CN111144281A - Urban rail transit OD passenger flow estimation method based on machine learning - Google Patents
Urban rail transit OD passenger flow estimation method based on machine learning Download PDFInfo
- Publication number
- CN111144281A CN111144281A CN201911357247.8A CN201911357247A CN111144281A CN 111144281 A CN111144281 A CN 111144281A CN 201911357247 A CN201911357247 A CN 201911357247A CN 111144281 A CN111144281 A CN 111144281A
- Authority
- CN
- China
- Prior art keywords
- passenger flow
- data
- rail transit
- fcn
- data set
- 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 26
- 238000010801 machine learning Methods 0.000 title claims abstract description 16
- 239000011159 matrix material Substances 0.000 claims abstract description 26
- 230000009467 reduction Effects 0.000 claims abstract description 5
- 238000013528 artificial neural network Methods 0.000 claims description 27
- 238000012549 training Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 7
- 230000015654 memory Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 2
- 230000002123 temporal effect Effects 0.000 claims description 2
- 230000006872 improvement Effects 0.000 description 4
- 230000008520 organization Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 1
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- G06N3/045—Combinations of networks
-
- 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
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- General Business, Economics & Management (AREA)
- Biophysics (AREA)
- Tourism & Hospitality (AREA)
- Biomedical Technology (AREA)
- Marketing (AREA)
- Molecular Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Multimedia (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Elevator Control (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an urban rail transit OD passenger flow estimation method based on machine learning, which determines key factors and interference factors of OD line network passenger flow from two aspects of space distribution and time distribution, and further eliminates interference data in rail transit passenger flow data according to the two factors, so that OD passenger flow data can be more effectively predicted; furthermore, the invention constructs an OD matrix prediction model of the urban rail transit based on the FCN-LSTM structure, performs effective passenger flow prediction under the condition of ensuring no reduction of space dimension, and provides support for operation management and ticket clearing of the rail transit.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an OD passenger flow estimation method for urban rail transit based on machine learning.
Background
With the rapid increase of urban economy, the traffic volume is greatly increased, the urban rail transit network is increasingly perfected, and the phenomenon of passenger flow over-saturation often occurs, especially in the early-late peak period of a working day, so that huge potential safety hazards are brought. OD estimation is an important basis for operation management and control of a rail transit system, and whether the real-time estimation problem of a dynamic OD matrix can be effectively solved or not can directly influence the application of an upper management system. Therefore, how to accurately predict the OD passenger flow of the urban rail transit and make a scientific passenger transport plan and organization scheme according to the OD passenger flow, the OD passenger flow prediction method has important values for maintaining the operation safety of the rail transit, improving the operation efficiency and reducing the operation cost, and the accurate traffic demand prediction can provide a basis for analyzing the influence evaluation on the existing road network after the new line is accessed, further analyze the matching condition of the transport capacity and the transport capacity of the existing road network, find weak links in the aspects of equipment facility configuration of transfer stations, passenger transport organization, engineering construction and the like, and put forward the rectification suggestion in time.
The scale of the rail transit network and the number of OD pairs are very large, and the rail transit network often comprises tens of thousands of OD pairs, on one hand: the key for meeting the real-time estimation of the passenger flow demand is to ensure the solving efficiency of the model, and the practical timeliness demand is difficult to meet by using the existing methods such as a least square method, a Bayesian inference method, a Kalman filtering method and the like, on the other hand: there are many algorithm researches on machine learning at home and abroad, machine learning has relatively wide application in data mining, search engines, intelligent robots, processing of natural language, recognition of voice and handwriting, recognition of biological characteristics, medical diagnosis, stock market and the like, and has certain reference significance, but the researches on machine learning theory or machine learning algorithm and urban rail transit OD estimation are rare, and some methods are only estimated for a certain line of rail transit. Based on the current situation, the invention utilizes machine learning to estimate the OD passenger flow of the rail transit whole line network.
The passenger flow distribution model is used as an important step in traffic demand prediction and has important functions of starting and starting. The method can provide a data base for rail transit passenger flow distribution, and is a key link for determining whether traffic demand prediction is accurate or not. By combining the existing data, an accurate, practical and efficient urban rail transit passenger flow distribution prediction model is provided, and a solid foundation is provided for traffic demand prediction.
Disclosure of Invention
In order to solve the existing problems, the invention provides the urban rail transit OD passenger flow estimation method based on machine learning, and the method carries out whole-network OD passenger flow prediction from two aspects of space and time, overcomes the problems of insufficient whole-network OD passenger flow estimation efficiency and accuracy under the background of big data, and can provide a basis for operation management and ticket clearing of rail transit.
In order to achieve the purpose, the technical method adopted by the invention is as follows: the method for estimating the OD passenger flow of the urban rail transit based on machine learning comprises the following steps:
s1, determining influence factors of data to be predicted based on time and space characteristics of OD passenger flow of rail transit, wherein the influence factors include two major factors which play a key role and an interference role in a prediction result;
s2, original passenger flow data collected from an AFC system to which the predicted target data belongs are subjected to screening pretreatment according to two major influencing factors, and a passenger flow data set is established;
s3, dividing the data in the passenger flow data set into granularity according to a certain time interval, and converting the granularity into an OD matrix form to construct an OD passenger flow data set;
s4, designing an urban rail transit OD matrix prediction model based on an FCN-LSTM structure according to the data characteristics of the OD passenger flow data set and the time and space characteristics of the OD passenger flow;
s5, dividing the OD passenger flow data set into a training data set and a prediction data set according to a certain proportion, wherein the training data set is used for training a model, and the prediction data set is used for final prediction;
s6, inputting the data in the training data set into a full convolution neural network FCN, extracting all characteristic points of a full line network OD passenger flow matrix, and outputting full line network OD passenger flow data with the characteristic points;
s7, inputting the OD passenger flow data with the characteristic points of the full-line network, which are output in the step S6 of claim 1, into a long-short term memory neural network (LSTM) to complete the training of the urban rail transit OD matrix prediction model of the FCN-LSTM structure;
and S8, inputting the data in the prediction data set into the trained urban rail transit OD matrix prediction model with the FCN-LSTM structure to obtain a final prediction result.
As an improvement of the present invention, in step S2, the step of removing the interference data from the rail transit passenger flow data according to two major factors, namely, the key factor and the interference factor for determining the OD line network passenger flow from both the spatial distribution and the temporal distribution, and establishing a data set to be predicted includes: the passengers enter and exit from the same station, enter and exit from the station across days and unpaired OD passenger flow data caused by misoperation of the passengers in and out of the station.
As an improvement of the present invention, the specific method for designing the urban rail transit OD matrix prediction model based on the FCN-LSTM structure in step S4 includes:
constructing a prediction model of an FCN-LSTM structure, wherein an FCN neural network is good at processing images, an OD passenger flow matrix can be regarded as one image, and the FCN neural network can extract feature points at each position in the OD passenger flow matrix; while the LSTM neural network is characterized by having a forgetting gate, it is well suited for data prediction where it excels in processing data sets over time. Finally, the prediction model of the FCN-LSTM structure is constructed, and the advantages of the two neural networks are combined.
As an improvement of the present invention, in the step S6, the data in the training data set is input into the full convolution neural network FCN, all feature points of the full-line network OD passenger flow matrix are extracted, the full-line network OD passenger flow data with the feature points is output, the full-line network OD passenger flow data feature extraction is performed on the rail transit full-line network OD passenger flow matrix data processed according to the two major influencing factors by using the full convolution neural network FCN, the feature belongs to a spatial feature, and the output result and the input data belong to the same dimension, so that spatial dimension reduction is not generated, and spatial distribution of the OD passenger flow data is satisfied.
As an improvement of the present invention, in the process of inputting the OD passenger flow data with the full-line network feature points into the long-short term memory neural network LSTM in step S7, the LSTM neural network learns along with the time distribution, and the output result belongs to the same dimension as the input data and includes the time feature, so as to satisfy the time distribution of the OD passenger flow data.
Compared with the prior art, the invention provides the method for estimating the OD passenger flow of the urban rail transit based on the machine learning, which has the beneficial effects that: determining key factors and interference factors of OD line network passenger flow from two aspects of spatial distribution and time distribution, and further removing interference data in rail transit passenger flow data according to the two factors, so that OD passenger flow data can be more effectively predicted; furthermore, the invention constructs an OD matrix prediction model of the urban rail transit based on the FCN-LSTM structure, performs effective passenger flow prediction under the condition of ensuring no reduction of space dimension, and provides support for operation management and ticket clearing of the rail transit.
Drawings
FIG. 1 is a flow chart of the operation of the present invention;
FIG. 2 is a diagram of a full convolution neural network.
Detailed Description
The invention is described in further detail below with reference to the following detailed description and accompanying drawings:
the invention provides an urban rail transit OD passenger flow estimation method based on machine learning, which comprises the following steps:
step1, analyzing the space and time distribution characteristics of rail transit OD passenger flows
Because the rail transit has unique scale and passenger flow volume, the time and space characteristics of the rail transit are uniquely analyzed, if the rail transit has n stations, each determined time period T corresponds to an OD passenger flow matrix with the size of n multiplied by n, and the OD passenger flow number of any two stations in the T time can be known by the matrix;
step2, eliminating interference data and establishing a passenger flow data set
And carrying out data elimination and other processing by utilizing the key factors and the interference factors of the target, such as: the method comprises the steps of eliminating OD passenger flow data which are caused by misoperation of passengers on entering and leaving stations and are in and out of the same station, entering and leaving stations across days and unpaired OD, eliminating interference data, and then performing time sequencing by taking the entering time as an index to establish a passenger flow data set;
step3, further processing the data and establishing an OD passenger flow data set
Dividing the passenger flow data in the passenger flow data set processed in Step2 according to a specific time interval T, converting the passenger flow data into an OD matrix form, establishing an OD passenger flow data set, dividing the data in the data set into a training data set and a prediction data set according to a certain proportion, for example, after the passenger flow data in six months is divided according to the proportion of 5:1, the passenger flow data in the first five months is taken as the training data, and the data in the remaining one month is taken as the prediction data;
step4, constructing a track traffic OD passenger flow prediction model based on a full convolution neural network FCN
The training data of the rail transit whole line network OD passenger flow data set processed according to the two major influencing factors are input into a full convolution neural network FCN, the purpose is to extract the characteristics of the whole line network OD passenger flow data, the characteristics belong to spatial characteristics, the output result and the input data belong to the same dimension, space dimensionality reduction cannot be generated, and the spatial distribution of the OD passenger flow data is met. Each layer of data in the full convolution network is a three-dimensional array of n multiplied by d, wherein n is the dimension of the array, and d is the number of channels of the convolution network. A full convolution neural network is shown in figure 2.
Step5, constructing a track traffic OD passenger flow prediction model based on long-term and short-term memory neural network LSTM
The data with the spatial characteristics output by the full convolution neural network FCN is input into the LSTM, the LSTM neural network can learn along with the time distribution, the output result and the input data belong to the same dimension, and the time characteristics are included, so that the time distribution of OD passenger flow data is met.
Step6, constructing a track traffic OD passenger flow prediction model based on FCN-LSTM
After a rail transit OD passenger flow prediction model is completely established according to the selected rail transit network scale and the corresponding passenger flow within a certain time, the passenger flow data of a prediction data set in Step3 is input for final prediction;
step7, model index verification
And comparing the final predicted data with the actual passenger flow data by using the MAPE index, repeating Step4-Step4 if the final predicted data does not reach the actual passenger flow data, and reconstructing the neural network until the predicted result reaches the standard.
The foregoing is illustrative of the present invention and is not to be construed as limiting thereof, but rather as embodying the invention in any other form, which is equivalent or modified, within the scope of the invention as hereinafter claimed.
Claims (5)
1. The method for estimating the OD passenger flow of the urban rail transit based on machine learning is characterized by comprising the following steps of:
s1, determining influence factors of data to be predicted based on time and space characteristics of OD passenger flow of rail transit, wherein the influence factors include two major factors which play a key role and an interference role in a prediction result;
s2, original passenger flow data collected from an AFC system to which the predicted target data belongs are subjected to screening pretreatment according to two major influence factors which play a key role and an interference role in a prediction result, and a passenger flow data set is established;
s3, dividing the data in the passenger flow data set established in the step S2 into granularity according to a certain time interval, and converting the granularity into an OD matrix form to construct an OD passenger flow data set;
s4, designing an urban rail transit OD matrix prediction model based on an FCN-LSTM structure according to the data characteristics of the OD passenger flow data set and the time and space characteristics of the OD passenger flow;
s5, dividing the OD passenger flow data set into a training data set and a prediction data set according to a certain proportion, wherein the training data set is used for training a model, and the prediction data set is used for final prediction;
s6, inputting the data in the training data set into a full convolution neural network FCN, extracting all characteristic points of a full line network OD passenger flow matrix, and outputting full line network OD passenger flow data with the characteristic points;
s7, inputting the OD passenger flow data with the full-line network characteristic points output in the step S6 into a long-short term memory neural network LSTM to complete the training of the urban rail transit OD matrix prediction model with the FCN-LSTM structure;
and S8, inputting the data in the prediction data set into the trained urban rail transit OD matrix prediction model with the FCN-LSTM structure to obtain a final prediction result.
2. The method for estimating OD passenger flow in urban rail transit based on machine learning according to claim 1, wherein in step S2, the step of removing the interference data in the rail transit passenger flow data according to two major factors, namely, the key factor and the interference factor for determining OD net passenger flow from both spatial distribution and temporal distribution, and creating the data set to be predicted includes: the passengers enter and exit from the same station, enter and exit from the station across days and unpaired OD passenger flow data caused by misoperation of the passengers in and out of the station.
3. The method for estimating OD passenger flow of urban rail transit based on machine learning according to claim 1, wherein the specific method for designing the OD matrix prediction model of urban rail transit based on FCN-LSTM structure in step S4 includes:
constructing a prediction model of an FCN-LSTM structure, wherein an FCN neural network is good at processing images, an OD passenger flow matrix is regarded as one image, and the FCN neural network can extract feature points at each position in the OD passenger flow matrix; while the LSTM neural network is characterized by having a forgetting gate, it is well suited for data prediction where it excels in processing data sets over time.
4. The method as claimed in claim 1, wherein the step S6 includes inputting data in the training data set into a full convolution neural network FCN, extracting all feature points of a full net OD passenger flow matrix, and outputting full net OD passenger flow data with the feature points, and extracting features of the full net OD passenger flow data by using the full convolution neural network FCN according to the track traffic full net OD passenger flow matrix data processed according to the two major influencing factors, where the features belong to spatial features, and the output result and the input data belong to the same dimension, which does not produce spatial dimension reduction, and satisfy spatial distribution of the OD passenger flow data.
5. The method as claimed in claim 1, wherein the OD traffic data with the full-line network feature points in step S7 is input into the LSTM neural network, the LSTM neural network learns over time as the time distribution progresses, and the output and the input data belong to the same dimension and include time features to satisfy the time distribution of the OD traffic data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911357247.8A CN111144281B (en) | 2019-12-25 | 2019-12-25 | Urban rail transit OD passenger flow estimation method based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911357247.8A CN111144281B (en) | 2019-12-25 | 2019-12-25 | Urban rail transit OD passenger flow estimation method based on machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111144281A true CN111144281A (en) | 2020-05-12 |
| CN111144281B CN111144281B (en) | 2022-11-18 |
Family
ID=70519971
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911357247.8A Active CN111144281B (en) | 2019-12-25 | 2019-12-25 | Urban rail transit OD passenger flow estimation method based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111144281B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111860951A (en) * | 2020-06-12 | 2020-10-30 | 北京工业大学 | Rail transit passenger flow prediction method based on dynamic hypergraph convolutional network |
| CN112288272A (en) * | 2020-10-29 | 2021-01-29 | 北京交通大学 | Subway passenger flow regulation and control plan compilation method based on demand evolution and flow propagation |
| CN113762590A (en) * | 2021-07-20 | 2021-12-07 | 北京交通大学 | Urban rail transit holiday passenger flow prediction system |
| CN114912233A (en) * | 2022-04-19 | 2022-08-16 | 华北科技学院(中国煤矿安全技术培训中心) | Method and system for determining and cooperatively managing and controlling influence range of road network transportation capacity reduction |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106485359A (en) * | 2016-10-13 | 2017-03-08 | 东南大学 | A kind of urban track traffic section passenger flow estimation method based on train schedule |
| CN106875314A (en) * | 2017-01-31 | 2017-06-20 | 东南大学 | A kind of Urban Rail Transit passenger flow OD method for dynamic estimation |
| CN109583656A (en) * | 2018-12-06 | 2019-04-05 | 重庆邮电大学 | Passenger Flow in Urban Rail Transit prediction technique based on A-LSTM |
-
2019
- 2019-12-25 CN CN201911357247.8A patent/CN111144281B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106485359A (en) * | 2016-10-13 | 2017-03-08 | 东南大学 | A kind of urban track traffic section passenger flow estimation method based on train schedule |
| CN106875314A (en) * | 2017-01-31 | 2017-06-20 | 东南大学 | A kind of Urban Rail Transit passenger flow OD method for dynamic estimation |
| CN109583656A (en) * | 2018-12-06 | 2019-04-05 | 重庆邮电大学 | Passenger Flow in Urban Rail Transit prediction technique based on A-LSTM |
Non-Patent Citations (1)
| Title |
|---|
| 刘洋等: "城市轨道交通线网客流动态起讫点估计框架及关键技术", 《城市轨道交通研究》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111860951A (en) * | 2020-06-12 | 2020-10-30 | 北京工业大学 | Rail transit passenger flow prediction method based on dynamic hypergraph convolutional network |
| CN111860951B (en) * | 2020-06-12 | 2023-09-26 | 北京工业大学 | Rail transit passenger flow prediction method based on dynamic hypergraph convolutional network |
| CN112288272A (en) * | 2020-10-29 | 2021-01-29 | 北京交通大学 | Subway passenger flow regulation and control plan compilation method based on demand evolution and flow propagation |
| CN113762590A (en) * | 2021-07-20 | 2021-12-07 | 北京交通大学 | Urban rail transit holiday passenger flow prediction system |
| CN113762590B (en) * | 2021-07-20 | 2023-08-01 | 北京交通大学 | Urban rail transit holiday passenger flow prediction system |
| CN114912233A (en) * | 2022-04-19 | 2022-08-16 | 华北科技学院(中国煤矿安全技术培训中心) | Method and system for determining and cooperatively managing and controlling influence range of road network transportation capacity reduction |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111144281B (en) | 2022-11-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111144281B (en) | Urban rail transit OD passenger flow estimation method based on machine learning | |
| CN110070713B (en) | Traffic flow prediction method based on bidirectional nested LSTM neural network | |
| Bi et al. | Daily tourism volume forecasting for tourist attractions | |
| Zhang et al. | Air quality index forecast in Beijing based on CNN-LSTM multi-model | |
| CN110570651A (en) | Road network traffic situation prediction method and system based on deep learning | |
| CN114330671A (en) | Traffic flow prediction method based on Transformer space-time diagram convolution network | |
| CN111506835B (en) | Data feature extraction method fusing user time features and individual features | |
| CN112053560B (en) | Short-time traffic flow prediction method, system and storage medium based on neural network | |
| CN110836675B (en) | Decision tree-based automatic driving search decision method | |
| CN115204478A (en) | Public traffic flow prediction method combining urban interest points and space-time causal relationship | |
| Lin et al. | Short-term metro passenger flow prediction based on random forest and LSTM | |
| CN114492978A (en) | Time-space sequence prediction method and device based on multi-layer attention mechanism | |
| CN112580951A (en) | Urban ground bus operation monitoring key index screening method based on passenger trip | |
| CN112419711A (en) | Closed parking lot parking demand prediction method based on improved GMDH algorithm | |
| CN107368895A (en) | A kind of combination machine learning and the action knowledge extraction method planned automatically | |
| CN111899511A (en) | Bus arrival time prediction method for AVL data of collinear line | |
| CN113240219A (en) | Land utilization simulation and prediction method | |
| CN113221443A (en) | Land use modeling and simulation method integrating SDGs and beauty indexes | |
| Wang et al. | Short-term passenger flow prediction for urban rail stations using learning network based on optimal passenger flow information input algorithm | |
| CN113159371A (en) | Unknown target feature modeling and demand prediction method based on cross-modal data fusion | |
| CN116862315A (en) | Low-efficiency industrial land performance scoring method, device, equipment and storage medium | |
| Zaman et al. | Assessing the suitability of different machine learning approaches for smart traffic mobility | |
| CN112634620B (en) | Road network dynamic traffic distribution method based on Encoder-Decoder deep neural network | |
| CN109447498B (en) | Rail transit system cost association multi-domain influence element big data driving analysis method | |
| Chunmei et al. | The research of method of short-term traffic flow forecast based on ga-bp neural network and chaos theory |
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 |