CN107103758A - A kind of city area-traffic method for predicting based on deep learning - Google Patents

A kind of city area-traffic method for predicting based on deep learning Download PDF

Info

Publication number
CN107103758A
CN107103758A CN201710427408.0A CN201710427408A CN107103758A CN 107103758 A CN107103758 A CN 107103758A CN 201710427408 A CN201710427408 A CN 201710427408A CN 107103758 A CN107103758 A CN 107103758A
Authority
CN
China
Prior art keywords
lpr
net region
data
equipment
period
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
Application number
CN201710427408.0A
Other languages
Chinese (zh)
Other versions
CN107103758B (en
Inventor
范晓亮
郑传潘
李军
王程
陈龙彪
臧彧
温程璐
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xiamen University
Original Assignee
Xiamen University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Xiamen University filed Critical Xiamen University
Priority to CN201710427408.0A priority Critical patent/CN107103758B/en
Publication of CN107103758A publication Critical patent/CN107103758A/en
Application granted granted Critical
Publication of CN107103758B publication Critical patent/CN107103758B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0129—Traffic data processing for creating historical data or processing based on historical data

Abstract

The invention discloses a kind of city area-traffic method for predicting based on deep learning, this method provides a kind of new thinking by extracting Higher Dimensional Space Time feature that the magnitude of traffic flow changes to the magnitude of traffic flow in each region in city while being predicted for Forecast of Urban Traffic Flow forecasting problem.The historical traffic of urban area each period is calculated according to the data of LPR equipment first；Then ConvLSTM and CNN design flow forecast models are utilized, and extract the data on flows for the material time section for influenceing prediction period as input training pattern；The prediction of city area-traffic flow is finally carried out using the model trained.

Description

A kind of city area-traffic method for predicting based on deep learning
Technical field
The present invention relates to a kind of city area-traffic method for predicting based on deep learning, by using deep learning Convolutional neural networks and convolution length in technology memory network in short-term, with reference to the net region division methods of city road network, are realized The prediction of city area-traffic flow, belongs to the interleaving techniques application field of deep learning and intelligent transportation system.
Background technology
Intelligent transportation system (ITS) is the system that information and communication technology (ICT) is applied to road transport field, and it is by handing over The innovation of logical management mode, enables people to be best understood from, more coordinates, reasonably utilizes transportation network.In recent years, intelligence The fast development of traffic system provides effective solution for the continuous growth of transportation network demand, is to build smart city Core link.At present, intelligent transportation system is solving urban road congestion, city capacity deployment, urban safety, city basis Have been obtained for being widely applied on the problems such as facilities planning.
Accurate traffic flow forecasting system is ITS core, and people have done in traffic flow forecasting problem Substantial amounts of research work.These research work can substantially be divided into two classes：One class is with the traditional mathematicses physics such as mathematical statistics Forecast model based on method, such as autoregression model (AR), ARMA model (ARIMA), history averaging model (HA), Kalman filter model (KFM) etc.；Another kind of is the forecast model based on neutral net, such as BP neural network mould Type, stack own coding (SAE), convolutional neural networks model (CNN), recurrent neural networking model (RNN) etc..
Existing method or the defect of invention：1) existing method only focuses on the traffic flow forecasting of single-point or single channel section mostly, The volume forecasting in region is not suitable for, because point or section can not represent region；2) existing method only considers traffic mostly Changes in flow rate is in the dependence of time dimension or the relevance of Spatial Dimension, the space-time without considering magnitude of traffic flow change simultaneously Feature；3) existing method only focuses on traffic flow forecasting in short-term mostly, and lacks the support to long-time method for predicting.
The content of the invention
It is an object of the invention to provide a kind of city area-traffic method for predicting based on deep learning, by depth Practise and be applied to city area-traffic volume forecasting, using the traffic flow data of history as input, entered using multi-layer C onvLSTM Row Higher Dimensional Space Time feature extraction, dimension-reduction treatment is made finally by the CNN of individual layer, and acquisition predicts the outcome, and this method is handed over by extracting The Higher Dimensional Space Time feature of through-current capacity change is predicted simultaneously to the magnitude of traffic flow in each region in city, is that Forecast of Urban Traffic Flow is pre- Survey problem provides a kind of new thinking.
The historical traffic of urban area each period is calculated according to the data of LPR equipment first；Then utilize ConvLSTM and CNN design flow forecast models, and extract the data on flows work of the material time section of influence prediction period For input training pattern；The prediction of city area-traffic flow is finally carried out using the model trained.
Concretely comprise the following steps：
S1, the net region that city road network is divided into M × N, according to longitude and latitude by each LPR device maps to grid regions In domain；
S2, LPR data are pre-processed, obtain each LPR equipment each period crosses car record, is set with reference to LPR The standby mapping relations with net region, obtain traffic flow data of each net region within each period；
S3, the data on flows of the material time section of selection influence prediction period are used as the input of traffic flow forecasting module；
S4, using convolution length, memory network and convolutional neural networks build forecast model in short-term, and forecast model is instructed Practice, choose the minimum model of error as optimum prediction model, calculated by the model and obtain the pre- of city area-traffic flow Measured value.
Further, step S1 is specifically included：
S11, the net region for according to longitude and latitude city road network being divided into M × N；
S12, each LPR equipment is mapped in net region according to longitude and latitude, the LPR in net region (m, n) is set It is standby to be designated as L (m, n)={ L1, L2... Li..., Lk, wherein LiRepresent the numbering of i-th of equipment in net region (m, n), k Represent to have k equipment in the net region.
Further, step S2 is specifically included
S21, the critical field { L, P, τ } for extracting LPR data, wherein L represent device numbering, and P represents the car of equipment L records The trade mark, τ represents the time of its record；
S22, to LPR data carry out filtering cleaning, deletion error, redundant data；
S23, by one day T period was divided into, according to S22 result, extracts each equipment in each time Car record is crossed in section；
S24, the mapping relations according to LPR equipment and net region, are associated with its corresponding by the record of car excessively of LPR equipment In net region, obtain each LPR equipment in each net region and cross car record within each period；
S25, the LPR number of devices in each net region calculate the traffic in each each period of net region Data on flows；
S26, to obtained in S25 all periods all net regions data on flows x be normalized, then haveIn formula, x ' is the flow after normalization, xmaxAnd xminFor all net region flows of all periods most Big value and minimum value, the data on flows of time period t is the three-dimensional matrice of the passage of M row N row 1 after normalization, is designated as Xt∈RM×N×1。
Further, the computational methods of the traffic flow data in step S25 in each each period of net region are：
If not being predicted in a, net region (m, n) without LPR equipment to its flow then, flow is designated as 0；
If only one of which LPR equipment in b, net region (m, n), then calculate this LPR equipment and cross car number in time period t It is used as flow of the region in time period t；
If the number of devices more than one in c, net region (m, n), each mistake of LPR equipment in time period t is calculated first Car number is simultaneously summed, and when then multiple LPR equipment for being likely to occur record same vehicle, is handled in such a way：
In net region if (m, n), LPR equipment LIAnd LjSame vehicle P is successively recorded in same time period tA, it is remembered The record time is respectively τiWith τjIf,Then it is considered vehicle PAIdentical strip path curve be repeatedly recorded, asked above-mentioned The result of sum subtracts 1；Otherwise former result is retained；In formula, d (Li, Lj) it is LPR equipment Li、LjThe distance between, λ is given threshold.
Further, step S3 is specifically included：
S31, selection are nearestThe data on flows of section at the same time on the same day in week, is designated as
S32, selection are nearestThe data on flows of its section at the same time, is designated as
S33, selection are nearestThe data on flows of individual period, is designated as
S34, using the combination of above-mentioned three groups of data as input, be designated asXtIt is used as output, structure Build a sampleAll data are according to said method built into sample, and be divided into by a certain percentage training set, checking collection with Test set.
Further, step S4 is specifically included：
S41, structure forecast model, the model include 4 layers of convolution length memory network layer, 4 layers batches of specifications layers and one layer in short-term Convolutional neural networks layer；
S42, forecast model are 9 layers of network, wherein first 8 layers are convolution length memory network layer and batch group of specification layer in short-term Close, i.e., memory network layer is followed by one batch of specification layer to each convolution length in short-term, and each batch of specification layer is followed by a convolution length When memory network layer, the 9th layer for individual layer convolutional neural networks layer；
Memory network layer, using the convolution kernel of 64 3 × 3, is operated using zero padding, used in short-term for S43, each convolution length Relu functions are used as activation primitive；
S44, convolutional neural networks use the convolution kernel of 13 × 3 layer by layer, are operated using zero padding, use sigmoid functions It is used as activation primitive；
S45, the object function of forecast model are mean square error function MSE, then have：
Wherein, XiRepresent real traffic,Predicted flow rate is represented, s represents sample number, M, and N is the line number and columns of grid；
S46, being trained in training set input prediction model, the minimum models of MSE are chosen as most according to checking collection Whole forecast model；
In S47, the model that test set input S46 is trained, obtain after output result, then carry out renormalization, obtain Final urban area volume forecasting result.
After adopting the above technical scheme, the present invention has the following advantages that compared with background technology：
1st, existing method only focuses on the volume forecasting of single-point or single channel section mostly, and method proposed by the present invention is based on convolution The long layer of memory network in short-term is predicted with convolutional neural networks layer, the magnitude of traffic flow in the region of each in city and its peripheral region The magnitude of traffic flow in other regions is related in domain or even whole city, and convolutional coding structure can learn a region and other weeks The discharge relation in region is enclosed, with the intensification of the convolution number of plies, effect characteristicses of the peri-urban region to the region can be learnt；2、 Existing method only considers magnitude of traffic flow change feature in time or spatially mostly, and the convolution in Forecasting Methodology of the present invention The long layer of memory network in short-term extracts space characteristics by convolutional coding structure, and temporal characteristics are obtained by LSTM structures, and in its algorithm Bottom is combined convolutional neural networks with LSTM, can learn the high-dimensional space-time characteristic of magnitude of traffic flow change, effective integration Time dimension and Spatial Dimension, so as to substantially increase precision of prediction；
3rd, convolutional Neural sets a convolution kernel, can make dimension-reduction treatment to high-dimensional space-time characteristic, be operated by zero padding, The volume forecasting in all regions in city can be realized；
4th, existing method only focuses on short-term traffic flow forecast mostly, and city area-traffic flow proposed by the present invention is pre- Survey method can realize regional traffic flow prediction in short-term in one hour by choosing specific list entries, both, can also be real Existing 24 hours, the prolonged regional traffic flow prediction such as one week；
To sum up, the other occasion of City-level and the emphasis of festivals or holidays prison therefore disclosed method is particularly suitable for use in Survey the traffic flow forecasting in region.
Brief description of the drawings
Fig. 1 is the algorithm flow chart of the city area-traffic method for predicting based on deep learning；
Fig. 2 is that city road network net region divides schematic diagram；
Fig. 3 represents X for the flow of time period t city area-traffic flowt；
Fig. 4 is input and the schematic diagram exported；
Fig. 5 is the schematic diagram of forecast model calculating process.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and It is not used in the restriction present invention.
Embodiment
As shown in Fig. 1 the algorithm flow chart of the city area-traffic method for predicting based on deep learning, its is pre- Examining system includes magnitude of traffic flow computing module and traffic flow forecasting module based on net region.In magnitude of traffic flow computing module In, net region division is carried out to urban road network according to longitude and latitude first, and by the car plate in the section of each in city road network Recognize (LPR) device map into net region；Secondly, obtained according to the data of LPR equipment in each equipment each period Cross car record；Again, the result of above-mentioned two step of fusion calculates the magnitude of traffic flow in each period of each net region；Most Afterwards, data on flows is normalized.In traffic flow forecasting module, the magnitude of traffic flow of material time section is chosen first Data as convolution length memory network (ConvLSTM) in short-term input, during the higher-dimension changed by the e-learning magnitude of traffic flow Empty feature；Secondly, dimension-reduction treatment is carried out to Higher Dimensional Space Time feature by convolutional neural networks (CNN)；Finally, renormalization is passed through Obtain final urban area volume forecasting result.
Concretely comprise the following steps：
S1, city road network is subjected to net region division, according to longitude and latitude by each LPR device maps to net region In：
S11, the net region for according to longitude and latitude city road network being divided into M × N；
S12, each LPR equipment is mapped in net region according to longitude and latitude, the LPR in such as net region (m, n) is set It is standby to be designated as L (m, n)={ L1, L2... Li..., Lk, wherein LiRepresent the numbering of i-th of equipment in net region (m, n), k Represent to have k equipment in the net region.
S2, LPR data are pre-processed, obtain each equipment each period crosses car record, with reference to LPR equipment with The mapping relations of net region, obtain traffic flow data of each net region within each period；
S21, the critical field { L, P, τ } for extracting LPR data, wherein L represent device numbering, and P represents the car of equipment L records The trade mark, τ represents the time of its record；
S22, to LPR data carry out filtering cleaning, deletion error, redundant data；
S23, by one day T period was divided into, according to S22 result, extracts each equipment in each time Car record is crossed in section；
S24, the mapping relations according to LPR equipment and net region, are associated with its corresponding by the record of car excessively of LPR equipment In net region, obtain crossing car record in each equipment each period in each net region；
S25, the magnitude of traffic flow for net region (m, n) in time period t, point following three kinds of situations are calculated：
Without LPR equipment in net region if (m, n), expression is without road network or is not traffic hot spot region, not to it Flow is predicted, and flow is designated as 0；
If only one of which LPR equipment in net region (m, n), then calculate this equipment and cross car number conduct in time period t Flow of the region in time period t；
If the number of devices more than one in net region (m, n), each equipment is calculated first and crosses car number in time period t And sum, when then the multiple equipment for being likely to occur records same vehicle, handle in such a way：
If in grid (m, n), LI、LjSame vehicle P is successively recorded in same time period tA, the record time is respectively τi、 τj(τi、τjFor registration of vehicle P in the net regionAThe closest time, i.e., in time period t, to region (m, n),If(wherein, d (Li, Lj) it is equipment LI、 LjThe distance between, λ is given threshold), then it is assumed that it is vehicle PAIdentical strip path curve be repeatedly recorded, by the knot of above-mentioned summation Fruit subtracts 1, does not otherwise subtract 1；
The traffic flow data in each period of each net region is calculated as stated above.
S26, by obtain all periods all net regions data on flows carry out unified normalized, calculate public Formula：Wherein x ' is the flow after normalization, xmaxAnd xminFor all net region flows of all periods The data on flows of time period t is the three-dimensional matrice of the passage of M row N row 1 after maximum and minimum value, normalization, is designated as Xt∈RM ×N×1。
S3, the data on flows of the material time section of selection influence prediction period are used as the input of traffic flow forecasting module：
S31, for prediction Xt, choose nearestThe data on flows of section at the same time on the same day in week, is designated as
S32, for prediction Xt, choose nearestThe data on flows of its section at the same time, is designated as
S33, for prediction Xt, choose nearestThe data on flows of individual period, is designated as
S34, using the combination of above-mentioned three groups of data as input, be designated asXtIt is used as output, structure Build a sampleAll data are according to said method built into sample, and be divided into by a certain percentage training set, checking collection with Test set.
S4, using convolution length, memory network (ConvLSTM) and convolutional neural networks (CNN) build forecast model in short-term, right Forecast model is trained, and is chosen the minimum model of error as optimum prediction model, is calculated by the model and obtain metropolitan district The predicted value of the domain magnitude of traffic flow.
S41, structure forecast model, the model include 4 layers of convolution length memory network layer (ConvLSTM), 4 layers batches of rule in short-term Model layer (Batch Normalization) and one layer of convolutional neural networks layer (CNN)；
S42, forecast model are 9 layers of network, wherein the first 8 layers combination for ConvLSTM and batch specification layer is (each ConvLSTM layers are followed by one batch of specification layer, then connect ConvLSTM layers, so series connection, constitute 8 layers of network), the 9th layer is single The CNN of layer；
S43, each ConvLSTM layers use the convolution kernel of 64 3 × 3, (zero-padding) is operated using zero padding, made Activation primitive is used as with relu functions；
S44, CNN layers, using the convolution kernel of 13 × 3, are operated using zero padding, and activation letter is used as using sigmoid functions Number；
S45, the object function of forecast model are mean square error function (MSE), as follows：
Wherein, XiRepresent real traffic,Predicted flow rate is represented, s represents sample number, M, and N is the line number and columns of grid；
S46, being trained in training set input prediction model, the minimum models of MSE are chosen as most according to checking collection Whole forecast model；
In S47, the model that test set input S46 is trained, obtain after output result, then carry out renormalization, obtain Finally predict the outcome.
Some steps come with reference to specific example in detailed description method.
First, city road network net region is divided
Fig. 2 show the net region of Fujian province Xiamen City Xiamen Island road network 18 × 18 and divides schematic diagram, is set according to LPR Each device map into net region, is obtained the LPR device numberings included in each net region, such as net by standby longitude and latitude LPR equipment in lattice region (m, n) is designated as L (m, n) { L1, L2... Li..., Lk}。
2nd, the magnitude of traffic flow is calculated
Period division was carried out for interval (T=24) with one hour according to the record time of LPR device datas, grid is counted The car of crossing of region daily 24 periods each period is recorded, and according to LPR equipment and the mapping relations of net region, counts net Car record is crossed in each period of lattice region, the magnitude of traffic flow number in each period in net region is calculated by the following method According to：
Without LPR equipment in net region if (m, n), expression is without road network or is not traffic hot spot region, not to it Flow is predicted, and flow is designated as 0；
If only one of which LPR equipment in net region (m, n), then the car number scale of crossing for calculating the equipment each period is to be somebody's turn to do The magnitude of traffic flow in each period of region；
If the number of devices more than one in net region (m, n), is illustrated below：
Assuming that having two equipment L in net region (m, n)1、L2, in time period t, L1Be recorded asL2Be recorded as If(λ is threshold value, be may be set to 10), then net The magnitude of traffic flow of the lattice region (m, n) in time period t is 3+2-1=4, is otherwise 5；
Method can calculate the magnitude of traffic flow for obtaining regional in each hours section, such as Fig. 3 as described above The city area-traffic flow for showing time period t represents Xt, then it is normalized according to min-max standardized methods.
3rd, list entries is obtained
The flow of time period t with its beforeThe flow of individual time step has certain continuity, and before itIts synchronization Flow has certain periodicity, and before itThe flow of all synchronizations on the same day has certain similitude.For prediction Xt, Take Order inputInputting step-length is Desired output is Xt, sample pair is built, and by 8:1:1 point is training set, checking collection and test set.
By designing list entries, but realize in short-term or it is long when volume forecasting.It is exemplified below：
If following one hour urban area flow of prediction, can set T=24, If Urban area flow after predicting 24 hours, can set T=24,If after prediction one week Urban area flow, can set T=24,It is illustrated in figure 4 the input and output of system Schematic diagram.
The design and training of forecast model：
Forecast model is made up of 4 layers ConvLSTM layers, 4 layers batches of specification layers and one layer of CNN layers.8 layers are before network (each ConvLSTM layers is followed by one batch of specification layer, then connects ConvLSTM layers, so for the combination of ConvLSTM and batch specification layer Series connection, the network of 8 layers of composition), the 9th layer of CNN for individual layer.
Each ConvLSTM layers, using the convolution kernel of 64 3 × 3, operate (zero-padding) using zero padding, use Relu functions are as activation primitive, and the input and output sequence length of ConvLSTM layers of three first layers is identical, last layer of ConvLSTM The output sequence length of layer is 1；CNN layers, using the convolution kernel of 13 × 3, operate (zero-padding) using zero padding, use Sigmoid functions are used as activation primitive；The object function of forecast model is mean square error function (MSE).
Fig. 5 is the schematic diagram of forecast model calculating process.Being trained in training set input prediction model, according to checking Collection chooses the minimum models of MSE as final forecast model, and test set is inputted in the model trained, output result is obtained Afterwards, then renormalization is carried out, is finally predicted the outcome.
The foregoing is only a preferred embodiment of the present invention, but protection scope of the present invention be not limited thereto, Any one skilled in the art the invention discloses technical scope in, the change or replacement that can be readily occurred in, It should all be included within the scope of the present invention.Therefore, protection scope of the present invention should be with scope of the claims It is defined.

Claims (6)

1. a kind of city area-traffic method for predicting based on deep learning, it is characterised in that：Comprise the following steps：
S1, the net region that city road network is divided into M × N, according to longitude and latitude by each LPR device maps to net region In；
S2, LPR data are pre-processed, obtain each LPR equipment each period crosses car record, with reference to LPR equipment with The mapping relations of net region, obtain traffic flow data of each net region within each period；
S3, the data on flows of the material time section of selection influence prediction period are used as the input of traffic flow forecasting module；
S4, using convolution length, memory network and convolutional neural networks build forecast model in short-term, and forecast model is trained, selected Take the minimum model of error as optimum prediction model, the predicted value for obtaining city area-traffic flow is calculated by the model.
2. a kind of city area-traffic method for predicting based on deep learning according to claim 1, its feature exists In step S1 is specifically included：
S11, the net region for according to longitude and latitude city road network being divided into M × N；
S12, each LPR equipment is mapped in net region according to longitude and latitude, the LPR equipment in net region (m, n) is remembered For L (m, n)={ L1, L2... Li..., Lk, wherein LiThe numbering of i-th of equipment in net region (m, n) is represented, k is represented K equipment is had in the net region.
3. a kind of city area-traffic method for predicting based on deep learning according to claim 1, its feature exists In step S2 is specifically included：
S21, the critical field { L, P, τ } for extracting LPR data, wherein L represent device numbering, and P represents the car plate of equipment L records Number, τ represents the time of its record；
S22, to LPR data carry out filtering cleaning, deletion error, redundant data；
S23, by one day T period was divided into, according to S22 result, extracts each equipment within each period Cross car record；
S24, the mapping relations according to LPR equipment and net region, its corresponding grid is associated with by the car record of crossing of LPR equipment In region, obtain each LPR equipment in each net region and cross car record within each period；
S25, the LPR number of devices in each net region calculate the magnitude of traffic flow in each each period of net region Data；
S26, to obtained in S25 all periods all net regions data on flows x be normalized, then haveIn formula, x ' is the flow after normalization, xmaxAnd xminFor all net region flows of all periods most Big value and minimum value, the data on flows of time period t is the three-dimensional matrice of the passage of M row N row 1 after normalization, is designated as Xt∈RM×N×1。
4. a kind of city area-traffic method for predicting based on deep learning according to claim 3, its feature exists In the computational methods of the traffic flow data in step S25 in each period of each net region are：
If not being predicted in a, net region (m, n) without LPR equipment to its flow then, flow is designated as 0；
If only one of which LPR equipment in b, net region (m, n), then calculate this LPR equipment and cross car number conduct in time period t Flow of the region in time period t；
If the number of devices more than one in c, net region (m, n), each LPR equipment is calculated first and crosses car number in time period t And sum, when then multiple LPR equipment for being likely to occur record same vehicle, handle in such a way：
In net region if (m, n), LPR equipment LIAnd LjSame vehicle P is successively recorded in same time period tA, when it is recorded Between be respectively τiWith τjIf,Then it is considered vehicle PAIdentical strip path curve be repeatedly recorded, by above-mentioned summation As a result subtract 1；Otherwise former result is retained；In formula, d (Li, Lj) it is LPR equipment Li、LjThe distance between, λ is given threshold.
5. a kind of city area-traffic method for predicting based on deep learning according to claim 1, its feature exists In step S3 is specifically included：
S31, selection are nearestThe data on flows of section at the same time on the same day in week, is designated as
S32, the data on flows for choosing nearest d days sections at the same time, are designated as
S33, selection are nearestThe data on flows of individual period, is designated as
S34, using the combination of above-mentioned three groups of data as input, be designated asXtAs output, one is built Individual sampleAll data are according to said method built into sample, and are divided into training set, checking collection and test by a certain percentage Collection.
6. a kind of city area-traffic method for predicting based on deep learning according to claim 1, its feature exists In step S4 is specifically included：
S41, structure forecast model, the model include 4 layers of convolution length memory network layer, 4 layers batches of specifications layers and one layer of volume in short-term Product neural net layer；
S42, forecast model are 9 layers of network, wherein first 8 layers are convolution length memory network layer and batch combination of specification layer in short-term, Memory network layer is followed by one batch of specification layer to i.e. each convolution length in short-term, and each batch of specification layer is followed by a convolution length and remembered in short-term Recall Internet, the 9th layer of convolutional neural networks layer for individual layer；
Memory network layer, using the convolution kernel of 64 3 × 3, is operated using zero padding, uses relu letters in short-term for S43, each convolution length Number is used as activation primitive；
S44, convolutional neural networks use the convolution kernel of 13 × 3 layer by layer, are operated using zero padding, using sigmoid functions as Activation primitive；
S45, the object function of forecast model are mean square error function MSE, then have：
<mrow> <mi>M</mi> <mi>S</mi> <mi>E</mi> <mo>=</mo> <mfrac> <mn>1</mn> <mi>s</mi> </mfrac> <mo>&amp;times;</mo> <mfrac> <mn>1</mn> <mrow> <mi>M</mi> <mo>&amp;times;</mo> <mi>N</mi> </mrow> </mfrac> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>s</mi> </munderover> <msup> <mrow> <mo>(</mo> <msub> <mi>X</mi> <mi>i</mi> </msub> <mo>-</mo> <msub> <mover> <mi>X</mi> <mo>^</mo> </mover> <mi>i</mi> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> </mrow>
Wherein, XiRepresent real traffic,Predicted flow rate is represented, s represents sample number, M, and N is the line number and columns of grid；
S46, being trained in training set input prediction model, the minimum models of MSE are chosen as final pre- according to checking collection Survey model；
In S47, the model that test set input S46 is trained, obtain after output result, then carry out renormalization, obtain final Urban area volume forecasting result.
CN201710427408.0A 2017-06-08 2017-06-08 A kind of city area-traffic method for predicting based on deep learning Active CN107103758B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710427408.0A CN107103758B (en) 2017-06-08 2017-06-08 A kind of city area-traffic method for predicting based on deep learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710427408.0A CN107103758B (en) 2017-06-08 2017-06-08 A kind of city area-traffic method for predicting based on deep learning

Publications (2)

Publication Number Publication Date
CN107103758A true CN107103758A (en) 2017-08-29
CN107103758B CN107103758B (en) 2019-06-21

Family

ID=59659757

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710427408.0A Active CN107103758B (en) 2017-06-08 2017-06-08 A kind of city area-traffic method for predicting based on deep learning

Country Status (1)

Country Link
CN (1) CN107103758B (en)

Cited By (62)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107967532A (en) * 2017-10-30 2018-04-27 厦门大学 The Forecast of Urban Traffic Flow Forecasting Methodology of integration region vigor
CN108053653A (en) * 2018-01-11 2018-05-18 广东蔚海数问大数据科技有限公司 Vehicle behavior Forecasting Methodology and device based on LSTM
CN108280441A (en) * 2018-02-09 2018-07-13 北京天元创新科技有限公司 A kind of crowd's method for predicting and system
CN108364087A (en) * 2018-01-11 2018-08-03 安徽优思天成智能科技有限公司 A kind of spatio-temporal prediction method of urban mobile tail gas concentration
CN108399745A (en) * 2018-03-01 2018-08-14 北京航空航天大学合肥创新研究院 A kind of city road network trend prediction method at times based on unmanned plane
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
CN108564228A (en) * 2018-04-26 2018-09-21 重庆大学 A method of based on the temporal aspect predicted orbit traffic OD volumes of the flow of passengers
CN108647834A (en) * 2018-05-24 2018-10-12 浙江工业大学 A kind of traffic flow forecasting method based on convolutional neural networks structure
CN108876045A (en) * 2018-06-25 2018-11-23 上海应用技术大学 Emergency tender optimal route recommended method based on LSTM model prediction
CN108900346A (en) * 2018-07-06 2018-11-27 西安电子科技大学 Wireless network traffic prediction technique based on LSTM network
CN108985475A (en) * 2018-06-13 2018-12-11 厦门大学 Net based on deep neural network about vehicle car service needing forecasting method
CN109034460A (en) * 2018-07-03 2018-12-18 深圳市和讯华谷信息技术有限公司 Prediction technique, device and system for scenic spot passenger flow congestion level
CN109087508A (en) * 2018-08-30 2018-12-25 广州市市政工程设计研究总院有限公司 Contiguous zone traffic analysis method and system based on high definition bayonet data
CN109117987A (en) * 2018-07-18 2019-01-01 厦门大学 Personalized street accidents risks based on deep learning predict recommended method
CN109165779A (en) * 2018-08-12 2019-01-08 北京清华同衡规划设计研究院有限公司 A kind of size of population prediction technique based on multi-source big data Yu shot and long term Memory Neural Networks model
CN109190795A (en) * 2018-08-01 2019-01-11 中山大学 A kind of interregional Travel Demand Forecasting method and device
CN109299401A (en) * 2018-07-12 2019-02-01 中国海洋大学 Metropolitan area space-time stream Predicting Technique based on deep learning model LSTM-ResNet
CN109300309A (en) * 2018-10-29 2019-02-01 讯飞智元信息科技有限公司 Road condition predicting method and device
CN109359698A (en) * 2018-10-30 2019-02-19 清华大学 Leakage loss recognition methods based on long Memory Neural Networks model in short-term
CN109544911A (en) * 2018-10-30 2019-03-29 中山大学 A kind of city road net traffic state prediction technique based on LSTM-CNN
CN109658695A (en) * 2019-01-02 2019-04-19 华南理工大学 A kind of multifactor Short-time Traffic Flow Forecasting Methods
CN109785629A (en) * 2019-02-28 2019-05-21 北京交通大学 A kind of short-term traffic flow forecast method
CN109887272A (en) * 2018-12-26 2019-06-14 阿里巴巴集团控股有限公司 A kind of prediction technique and device of traffic flow of the people
CN109886444A (en) * 2018-12-03 2019-06-14 深圳市北斗智能科技有限公司 A kind of traffic passenger flow forecasting, device, equipment and storage medium in short-term
CN109887290A (en) * 2019-03-30 2019-06-14 西安电子科技大学 Traffic flow forecasting method based on equilibrium index exponential smoothing and stack self-encoding encoder
CN109902880A (en) * 2019-03-13 2019-06-18 南京航空航天大学 A kind of city stream of people's prediction technique generating confrontation network based on Seq2Seq
CN109978279A (en) * 2019-04-10 2019-07-05 青岛农业大学 Marine surface temperature regional prediction method
CN109995601A (en) * 2017-12-29 2019-07-09 中国移动通信集团上海有限公司 A kind of network flow identification method and device
CN110047291A (en) * 2019-05-27 2019-07-23 清华大学深圳研究生院 A kind of Short-time Traffic Flow Forecasting Methods considering diffusion process
CN110046787A (en) * 2019-01-15 2019-07-23 重庆邮电大学 A kind of urban area charging demand for electric vehicles spatio-temporal prediction method
CN110098944A (en) * 2018-01-29 2019-08-06 中国科学院声学研究所 A method of protocol data flow is predicted based on FP-Growth and RNN
CN110148296A (en) * 2019-04-16 2019-08-20 南京航空航天大学 A kind of trans-city magnitude of traffic flow unified prediction based on depth migration study
CN110147904A (en) * 2019-04-23 2019-08-20 深圳先进技术研究院 A kind of urban agglomerations event prediction and localization method and device
CN110164127A (en) * 2019-04-04 2019-08-23 中兴飞流信息科技有限公司 A kind of method, apparatus and server of vehicle flowrate prediction
CN110188263A (en) * 2019-05-29 2019-08-30 国网山东省电力公司电力科学研究院 It is a kind of towards isomery when away from scientific research hotspot prediction method and system
CN110310474A (en) * 2018-05-14 2019-10-08 桂林远望智能通信科技有限公司 A kind of vehicle flowrate prediction technique and device based on space-time residual error network
CN110335466A (en) * 2019-07-11 2019-10-15 青岛海信网络科技股份有限公司 Traffic flow forecasting method and equipment
CN110398369A (en) * 2019-08-15 2019-11-01 贵州大学 A kind of Fault Diagnosis of Roller Bearings merged based on 1-DCNN and LSTM
CN110414747A (en) * 2019-08-08 2019-11-05 东北大学秦皇岛分校 A kind of space-time shot and long term urban human method for predicting based on deep learning
CN110570035A (en) * 2019-09-02 2019-12-13 上海交通大学 people flow prediction system for simultaneously modeling space-time dependency and daily flow dependency
CN110766942A (en) * 2019-10-18 2020-02-07 北京大学 Traffic network congestion prediction method based on convolution long-term and short-term memory network
CN110929962A (en) * 2019-12-13 2020-03-27 中国科学院深圳先进技术研究院 Traffic flow prediction method and device based on deep learning
CN111009129A (en) * 2020-01-08 2020-04-14 武汉大学 Urban road traffic flow prediction method and device based on space-time deep learning model
CN111260927A (en) * 2020-05-07 2020-06-09 北京航空航天大学 Road network flow prediction method
CN111371609A (en) * 2020-02-28 2020-07-03 同济大学 Internet of vehicles communication prediction method based on deep learning
CN111882869A (en) * 2020-07-13 2020-11-03 大连理工大学 Deep learning traffic flow prediction method considering adverse weather
CN111915081A (en) * 2020-08-03 2020-11-10 东北大学秦皇岛分校 Peak-sensitive travel demand prediction method based on deep learning
CN112017436A (en) * 2020-09-09 2020-12-01 中国科学院自动化研究所 Method and system for predicting urban traffic travel time
JPWO2019159585A1 (en) * 2018-02-14 2020-12-03 株式会社Ｎｔｔドコモ Learning system, estimation system and trained model
CN112396837A (en) * 2020-11-13 2021-02-23 重庆中信科信息技术有限公司 Congestion area vehicle source path analysis method and system based on traffic big data
CN112561174A (en) * 2020-12-18 2021-03-26 西南交通大学 Method for predicting geothermal energy production based on LSTM and MLP superimposed neural network
CN112613630A (en) * 2021-01-05 2021-04-06 大连理工大学 Short-term traffic demand prediction method integrating multi-scale space-time statistical information
CN112712695A (en) * 2020-12-30 2021-04-27 桂林电子科技大学 Traffic flow prediction method, device and storage medium
CN112862240A (en) * 2020-12-30 2021-05-28 厦门大学 Road obstacle risk assessment method and device based on urban big data and readable storage medium
CN113053123A (en) * 2021-03-23 2021-06-29 长安大学 Traffic prediction method and device based on space-time big data
CN113313303A (en) * 2021-05-28 2021-08-27 南京师范大学 Urban area road network traffic flow prediction method and system based on hybrid deep learning model
US20210303969A1 (en) * 2020-03-30 2021-09-30 Ciena Corporation Forecasting routines utilizing a mixer to combine Deep Neural Network (DNN) forecasts of multi-variate time-series datasets
CN113570004A (en) * 2021-09-24 2021-10-29 西南交通大学 Riding hot spot area prediction method, device, equipment and readable storage medium
CN113673780A (en) * 2021-09-02 2021-11-19 大连理工大学 Traffic sparse demand prediction method based on deep ensemble learning
CN113792945A (en) * 2021-11-17 2021-12-14 西南交通大学 Dispatching method, device, equipment and readable storage medium of commercial vehicle
US11238729B1 (en) * 2020-09-11 2022-02-01 Toyota Motor Engineering & Manufacturing North America, Inc. Systems and methods for traffic flow prediction
CN114187759A (en) * 2021-11-19 2022-03-15 东南大学 Road side unit driving assistance method and device based on data driving model

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101111741A (en) * 2005-01-31 2008-01-23 株式会社查纳位资讯情报 Navigation device traffic information reception method
CN101154317A (en) * 2006-09-27 2008-04-02 株式会社查纳位资讯情报 Traffic state predicting apparatus
CN105160866A (en) * 2015-08-07 2015-12-16 浙江高速信息工程技术有限公司 Traffic flow prediction method based on deep learning nerve network structure
CN105389980A (en) * 2015-11-09 2016-03-09 上海交通大学 Short-time traffic flow prediction method based on long-time and short-time memory recurrent neural network
CN106251625A (en) * 2016-08-18 2016-12-21 上海交通大学 Three-dimensional urban road network global state Forecasting Methodology under big data environment
KR101742043B1 (en) * 2016-11-15 2017-05-31 한국과학기술정보연구원 Apparatus and method for travel mode choice prediction
KR101742042B1 (en) * 2016-11-15 2017-05-31 한국과학기술정보연구원 Apparatus and method for traffic flow prediction

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101111741A (en) * 2005-01-31 2008-01-23 株式会社查纳位资讯情报 Navigation device traffic information reception method
CN101154317A (en) * 2006-09-27 2008-04-02 株式会社查纳位资讯情报 Traffic state predicting apparatus
CN105160866A (en) * 2015-08-07 2015-12-16 浙江高速信息工程技术有限公司 Traffic flow prediction method based on deep learning nerve network structure
CN105389980A (en) * 2015-11-09 2016-03-09 上海交通大学 Short-time traffic flow prediction method based on long-time and short-time memory recurrent neural network
CN106251625A (en) * 2016-08-18 2016-12-21 上海交通大学 Three-dimensional urban road network global state Forecasting Methodology under big data environment
KR101742043B1 (en) * 2016-11-15 2017-05-31 한국과학기술정보연구원 Apparatus and method for travel mode choice prediction
KR101742042B1 (en) * 2016-11-15 2017-05-31 한국과학기술정보연구원 Apparatus and method for traffic flow prediction

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
YONGXUE TIAN等: "Predicting Short-term Traffic Flow by Long Short-Term Memory Recurrent Neural Network", 《COMPUTER SOCIETY》 *
尹邵龙 等: "深度学习在城市交通流预测中的实践研究", 《现代电子技术》 *

Cited By (93)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107967532A (en) * 2017-10-30 2018-04-27 厦门大学 The Forecast of Urban Traffic Flow Forecasting Methodology of integration region vigor
CN107967532B (en) * 2017-10-30 2020-07-07 厦门大学 Urban traffic flow prediction method fusing regional vitality
CN109995601A (en) * 2017-12-29 2019-07-09 中国移动通信集团上海有限公司 A kind of network flow identification method and device
CN109995601B (en) * 2017-12-29 2020-12-01 中国移动通信集团上海有限公司 Network traffic identification method and device
CN108364087A (en) * 2018-01-11 2018-08-03 安徽优思天成智能科技有限公司 A kind of spatio-temporal prediction method of urban mobile tail gas concentration
CN108053653A (en) * 2018-01-11 2018-05-18 广东蔚海数问大数据科技有限公司 Vehicle behavior Forecasting Methodology and device based on LSTM
CN110098944B (en) * 2018-01-29 2020-09-08 中国科学院声学研究所 Method for predicting protocol data traffic based on FP-Growth and RNN
CN110098944A (en) * 2018-01-29 2019-08-06 中国科学院声学研究所 A method of protocol data flow is predicted based on FP-Growth and RNN
CN108280441A (en) * 2018-02-09 2018-07-13 北京天元创新科技有限公司 A kind of crowd's method for predicting and system
JPWO2019159585A1 (en) * 2018-02-14 2020-12-03 株式会社Ｎｔｔドコモ Learning system, estimation system and trained model
CN108399745A (en) * 2018-03-01 2018-08-14 北京航空航天大学合肥创新研究院 A kind of city road network trend prediction method at times based on unmanned plane
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
CN108564228A (en) * 2018-04-26 2018-09-21 重庆大学 A method of based on the temporal aspect predicted orbit traffic OD volumes of the flow of passengers
CN110310474A (en) * 2018-05-14 2019-10-08 桂林远望智能通信科技有限公司 A kind of vehicle flowrate prediction technique and device based on space-time residual error network
CN108647834A (en) * 2018-05-24 2018-10-12 浙江工业大学 A kind of traffic flow forecasting method based on convolutional neural networks structure
CN108647834B (en) * 2018-05-24 2021-12-17 浙江工业大学 Traffic flow prediction method based on convolutional neural network structure
CN108985475A (en) * 2018-06-13 2018-12-11 厦门大学 Net based on deep neural network about vehicle car service needing forecasting method
CN108876045A (en) * 2018-06-25 2018-11-23 上海应用技术大学 Emergency tender optimal route recommended method based on LSTM model prediction
CN109034460A (en) * 2018-07-03 2018-12-18 深圳市和讯华谷信息技术有限公司 Prediction technique, device and system for scenic spot passenger flow congestion level
CN108900346A (en) * 2018-07-06 2018-11-27 西安电子科技大学 Wireless network traffic prediction technique based on LSTM network
CN108900346B (en) * 2018-07-06 2021-04-06 西安电子科技大学 Wireless network flow prediction method based on LSTM network
CN109299401B (en) * 2018-07-12 2022-02-08 中国海洋大学 Metropolitan area space-time flow prediction method based on mixed deep learning model LSTM-ResNet
CN109299401A (en) * 2018-07-12 2019-02-01 中国海洋大学 Metropolitan area space-time stream Predicting Technique based on deep learning model LSTM-ResNet
CN109117987A (en) * 2018-07-18 2019-01-01 厦门大学 Personalized street accidents risks based on deep learning predict recommended method
CN109117987B (en) * 2018-07-18 2020-09-29 厦门大学 Personalized traffic accident risk prediction recommendation method based on deep learning
CN109190795B (en) * 2018-08-01 2022-02-18 中山大学 Inter-area travel demand prediction method and device
CN109190795A (en) * 2018-08-01 2019-01-11 中山大学 A kind of interregional Travel Demand Forecasting method and device
CN109165779A (en) * 2018-08-12 2019-01-08 北京清华同衡规划设计研究院有限公司 A kind of size of population prediction technique based on multi-source big data Yu shot and long term Memory Neural Networks model
CN109165779B (en) * 2018-08-12 2022-04-08 北京清华同衡规划设计研究院有限公司 Population quantity prediction method based on multi-source big data and long-short term memory neural network model
CN109087508B (en) * 2018-08-30 2021-09-21 广州市市政工程设计研究总院有限公司 High-definition bayonet data-based adjacent area traffic volume analysis method and system
CN109087508A (en) * 2018-08-30 2018-12-25 广州市市政工程设计研究总院有限公司 Contiguous zone traffic analysis method and system based on high definition bayonet data
CN109300309A (en) * 2018-10-29 2019-02-01 讯飞智元信息科技有限公司 Road condition predicting method and device
CN109544911A (en) * 2018-10-30 2019-03-29 中山大学 A kind of city road net traffic state prediction technique based on LSTM-CNN
CN109359698A (en) * 2018-10-30 2019-02-19 清华大学 Leakage loss recognition methods based on long Memory Neural Networks model in short-term
CN109359698B (en) * 2018-10-30 2020-07-21 清华大学 Leakage identification method based on long-time memory neural network model
CN109886444A (en) * 2018-12-03 2019-06-14 深圳市北斗智能科技有限公司 A kind of traffic passenger flow forecasting, device, equipment and storage medium in short-term
CN109887272A (en) * 2018-12-26 2019-06-14 阿里巴巴集团控股有限公司 A kind of prediction technique and device of traffic flow of the people
CN109887272B (en) * 2018-12-26 2021-08-13 创新先进技术有限公司 Traffic pedestrian flow prediction method and device
CN109658695A (en) * 2019-01-02 2019-04-19 华南理工大学 A kind of multifactor Short-time Traffic Flow Forecasting Methods
CN110046787A (en) * 2019-01-15 2019-07-23 重庆邮电大学 A kind of urban area charging demand for electric vehicles spatio-temporal prediction method
CN109785629A (en) * 2019-02-28 2019-05-21 北京交通大学 A kind of short-term traffic flow forecast method
CN109902880A (en) * 2019-03-13 2019-06-18 南京航空航天大学 A kind of city stream of people's prediction technique generating confrontation network based on Seq2Seq
CN109887290B (en) * 2019-03-30 2021-03-23 西安电子科技大学 Traffic flow prediction method based on balance index smoothing method and stack type self-encoder
CN109887290A (en) * 2019-03-30 2019-06-14 西安电子科技大学 Traffic flow forecasting method based on equilibrium index exponential smoothing and stack self-encoding encoder
CN110164127A (en) * 2019-04-04 2019-08-23 中兴飞流信息科技有限公司 A kind of method, apparatus and server of vehicle flowrate prediction
CN110164127B (en) * 2019-04-04 2021-06-25 中兴飞流信息科技有限公司 Traffic flow prediction method and device and server
CN109978279A (en) * 2019-04-10 2019-07-05 青岛农业大学 Marine surface temperature regional prediction method
CN109978279B (en) * 2019-04-10 2023-05-02 青岛农业大学 Ocean surface temperature area prediction method
CN110148296A (en) * 2019-04-16 2019-08-20 南京航空航天大学 A kind of trans-city magnitude of traffic flow unified prediction based on depth migration study
CN110147904A (en) * 2019-04-23 2019-08-20 深圳先进技术研究院 A kind of urban agglomerations event prediction and localization method and device
WO2020215793A1 (en) * 2019-04-23 2020-10-29 深圳先进技术研究院 Urban aggregation event prediction and positioning method and device
CN110147904B (en) * 2019-04-23 2021-06-18 深圳先进技术研究院 Urban gathering event prediction and positioning method and device
CN110047291A (en) * 2019-05-27 2019-07-23 清华大学深圳研究生院 A kind of Short-time Traffic Flow Forecasting Methods considering diffusion process
CN110188263A (en) * 2019-05-29 2019-08-30 国网山东省电力公司电力科学研究院 It is a kind of towards isomery when away from scientific research hotspot prediction method and system
CN110188263B (en) * 2019-05-29 2021-11-30 国网山东省电力公司电力科学研究院 Heterogeneous time interval-oriented scientific research hotspot prediction method and system
CN110335466A (en) * 2019-07-11 2019-10-15 青岛海信网络科技股份有限公司 Traffic flow forecasting method and equipment
CN110335466B (en) * 2019-07-11 2021-01-26 青岛海信网络科技股份有限公司 Traffic flow prediction method and apparatus
CN110414747B (en) * 2019-08-08 2022-02-01 东北大学秦皇岛分校 Space-time long-short-term urban pedestrian flow prediction method based on deep learning
CN110414747A (en) * 2019-08-08 2019-11-05 东北大学秦皇岛分校 A kind of space-time shot and long term urban human method for predicting based on deep learning
CN110398369A (en) * 2019-08-15 2019-11-01 贵州大学 A kind of Fault Diagnosis of Roller Bearings merged based on 1-DCNN and LSTM
CN110570035A (en) * 2019-09-02 2019-12-13 上海交通大学 people flow prediction system for simultaneously modeling space-time dependency and daily flow dependency
CN110570035B (en) * 2019-09-02 2023-04-07 上海交通大学 People flow prediction system for simultaneously modeling space-time dependency and daily flow dependency
CN110766942B (en) * 2019-10-18 2020-12-22 北京大学 Traffic network congestion prediction method based on convolution long-term and short-term memory network
CN110766942A (en) * 2019-10-18 2020-02-07 北京大学 Traffic network congestion prediction method based on convolution long-term and short-term memory network
CN110929962A (en) * 2019-12-13 2020-03-27 中国科学院深圳先进技术研究院 Traffic flow prediction method and device based on deep learning
CN111009129B (en) * 2020-01-08 2021-06-15 武汉大学 Urban road traffic flow prediction method and device based on space-time deep learning model
CN111009129A (en) * 2020-01-08 2020-04-14 武汉大学 Urban road traffic flow prediction method and device based on space-time deep learning model
CN111371609A (en) * 2020-02-28 2020-07-03 同济大学 Internet of vehicles communication prediction method based on deep learning
US20210303969A1 (en) * 2020-03-30 2021-09-30 Ciena Corporation Forecasting routines utilizing a mixer to combine Deep Neural Network (DNN) forecasts of multi-variate time-series datasets
US11704539B2 (en) * 2020-03-30 2023-07-18 Ciena Corporation Forecasting routines utilizing a mixer to combine deep neural network (DNN) forecasts of multi-variate time-series datasets
CN111260927A (en) * 2020-05-07 2020-06-09 北京航空航天大学 Road network flow prediction method
CN111882869A (en) * 2020-07-13 2020-11-03 大连理工大学 Deep learning traffic flow prediction method considering adverse weather
CN111882869B (en) * 2020-07-13 2022-10-04 大连理工大学 Deep learning traffic flow prediction method considering adverse weather
CN111915081A (en) * 2020-08-03 2020-11-10 东北大学秦皇岛分校 Peak-sensitive travel demand prediction method based on deep learning
CN111915081B (en) * 2020-08-03 2023-10-17 东北大学秦皇岛分校 Peak sensitive travel demand prediction method based on deep learning
CN112017436A (en) * 2020-09-09 2020-12-01 中国科学院自动化研究所 Method and system for predicting urban traffic travel time
CN112017436B (en) * 2020-09-09 2021-09-28 中国科学院自动化研究所 Method and system for predicting urban traffic travel time
US11238729B1 (en) * 2020-09-11 2022-02-01 Toyota Motor Engineering & Manufacturing North America, Inc. Systems and methods for traffic flow prediction
CN112396837A (en) * 2020-11-13 2021-02-23 重庆中信科信息技术有限公司 Congestion area vehicle source path analysis method and system based on traffic big data
CN112561174A (en) * 2020-12-18 2021-03-26 西南交通大学 Method for predicting geothermal energy production based on LSTM and MLP superimposed neural network
CN112712695B (en) * 2020-12-30 2021-11-26 桂林电子科技大学 Traffic flow prediction method, device and storage medium
CN112862240A (en) * 2020-12-30 2021-05-28 厦门大学 Road obstacle risk assessment method and device based on urban big data and readable storage medium
CN112712695A (en) * 2020-12-30 2021-04-27 桂林电子科技大学 Traffic flow prediction method, device and storage medium
CN112862240B (en) * 2020-12-30 2022-05-17 厦门大学 Road obstacle risk assessment method and device based on urban big data and readable storage medium
CN112613630A (en) * 2021-01-05 2021-04-06 大连理工大学 Short-term traffic demand prediction method integrating multi-scale space-time statistical information
CN112613630B (en) * 2021-01-05 2022-09-20 大连理工大学 Short-term traffic demand prediction method integrating multi-scale space-time statistical information
CN113053123A (en) * 2021-03-23 2021-06-29 长安大学 Traffic prediction method and device based on space-time big data
CN113313303A (en) * 2021-05-28 2021-08-27 南京师范大学 Urban area road network traffic flow prediction method and system based on hybrid deep learning model
CN113673780A (en) * 2021-09-02 2021-11-19 大连理工大学 Traffic sparse demand prediction method based on deep ensemble learning
CN113570004A (en) * 2021-09-24 2021-10-29 西南交通大学 Riding hot spot area prediction method, device, equipment and readable storage medium
CN113792945B (en) * 2021-11-17 2022-02-08 西南交通大学 Dispatching method, device, equipment and readable storage medium of commercial vehicle
CN113792945A (en) * 2021-11-17 2021-12-14 西南交通大学 Dispatching method, device, equipment and readable storage medium of commercial vehicle
CN114187759A (en) * 2021-11-19 2022-03-15 东南大学 Road side unit driving assistance method and device based on data driving model

Also Published As

Publication number Publication date
CN107103758B (en) 2019-06-21

Similar Documents

Publication Publication Date Title
CN107103758B (en) A kind of city area-traffic method for predicting based on deep learning
US11270579B2 (en) Transportation network speed foreeasting method using deep capsule networks with nested LSTM models
Liu et al. Contextualized spatial–temporal network for taxi origin-destination demand prediction
Grudgings et al. Why don’t more women cycle? An analysis of female and male commuter cycling mode-share in England and Wales
CN109117987B (en) Personalized traffic accident risk prediction recommendation method based on deep learning
CN108985475A (en) Net based on deep neural network about vehicle car service needing forecasting method
CN109448361B (en) Resident traffic travel flow prediction system and prediction method thereof
CN109886444A (en) A kind of traffic passenger flow forecasting, device, equipment and storage medium in short-term
CN103747523B (en) A kind of customer location forecasting system and method based on wireless network
CN109285346A (en) A kind of city road net traffic state prediction technique based on key road segment
CN107529651A (en) A kind of urban transportation passenger flow forecasting and equipment based on deep learning
CN107766879A (en) The MLP electric network fault cause diagnosis methods of feature based information extraction
CN106910351A (en) A kind of traffic signals self-adaptation control method based on deeply study
CN109166309A (en) A kind of missing data on flows restoration methods towards complicated urban traffic network
CN107045673A (en) Public bicycles changes in flow rate amount Forecasting Methodology based on heap Model Fusion
CN108596470A (en) A kind of power equipments defect text handling method based on TensorFlow frames
CN108108808A (en) A kind of position predicting method and device based on depth belief network
CN115204478A (en) Public traffic flow prediction method combining urban interest points and space-time causal relationship
CN112071062A (en) Driving time estimation method based on graph convolution network and graph attention network
CN110210664A (en) The deep learning method of multiple individual vehicle usage behavior short-term predictions
CN115206092B (en) Traffic prediction method of BiLSTM and LightGBM models based on attention mechanism
CN114495500B (en) Traffic prediction method based on dual dynamic space-time diagram convolution
CN105976020A (en) Network flow prediction method considering wavelet cross-layer correlations
CN114692984A (en) Traffic prediction method based on multi-step coupling graph convolution network
Li et al. Urban travel behavior study based on data fusion model

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