CN113570862B - XGboost algorithm-based large traffic jam early warning method - Google Patents
XGboost algorithm-based large traffic jam early warning method Download PDFInfo
- Publication number
- CN113570862B CN113570862B CN202110862251.0A CN202110862251A CN113570862B CN 113570862 B CN113570862 B CN 113570862B CN 202110862251 A CN202110862251 A CN 202110862251A CN 113570862 B CN113570862 B CN 113570862B
- Authority
- CN
- China
- Prior art keywords
- xgboost algorithm
- algorithm model
- flow data
- traffic flow
- training
- 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
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
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
Abstract
The invention relates to a large traffic jam early warning method based on an XGboost algorithm, which comprises the following steps: acquiring historical traffic flow data of a specified time period from a traffic database, distinguishing and labeling the congestion condition of an event represented by each historical traffic flow data, and dividing the labeled historical traffic flow data into a training set and a test set; building an XGboost algorithm model, inputting historical traffic flow data serving as a training set into the XGboost algorithm model for training, inputting the historical traffic flow data serving as a test set into the XGboost algorithm model after training is finished, and verifying accuracy; and inputting traffic flow data of the road to be predicted in a specified time period into the XGboost algorithm model, and outputting a result as early warning of the traffic jam condition of the road network. By the method and the device, the effect of traffic jam early warning can be achieved only according to the historical traffic event sequence without calling the latest traffic data in real time, and the method and the device have universality.
Description
Technical Field
The invention relates to the technical field of deep learning, in particular to a large-scale traffic jam early warning method based on an XGboost algorithm.
Background
At present, whether a certain road is congested or not is generally judged by identifying the trend of a traffic flow state, and in the aspect of identifying and predicting the traffic flow state, many scholars at home and abroad obtain a series of models through long-time research and experiments, and the models can be divided into three categories according to different theoretical foundations, namely a model established according to a statistical theory, a nonlinear system theoretical model and a model identified by artificial intelligence. In China, the traffic flow detection and analysis is also utilized, and the road congestion condition is measured by collecting and analyzing data such as weather, speed, distance between vehicles, signal lamps and even carbon dioxide emission collected by a road sensor.
The three models in the prior art have respective disadvantages, although the linear theory model is simple and easy to understand, a large amount of historical data is needed to establish the models, however, traffic data is not invariable, and traffic data flow becomes complicated and changeable due to uncertainty of traffic road conditions, so that the models cannot accurately predict traffic jam; on the basis of the nonlinear theory, although the traffic road condition can be accurately reflected, the model is very difficult to construct due to the fact that the theoretical cost is lost; although the artificial intelligence model represented by the neural network is far greater than the former two models in accuracy and application range, the calculation process is complex, the calculation time is long, the setting of algorithm parameters needs specific personnel to set, and the utilization rate of the model is reduced. These models exist only in theory due to their respective advantages and disadvantages, and there are few models that can be applied to reality to form a system. In addition, due to uncertainty of motor vehicles and interference of pedestrians or other factors, congestion can occur at any time, and under the background, the existing early warning system cannot process all event data types, so that system failure can be caused, and the traffic congestion situation is further increased.
Disclosure of Invention
The invention aims to solve the technical problem of providing a large-scale traffic jam early warning method based on an XGboost algorithm aiming at the defects of the prior art.
The technical scheme adopted by the invention for solving the technical problems is as follows: a large traffic jam early warning method based on an XGboost algorithm is constructed, and comprises the following steps:
acquiring historical traffic flow data of a specified time period from a traffic database, distinguishing and labeling congestion situations of events represented by each piece of historical traffic flow data, distinguishing severe congestion events and non-severe congestion events according to the congestion situations, and dividing the labeled historical traffic flow data into a training set and a test set;
building an XGboost algorithm model, inputting historical traffic flow data serving as a training set into the XGboost algorithm model for training, adjusting network parameters and functions until the output result is the same as the corresponding labeling result, inputting the historical traffic flow data serving as a test set into the XGboost algorithm model after training is finished, and verifying the accuracy of the XGboost algorithm model;
and inputting traffic flow data of the road to be predicted in a specified time period into the trained XGBoost algorithm model, and outputting a result serving as early warning of the traffic jam condition of the road network through calculation of the network model.
The method comprises the following steps of distinguishing and labeling the congestion conditions of events represented by each piece of historical traffic flow data, wherein the steps comprise the following steps:
identifying congestion condition event types of historical traffic data streams, marking the congestion condition event types as 1 and 0, and forming a sequence; wherein, 1 represents causing a severe congestion event 0 represents not causing a severe congestion event;
and inverting the sequence, writing a function returning to the corresponding event list, converting the label, and filling the sequence.
The XGBoost algorithm model construction method comprises the following steps:
constructing an XGboost algorithm model by utilizing an XGboost algorithm in a Keras neural network database;
training parameters are defined and adjusted according to the traffic data stream.
The XGBoost algorithm model training method comprises the following steps:
establishing an XGboost algorithm model, inputting a training set into the XGboost algorithm model, and calculating a predicted value;
adding a sequence model, and calculating a specificity model index to evaluate the performance of the XGboost algorithm model;
and (4) constructing an ROC curve, observing an evaluation index result of the XGboost algorithm model, and outputting an effect file.
And observing the loss curves of the training set and the test set through the training curve, wherein if the loss curves show a descending trend, the learning success rate of the XGBoost algorithm model generally shows an ascending trend.
Different from the prior art, the invention provides a large traffic jam early warning method based on an XGboost algorithm, which comprises the following steps: acquiring historical traffic flow data of a specified time period from a traffic database, distinguishing and labeling the congestion conditions of events represented by each piece of historical traffic flow data, and dividing the labeled historical traffic flow data into a training set and a test set; constructing an XGboost algorithm model, inputting historical traffic flow data serving as a training set into the XGboost algorithm model for training, inputting the historical traffic flow data serving as a test set into the XGboost algorithm model after training is completed, and verifying accuracy; and inputting traffic flow data of the road to be predicted in a specified time period into the XGboost algorithm model, and outputting a result as early warning of the traffic jam condition of the road network. By the method and the device, the effect of traffic jam early warning can be achieved only according to the historical traffic event sequence without calling the latest traffic data in real time, and the method and the device have universality.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
fig. 1 is a schematic flow diagram of a large traffic congestion early warning method based on an XGboost algorithm provided by the present invention.
Fig. 2 is a logic schematic diagram of a large traffic jam early warning method based on an XGboost algorithm provided by the present invention.
Detailed Description
For a more clear understanding of the technical features, objects and effects of the present invention, embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
As shown in fig. 1 and fig. 2, the invention provides a large traffic congestion early warning method based on an XGboost algorithm, which includes:
acquiring historical traffic flow data of a specified time period from a traffic database, distinguishing and labeling congestion situations of events represented by each piece of historical traffic flow data, distinguishing severe congestion events and non-severe congestion events according to the congestion situations, and dividing the labeled historical traffic flow data into a training set and a test set;
building an XGboost algorithm model, inputting historical traffic flow data serving as a training set into the XGboost algorithm model for training, adjusting network parameters and functions until the output result is the same as the corresponding labeling result, inputting the historical traffic flow data serving as a test set into the XGboost algorithm model after training is finished, and verifying the accuracy of the XGboost algorithm model;
and inputting traffic flow data of the road to be predicted in a specified time period into the trained XGBoost algorithm model, and outputting a result serving as early warning of the traffic jam condition of the road network through calculation of the network model.
The method comprises the following steps of distinguishing and labeling the congestion conditions of events represented by each piece of historical traffic flow data, wherein the steps comprise the following steps:
identifying congestion condition event types of historical traffic data streams, marking the congestion condition event types as 1 and 0, and forming a sequence; wherein, 1 represents causing a severe congestion event 0 represents not causing a severe congestion event;
and inverting the sequence, writing a function returning to the corresponding event list, converting the label, and filling the sequence.
The XGBoost algorithm model construction method comprises the following steps:
constructing an XGboost algorithm model by utilizing an XGboost algorithm in a Keras neural network database;
training parameters are defined and adjusted according to the traffic data stream.
The XGBoost algorithm model training method comprises the following steps:
establishing an XGboost algorithm model, inputting a training set into the XGboost algorithm model, and calculating a predicted value;
adding a sequence model, and calculating a specificity model index to evaluate the performance of the XGboost algorithm model;
and (4) constructing an ROC curve, observing an evaluation index result of the XGboost algorithm model, and outputting an effect file.
And observing the loss curves of the training set and the test set through the training curve, wherein if the loss curves show a descending trend, the learning success rate of the XGBoost algorithm model generally shows an ascending trend.
FIG. 2 is a logic diagram of the present invention. The traffic data flow data stored in the traffic database is huge, the data is updated quickly, and the real-time requirement is high. The XGboost (extreme Gradient boosting) iterative regression tree algorithm is developed according to a Gradient boosting decision tree algorithm, and compared with other algorithms, the XGboost (extreme Gradient boosting) iterative regression tree algorithm is parallel, fast in speed and more outstanding in robustness, is simpler and faster, and is very wide in reference range. And the operation speed of the XGBoost algorithm under the structured data is even dozens of times of the operation speed of other algorithms of the same type. The XGboost has the function of automatically learning the splitting direction, can expand the objective function, improves the calculation accuracy and better conforms to the analysis and prediction of a large amount of structured traffic flow data.
Due to the fact that the traffic condition is changed, traffic flow data are updated continuously, data information is huge, and real-time performance is strong. The traffic jam data is usually a combination of numbers and characters, and the XGboost algorithm is used for classifying text information and backtracking, training and predicting traffic events. The specific method is to divide the obtained event types into events causing severe congestion and events not causing severe congestion, mark the events as a sequence 1 and a sequence 0, and trace back the events in the previous 20 minutes in each sequence. And constructing an XGboost algorithm model to train a training set, comparing a predicted label result obtained by model training with a label of an existing event result of the training set, calculating the fitting degree of the predicted label result and the label, and expressing the accuracy degree of the algorithm model for traffic jam prediction by using an ROC curve and an AUC value. Under the support of a large number of training models, the algorithm model can be considered to realize traffic jam prediction to a certain extent.
The method is characterized in that an existing preamble special event sequence set is trained based on an XGboost algorithm, a prediction label for judging whether congestion occurs or not is obtained in the XGboost algorithm through an event number sequence of a verification set, the prediction label is compared with a label value of a sample event of the existing training set, the accuracy of the prediction label and the accuracy of the label value after fitting are displayed, the accuracy can be considered as the traffic congestion probability predicted by the congestion model algorithm, and the traffic congestion early warning effect is realized on the premise of a large amount of training data.
Different from the prior art, the invention provides a large traffic jam early warning method based on an XGboost algorithm, which comprises the following steps: acquiring historical traffic flow data of a specified time period from a traffic database, distinguishing and labeling the congestion conditions of events represented by each piece of historical traffic flow data, and dividing the labeled historical traffic flow data into a training set and a test set; constructing an XGboost algorithm model, inputting historical traffic flow data serving as a training set into the XGboost algorithm model for training, inputting the historical traffic flow data serving as a test set into the XGboost algorithm model after training is completed, and verifying accuracy; and inputting traffic flow data of the road to be predicted in a specified time period into the XGboost algorithm model, and outputting a result as early warning of the traffic jam condition of the road network. By the method and the device, the effect of traffic jam early warning can be achieved only according to the historical traffic event sequence without calling the latest traffic data in real time, and the method and the device have universality.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (1)
1. A large traffic jam early warning method based on an XGboost algorithm is characterized by comprising the following steps:
acquiring historical traffic flow data of a specified time period from a traffic database, distinguishing and labeling congestion situations of events represented by each piece of historical traffic flow data, distinguishing severe congestion events and non-severe congestion events according to the congestion situations, and dividing the labeled historical traffic flow data into a training set and a test set;
the method comprises the following steps of distinguishing and labeling the congestion conditions of the events represented by each piece of historical traffic flow data, wherein the steps comprise the following steps:
identifying congestion condition event types of historical traffic data streams, marking the congestion condition event types as 1 and 0, and forming a sequence; wherein, 1 represents causing a severe congestion event 0 represents not causing a severe congestion event;
inverting the sequence, writing a function returning to a corresponding event list, converting the label, and filling the sequence;
building an XGboost algorithm model, inputting historical traffic flow data serving as a training set into the XGboost algorithm model for training, adjusting network parameters and functions until the output result is the same as the corresponding labeling result, inputting the historical traffic flow data serving as a test set into the XGboost algorithm model after training is finished, and verifying the accuracy of the XGboost algorithm model;
in the step of constructing the XGBoost algorithm model, the XGBoost algorithm model comprises the following steps:
constructing an XGboost algorithm model by utilizing an XGboost algorithm in a Keras neural network database;
defining and adjusting training parameters according to the traffic data stream;
inputting traffic flow data of a road to be predicted in a specified time period into the trained XGBoost algorithm model, and outputting a result as early warning of traffic jam of a road network through calculation of the network model;
in the step of training the XGBoost algorithm model, the method comprises the following steps:
establishing an XGboost algorithm model, inputting a training set into the XGboost algorithm model, and calculating a predicted value;
adding a sequence model, and calculating a specificity model index to evaluate the performance of the XGboost algorithm model;
constructing an ROC curve, observing an evaluation index result of the XGboost algorithm model, and outputting an effect file;
and observing the loss curves of the training set and the test set through the training curves, and if the loss curves show a descending trend, the learning success rate of the XGboost algorithm model generally shows an ascending trend.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110862251.0A CN113570862B (en) | 2021-07-28 | 2021-07-28 | XGboost algorithm-based large traffic jam early warning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110862251.0A CN113570862B (en) | 2021-07-28 | 2021-07-28 | XGboost algorithm-based large traffic jam early warning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113570862A CN113570862A (en) | 2021-10-29 |
| CN113570862B true CN113570862B (en) | 2022-05-10 |
Family
ID=78168933
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110862251.0A Active CN113570862B (en) | 2021-07-28 | 2021-07-28 | XGboost algorithm-based large traffic jam early warning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113570862B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115424447A (en) * | 2022-11-04 | 2022-12-02 | 华路易云科技有限公司 | Signal control method and signal control platform supporting autonomous configuration threshold |
| CN117275236B (en) * | 2023-10-11 | 2024-04-05 | 宁波宁工交通工程设计咨询有限公司 | Traffic jam management method and system based on multi-target recognition |
| CN117274929A (en) * | 2023-11-21 | 2023-12-22 | 深圳中科超远科技有限公司 | Traffic management method and system based on visual analysis |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846521A (en) * | 2018-06-22 | 2018-11-20 | 西安电子科技大学 | Shield-tunneling construction unfavorable geology type prediction method based on Xgboost |
| CN109101568A (en) * | 2018-07-16 | 2018-12-28 | 江苏智通交通科技有限公司 | Traffic high-risk personnel recognition methods based on XgBoost algorithm |
| CN109191883A (en) * | 2018-09-29 | 2019-01-11 | 电子科技大学 | A kind of intelligent transportation system based on intelligent perception |
| CN109191840A (en) * | 2018-09-13 | 2019-01-11 | 电子科技大学 | A kind of real-time traffic condition determination method based on intelligent terminal |
| CN109697852A (en) * | 2019-01-23 | 2019-04-30 | 吉林大学 | Urban road congestion degree prediction technique based on timing traffic events |
| CN109993356A (en) * | 2019-03-25 | 2019-07-09 | 广东工业大学 | A kind of traffic optimization system and method based on XGBOOST |
| CN110533214A (en) * | 2019-07-12 | 2019-12-03 | 北京航空航天大学 | A kind of subway passenger flow Forecasting Approach for Short-term based on XGBoost algorithm |
| CN110555989A (en) * | 2019-08-16 | 2019-12-10 | 华南理工大学 | Xgboost algorithm-based traffic prediction method |
| CN111063393A (en) * | 2019-12-26 | 2020-04-24 | 青岛科技大学 | Prokaryotic acetylation site prediction method based on information fusion and deep learning |
| CN111063194A (en) * | 2020-01-13 | 2020-04-24 | 兰州理工大学 | Traffic flow prediction method |
| CN111462485A (en) * | 2020-03-31 | 2020-07-28 | 电子科技大学 | Traffic intersection congestion prediction method based on machine learning |
| CN111626508A (en) * | 2020-05-27 | 2020-09-04 | 华东师范大学 | Rail transit vehicle-mounted data prediction method based on xgboost model |
| US10783433B1 (en) * | 2019-04-22 | 2020-09-22 | Bell Integrator Inc. | Method for training and self-organization of a neural network |
| CN112232366A (en) * | 2020-09-09 | 2021-01-15 | 国网上海市电力公司 | Electrical equipment fault early warning method and system based on RFID monitoring |
| CN112634614A (en) * | 2020-12-16 | 2021-04-09 | 安徽百诚慧通科技有限公司 | Long downhill traffic incident real-time detection method, device and storage medium |
| CN113139876A (en) * | 2021-04-22 | 2021-07-20 | 平安壹钱包电子商务有限公司 | Risk model training method and device, computer equipment and readable storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190354838A1 (en) * | 2018-05-21 | 2019-11-21 | Uber Technologies, Inc. | Automobile Accident Detection Using Machine Learned Model |
-
2021
- 2021-07-28 CN CN202110862251.0A patent/CN113570862B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846521A (en) * | 2018-06-22 | 2018-11-20 | 西安电子科技大学 | Shield-tunneling construction unfavorable geology type prediction method based on Xgboost |
| CN109101568A (en) * | 2018-07-16 | 2018-12-28 | 江苏智通交通科技有限公司 | Traffic high-risk personnel recognition methods based on XgBoost algorithm |
| CN109191840A (en) * | 2018-09-13 | 2019-01-11 | 电子科技大学 | A kind of real-time traffic condition determination method based on intelligent terminal |
| CN109191883A (en) * | 2018-09-29 | 2019-01-11 | 电子科技大学 | A kind of intelligent transportation system based on intelligent perception |
| CN109697852A (en) * | 2019-01-23 | 2019-04-30 | 吉林大学 | Urban road congestion degree prediction technique based on timing traffic events |
| CN109993356A (en) * | 2019-03-25 | 2019-07-09 | 广东工业大学 | A kind of traffic optimization system and method based on XGBOOST |
| US10783433B1 (en) * | 2019-04-22 | 2020-09-22 | Bell Integrator Inc. | Method for training and self-organization of a neural network |
| CN110533214A (en) * | 2019-07-12 | 2019-12-03 | 北京航空航天大学 | A kind of subway passenger flow Forecasting Approach for Short-term based on XGBoost algorithm |
| CN110555989A (en) * | 2019-08-16 | 2019-12-10 | 华南理工大学 | Xgboost algorithm-based traffic prediction method |
| CN111063393A (en) * | 2019-12-26 | 2020-04-24 | 青岛科技大学 | Prokaryotic acetylation site prediction method based on information fusion and deep learning |
| CN111063194A (en) * | 2020-01-13 | 2020-04-24 | 兰州理工大学 | Traffic flow prediction method |
| CN111462485A (en) * | 2020-03-31 | 2020-07-28 | 电子科技大学 | Traffic intersection congestion prediction method based on machine learning |
| CN111626508A (en) * | 2020-05-27 | 2020-09-04 | 华东师范大学 | Rail transit vehicle-mounted data prediction method based on xgboost model |
| CN112232366A (en) * | 2020-09-09 | 2021-01-15 | 国网上海市电力公司 | Electrical equipment fault early warning method and system based on RFID monitoring |
| CN112634614A (en) * | 2020-12-16 | 2021-04-09 | 安徽百诚慧通科技有限公司 | Long downhill traffic incident real-time detection method, device and storage medium |
| CN113139876A (en) * | 2021-04-22 | 2021-07-20 | 平安壹钱包电子商务有限公司 | Risk model training method and device, computer equipment and readable storage medium |
Non-Patent Citations (2)
| Title |
|---|
| An LSTM‐Based Method Considering History and;Ouyang Qi;《applied sciences》;20200529;全文 * |
| 基于改进的XGBoost的短期交通流预测;刘伟;《万方》;20201230;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113570862A (en) | 2021-10-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113570862B (en) | XGboost algorithm-based large traffic jam early warning method | |
| CN111832225B (en) | Method for constructing driving condition of automobile | |
| CN109840660B (en) | Vehicle characteristic data processing method and vehicle risk prediction model training method | |
| CN104809878B (en) | Method for detecting abnormal condition of urban road traffic by utilizing GPS (Global Positioning System) data of public buses | |
| Lécué et al. | Predicting severity of road traffic congestion using semantic web technologies | |
| Fang et al. | FTPG: A fine-grained traffic prediction method with graph attention network using big trace data | |
| CN108597227B (en) | Method for predicting traffic flow of lower lane of highway toll station | |
| CN109191849B (en) | Traffic jam duration prediction method based on multi-source data feature extraction | |
| WO2021013190A1 (en) | Meteorological parameter-based high-speed train positioning method and system in navigation blind zone | |
| CN111292534A (en) | Traffic state estimation method based on clustering and deep sequence learning | |
| CN112884014A (en) | Traffic speed short-time prediction method based on road section topological structure classification | |
| CN114882069A (en) | Taxi track abnormity detection method based on LSTM network and attention mechanism | |
| CN112633602B (en) | Traffic congestion index prediction method and device based on GIS map information | |
| CN109993966A (en) | A kind of method and device of building user portrait | |
| CN110738855A (en) | Road traffic flow condition prediction method for data sparse time periods | |
| CN114299742B (en) | Speed limit information dynamic identification and update recommendation method for expressway | |
| CN115099328A (en) | Traffic flow prediction method, system, device and storage medium based on countermeasure network | |
| Gkountouna et al. | Traffic flow estimation using probe vehicle data | |
| CN112149922A (en) | Method for predicting severity of accident in exit and entrance area of down-link of highway tunnel | |
| CN114463978B (en) | Data monitoring method based on track traffic information processing terminal | |
| CN113674525B (en) | Signalized intersection vehicle queuing length prediction method based on sparse data | |
| CN114495486B (en) | Microcosmic traffic flow prediction system and microcosmic traffic flow prediction method based on hierarchical reinforcement learning | |
| Wen et al. | Traffic incident duration prediction based on K-nearest neighbor | |
| CN112132088B (en) | Inspection point missing inspection identification method | |
| Byju et al. | Pedestrian Detection and Tracking in Challenging Conditions |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Fang Yaling Inventor after: Wang Jinhong Inventor after: Jia Yiqi Inventor after: Yan Gaowei Inventor before: Fang Lingya Inventor before: Wang Jinhong Inventor before: Jia Yiqi Inventor before: Yan Gaowei |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |