengers；FtFor passenger flow forecast amount, to target
Function sets desired value.
3) fitness function value is calculated, end condition is set：Fitness function value reaches desired value or iterations reach
To maximum value.If reaching end condition, the SI-PFPM parameter values exported at this time are combined as optimal parameter；If not reaching eventually
Only condition is intersected using wheel disc algorithm eliminative mechanism, and the genetic manipulations such as variation handle Current generation group, under generation
Generation group.
4) circulate operation step (3), until reaching desired value or iterations reach maximum value.
The parameter l trained by genetic algorithms=4, Q=1, η1=0.6986, η2=-0.1841.
(2) the parameter l come will be traineds=4, Q=1, η1=0.6986, η2=-0.1841 and table in data substitute under
Formula：
In formula：lprIndicate prediction step, t ' ,=t0+lpr-ls, auxiliary variable A1(k, t), A2(k, t), A3(k, t), A4
(k, t), A5(k,t)：
T (17)=16.3092 is calculated, it is close with actual value 17.
Content described in this specification embodiment is only enumerating to the way of realization of inventive concept, protection of the invention
Range is not construed as being only limitted to the concrete form that embodiment is stated, protection scope of the present invention is also and in art technology
Personnel according to present inventive concept it is conceivable that equivalent technologies mean.
Claims (1)
1. a kind of string invariant prediction technique of bus passenger flow in short-term, includes the following steps：
(1) according to the prediction principle of bus passenger flow data characteristic and string invariant model, design SI-PFPM is to the visitor of public transport in short-term
Stream is predicted, if bus passenger flow time series is T (k), k=1,2,3 ..., and wherein k is the index of time series, and T (k) is
The corresponding passenger flow magnitudes of k are indexed, volume of the flow of passengers unit is number, and this time sequence is done following conversion：
In formula：T (t) indicates that corresponding passenger flow magnitude, that is, current index value is the passenger flow magnitude corresponding to t, T (t+h) as k=t
Indicate that corresponding passenger flow magnitude indicates to lag the passenger flow magnitude of h sequence, formula (1) apart from current index value t as k=t+h
The change rate of the volume of the flow of passengers between two sequences of expression；
(2) it is based on string theory, single-ended point is defined and opens string model:
In formula：Subscript (1) refers to that endpoint quantity is 1, lsRefer to chord length, variable h is indicated by chord length lsThe extra dimension of limitation is prolonged
It stretches, this model should meet reed profit Cray boundary condition：
T(1)(t, h)=0 (3)
(3) it in order to embody influence of the rare events to bus passenger flow, introduces power rate Q model and deformation process is carried out to master mould：
In formula：Q is power rate parameter, and the definition of single-ended string reflects T-sequence in lsOn linear trend, introduce both-end point open string T(2)(t, h) indicates T-sequence nonlinear trend：
This model should meet reed profit Cray boundary condition：
T(2)(t, 0)=T(2)(t,ls)=0 (6)
(4) the string invariant defined in SI-PFPM is the immovable characteristic in string transformation, and it is statistics to define constant duration set
A kind of form of middle correlation function：
In formula：K=ls-lpr, lprFor prediction step, ls>lpr, η1∈ (- 1,1), η2∈ (- 1,1) is homotopy parameter, ls, lpr, Q,
η1, η2This five parameters need to optimize assignment with the difference of prediction object, and weight W (h) is piecewise function：
Wherein：
(5) string object is simulated in passenger flow time series data and find invariant, and stage passenger flow after being predicted using invariant
Time sequential value, anticipation function derive following invariant by formula (7)：
R(t0, k) and=R (t0+lpr, k) and k=ls-lpr (10)
In order to concisely indicate derivation result, auxiliary variable A is introduced1(k, t), A2(k, t), A3(k, t), A4(k, t), A5
(k,t)：
Derive predicted value：
In formula：lprIndicate prediction step, t ' ,=t0+lpr-ls, it is obtained from this formula：T ' ＜ t0, T can be passed through according to formula (12)
The l after passenger flow data sequence and optimal design-aside before (t ')s, lpr, Q, η1, η2This five parameter prediction t0+lprIndex institute is right
The passenger flow value answered；Time interior prediction short at time series interval SI-PFPM is better, therefore carries out parameter to prediction step
Setting carries out single step loop iteration prediction, even l to passenger flowpr=1；It finally needs to l in SI-PFPMs,Q,η1,η24 parameters
It is trained, seeks and take best parameter group；
(6) .SI-PFPM parameter optimizations：
In genetic algorithm optimization parametric procedure it needs to be determined that the coding mode of parameter, initial population number, crossing-over rate, aberration rate,
Fitness function, setting end condition are constructed according to SI-PFPM Parametric optimization problems, something lost is used in SI-PFPM parameter optimizations
Steps are as follows for the specific implementation of propagation algorithm：
1) SI-PFPM parameter sets and parameter area are set, one group of SI-PFPM parameter is randomly generated, using binary coding mode
SI-PFPM parameters are encoded, determine initial population size, aberration rate, crossing-over rate；
2) determine that fitness function is average relative error function：
In formula：N is the quantity of training set volume of the flow of passengers time series；AtThe practical volume of the flow of passengers；FtFor passenger flow forecast amount, to object function
Set desired value；
3) fitness function value is calculated, end condition is set：Fitness function value reaches desired value or iterations reach most
Big value；If reaching end condition, the SI-PFPM parameter values exported at this time are combined as optimal parameter；If not reaching termination item
Part is intersected using wheel disc algorithm eliminative mechanism, and the genetic manipulations such as variation handle Current generation group, is generated next-generation
Group；
4) circulate operation step (3), until reaching desired value or iterations reach maximum value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810139745.4A CN108491958B (en) | 2018-02-11 | 2018-02-11 | Short-time bus passenger flow chord invariant prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810139745.4A CN108491958B (en) | 2018-02-11 | 2018-02-11 | Short-time bus passenger flow chord invariant prediction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108491958A true CN108491958A (en) | 2018-09-04 |
| CN108491958B CN108491958B (en) | 2021-05-07 |
Family
ID=63340510
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810139745.4A Active CN108491958B (en) | 2018-02-11 | 2018-02-11 | Short-time bus passenger flow chord invariant prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108491958B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110211379A (en) * | 2019-05-27 | 2019-09-06 | 南京航空航天大学 | A kind of public transport method for optimizing scheduling based on machine learning |
| CN111723871A (en) * | 2020-07-09 | 2020-09-29 | 广州市公共交通数据管理中心 | Estimation method for real-time carriage full load rate of bus |
| CN112215409A (en) * | 2020-09-24 | 2021-01-12 | 交控科技股份有限公司 | Rail transit station passenger flow prediction method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5148416B2 (en) * | 2008-09-03 | 2013-02-20 | 公益財団法人鉄道総合技術研究所 | Passenger flow prediction system |
| CN104298881A (en) * | 2014-10-15 | 2015-01-21 | 南通大学 | Bayesian network model based public transit environment dynamic change forecasting method |
| CN104517159A (en) * | 2014-12-18 | 2015-04-15 | 上海交通大学 | Method for predicting short-time passenger flow of bus |
| CN104573849A (en) * | 2014-12-12 | 2015-04-29 | 安徽富煌和利时科技股份有限公司 | Bus dispatch optimization method for predicting passenger flow based on ARIMA model |
| CN107103394A (en) * | 2017-05-27 | 2017-08-29 | 重庆大学 | A kind of real-time passenger flow forecasting of track traffic based on neutral net |
-
2018
- 2018-02-11 CN CN201810139745.4A patent/CN108491958B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5148416B2 (en) * | 2008-09-03 | 2013-02-20 | 公益財団法人鉄道総合技術研究所 | Passenger flow prediction system |
| CN104298881A (en) * | 2014-10-15 | 2015-01-21 | 南通大学 | Bayesian network model based public transit environment dynamic change forecasting method |
| CN104573849A (en) * | 2014-12-12 | 2015-04-29 | 安徽富煌和利时科技股份有限公司 | Bus dispatch optimization method for predicting passenger flow based on ARIMA model |
| CN104517159A (en) * | 2014-12-18 | 2015-04-15 | 上海交通大学 | Method for predicting short-time passenger flow of bus |
| CN107103394A (en) * | 2017-05-27 | 2017-08-29 | 重庆大学 | A kind of real-time passenger flow forecasting of track traffic based on neutral net |
Non-Patent Citations (2)
| Title |
|---|
| NATASA GLISOVIC.: "A hybrid model for forecasting the volume of passenger", 《OPERATIONAL RESEARCH》 * |
| 董升伟: "基于改进BP神经网络的轨道交通短时客流预测方法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110211379A (en) * | 2019-05-27 | 2019-09-06 | 南京航空航天大学 | A kind of public transport method for optimizing scheduling based on machine learning |
| CN111723871A (en) * | 2020-07-09 | 2020-09-29 | 广州市公共交通数据管理中心 | Estimation method for real-time carriage full load rate of bus |
| CN112215409A (en) * | 2020-09-24 | 2021-01-12 | 交控科技股份有限公司 | Rail transit station passenger flow prediction method and system |
| CN112215409B (en) * | 2020-09-24 | 2024-01-30 | 交控科技股份有限公司 | Rail transit station passenger flow prediction method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108491958B (en) | 2021-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111210633B (en) | Short-term traffic flow prediction method based on deep learning | |
| Li et al. | Hydraulic turbine governing system identification using T–S fuzzy model optimized by chaotic gravitational search algorithm | |
| CN104331635B (en) | The method of power optical fiber Communication ray power prediction | |
| CN106951919A (en) | A kind of flow monitoring implementation method based on confrontation generation network | |
| CN108694484A (en) | A kind of photovoltaic power generation power prediction method | |
| CN107909206A (en) | A kind of PM2.5 Forecasting Methodologies based on deep structure Recognition with Recurrent Neural Network | |
| CN103488869A (en) | Wind power generation short-term load forecast method of least squares support vector machine | |
| CN109359815A (en) | Based on the smart grid deep learning training sample generation method for generating confrontation network | |
| CN113344288B (en) | Cascade hydropower station group water level prediction method and device and computer readable storage medium | |
| CN105096614A (en) | Newly established crossing traffic flow prediction method based on generating type deep belief network | |
| CN108491958A (en) | A kind of bus passenger flow string invariant prediction technique in short-term | |
| CN107133695A (en) | A kind of wind power forecasting method and system | |
| CN113554466B (en) | Short-term electricity consumption prediction model construction method, prediction method and device | |
| CN103268519A (en) | Electric power system short-term load forecast method and device based on improved Lyapunov exponent | |
| CN109086926B (en) | Short-time rail transit passenger flow prediction method based on combined neural network structure | |
| CN105160204A (en) | Carbon emission price combination prediction method | |
| CN109754122A (en) | A kind of Numerical Predicting Method of the BP neural network based on random forest feature extraction | |
| Li et al. | A two-tier wind power time series model considering day-to-day weather transition and intraday wind power fluctuations | |
| CN107463879A (en) | Human bodys' response method based on deep learning | |
| CN113156376A (en) | Radar radiation source signal identification method based on SACNN | |
| CN106570594A (en) | Similar day photovoltaic power generation short period prediction method based on TMBP | |
| CN110443422B (en) | OD attraction degree-based urban rail transit OD passenger flow prediction method | |
| CN106782577A (en) | A kind of voice signal coding and decoding methods based on Chaotic time series forecasting model | |
| CN113595798A (en) | Network flow prediction method and system for improving lightning connection process optimization algorithm | |
| CN112836876A (en) | Power distribution network line load prediction method based on deep learning |
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 |