CN110956808B - Heavy truck traffic flow prediction method based on non-full-sample positioning data - Google Patents
Heavy truck traffic flow prediction method based on non-full-sample positioning data Download PDFInfo
- Publication number
- CN110956808B CN110956808B CN201911336098.7A CN201911336098A CN110956808B CN 110956808 B CN110956808 B CN 110956808B CN 201911336098 A CN201911336098 A CN 201911336098A CN 110956808 B CN110956808 B CN 110956808B
- Authority
- CN
- China
- Prior art keywords
- traffic flow
- data
- road
- flow
- time
- 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.)
- Expired - Fee Related
Links
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
Abstract
The invention relates to a heavy truck traffic flow prediction method based on non-full-sample positioning data, and provides a scheme of firstly expanding samples and then predicting aiming at the problem that GPS traffic flow is not full. A segmentation constant coefficient method determined by flow self-distribution is provided in the sample expansion method, a long-time and short-time recurrent neural network (LSTM) model capable of solving the long-time memory problem is provided in the prediction method, and the purpose that the traffic flow of the heavy truck is closer to the actual flow is achieved. The invention overcomes the defect of low acquisition precision of traditional coils and video flow during data acquisition, adopts GPS data of a satellite positioning device to predict traffic flow, and has higher precision. The invention provides a more comprehensive and comprehensive method for predicting the traffic flow of the heavy truck, and can play an active role in relieving urban traffic jam and improving the operation efficiency of urban traffic. The method has practical application value in engineering, and can be migrated and applied in related fields.
Description
Technical Field
The invention relates to the field of intelligent transportation, in particular to a heavy goods vehicle traffic flow prediction method based on non-full-sample positioning data.
Background
The traffic flow prediction is used as an important research content of an intelligent traffic system, and the accuracy and the real-time performance of the traffic flow prediction play an important role in relieving traffic jam and the like. The traditional traffic flow prediction method is mainly used for passenger cars, and deep discussion is rarely made for the flow prediction of heavy trucks. In addition, the conventional passenger car flow data acquisition mainly comprises coil detection and video detection, so that the problems of inaccurate vehicle type detection and missing flow counting often exist, and meanwhile, the problem that all lanes cannot be detected comprehensively is solved. The national road transport vehicle dynamic supervision and management method in 2014 requires that a satellite positioning device must be installed on each truck and a corresponding monitoring platform must be accessed to each truck for heavy trucks of more than 12 tons. Therefore, in the traffic flow prediction of heavy trucks, in order to avoid the inaccuracy of the traditional traffic flow data type, more accurate GPS traffic flow data is considered.
In practice, a small part of heavy goods vehicles still have no satellite positioning device, and the situation that the device is damaged and data cannot be transmitted in real time exists. Therefore, a new method needs to be introduced to repair the traffic flow data quality, and sample expansion and traffic flow prediction are performed on the GPS traffic flow, so that the traffic flow of the heavy truck is closer to the actual flow.
Disclosure of Invention
In order to overcome the problems, the invention aims to provide a heavy truck traffic flow prediction method based on non-full-scale positioning data.
The invention achieves the aim by the following method:
a heavy goods vehicle traffic flow prediction method based on non-full-scale positioning data comprises the following steps:
step 1: acquiring heavy truck GPS data based on a vehicle-mounted satellite positioning device;
step 2: merging the GPS data with the position of the road section according to the designated time interval to obtain the traffic flow;
and step 3: and (3) performing sample expansion on the traffic flow obtained after the merging in the step (2) by adopting a piecewise constant coefficient method according to the road grade and the flow range.
And 4, step 4: and carrying out standardization processing on the data after sample expansion.
And 5: and predicting the traffic flow by using the long-time and short-time cyclic neural network model.
Step 6: and performing anti-standardization processing on the predicted traffic flow.
And 7: and comparing the denormalized data with the traffic survey data.
And 8: and adjusting the traffic flow of the heavy truck by adopting a total control method.
On the basis of the above scheme, the GPS data in step 1 includes: recording time, longitude, latitude and license plate number;
on the basis of the above scheme, the step 2 specifically includes: the urban road network is numbered to form road section IDs, GPS data is aggregated for each road section ID according to a specified time interval, and traffic flow data with road section attributes and time interval attributes is formed.
On the basis of the scheme, the specified time interval in the step 2 is 1 h.
On the basis of the scheme, the road grade in the step 3 comprises a highway grade and an urban road grade, and 10 grades are subdivided from the highway grade and the urban road grade;
the road grade includes: freeways, first-level highways, second-level highways, third-level highways and fourth-level highways;
the urban road grade includes: express way, main road, secondary road, branch road, others, the others representing the rest of the road sections not belonging to the above-mentioned urban road class.
On the basis of the scheme, the step 3 specifically comprises the following steps:
step 31: totaling all road section traffic flows according to time intervals;
step 32: selecting the time period of the maximum flow after the summation as a sequencing basis, and sequencing the traffic flow of all road section IDs in a descending order;
step 33: carrying out parameter estimation on the distribution function presented by the sorted traffic flow,
yi＝ke-ax+b (1)
wherein, yiRepresenting the flow of the road section i, x representing the road section sequence after descending, and k, a and b representing the estimation parameters of the distribution function;
step 34: and (4) carrying out interval segmentation on all road sections according to the flow, and calculating sample expansion coefficients in the interval according to a probability density function.
Wherein m isi,jSerial number of road section [ i, j ]]Spread sample coefficients of the intervals. x is the number ofi，xjThe representative sequence is a link sequence number of i, j.
On the basis of the scheme, the step 4 specifically comprises the following steps: and screening all the flow of the road section ID, selecting the maximum traffic flow, and normalizing the ratio of each traffic flow to the maximum traffic flow into a [0,1] interval.
On the basis of the above scheme, step 5 specifically includes the following steps:
step 51: all traffic flow data is divided into a training set and a testing set.
Step 52: and setting parameters.
Step 53: and training and adjusting parameters of the model, and training the model to an optimal state.
Step 54: and predicting the traffic flow of the heavy truck, predicting the data of the test set by using the trained model, and evaluating the effect of the model by using a Mean Absolute Error (MAE), a percentage error (MAPE), a Root Mean Square Error (RMSE) and an explained variance fraction (EVS).
The Explained Variance Score (EVS) calculation formula is:
wherein, YtFor the traffic flow data at time t,
is predicted traffic flow data at time t.
On the basis of the above scheme, the parameters of step 52 include: hidden layer units size, time step size, sample size per input, activation function, loss function, loop step number epotch.
The invention has the beneficial effects that:
the non-full-sample heavy truck traffic flow prediction method can overcome the defects of the traditional traffic flow acquisition equipment, and can accurately depict the actual quantity of the future traffic flow by using GPS traffic flow data as a support through sample expansion and prediction dual means from the aspect of engineering practice. Technical support and theoretical reference are provided for relieving traffic jam of the heavy truck and improving road running conditions.
Drawings
The invention has the following drawings:
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a graph of traffic flow at 24 hours;
FIG. 3 is a graph of a traffic flow sequenced index profile;
FIG. 4 is a graph of the predicted effect of the long and short recurrent neural networks LSTM;
FIG. 5 is a schematic diagram comparing original GPS data, sample expansion data, predicted data after sample expansion and traffic survey data.
Detailed Description
The present invention will be described in further detail with reference to the accompanying fig. 1-5 and the embodiments.
The invention relates to a heavy goods vehicle traffic flow prediction method based on non-full-scale positioning data, which mainly comprises the following steps:
step 1: acquiring GPS data of a heavy truck in Zhengzhou city based on a vehicle-mounted satellite positioning device, wherein the content comprises recording time, longitude, latitude and license plate number;
step 2: merging the GPS data with the position of the road section according to the designated time interval; specifically, the urban road network is numbered to form road section IDs, GPS data is aggregated for each road section ID according to a specified time interval, and traffic flow data with road section attributes and time interval attributes is formed.
Sample protocols are shown in table 1:
TABLE 1 sample of integrated GPS traffic flow data
And step 3: and carrying out sample expansion on the merged traffic flow by adopting a piecewise constant coefficient method according to the road grade and the flow range.
The road grade includes a highway grade and an urban road grade, and 10 grades are subdivided from the highway grade and the urban road grade.
The grades of the road include: freeways, first-level highways, second-level highways, third-level highways and fourth-level highways;
the grade of the urban road comprises: express way, main road, secondary road, branch road, others, the others representing the rest of the road sections not belonging to the above-mentioned urban road class.
The step 3 specifically comprises the following steps:
step 31: totaling all road section traffic flows according to time intervals;
step 32: the time period of the summed maximum flow is selected, as shown in fig. 2, with the flow at the abscissa time "17" being the maximum.
Step 33: taking the traffic flow of all the road section IDs as a sorting basis at the time '17', and sorting in a descending order, as shown in the attached figure 3;
step 34: figure 3 shows parameter estimation of an exponential distribution function presented by the sorted traffic flows,
yi＝ke-ax+b (1)
wherein, yiThe flow rate of the link i is represented, x represents the link sequence after descending, k, a and b represent parameters, and the estimated parameters k, a and b in fig. 3 are 555.17, 0.013 and 0, respectively.
And step 35, performing interval segmentation on all road sections according to the flow. The intervals are (1, 100], (100, 200], (200, 300], (300, 417) in descending order of the numbers.
And step 36, calculating sample expansion coefficients in the interval according to the probability density function.
Wherein m isi,jSerial number of road section [ i, j ]]Spread sample coefficients of the intervals.
The probability density of each freight car flow interval shown in FIG. 3 is
The ratio of the flow of the cargo vehicles in the four intervals is as follows:
sample expansion coefficients of four intervals are obtained, and are respectively: 72.68%, 19.72%, 5.39%, 2.21%.
(4) And 4, step 4: and carrying out standardization processing on the data after sample expansion. And screening all the flow of the road section ID, selecting the maximum traffic flow, and normalizing the ratio of each traffic flow to the maximum traffic flow into a [0,1] interval.
And 5: and (3) utilizing a long-time and short-time recurrent neural network (LSTM) model to predict the traffic flow.
The specific steps of the step 5 are as follows:
step 51: all traffic flow data is divided into a training set and a testing set. In this case, data No. 11/28 in 2018 of a heavy truck in zhengzhou city is taken as a training set, and data No. 12/01 in 2018 is taken as a testing set.
Step 52: the long and short time circulation neural network (LSTM) model is different from a conventional neuron in storage unit, and each storage unit is composed of an input gate, an output gate and a forgetting gate. The calculation formulas of the LSTM input gate, the LSTM output gate and the LSTM forgetting gate are as follows:
an input gate: i.e. it＝σ(ωmimt+ωhiht-1+ωcict-1+bi) (3)
Forget the door: f. oft＝σ(ωmfmt+ωhfht-1+ωcfct-1+bi) (4)
An output gate: ot＝σ(ωmoxt+ωhoht-1+ωcoct+bo) (5)
Wherein it、ft、otRespectively representing input gate output, forgetting gate output and output gate output, mtAn input representing time t; h ist-1Representing the output value of the hidden layer at the moment before t; c. Ct-1An output value representing the intermediate state of the hidden layer at a time immediately before t; c. CtAn output value representing an intermediate state of the hidden layer; omegami、ωhi、ωciRespectively an input gate and mtWeight, input gate and ht-1Weight, input gate and ct-1The weight of (2); omegamf、ωhf、ωcfRespectively a forgetting gate and mtWeight, forget gate and ht-1Weight, forget gate and ct-1The weight of (2); omegamo、ωho、ωcoRespectively an output gate and mtWeight, output gate and ht-1Weight, output gate and ct-1The weight of (2); bi、boAll represent bias terms;
step 53: and setting parameters.
The setting includes: hidden layer units size, time step size, sample size per input, activation function, loss function, loop step number epotch.
Step 54: and training and adjusting parameters of the model, and training the model to an optimal state. For this training data, the optimal parameters of the model are hidden layer units of 5, time step of 5, batch _ size of 1, loss function loss of MAE, loop step number epotch of 100, and activation function of tanh.
Step 55: and predicting the traffic flow of the heavy truck, predicting the data of the test set by using the trained model, and evaluating the effect of the model by using a Mean Absolute Error (MAE), a percentage error (MAPE), a Root Mean Square Error (RMSE) and an explained variance fraction (EVS).
The EVS calculation formula is as follows:
wherein, YtFor the traffic flow data at time t,
is predicted traffic flow data at time t.
Step 56: the evaluation parameters obtained in this case are shown in table 2.
TABLE 2 evaluation of long-and-short-term recurrent neural network model prediction effectiveness
The closer the Explained Variance Score (EVS) is to 1, the better the fitting of the model. The prediction effect of the case shows that the EVS is 0.94 and is close to 1, and the model fitting effect is good. The effect of the predicted value and the original value of the GPS data with the link number ID of 3423864 is shown in fig. 4. The first 5 hours were used to predict the sixth hour and the values of the evaluation parameters are shown in Table 3.
TABLE 3 evaluation parameters for road segment ID 3423864
Step 6: and performing anti-standardization processing on the predicted traffic flow.
And 7: and comparing the denormalized data with the traffic survey data.
FIG. 5 is a schematic diagram comparing original GPS data, sample expansion data, predicted data after sample expansion, and traffic survey data.
It is analyzed from fig. 5 that the predicted traffic flow data after sample expansion more closely approximates traffic survey data.
And 8: and adjusting the traffic flow of the heavy truck by adopting a total control method.
While embodiments of the invention have been described in detail, it is not intended to be limited to the details of the embodiments set forth, and that various equivalents may be made within the spirit and scope of the invention.
Those not described in detail in this specification are within the skill of the art.
Claims (8)
1. A heavy goods vehicle traffic flow prediction method based on non-full-scale positioning data is characterized by comprising the following steps:
step 1: acquiring heavy truck GPS data based on a vehicle-mounted satellite positioning device;
step 2: merging the GPS data with the position of the road section according to the designated time interval to obtain the traffic flow;
and step 3: carrying out sample expansion on the traffic flow obtained after merging in the step 2 by adopting a piecewise constant coefficient method according to the road grade and the flow range;
and 4, step 4: carrying out standardization processing on the data after sample expansion;
and 5: predicting the traffic flow by utilizing a long-time and short-time cyclic neural network model;
step 6: carrying out anti-standardization processing on the predicted traffic flow;
and 7: comparing the denormalized data with traffic survey data;
and 8: adjusting the traffic flow of the heavy truck by adopting a total control method;
the step 3 specifically comprises the following steps:
step 31: totaling all road section traffic flows according to time intervals;
step 32: selecting the time period of the maximum flow after the summation as a sequencing basis, and sequencing the traffic flow of all road section IDs in a descending order;
step 33: carrying out parameter estimation on the distribution function presented by the sorted traffic flow,
yi＝ke-ax+b (1)
wherein, yiFlow rate of a road section i, x represents a road section sequence after descending, and k, a and b are generationsAn estimated parameter of the table distribution function;
step 34: all road sections are segmented according to the flow, and sample expansion coefficients in the interval are calculated according to a probability density function;
wherein m isi,jSerial number of road section [ i, j ]]Sample expansion coefficients of the intervals; x is the number ofi，xjThe representative sequence is a link sequence number of i, j.
2. The method for heavy goods vehicle traffic flow prediction based on non-global positioning data of claim 1, wherein the GPS data of step 1 comprises: record the time, longitude, latitude, and license plate number.
3. The method for predicting the traffic flow of a heavy goods vehicle based on the non-global positioning data as claimed in claim 1, wherein the step 2 specifically comprises: the urban road network is numbered to form road section IDs, GPS data is aggregated for each road section ID according to a specified time interval, and traffic flow data with road section attributes and time interval attributes is formed.
4. The method of claim 3, wherein the specified time interval of step 2 is 1 h.
5. The method for predicting the traffic flow of a heavy goods vehicle based on the non-global positioning data as claimed in claim 1, wherein the road grade in step 3 comprises a highway grade and an urban road grade, and 10 grades are subdivided from the highway grade and the urban road grade;
the road grade includes: freeways, first-level highways, second-level highways, third-level highways and fourth-level highways;
the urban road grade includes: express way, main road, secondary road, branch road, others, the others representing the rest of the road sections not belonging to the above-mentioned urban road class.
6. The heavy goods vehicle traffic flow prediction method based on the non-global positioning data as claimed in claim 1, wherein the step 4 is specifically as follows: and screening all the flow of the road section ID, selecting the maximum traffic flow, and normalizing the ratio of each traffic flow to the maximum traffic flow into a [0,1] interval.
7. The heavy goods vehicle traffic flow prediction method based on non-global positioning data as claimed in claim 1, wherein the step 5 comprises the following steps:
step 51: dividing all traffic flow data into a training set and a testing set;
step 52: setting parameters;
step 53: training and parameter adjustment of the model, and training the model to an optimal state;
step 54: predicting the traffic flow of the heavy truck, predicting the data of the test set by the trained model, and evaluating the effect of the model by adopting average absolute error, percentage error, root mean square error and explanation variance fraction;
the interpretation variance score calculation formula is:
wherein, YtFor the traffic flow data at time t,
is predicted traffic flow data at time t.
8. The method of claim 7 wherein the parameters of step 52 comprise: hidden layer size, time step, number of samples input each time, activation function, loss function, number of loop steps.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911336098.7A CN110956808B (en) | 2019-12-23 | 2019-12-23 | Heavy truck traffic flow prediction method based on non-full-sample positioning data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911336098.7A CN110956808B (en) | 2019-12-23 | 2019-12-23 | Heavy truck traffic flow prediction method based on non-full-sample positioning data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110956808A CN110956808A (en) | 2020-04-03 |
| CN110956808B true CN110956808B (en) | 2020-11-24 |
Family
ID=69983383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911336098.7A Expired - Fee Related CN110956808B (en) | 2019-12-23 | 2019-12-23 | Heavy truck traffic flow prediction method based on non-full-sample positioning data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110956808B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112767690B (en) * | 2020-12-27 | 2022-03-29 | 交通运输部规划研究院 | Regional road network heavy truck traffic estimation method based on section survey data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101127040A (en) * | 2007-09-14 | 2008-02-20 | 东南大学 | Highway origin-destination traffic flow character extraction method |
| CN102289932A (en) * | 2011-06-17 | 2011-12-21 | 同济大学 | Dynamic OD (Origin Destination) matrix estimating method based on AVI (Automatic Vehicle Identification) device |
| CN104731853A (en) * | 2014-12-18 | 2015-06-24 | 东南大学 | Public transport passenger flow spatial and temporal distribution simulation method and simulation system based on individual activity chain |
| CN107123265A (en) * | 2017-06-12 | 2017-09-01 | 东南大学 | A kind of traffic status of express way method of estimation based on parallel computation |
| CN108629972A (en) * | 2018-05-07 | 2018-10-09 | 广州市交通规划研究院 | A kind of resident trip survey synthesis expansion sample check method being combined based on big data and conventional method |
| CN109800916A (en) * | 2019-01-23 | 2019-05-24 | 山东省交通规划设计院 | The modeling method of vehicle flowrate is driven into a kind of Expressway Service |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6282486B1 (en) * | 2000-04-03 | 2001-08-28 | International Business Machines Corporation | Distributed system and method for detecting traffic patterns |
| US20100262901A1 (en) * | 2005-04-14 | 2010-10-14 | Disalvo Dean F | Engineering process for a real-time user-defined data collection, analysis, and optimization tool (dot) |
| CN102097004B (en) * | 2011-01-31 | 2013-02-20 | 上海美慧软件有限公司 | Mobile phone positioning data-based traveling origin-destination (OD) matrix acquisition method |
| CN105513351A (en) * | 2015-12-17 | 2016-04-20 | 北京亚信蓝涛科技有限公司 | Traffic travel characteristic data extraction method based on big data |
| CN108921465A (en) * | 2018-06-11 | 2018-11-30 | 华南理工大学 | A kind of network of highways cargo transport index automation statistical method |
| CN110264709B (en) * | 2019-05-06 | 2021-02-12 | 北京交通大学 | Method for predicting traffic flow of road based on graph convolution network |
| CN110516833A (en) * | 2019-07-03 | 2019-11-29 | 浙江工业大学 | A method of the Bi-LSTM based on feature extraction predicts road traffic state |
| CN110288170B (en) * | 2019-07-29 | 2020-04-14 | 重庆电子工程职业学院 | Prediction model construction method, traffic flow prediction device and electronic equipment |
| CN110545558B (en) * | 2019-09-06 | 2023-03-28 | 山东省交通规划设计院集团有限公司 | High-speed service area crowd density estimation system based on Wi-Fi data |
-
2019
- 2019-12-23 CN CN201911336098.7A patent/CN110956808B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101127040A (en) * | 2007-09-14 | 2008-02-20 | 东南大学 | Highway origin-destination traffic flow character extraction method |
| CN102289932A (en) * | 2011-06-17 | 2011-12-21 | 同济大学 | Dynamic OD (Origin Destination) matrix estimating method based on AVI (Automatic Vehicle Identification) device |
| CN104731853A (en) * | 2014-12-18 | 2015-06-24 | 东南大学 | Public transport passenger flow spatial and temporal distribution simulation method and simulation system based on individual activity chain |
| CN107123265A (en) * | 2017-06-12 | 2017-09-01 | 东南大学 | A kind of traffic status of express way method of estimation based on parallel computation |
| CN108629972A (en) * | 2018-05-07 | 2018-10-09 | 广州市交通规划研究院 | A kind of resident trip survey synthesis expansion sample check method being combined based on big data and conventional method |
| CN109800916A (en) * | 2019-01-23 | 2019-05-24 | 山东省交通规划设计院 | The modeling method of vehicle flowrate is driven into a kind of Expressway Service |
Non-Patent Citations (1)
| Title |
|---|
| 居民出行调查数据扩样方法研究;马小毅;《交通运输工程与信息学报》;20100331;正文第1-7页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110956808A (en) | 2020-04-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107330217B (en) | Mesoscopic oil consumption prediction method based on RBFNN | |
| CN111583628B (en) | Road network heavy truck traffic flow prediction method based on data quality control | |
| CN110197588A (en) | A kind of truck driving behavior appraisal procedure and device based on GPS track data | |
| Lin et al. | A review of travel-time prediction in transport and logistics | |
| CN111539454B (en) | Vehicle track clustering method and system based on meta-learning | |
| CN109002622B (en) | Method for estimating overall load response of large-span bridge under random traffic flow effect | |
| CN114187766B (en) | Road service level evaluation method based on saturation rate | |
| CN106649709B (en) | Vehicle stopping behavior pattern prediction and evaluation method based on data mining | |
| CN114783183A (en) | Monitoring method and system based on traffic situation algorithm | |
| CN115240431A (en) | Real-time online simulation system and method for traffic flow of highway toll station | |
| CN105869402B (en) | Express highway section speed modification method based on polymorphic type floating car data | |
| CN115691120A (en) | Congestion identification method and system based on highway running water data | |
| CN106845768A (en) | Bus hourage model building method based on survival analysis parameter distribution | |
| CN111612670A (en) | Method and device for constructing motor vehicle emission list and computer equipment | |
| CN109493449B (en) | Freight train cargo state estimation method based on freight train GPS track data and high-speed transaction data | |
| CN106023592A (en) | Traffic jam detection method based on GPS data | |
| CN114881356A (en) | Urban traffic carbon emission prediction method based on particle swarm optimization BP neural network optimization | |
| CN113449905A (en) | Traffic jam early warning method based on gated cyclic unit neural network | |
| CN109979194B (en) | Heavy vehicle ramp crawling behavior identification method based on Markov chain | |
| CN110956808B (en) | Heavy truck traffic flow prediction method based on non-full-sample positioning data | |
| Cunillera et al. | Real-time train motion parameter estimation using an unscented Kalman filter | |
| CN112767686B (en) | Road network automobile emission estimation method based on multi-source data fusion | |
| CN111680888B (en) | Method for determining road network capacity based on RFID data | |
| CN110264725B (en) | Method and device for determining road section flow | |
| CN111640294A (en) | Method for predicting passenger flow change of urban bus line under influence of newly-built subway line |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20201124 Termination date: 20211223 |