CN115035715B - Expressway flow prediction method based on decision tree and multi-element auxiliary information - Google Patents
Expressway flow prediction method based on decision tree and multi-element auxiliary information Download PDFInfo
- Publication number
- CN115035715B CN115035715B CN202210588240.2A CN202210588240A CN115035715B CN 115035715 B CN115035715 B CN 115035715B CN 202210588240 A CN202210588240 A CN 202210588240A CN 115035715 B CN115035715 B CN 115035715B
- Authority
- CN
- China
- Prior art keywords
- information
- time
- flow
- decision tree
- feature
- 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.)
- Active
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
- G08G1/0133—Traffic data processing for classifying traffic situation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
-
- 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
- G08G1/015—Detecting movement of traffic to be counted or controlled with provision for distinguishing between two or more types of vehicles, e.g. between motor-cars and cycles
-
- 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
- G08G1/048—Detecting movement of traffic to be counted or controlled with provision for compensation of environmental or other condition, e.g. snow, vehicle stopped at detector
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a highway flow prediction method based on decision trees and multi-element auxiliary information. The method comprises the steps of firstly establishing a multi-element auxiliary information time sequence of a multi-scale time span, learning characteristic representation of information such as flow and weather by using an LSTM model perceived by multi-element information, then establishing a time sequence with multi-element information, training the model by using a gradient lifting decision tree, and improving accuracy of flow prediction in a highway scene. The invention constructs a data set of multi-element information by using a real expressway microwave vehicle detector and a meteorological detector data set, comprehensively considers various characteristic factors influencing traffic flow by using a sliding window, predicts the flow in an expressway scene by using a model based on a gradient lifting decision tree, and has higher accuracy.
Description
Technical Field
The invention belongs to the field of data mining and intelligent traffic, and particularly relates to a highway flow prediction method based on decision trees and multi-element auxiliary information.
Background
In recent years, china has achieved historical achievements in transportation, wherein according to data of China department of transportation, the mileage of China expressway reaches 16.10 ten thousand kilometers by the year 2020, and the first place in the world. With the rapid development of economy, the number of motor vehicles in China is rapidly increased, and the difficulty of daily maintenance, congestion management and other works of high-speed management departments is increasing. In order to alleviate the management difficulty, more and more intelligent sensor devices such as microwave car detectors are installed on expressway sections for recording data such as total traffic flow, average speed, average distance between cars, average length of cars and traffic flow of small, medium and large car types in a fixed time period. The recorded data can reflect the current traffic flow rule of the expressway, and is an important basis for providing scientific decisions for high-speed management departments.
At present, researchers at home and abroad do a lot of valuable research work on road flow prediction. Existing road traffic prediction algorithms are mainly divided into two categories based on time series data: a model based on statistical learning and a model based on machine learning. The related statistics learning method comprises differential autoregressive moving average (ARIMA), kalman filtering, linear regression and the like, and the machine learning method comprises a support vector machine (Support Vector Machine, SVM), a K-Nearest Neighbor algorithm (K-Nearest Neighbor), a gradient lifting decision tree (XGBoost) and the like. In addition, with the rapid development of deep learning, there are also some studies to use neural network models such as a recurrent neural network (Recurrent Neural Network, RNN) and a convolutional neural network (Convolutional Neural Network, CNN) to improve the accuracy of road traffic prediction. For example, long-short-term memory (LSTM) network can capture the time series characteristics in longer time span with better performance by introducing memory units (memory units) without attenuating the existing information with the increase of time series.
However, the time sequence of the expressway traffic is often a result of the combined action of multiple factors, and it is difficult to provide high-accuracy traffic prediction only by means of the historical data of the road traffic, so that the road management department cannot acquire data support for predicting the future road traffic condition. Meanwhile, the traffic data of the expressway has the following characteristics, so that the prediction process is more challenging: 1) The flow is greatly influenced by factors such as time, holidays, meteorological conditions and the like, the prediction difficulty is high, and 2) the facilities of the microwave vehicle detector are not perfect and operate unstably, a large number of missing or independent records exist, and the accuracy of flow prediction is influenced. Most of the existing road traffic prediction methods are aimed at urban road scenes, and lack of traffic prediction methods for application scenes of highways.
Disclosure of Invention
Aiming at the problems of difficult flow prediction and low accuracy caused by various complex factors and a large number of missing traffic detector flow records in the expressway scene, the invention provides the expressway flow prediction method based on the decision tree and the multi-element auxiliary information.
The method comprises the following specific steps:
and (1) taking the pluripotency of the flow prediction factors under the expressway scene into consideration, and collecting the data of the microwave vehicle detector and the meteorological instrument detector of the expressway section to construct a pluripotency auxiliary information data set.
And (2) carrying out feature extraction and data preprocessing on the basis of the step (1), wherein the method comprises the following substeps:
step (2.1) extracting the total traffic flow tr of the expressway lane level t Traffic flow tr for distinguishing small, medium and large vehicle types s 、tr m 、tr l Average vehicle speed s, average vehicle length l, etc.;
step (2.2) extracting meteorological instrument detection information including visibility w in a certain range of a high-speed road section v Degree of road surface wet skid w p ；
Extracting time features based on the information acquisition time stamp, including time period features ti h Date feature ti d Week characteristics ti w Month characteristics ti m 。
Step (3) setting the sliding window sizes of different time spans based on the step (2), and constructing the time of different types of informationThe sequence, LSTM (Long Short-Term Memory) model of the multi-element information perception is combined to perform characteristic learning on the time sequence, and characteristic representation of the multi-element information is obtained; wherein the traffic flow information after feature fusion is expressed as tr' t ，tr′ s ，tr′ m ，tr′ l S ', l ' weather information is expressed as w ' v ，w′ p The time information is expressed as ti' h ，ti′ d ，ti′ w ，ti′ m 。
Step (4) considering the problems of unstable operation of facilities such as microwave car detectors and the like in expressway scenes and a large number of defects or independent records, the invention provides a method for establishing a characteristic sequence based on a time window, and alleviating the problems by utilizing periodic variation law characteristics, wherein the characteristic sequence based on the time window is defined as follows:
step (4.1) setting the multi-element information sequence which can be obtained at all time intervals as s 1 ，s 2 ，...，s t Wherein s is t Multiple information representing the t-th time interval, and s t Is composed of traffic flow, weather and time, i.e
And (4.1) splicing multiple information sequences of a plurality of time intervals according to time sequence based on the characteristic sequence of the time window, setting the window size as size, and the fused time sequence is as follows: s' t ＝s t-size ||s t-size+1 ||...||s t Where (a||b) denotes stitching two dimensional 12 sequences a and b into one dimensional 24 sequence.
And (5) constructing a multi-feature gradient lifting decision tree model combined with the multi-element auxiliary information based on the feature sequence based on the time window, and further training and learning the multi-element auxiliary information feature representation. The model learning objective function of the invention is:
where n represents the sample space size, y t Representing the actual flow value, the predicted flow valueIs obtained by combining a plurality of decision trees, and the calculation mode is as follows:
where K represents the number of regression trees and fk () represents the kth tree.Defined as the square loss function of the L2 regularization, reduces the probability of overfitting of the model.
And (6) a flow prediction process. And (3) inputting historical flow information, weather information and time information of the road to be predicted based on the decision tree model trained in the step (5). The flow information comprises total vehicle flow, vehicle flow for distinguishing small, medium and large vehicle types, average vehicle speed and average vehicle length; the meteorological information comprises road section visibility and road surface wet and slippery degree; the time information includes a time period (hour), a date, a week, and a month. And inputting the data into a decision tree model to obtain a flow prediction result.
The invention has the beneficial effects that:
the accuracy of flow prediction is low by using a historical flow time sequence as input in many works, and the influence of time context, weather context and other multiple information is easily ignored.
The invention constructs a data set of multi-element information by using a real expressway microwave vehicle detector and a meteorological detector data set, comprehensively considers various characteristic factors influencing traffic flow by using a sliding window, predicts the flow in an expressway scene by using a model based on a gradient lifting decision tree, and has higher accuracy.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a schematic diagram of a multi-element auxiliary information extraction module;
fig. 3. A sliding window schematic based on time span.
Detailed Description
The method for predicting the expressway traffic based on the decision tree and the multi-element auxiliary information is specifically described below.
As shown in fig. 1, the specific steps of the present invention are as follows:
step (1) input: taking the pluralism of influence flow prediction factors in expressway scenes into consideration, acquiring the data of microwave vehicle detectors and meteorological instrument detectors of expressway sections to construct a pluralism auxiliary information data set. The specific process is as follows:
and (1.1) recording information in the microwave vehicle detector every 5 minutes, wherein the information comprises a time stamp, the total traffic of the vehicles in the separated lanes, the traffic of the vehicles in the separated vehicles, the average vehicle speed, the average vehicle length, the average vehicle distance and the like. The weather meter detector also records information once every 5 minutes, including various weather information such as precipitation, visibility, road surface smoothness, wind speed, wind direction and the like, but many attributes have the phenomenon of missing or abnormal recorded values. Aiming at a high-speed scene, the method selects two attributes with larger influence on flow rate, namely visibility and road surface smoothness, and collects the attributes. In the expressway scene, the situation that no vehicle passes at some time or the flow is very low exists, in order to focus on the flow prediction under the normal condition, the invention performs the aggregation operation on the data acquired in 5 minutes, namely, 12 recording points (1 hour) are taken as a group of data taking the average value as a time point, and a data set is constructed on the basis.
And (2) carrying out feature extraction and data preprocessing on the basis of the step (1), wherein the method comprises the following substeps:
step (2.1) extracting the total traffic flow tr of the expressway lane level t Traffic flow tr for distinguishing small, medium and large vehicle types s 、tr m 、tr 1 Average vehicle speed s, average vehicle length l. For the attribute, filling data in a mode of adopting a smooth average value to the missing value or the abnormal value;
step (2.2) extracting weather information including visibility w in a certain range of the high-speed road section v Degree of road surface wet skid w p . For the attribute, filling data in a mode of adopting a smooth average value to the missing value or the abnormal value;
extracting time features based on the information acquisition time stamp, including time period features ti h Date feature ti d Week characteristics ti w Month characteristics ti m 。
And (3) setting the sliding window sizes of different time spans on the basis of the step (2), constructing time sequences of different types of information, and carrying out feature learning on the time sequences by combining with an LSTM model perceived by the multi-element information to obtain the feature representation of the multi-element information. The specific steps are as follows:
step (3.1) for traffic information and weather information, such as total traffic flow tr per time interval t The size of the time sliding window is divided by two time spans of day and week respectively, flow time sequences of different time spans are constructed, and for the part with the length smaller than the size of the window, the average value of all flows is used for filling.
Step (3.2) the time series length is set as T, and the time series lengths of the spans of days and weeks are 24 and 168 respectively. The time series construction process is shown in fig. 3. For total traffic flow tr t Traffic flow tr for distinguishing small, medium and large vehicle types s 、tr m 、tr l Average vehicle speed s, average vehicle length l, and weather feature visibility w v Degree of road surface wet skid w p Respectively as inputs x of LSTM model t The characteristic learning is carried out, and the process is as follows:
wherein (-) represents the feature learning result in the case of two spans, take on values d (days) and w (weeks),andthe input at this time and the output at the previous time of the model are represented respectively. />Respectively representing an input door, a forget door and an output door,>indicating the input state at this moment,/->Representing the memory state of the last moment, +.>Respectively representing the memory state and the output state at the moment, W and b respectively represent different gates andthe weight matrix and bias of nonlinear activation functions sigma and tanh in the state calculation process. The input gate determines which of the current input states can be saved to the current memory state, the forget gate controls which of the memory states at the previous moment are saved to the current moment, and the output gate determines the output state at the current moment.
Through the study of the LSTM model, the characteristics expressed by the time span of days and weeks can be obtained respectivelyThe characteristic representation of the remaining attributes can be obtained according to the same processing procedure, namely: traffic flow of small, medium and large vehicle types>Average vehicle speed>Average length +.>Weather feature visibility ++>Road surface wet skid degree->
Step (3.3) fusion is performed for the characteristic representations of the two time spans as follows:
h′＝γh (d) +(1-γ)h (w)
wherein γ represents the impact weight of two time span feature representations, h' is a general representation of the information feature representation, and specifically, all the attributes in step (3.2) can be calculated, that is, the feature representations of the flow information and the weather information are finally obtained: tr' t ，tr′ s ，tr′ m ，tr′ l ，s′，l′，w′ p ，w′ v . Consider that step (3.2) and step (3.3) fuse different spansThe time information of the degree, so the result of step (2.3) is directly used as the final time feature representation: ti' h ，ti′ d ，ti′ w ，ti′ m 。
Step (4) considering the problems of unstable operation of facilities such as microwave car detectors and the like in expressway scenes and a large number of defects or independent records, the invention provides a method for establishing a characteristic sequence based on a time window, and alleviating the problems by utilizing periodic variation law characteristics, wherein the characteristic sequence based on the time window is defined as follows:
step (4.1) setting the multi-element information sequence which can be obtained at all time intervals as s 1 ，s 2 ，...，s t Wherein s is t Multiple information representing the t-th time interval, and s t Is composed of traffic flow, weather and time, i.e
And (4.1) splicing multiple information sequences of a plurality of time intervals according to time sequence based on the characteristic sequence of the time window, setting the window size as size, and the fused time sequence is as follows: s' t ＝s t-size ||s t-size+1 ||...||s t Where (a||b) denotes stitching two dimensional 12 sequences a and b into one dimensional 24 sequence.
And (5) constructing a multi-feature gradient lifting decision tree model combined with the multi-element auxiliary information based on the feature sequence based on the time window, and further training and learning the multi-element auxiliary information feature representation. The model learning objective function of the invention is:
where n represents the sample space size, y t Representing the actual flow value, the predicted flow valueIs obtained by combining a plurality of decision trees, and the calculation mode is as follows:
where K represents the number of regression trees, f k () Representing the kth tree.Defined as the square loss function of the L2 regularization, reduces the probability of overfitting of the model.
And (6) a flow prediction process. And (3) inputting historical flow information, weather information and time information of the road to be predicted based on the decision tree model trained in the step (5). The flow information comprises total vehicle flow, vehicle flow for distinguishing small, medium and large vehicle types, average vehicle speed and average vehicle length; the meteorological information comprises road section visibility and road surface wet and slippery degree; the time information includes a time period (hour), a date, a week, and a month. And inputting the data into a decision tree model to obtain a flow prediction result.
Comparing the results obtained by the method with the results obtained by other methods, and the following table is provided:
as can be seen from the table, the flow prediction accuracy in the expressway scene can be remarkably improved.
The expressway flow prediction method based on the decision tree and the multi-element auxiliary information provided by the invention can be implemented by two modules: and the multi-element auxiliary information extraction module and the gradient lifting decision tree flow prediction module.
In a certain embodiment, the multiple auxiliary information extraction module corresponds to steps (1), (2) and (3) above, as shown in fig. 2. Firstly, gathering data acquired every 5 minutes by a microwave vehicle detector, taking an average value recorded every 6 times as flow data of every half hour, simultaneously carrying out null filling and other processing on information of vehicle types, vehicle distances, vehicle speeds and the like related to flow in the records, calculating by using a recording timestamp to obtain weather information such as hours, weeks, months and the like, and detecting data by using peripheral weather instruments to obtain weather information such as visibility, road surface wet smoothness and the like. And finally, performing feature learning on time sequences of different features by utilizing the LSTM model perceived by the multivariate information to acquire flow and feature representation of the multivariate information, and using the flow and the feature representation in the next module for flow prediction.
In one embodiment, the gradient-lifting decision tree traffic prediction module corresponds to steps (4) and (5) above. The module takes multielement auxiliary information obtained by LSTM learning as input based on a flow prediction model of a gradient lifting decision tree, constructs a plurality of sub decision trees with various characteristics, and finally gathers the losses of all sub trees to obtain a final flow prediction result. In the prediction process based on the decision tree, a characteristic sequence based on a time window is constructed, and the problems that facilities such as microwave car detectors and the like in expressway scenes are unstable in operation and have a large number of defects or independent records are relieved by utilizing periodic variation rule characteristics.
Claims (8)
1. The expressway flow prediction method based on the decision tree and the multi-element auxiliary information is characterized by comprising the following steps of:
step (1), acquiring data of a microwave vehicle detector and a meteorological instrument detector of a highway section, and constructing a multi-element auxiliary information data set;
step (2), extracting features on the basis of the step (1);
step (3), setting sliding window sizes of different time spans on the basis of the step (2), constructing time sequences of different types of information, and carrying out feature learning on the time sequences by combining an LSTM model perceived by multiple information to obtain feature representation of the multiple information, wherein the multiple information relates to flow, weather and time;
step (4), establishing a characteristic sequence based on a time window, which is specifically as follows:
step (4.1), setting the multi-element information sequence which can be obtained at all time intervals as s 1 ,s 2 ,...,s t Wherein s is t Multiple information representing the t-th time interval, and s t The system consists of traffic flow, weather and time information;
step (4.2), splicing a plurality of time-interval multi-element information sequences according to time sequence based on the characteristic sequence of the time window;
step (5), constructing a multi-feature gradient lifting decision tree model combined with multi-element auxiliary information based on a feature sequence based on a time window, and further training and learning the multi-element auxiliary information feature representation;
step (6), based on the decision tree model trained in the step (5), inputting historical flow information, weather information and time information of the road to be predicted, and obtaining a flow prediction result;
the step (3) specifically comprises:
step (3.1), dividing the size of a time sliding window by two time spans of day and week for flow information and weather information respectively, and constructing flow time sequences of different time spans;
step (3.2), setting the time sequence length as T, and setting the time sequence lengths of the day and week as spans as 24 and 168 respectively;
for total traffic flow tr t Traffic flow tr for small, medium and large vehicle types s 、tr m 、tr l Average vehicle speed s, average vehicle length l, and weather feature visibility w v Degree of road surface wet skid w p Respectively performing feature learning as the input of the LSTM model;
the time span of day and week is obtained asTraffic flow of small, medium and large vehicle typesAverage vehicle speed>Average ofLength->Weather feature visibility ++>Road surface wet skid degree->
Step (3.3), fusing the characteristic representations of the two time spans to finally obtain the characteristic representations of the flow information and the meteorological information: tr t ′ ,tr s ′ ,tr ′ m ,tr l ′ ,s ′ ,l ′ ,w p ′ ,w v ′ The method comprises the steps of carrying out a first treatment on the surface of the Time characteristic representation ti ′ h ,ti ′ d ,ti ′ w ,ti ′ m 。
2. The method for predicting highway traffic based on decision tree and multivariate assistance information as set forth in claim 1, wherein: the step (1) specifically comprises:
the microwave vehicle detector records information once every 5 minutes, including a time stamp, the total traffic of the split lanes, the traffic of the split vehicle types, the average vehicle speed, the average vehicle length and the average vehicle distance;
the meteorological instrument detector records information including precipitation, visibility, road surface smoothness, wind speed and wind direction once every 5 minutes.
3. The method for predicting highway traffic based on decision tree and multivariate assistance information as set forth in claim 2, wherein: and (3) carrying out aggregation operation on the data acquired in 5 minutes, namely taking 12 record points as a group of data taking an average value as a time point, and constructing a data set on the basis.
4. The method for predicting highway traffic based on decision tree and multivariate assistance information as set forth in claim 1, wherein: the step (2) specifically comprises:
step (2.1), extracting the total traffic flow tr of the expressway lane level t Traffic flow tr for small, medium and large vehicle types s 、tr m 、tr l Average speed s, average vehicle length l;
step (2.2), extracting weather information including visibility w in a certain range of the high-speed road section v Degree of road surface wet skid w p ；
Step (2.3) of extracting time features including time period features ti based on the information acquisition time stamps h Date feature ti d Week characteristics ti w Month characteristics ti m 。
5. The method for predicting highway traffic based on decision tree and multivariate assistance information as set forth in claim 1, wherein: and (3) filling data in a mode of adopting a smooth average value to the missing value or the abnormal value in the steps (2.1) and (2.2).
6. The method for predicting highway traffic based on decision tree and multivariate assistance information as set forth in claim 1, wherein: setting the window size as size in the step (4.1), and fusing the time sequence as follows: s' t ＝s t-size ||s t-size+1 ||...||s t Where (a||b) denotes stitching two dimensional 12 sequences a and b into one dimensional 24 sequence.
7. The method for predicting highway traffic based on decision tree and multivariate assistance information as set forth in claim 1, wherein: the objective function of multi-feature gradient lifting decision tree model learning in the step (5) is as follows:
wherein n represents the sample space size，y t The value of the true flow rate is indicated,representing a flow prediction value; />Representing the square loss function of the L2 regularization.
8. The method for predicting highway traffic based on decision tree and multivariate assistance information as set forth in claim 7, wherein: the flow predicted valueIs combined by a plurality of decision trees, and the calculation mode is as follows:
where K represents the number of regression trees, f k () Represents the kth tree, s t ′ Is a fused time series.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210588240.2A CN115035715B (en) | 2022-05-26 | 2022-05-26 | Expressway flow prediction method based on decision tree and multi-element auxiliary information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210588240.2A CN115035715B (en) | 2022-05-26 | 2022-05-26 | Expressway flow prediction method based on decision tree and multi-element auxiliary information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115035715A CN115035715A (en) | 2022-09-09 |
| CN115035715B true CN115035715B (en) | 2023-08-29 |
Family
ID=83121994
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210588240.2A Active CN115035715B (en) | 2022-05-26 | 2022-05-26 | Expressway flow prediction method based on decision tree and multi-element auxiliary information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115035715B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521989A (en) * | 2011-12-31 | 2012-06-27 | 山西省交通规划勘察设计院 | Dynamic-data-driven highway-exit flow-quantity predicting method |
| WO2015037375A1 (en) * | 2013-09-12 | 2015-03-19 | 独立行政法人宇宙航空研究開発機構 | Landing decision assistance system, landing decision assistance method, and landing decision assistance program |
| WO2019176997A1 (en) * | 2018-03-14 | 2019-09-19 | 日本電気株式会社 | Traffic analysis device, method, and program |
| CN110414719A (en) * | 2019-07-05 | 2019-11-05 | 电子科技大学 | A kind of vehicle flowrate prediction technique based on Multi-variable Grey Model time series |
| CN113096388A (en) * | 2021-03-22 | 2021-07-09 | 北京工业大学 | Short-term traffic flow prediction method based on gradient lifting decision tree |
| CN114493038A (en) * | 2022-02-17 | 2022-05-13 | 四川省生态环境科学研究院 | Traffic flow estimation method for all-time all-road network |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7813870B2 (en) * | 2006-03-03 | 2010-10-12 | Inrix, Inc. | Dynamic time series prediction of future traffic conditions |
| US20070208498A1 (en) * | 2006-03-03 | 2007-09-06 | Inrix, Inc. | Displaying road traffic condition information and user controls |
-
2022
- 2022-05-26 CN CN202210588240.2A patent/CN115035715B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521989A (en) * | 2011-12-31 | 2012-06-27 | 山西省交通规划勘察设计院 | Dynamic-data-driven highway-exit flow-quantity predicting method |
| WO2015037375A1 (en) * | 2013-09-12 | 2015-03-19 | 独立行政法人宇宙航空研究開発機構 | Landing decision assistance system, landing decision assistance method, and landing decision assistance program |
| WO2019176997A1 (en) * | 2018-03-14 | 2019-09-19 | 日本電気株式会社 | Traffic analysis device, method, and program |
| CN110414719A (en) * | 2019-07-05 | 2019-11-05 | 电子科技大学 | A kind of vehicle flowrate prediction technique based on Multi-variable Grey Model time series |
| CN113096388A (en) * | 2021-03-22 | 2021-07-09 | 北京工业大学 | Short-term traffic flow prediction method based on gradient lifting decision tree |
| CN114493038A (en) * | 2022-02-17 | 2022-05-13 | 四川省生态环境科学研究院 | Traffic flow estimation method for all-time all-road network |
Non-Patent Citations (1)
| Title |
|---|
| 面向交通流量预测的时空超关系图卷积网络;张永凯 等;计算机应用;第41卷(第12期);第3578-3584页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115035715A (en) | 2022-09-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ma et al. | Multi-lane short-term traffic forecasting with convolutional LSTM network | |
| CN110223510A (en) | A kind of multifactor short-term vehicle flowrate prediction technique based on neural network LSTM | |
| CN114049765B (en) | Urban road network traffic flow OD estimation method based on automatic vehicle number plate identification data | |
| CN108648445B (en) | Dynamic traffic situation prediction method based on traffic big data | |
| CN113096388B (en) | Short-term traffic flow prediction method based on gradient lifting decision tree | |
| CN108665093B (en) | Deep learning-based expressway traffic accident severity prediction method | |
| CN108122186B (en) | Job and live position estimation method based on checkpoint data | |
| CN112613225B (en) | Intersection traffic state prediction method based on neural network cell transmission model | |
| WO2021013190A1 (en) | Meteorological parameter-based high-speed train positioning method and system in navigation blind zone | |
| CN112863182B (en) | Cross-modal data prediction method based on transfer learning | |
| CN114596700B (en) | Real-time traffic estimation method for expressway section based on portal data | |
| CN114882069A (en) | Taxi track abnormity detection method based on LSTM network and attention mechanism | |
| CN116052435B (en) | Urban road congestion influence range definition and road influence calculation method | |
| CN112767684A (en) | Highway traffic jam detection method based on charging data | |
| CN112884014A (en) | Traffic speed short-time prediction method based on road section topological structure classification | |
| CN112860782A (en) | Pure electric vehicle driving range estimation method based on big data analysis | |
| Zou et al. | The method of dynamic identification of the maximum speed limit of expressway based on electronic toll collection data | |
| CN112101132B (en) | Traffic condition prediction method based on graph embedding model and metric learning | |
| CN108710967B (en) | Expressway traffic accident severity prediction method based on data fusion and support vector machine | |
| CN115035715B (en) | Expressway flow prediction method based on decision tree and multi-element auxiliary information | |
| CN114757447B (en) | Multi-model mixed passenger transport hub station passenger flow prediction method and system | |
| CN109255956A (en) | A kind of charge station's magnitude of traffic flow method for detecting abnormality | |
| CN115271565A (en) | DEA-based method, device and equipment for evaluating highway pavement maintenance measures | |
| Loubesi et al. | Road trafficking description and short term travel time forecasting, with a classification method | |
| CN114091581A (en) | Vehicle operation behavior type identification method based on sparse track |
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 |