CN106447137A - Traffic passenger flow forecasting method based on information fusion and Markov model - Google Patents
Traffic passenger flow forecasting method based on information fusion and Markov model Download PDFInfo
- Publication number
- CN106447137A CN106447137A CN201611018804.XA CN201611018804A CN106447137A CN 106447137 A CN106447137 A CN 106447137A CN 201611018804 A CN201611018804 A CN 201611018804A CN 106447137 A CN106447137 A CN 106447137A
- Authority
- CN
- China
- Prior art keywords
- data
- traffic
- website
- passenger flow
- markov model
- 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
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"
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a traffic passenger flow forecasting method based on information fusion and a Markov model. According to the method, through the combination of an information fusion technique and the Markov model, a novel method applicable to traffic flow forecasting is provided. According to the method, traffic flow data is processed through the information fusion technique, then the Markov model is constructed for the processed data, and meanwhile a transition probability matrix in the Markov model is trained by using the information fusion technique, so that the accuracy rate of traffic passenger flow forecasting is improved.
Description
Technical field
The present invention relates to data prediction field, more particularly, to a kind of based on information fusion and Markov model
Traffic passenger flow forecasting.
Background technology
With the quickening of urbanization and motorization process, the bus traveler assignment of early stage, line network planning have been not suitable with modernization
The needs of development, simultaneously urban traffic blocking become a difficult problem for puzzlement China urban development.In prior art, in intelligent transportation
Aspect carries out informationization to urban transportation, becomes more meticulous and intelligentized management, planning and design, improves bus traveler assignment, gauze rule
The reasonability drawn, it is ensured that progress is very few in terms of alleviating traffic congestion, also rarely has in prior art simultaneously and bus passenger flow is carried out
Monitoring and predicting, bus passenger flow be monitored and predict it is important that prediction to passenger flow, by history passenger flow data with real time
Monitoring Data and certain algorithm, can the predicted city traffic volume of the flow of passengers in a short time, so for scheduling public transport operation create
Advantage.
Content of the invention
The present invention provides a kind of traffic passenger flow forecasting based on information fusion and Markov model, and the method can carry
The accuracy rate of high traffic passenger flow estimation.
In order to reach above-mentioned technique effect, technical scheme is as follows:
A kind of traffic passenger flow forecasting based on information fusion and Markov model, comprises the following steps:
S1:Multi-source traffic data is passed through by information fusion technology and pre-processed the method combining step by step and pre-process;
S2:Using Markov model, passenger flow estimation is carried out to pretreated multi-source traffic data.
Further, the detailed process of described step S1 is as follows:
S11:Multi-source Information Fusion and ETL process-with information fusion technology are same type or different types of office
Portion's measured value is comprehensively complementary to one another, the redundancy before elimination information and untrue data, reduces single source measured value error institute
The impact bringing, then data is carried out with denoising, cleaning, conversion, reduction, repeated data block deletion action;
S12:Lossless data compression-in the form of wavelet transformation multilayer is decomposed, multilayer decomposition, space are carried out to data stream
After multilayer decomposition, parameter multilayer are decomposed, form the data compression stream temporally for clue, make the key character of traffic data abundant
Retain and highlight;
S13:Feature extraction-by the method for mapping or conversion, by the attribute space compression of the higher-dimension of multi-source traffic data
For the attribute space of low-dimensional, less new attribute will be transformed to by primitive attribute.
Further, the detailed process of described step S2 is as follows:
S21:The Markov model setting up traffic website needs the transition probability matrix of website and website;
S22:In the training process of Markov model transition probability matrix, by the multi-source traffic information obtaining using letter
Breath integration technology, to determine the transition probability between website using adaptive weighted average method;
S23:The state influence factor of analysis traffic website, determines transfer matrix by the influence factor identifying different
Dimension, and introduce transition probability matrix as state factor of influence, passenger flow is predicted.
Further, in described step S12, data stream is carried out with multilayer decomposition, spatial multi decomposes, parameter multilayer is decomposed
The form restoring data that data afterwards is reduced by multilayer is guaranteeing the lossless utilization of information.
Further, the detailed process of described step S11 includes:Storm using Twitter is carried out to traffic source data
Streaming calculates, and adopts redundant data deleting technique, to mitigate data storage pressure, reduces data redundancy, so that data is more had
Effect.This stage is concentrated mainly on the deletion to repeated data block, and the weakening of data noise.
Further, the detailed process of described step S23 is as follows:
1) define website A state be P x (t+k)=j | x (1)=i1, x (2)=i2... x (t)=it, due to passenger flow
State is generally tight with the passenger flow state relation of the website closer to it and time point, and website more remote therewith or time point
To it impact less it might even be possible to ignore, there is Markov property.Therefore, can be described as P x (t+k)=j | x (t)=
it, k >=1;
2), in the case of from A website to B website, it is transferred out of hair-like state i, transfer step k, reaches state j, its transition probability is Pij
(k)=Pij(t,t+k);
3) according to information fusion technology, judge the association website of observation website it is assumed that association website has n to contain observation website,
Determine transition probability matrix dimension be n, and according to correlation analysis passenger flow is carried out incident detection, passenger flow abnormality detection,
Section rule, forms state factor of influence ai=a1,a2,...an, 0 < i≤n;
4) the mixing probability of the wave filter mating with Markov model recommended in information fusion technology, visitor are adopted
The transition probability matrix of flow interactional factors composition n × n:
5) predict the state of observation website by probability matrix, predicted value is:
X (t)=a1s(t-1)p+a2s(t-2)p2+...+aks(t-k)pk.
Compared with prior art, the beneficial effect of technical solution of the present invention is:
The present invention passes through the combination of information fusion technology and Markov model, proposes to be applied to the new of traffic passenger flow estimation
Method, the method is processed to traffic flow data by information fusion technology, then builds Ma Er to the data after processing again
Can husband's model, simultaneously utilize information fusion technology train Markov model in transition probability matrix, improve traffic passenger flow pre-
The accuracy rate surveyed.
Brief description
Fig. 1 is the flow chart of the inventive method.
Specific embodiment
Being for illustration only property of accompanying drawing illustrates it is impossible to be interpreted as the restriction to this patent;
In order to the present embodiment is more preferably described, some parts of accompanying drawing have omission, zoom in or out, and do not represent actual product
Size;
To those skilled in the art, in accompanying drawing, some known features and its explanation may omission be to be appreciated that
's.
With reference to the accompanying drawings and examples technical scheme is described further.
Embodiment 1
As shown in figure 1, a kind of traffic passenger flow forecasting based on information fusion and Markov model, walk including following
Suddenly:
S1:Multi-source traffic data is passed through by information fusion technology and pre-processed the method combining step by step and pre-process;
S2:Using Markov model, passenger flow estimation is carried out to pretreated multi-source traffic data.
The traffic data wide material sources of intelligent transportation system, various informative, hand over including dynamic traffic flow data and intelligence
The management control data of logical subsystem, and the road environment data of static state etc.;Intelligent transportation system management and the object controlling
Traffic flow, traffic flow data is the series of values type data sequence obtaining of sampling in chronological order, be in traffic system
Important data, is also the key data source of passenger flow estimation, and intelligent transportation system have recorded a large amount of telecommunication flow informations, such as electronics
The illegal activities process image data of traffic offence vehicle is recorded by policing system, provides traffic offence information, bag
Include vehicle illegal place, the illegal date, the illegal time, Criminal type, illegal parameter, illegal vehicle panoramic image sequence, illegal
Vehicle license image;Traffic accident alarm and command system provides time of fire alarming, the friendship in warning place, alarm call number and correlation
Logical accident information;Traffic signal control system provides the running status relevant with crossing, color to walk information etc. of going forward one by one;
For the feature of intelligent transportation big data, model proposes Multi-source Information Fusion and pre-processes the side combining step by step
Formula, refers in data lead-in stage, data is carried out, data storage is compressed, algorithm is entered using front data
Row feature extraction;It is different from common data prediction flow process and mode, is not only minimizing data redundancy, solve general at this stage
Store-through big data storage a difficult problem, the degree of accuracy and the precision of algorithm can also be improved simultaneously further, make the big number of intelligent transportation
According to giving full play of potential value, it is that Analysis on Passenger Flow Forecast is got ready;
The detailed process of step S1 is as follows:
S11:Multi-source Information Fusion and ETL process-with information fusion technology are same type or different types of office
Portion's measured value is comprehensively complementary to one another, the redundancy before elimination information and untrue data, reduces single source measured value error institute
The impact bringing, then data is carried out with denoising, cleaning, conversion, reduction, repeated data block deletion action;
Be first data terminal gather after, data import distributed data base before carry out data message fusion and
Pretreatment operation, with information fusion technology same type or different types of local measurements in addition comprehensive, such as multi-source
Select optimal value in the data of detection, average, be complementary to one another, the redundancy before elimination information and untrue data, subtract
The brought impact of few list source measured value error.Information fusion technology is adopted in traffic passenger flow gathered data, can be from multi-source amount
Survey the optimum metrical information of data decimation, improve the confidence level of judged result;Can also be using computings such as detection and reasonings, effectively
Reduction event fuzzy program and uncertainty, effectively improve the accuracy rate of passenger flow forecasting.After information fusion technology
Data, then the operation such as maintenance data Denoising in Pretreatment, cleaning, conversion, reduction, the deletion of repeated data block;
Before generally general data is analyzed with assessment or digging utilization, all can adopt data prediction, for improving
The validity of data, but be all often the data after storing into database is carried out, converts, the operation such as reduction, and
Big data is very huger than common data, and is rapidly increased with referring to data, and intelligent transportation big data has collection terminal and divides
Feature scattered, that front end data storehouse is various, before these mass datas will be analyzed and utilize, needs to import data to
The large-scale distributed database of one concentration or distributed storage cluster.This patent, in this data lead-in stage, just introduces
Data cleansing and preconditioning technique, the multi-source passenger flow information that the technology such as combining RFID is perceived, using Storm pair of Twitter
Data carries out streaming calculating, and adopts redundant data deleting technique, to mitigate data storage pressure, reduces data redundancy, makes number
According to more effectively.This stage is concentrated mainly on the deletion to repeated data block, and the weakening of data noise;
S12:Lossless data compression-in the form of wavelet transformation multilayer is decomposed, multilayer decomposition, space are carried out to data stream
After multilayer decomposition, parameter multilayer are decomposed, form the data compression stream temporally for clue, make the key character of traffic data abundant
Retain and highlight;
This step mainly carries out time dimension compression to data, by carrying out recompiling reducing the superfluous of data to data
Remaining, this portion of techniques maturity in big data at this stage is processed is higher, the data compression scheme master to big data at present
Concentrate on some classical data compression algorithms, as common Huffman (Huffman) algorithm and LZW (Lempel mono- Ziv&W
El ch) compression algorithm;
For intelligent transportation big data, there is plenty of time sequence data, take and be applied to seasonal effect in time series and locate in advance
Reason mode time dimension reduction.For the feature being usually expressed as time series data in intelligent transportation big data, when ordinal number
Three-dimensional form description according to this, i.e. the feature (or variable) (feature/variable) of data, the record (or sample) of data
(record/sample) and data time dimension (time stamp/time dimension).Due to time series data and when
Between associated, thus its data volume is typically all very huge, this just timing driving technology is proposed higher will
Ask.The data compression of this step is concentrated mainly on the reduction of time dimension.Time dimension reduction is to when in time series data
Between point value carry out numerical value reduction, time dimension reduction be using substitute, less data representation format reduce data volume.
Parametric technique uses model estimated data, only need to deposit parameter (being also possible to is outlier) rather than real data. return and logarithm
Linear model is an example, and nonparametric technique includes histogram, cluster and sampling. histogram have wide, etc. frequency, V optimum,
MaxDiff, both are the most accurate and practical afterwards., in the form of the decomposition of wavelet transformation multilayer, research is in big data for this patent
Be applied to the compression algorithm of intelligent transportation data time dimension under amount, by decomposing to the multilayer of data flow, spatial multi decomposes,
After parameter multilayer is decomposed, form the data compression stream temporally for clue, so that the key character of traffic data is sufficiently reserved and dash forward
Aobvious, meanwhile, data after compression is preserved, the form restoring data that can also be reduced by multilayer is it is ensured that the lossless profit of information
With;
S13:Feature extraction-by the method for mapping or conversion, by the attribute space compression of the higher-dimension of multi-source traffic data
For the attribute space of low-dimensional, less new attribute will be transformed to by primitive attribute.
Markov model be according to system mode before transfer matrix following to describe stochastic systems
State of development, transition probability then reflect before each state in certain regularity, traffic passenger flow information is one dynamic to be believed
Breath, has the characteristics that randomness, and Markov model is just being suitable for describing this multidate information with random fluctuation feature.Cause
This, information fusion technology is combined it is adaptable to the prediction to the volume of the flow of passengers in traffic above-ground with Markov model.
Although traffic passenger flow is continuous in public transit system, but each website of road, centrifugal pump can be considered as, and
And the passenger flow state in traffic data website moment, the tightest with the passenger flow state relation of the website closer to it and time point
Close, and website more remote therewith or time point to it impact less it might even be possible to ignore, there is Markov property.Set up
The Markov model of website needs the transition probability matrix of website and website, in the instruction of Markov model transition probability matrix
During white silk, the multi-source traffic information of acquisition is adopted information fusion technology, to be determined using adaptive weighted average method
Transition probability between website, thus improve the accuracy rate of passenger flow estimation.Meanwhile, analyze the state influence factor of traffic website, such as
There is the operation factors such as fixing route, the public transport of run time, subway, passenger vehicle, or there is the stream of people of randomness, wagon flow operation
Factor, determines the dimension of transfer matrix by identifying different influence factors, and it is general to introduce transfer as state factor of influence
Rate matrix, is predicted to passenger flow.
The detailed process of step S2 is as follows:
S21:The Markov model setting up traffic website needs the transition probability matrix of website and website;
S22:In the training process of Markov model transition probability matrix, by the multi-source traffic information obtaining using letter
Breath integration technology, to determine the transition probability between website using adaptive weighted average method;
S23:The state influence factor of analysis traffic website, determines transfer matrix by the influence factor identifying different
Dimension, and introduce transition probability matrix as state factor of influence, passenger flow is predicted.
Further, the detailed process of described step S23 is as follows:
1) define website A state be P x (t+k)=j | x (1)=i1, x (2)=i2... x (t)=it, due to passenger flow
State is generally tight with the passenger flow state relation of the website closer to it and time point, and website more remote therewith or time point
To it impact less it might even be possible to ignore, there is Markov property.Therefore, can be described as P x (t+k)=j | x (t)=
it, k >=1;
2), in the case of from A website to B website, it is transferred out of hair-like state i, transfer step k, reaches state j, its transition probability is Pij
(k)=Pij(t,t+k);
3) according to information fusion technology, judge the association website of observation website it is assumed that association website has n to contain observation website,
Determine transition probability matrix dimension be n, and according to correlation analysis passenger flow is carried out incident detection, passenger flow abnormality detection,
Section rule, forms state factor of influence ai=a1,a2,...an, 0 < i≤n;
4) the mixing probability of the wave filter mating with Markov model recommended in information fusion technology, visitor are adopted
The transition probability matrix of flow interactional factors composition n × n:
5) predict the state of observation website by probability matrix, predicted value is:
X (t)=a1s(t-1)p+a2s(t-2)p2+...+aks(t-k)pk.
The present invention is directed to the feature of intelligent transportation big data, proposes the imagination of three step pretreatment modes, is different from common
Data prediction flow process and mode, make intelligent transportation big data give full play of potential value, prop up for good mining effect
Support.Substep pretreatment mode refers in data lead-in stage, data is carried out, and data storage is compressed, to algorithm
Carry out feature extraction using front data;Time series data for intelligent transportation big data carries out time dimension reduction, adopts
Decomposed with wavelet transformation multilayer and data is compressed preserving and pursue lossless reduction, effectively solving in terms of time dimension reduction
The information of retention data most possibly while data storage challenges;Knot by three step pretreatments and Markov model
Close, propose to be applied to the new method of traffic passenger flow estimation, the method by three step preconditioning techniques to traffic flow data at
Reason, then builds Markov model to the data after processing again, utilizes information fusion technology to train Markov model simultaneously
In transition probability matrix, improve traffic passenger flow estimation accuracy rate.
Same or analogous label corresponds to same or analogous part;
Described in accompanying drawing, position relationship illustrates it is impossible to be interpreted as the restriction to this patent for being for illustration only property;
Obviously, the above embodiment of the present invention is only intended to clearly illustrate example of the present invention, and is not right
The restriction of embodiments of the present invention.For those of ordinary skill in the field, also may be used on the basis of the above description
To make other changes in different forms.There is no need to be exhaustive to all of embodiment.All this
Any modification, equivalent and improvement made within the spirit of invention and principle etc., should be included in the claims in the present invention
Protection domain within.
Claims (6)
1. a kind of traffic passenger flow forecasting based on information fusion and Markov model is it is characterised in that include following walking
Suddenly:
S1:Multi-source traffic data is passed through by information fusion technology and pre-processed the method combining step by step and pre-process;
S2:Using Markov model, passenger flow estimation is carried out to pretreated multi-source traffic data.
2. the traffic passenger flow forecasting based on information fusion and Markov model according to claim 1, its feature
It is, the detailed process of described step S1 is as follows:
S11:Multi-source Information Fusion and ETL process-with information fusion technology, same type or different types of local are surveyed
Value is comprehensively complementary to one another, the redundancy before elimination information and untrue data, reduces the measured value error of single source and is brought
Impact, then data is carried out with denoising, cleaning, conversion, reduction, repeated data block deletion action;
S12:Lossless data compression-in the form of wavelet transformation multilayer is decomposed, multilayer decomposition, spatial multi are carried out to data stream
After decomposition, parameter multilayer are decomposed, form the data compression stream temporally for clue, so that the key character of traffic data is sufficiently reserved
With highlight;
S13:Feature extraction-and by the method for mapping or conversion, will be low for the attribute space boil down to of the higher-dimension of multi-source traffic data
The attribute space of dimension, will be transformed to less new attribute by primitive attribute.
3. the traffic passenger flow forecasting based on information fusion and Markov model according to claim 1, its feature
It is, the detailed process of described step S2 is as follows:
S21:The Markov model setting up traffic website needs the transition probability matrix of website and website;
S22:In the training process of Markov model transition probability matrix, the multi-source traffic information of acquisition is melted using information
Conjunction technology, to determine the transition probability between website using adaptive weighted average method;
S23:The state influence factor of analysis traffic website, determines the dimension of transfer matrix by identifying different influence factors
Degree, and introduce transition probability matrix as state factor of influence, passenger flow is predicted.
4. the traffic passenger flow forecasting based on information fusion and Markov model according to claim 2, its feature
Be, in described step S12, data stream is carried out multilayer decomposition, spatial multi decompose, parameter multilayer decompose after data pass through
The lossless utilization to guarantee information for the form restoring data of multilayer reduction.
5. the traffic passenger flow forecasting based on information fusion and Markov model according to claim 2, its feature
It is, the detailed process of described step S11 includes:Storm using Twitter carries out streaming calculating to traffic source data, and
Using redundant data deleting technique, to mitigate data storage pressure, reduce data redundancy, make data more effectively.This stage
It is concentrated mainly on the deletion to repeated data block, and the weakening of data noise.
6. the traffic passenger flow forecasting based on information fusion and Markov model according to claim 3, its feature
It is, the detailed process of described step S23 is as follows:
1) define website A state be P x (t+k)=j | x (1)=i1, x (2)=i2... x (t)=it, due to passenger flow state
Generally tight with the passenger flow state relation of the website closer to it and time point, and website more remote therewith or time point are to it
Impact less it might even be possible to ignore, there is Markov property.Therefore, can be described as P x (t+k)=j | x (t)=it, k
≥1;
2), in the case of from A website to B website, it is transferred out of hair-like state i, transfer step k, reaches state j, its transition probability is Pij(k)
=Pij(t,t+k);
3) according to information fusion technology, judge the association website of observation website it is assumed that association website has n to contain observation website, determine
Transition probability matrix dimension is n, and according to correlation analysis, passenger flow is carried out with incident detection, passenger flow abnormality detection, section
Rule, forms state factor of influence ai=a1,a2,...an, 0 < i≤n;
4) the mixing probability of the wave filter mating with Markov model recommended in information fusion technology, the volume of the flow of passengers are adopted
The transition probability matrix of interactional factors composition n × n:
5) predict the state of observation website by probability matrix, predicted value is:
X (t)=a1s(t-1)p+a2s(t-2)p2+...+aks(t-k)pk.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611018804.XA CN106447137A (en) | 2016-11-18 | 2016-11-18 | Traffic passenger flow forecasting method based on information fusion and Markov model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611018804.XA CN106447137A (en) | 2016-11-18 | 2016-11-18 | Traffic passenger flow forecasting method based on information fusion and Markov model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106447137A true CN106447137A (en) | 2017-02-22 |
Family
ID=58220367
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611018804.XA Pending CN106447137A (en) | 2016-11-18 | 2016-11-18 | Traffic passenger flow forecasting method based on information fusion and Markov model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106447137A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107977734A (en) * | 2017-11-10 | 2018-05-01 | 河南城建学院 | A kind of Forecasting Methodology based on mobile Markov model under space-time big data |
CN108399749A (en) * | 2018-03-14 | 2018-08-14 | 西南交通大学 | A kind of traffic trip needing forecasting method in short-term |
CN108600697A (en) * | 2018-04-23 | 2018-09-28 | 佛山市长郡科技有限公司 | A kind of environmental sanitation system based on Internet of Things |
CN108762993A (en) * | 2018-06-06 | 2018-11-06 | 山东超越数控电子股份有限公司 | A kind of virtual-machine fail moving method and device based on artificial intelligence |
CN108961749A (en) * | 2018-07-12 | 2018-12-07 | 南方科技大学 | A kind of intelligent transportation system and intellectual traffic control method |
CN111860997A (en) * | 2020-07-17 | 2020-10-30 | 海南大学 | Cross-data, information, knowledge modality and dimension early warning method and component |
CN116502055A (en) * | 2023-01-10 | 2023-07-28 | 昆明理工大学 | Multi-dimensional characteristic dynamic abnormal integral model based on quasi-Markov model |
-
2016
- 2016-11-18 CN CN201611018804.XA patent/CN106447137A/en active Pending
Non-Patent Citations (2)
Title |
---|
李存军: "基于集成神经网络的城市道路交通流量融合预测研究", 《中国优秀博硕士学位论文全文数据库(博士) 工程科技Ⅱ辑》 * |
谢辉 等: "轨道交通短期客流预测方法及其算法研究", 《现代城市轨道交通》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107977734A (en) * | 2017-11-10 | 2018-05-01 | 河南城建学院 | A kind of Forecasting Methodology based on mobile Markov model under space-time big data |
CN107977734B (en) * | 2017-11-10 | 2021-08-24 | 河南城建学院 | Prediction method based on mobile Markov model under space-time big data |
CN108399749A (en) * | 2018-03-14 | 2018-08-14 | 西南交通大学 | A kind of traffic trip needing forecasting method in short-term |
CN108600697A (en) * | 2018-04-23 | 2018-09-28 | 佛山市长郡科技有限公司 | A kind of environmental sanitation system based on Internet of Things |
CN108762993A (en) * | 2018-06-06 | 2018-11-06 | 山东超越数控电子股份有限公司 | A kind of virtual-machine fail moving method and device based on artificial intelligence |
CN108961749A (en) * | 2018-07-12 | 2018-12-07 | 南方科技大学 | A kind of intelligent transportation system and intellectual traffic control method |
CN111860997A (en) * | 2020-07-17 | 2020-10-30 | 海南大学 | Cross-data, information, knowledge modality and dimension early warning method and component |
CN111860997B (en) * | 2020-07-17 | 2021-12-28 | 海南大学 | Cross-data, information, knowledge modality and dimension early warning method and component |
CN116502055A (en) * | 2023-01-10 | 2023-07-28 | 昆明理工大学 | Multi-dimensional characteristic dynamic abnormal integral model based on quasi-Markov model |
CN116502055B (en) * | 2023-01-10 | 2024-05-03 | 昆明理工大学 | Multi-dimensional characteristic dynamic abnormal integral model based on quasi-Markov model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106447137A (en) | Traffic passenger flow forecasting method based on information fusion and Markov model | |
Yu et al. | Prediction of bus travel time using random forests based on near neighbors | |
CN105843942B (en) | A kind of Urban Flood control decision support method based on big data technology | |
CN104091070B (en) | Rail transit fault diagnosis method and system based on time series analysis | |
CN105023437B (en) | A kind of construction method and system of public transport OD matrixes | |
Yu et al. | Real time prediction of unoccupied parking space using time series model | |
CN105868861A (en) | Bus passenger flow evolution analysis method based on time-space data fusion | |
CN106507315A (en) | A kind of urban traffic accident Forecasting Methodology and system based on network social intercourse media data | |
Reddy et al. | Bus travel time prediction under high variability conditions | |
CN109241227A (en) | Space-time data based on stacking Ensemble Learning Algorithms predicts modeling method | |
CN104318327A (en) | Predictive parsing method for track of vehicle | |
CN112215409B (en) | Rail transit station passenger flow prediction method and system | |
CN112529284A (en) | Private car residence time prediction method, device and medium based on neural network | |
Bouman et al. | Detecting activity patterns from smart card data | |
CN104767534B (en) | A kind of controllable track of vehicle point compression and storage method of error and system | |
Büchel et al. | Modeling conditional dependencies for bus travel time estimation | |
CN109145175A (en) | Space-time data prediction technique based on stacking Ensemble Learning Algorithms | |
CN112188478B (en) | Resident population data acquisition method based on big data analysis | |
CN116824868A (en) | Method, device, equipment and medium for identifying illegal parking points and predicting congestion of vehicles | |
CN110782060A (en) | Rail transit section passenger flow short-time prediction method and system based on big data technology | |
CN105469601A (en) | A road traffic space data compression method based on LZW coding | |
CN114492544A (en) | Model training method and device and traffic incident occurrence probability evaluation method and device | |
Prabha et al. | A comprehensive insight towards pre-processing methodologies applied on GPS data | |
Wang et al. | Statistical learning for train delays and influence of winter climate and atmospheric icing | |
Shi et al. | Prediction and Impact Analysis of Passenger Flow in Urban Rail Transit in the Postpandemic Era |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination |