CN113807579B - Machine learning-based flight harbor-keeping delay time prediction method - Google Patents
Machine learning-based flight harbor-keeping delay time prediction method Download PDFInfo
- Publication number
- CN113807579B CN113807579B CN202111024195.XA CN202111024195A CN113807579B CN 113807579 B CN113807579 B CN 113807579B CN 202111024195 A CN202111024195 A CN 202111024195A CN 113807579 B CN113807579 B CN 113807579B
- Authority
- CN
- China
- Prior art keywords
- delay
- flight
- delay time
- harbor
- predicting
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000010801 machine learning Methods 0.000 title claims abstract description 24
- 238000012549 training Methods 0.000 claims abstract description 31
- 238000013145 classification model Methods 0.000 claims abstract description 22
- 238000012360 testing method Methods 0.000 claims description 25
- 238000003066 decision tree Methods 0.000 claims description 9
- 230000010006 flight Effects 0.000 claims description 6
- 238000004140 cleaning Methods 0.000 claims description 3
- 230000001934 delay Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 2
- 238000007637 random forest analysis Methods 0.000 abstract description 48
- 230000000452 restraining effect Effects 0.000 abstract description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013100 final test Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medical Informatics (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a machine learning-based method for predicting flight harbor delay time, which predicts specific flight harbor delay time and can assist decision-making for civil aviation management departments. Firstly, defining delay levels of the flight harbor-keeping time (classifying by taking a specific time period as a unit), carrying out finer granularity division, constructing a data set of the flight harbor-keeping delay, and marking. And then, performing classification prediction training of delay levels by using an RF (random forest) classification model, restraining specific delay time by the delay levels to ensure that the prediction error of the delay time is smaller, and finally, inputting data containing the predicted delay levels into an RF regression model to predict the specific harbor delay time of the sample. The method has significantly smaller errors and higher efficiency than other methods in the current stage.
Description
Technical Field
The invention belongs to the field of machine learning, and particularly relates to a method for predicting a flight harbor delay time based on machine learning.
Background
Random Forest (RF) is an extended variant of integrated method Bagging in machine learning. The RF further introduces random attribute selection in the training process of the decision tree on the basis of constructing Bagging integration by taking the decision tree as a base learner. Specifically, when selecting the partition attribute, the conventional decision tree selects a most available attribute from the attribute set of the current node; in RF, for each node of the base decision tree, a subset including a plurality of attributes is selected randomly from the set of attributes of the node, and then an optimal attribute is selected from the subset for partitioning.
In the continuous development of the civil aviation industry, the air transportation load capacity is rapidly increased in recent years, and more demands are brought to the aviation service industry, so that the occupation ratio of delay incidents of the civil aviation flight is larger and larger, and the management department faces more serious challenges. Through the flight delay prediction technology, the early warning and the emergency of the civil aviation delay event can be more perfect, better emergency decisions can be made, the loss brought by the civil aviation transportation industry is reduced, and the emergency level of the civil aviation delay event is improved.
At present, the prediction of the flight delay time is still in a preliminary stage, and certain difficulty is brought to the prediction of the specific time of the flight delay due to the complex and various factors influencing the flight delay. There are many methods for classification and prediction in machine learning, and since machine learning requires selecting sample attributes, strict screening of sample attributes is required in combination with professional background knowledge. The traditional machine learning method comprises a linear model, a decision tree, a neural network, a support vector machine, ensemble learning and the like. Traditional machine learning methods require samples to have attributes and labels (or results). The trained feature vectors are input into a model, trained according to the values of the various attributes, and then classified or regressed.
The existing flight delay time prediction method mainly has the following problems: firstly, the classification accuracy is low. And secondly, the generalization capability of the model is weak. Thirdly, the prediction method of the specific delay time is few and the error is large.
Disclosure of Invention
The invention provides a machine learning-based method for predicting the delay time of a flight harbor, which is used for solving the problem of predicting the specific delay time of the flight by applying the machine learning method to the delay of the flight.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
A method for predicting a delay time of a flight harbor based on machine learning comprises the following steps:
step one, classifying the delay time length of the flight harbor by sorting literature data of the civil aviation system and the prediction of the delay of the flight harbor, and determining delay grade parameters;
Step two, acquiring detailed information of flight delays of all airports, constructing a data set of the flight harbor delay and randomly dividing the data set into a training set and a testing set;
Step three, training for classifying the delay level of the flight by using an RF classification model;
Step four, learning a regression task on the training set by using an RF regression model;
Fifthly, predicting and assigning the attribute of the delay level of the test set of the RF regression task by using a trained RF classification model;
And step six, predicting the specific delay time of the flight by using the RF regression model to the test set for the RF regression task.
Further, the first step specifically comprises: by reading Guan Min documents classified by air transportation enterprise flight delay, aiming at the characteristics of the occurrence of the current civil aviation flight delay, analyzing the reason of the occurrence of the flight delay, selecting the attribute with important influence, classifying the delay time of the flight, and determining the time length parameter for distinguishing the delay grade;
The flight delay class is divided into the following five classes:
(A) 0 or more and less than 15 minutes, wherein: a view of 0 less than 0;
(B) 15 or more and less than 30 minutes;
(C) 30 minutes or more and less than 45 minutes;
(D) 45 or more and less than 60 minutes;
(E) 60 minutes or more;
A ranking parameter of the flight delay is then determined.
Further, the second step specifically comprises: and acquiring detailed information of flights on the internet, constructing a data set for predicting the delay time of the flights, randomly dividing the data set into a training set and a testing set, and marking delay grades.
Further, the steps of labeling the delay level are as follows:
(a) Preprocessing the acquired data, and cleaning to obtain data capable of being marked;
(b) Marking the delay grade of the data according to the known delay time of the port;
(c) The method is characterized in that the method is marked by integers, 0 represents delay time of 0-15 minutes, 1 represents delay time of 15-30 minutes, 2 represents delay time of 30-45 minutes, 3 represents delay time of 45-60 minutes, and 4 represents delay time of 60 minutes or more.
Further, the third step specifically comprises: and carrying out delay-level classification training on the training set by using an RF classification model, wherein the RF classification model finds the nonlinear relation of the data attribute.
Further, the fourth step specifically comprises: and carrying out regression training of specific delay time on the training set by using an RF regression model, wherein the RF regression model can carry out nonlinear combination on the attributes of the samples, predict the label of the flight delay time, and finally output the average value of the decision tree in the integrated model.
Further, the fifth step specifically comprises: and 3, predicting delay levels of samples in the RF regression model test set by using the model which is the trained RF classification model in the step three, and taking the samples as a final specific delay time prediction test set.
Further, the sixth step specifically includes: and D, predicting the specific delay time of the test set processed in the fifth step by using the RF regression model trained in the fourth step.
Specifically, the method comprises the following steps: the delay level is predicted first, and then the original data and the predicted delay level are combined to be used as the input of specific delay time prediction.
Further, the fifth step is to predict the delay level of the test set, and the sixth step combines the original data and the predicted delay level to be used as the test set for predicting the specific delay time.
Compared with the prior art, the invention has the following beneficial effects:
According to the invention, by defining delay levels of the flight harbor-keeping time (classifying by taking a specific time period as a unit), finer granularity division is carried out, and a data set of the flight harbor-keeping delay is constructed and marked. And then, performing classification prediction training of delay levels by using an RF (random forest) classification model, restraining specific delay time by the delay levels to ensure that the prediction error of the delay time is smaller, and finally, inputting data containing the predicted delay levels into an RF regression model to predict the specific harbor delay time of the sample. The method has significantly smaller errors and higher efficiency than other methods in the current stage.
Drawings
FIG. 1 is a flow chart of classified prediction of flight delay levels provided by the present invention.
Fig. 2 is a schematic diagram of a method for predicting a flight delay specific time regression according to the present invention.
Fig. 3 is a schematic diagram of a model structure of a method for predicting delay time of a flight harbor.
Detailed Description
The invention will be further illustrated with reference to examples.
The invention provides a machine learning-based flight harbor delay time prediction method, which comprises the steps of classification of flight delay grades, construction of a model frame, construction of a data set, classification training and regression training of delay time. And predicting the delay level of the flight through RF, and carrying out regression training of specific delay time by combining the original attribute with the predicted delay level. The trained model has better generalization capability, and can better complete the prediction of the delay time of the flight harbor. Further described below in connection with fig. 1-3 and the examples.
A method for predicting a delay time of a flight harbor based on machine learning comprises the following steps:
step one, classifying the delay time length of the flight harbor by sorting literature data of the civil aviation system and the prediction of the delay of the flight harbor, and determining delay grade parameters;
The first step is specifically as follows: by reading Guan Min documents classified by air transportation enterprise flight delay, aiming at the characteristics of the occurrence of the current civil aviation flight delay, analyzing the reason of the occurrence of the flight delay, selecting the attribute with important influence, classifying the delay time of the flight, and determining the time length parameter for distinguishing the delay grade;
The flight delay class is divided into the following five classes:
(A) 0 or more and less than 15 minutes (0 being considered as less than 0);
(B) 15 or more and less than 30 minutes;
(C) 30 minutes or more and less than 45 minutes;
(D) 45 or more and less than 60 minutes;
(E) 60 minutes or more;
A ranking parameter of the flight delay is then determined.
Step two, acquiring detailed information of flight delays of all airports, constructing a data set of the flight harbor delay and randomly dividing the data set into a training set and a testing set;
the second step is specifically as follows: and acquiring detailed information of flights on the internet, constructing a data set for predicting the delay time of the flights, randomly dividing the data set into a training set and a testing set, and marking delay grades.
The steps of the delay level marking are as follows:
(a) Preprocessing the acquired data, and cleaning to obtain data capable of being marked;
(b) Marking the delay grade of the data according to the known delay time of the port;
(c) The method is characterized in that the method is marked by integers, 0 represents delay time of 0-15 minutes, 1 represents delay time of 15-30 minutes, 2 represents delay time of 30-45 minutes, 3 represents delay time of 45-60 minutes, and 4 represents delay time of 60 minutes or more.
Such as: the sample flight delay time length attribute value represents the delay time length (in minutes) of the port of the flight, and the delay grade attribute value of the sample flight delay time length value is given as1 if the sample flight delay time length value is known as 25;
Namely: the sample ARR_DELAY attribute value represents the DELAY time (in minutes) of the flight, and given that the ARR_DELAY value of a sample is 25, the DELAY_LEVEL attribute value is assigned 1.
Step three, training for classifying the delay level of the flight by using an RF (random forest) classification model;
The third step is specifically as follows: and the RF (random forest) classification model is used for carrying out delay class classification training on the training set, and the RF classification model finds the nonlinear relation of the data attribute and has higher accuracy rate on the delay class classification of the harbor of the flight.
The attribute values of a certain sample are respectively as follows: the flight is in the first quarter, the month is one month, the day of the month is the first day, the day of the week is the second day, the estimated departure time is six points and three tenths, the departure delay time is one minute in advance, the estimated departure time is eight points and forty-one kilometer, the flight distance is five hundred forty kilometers, and the label delay grade of the sample is predicted to be 1 after the classification model is trained.
Namely: QUARTER is 1, day_of_moth is 1, day_of_week is 2, crs_dep_time is 630, dep_delay is-1, crs_arr_time is 841, distance is 541, and after the classification model is trained, the label delay level of the sample is predicted to be 1.
Each node of the RF (random forest) classification model pair and the decision tree is selected randomly a subset of k attributes from the set of attributes of that node, and then an optimal attribute is selected from this subset for partitioning.
Step four, learning a regression task on the training set by using an RF (random forest) regression model;
The fourth step is specifically as follows: and carrying out regression training of specific delay time on the training set by using an RF (random forest) regression model, wherein the RF regression model can carry out nonlinear combination on the attributes of the samples, forecast the label of the flight delay time, and finally output the average value of the decision tree in the integrated model.
It is known that each attribute value of a certain sample is: QUARTER is 1, DAY_OF_MONTH is 1, DAY_OF_WEEK is 2, CRS_DEP_TIME is 630, DEP_DELAY is-1, CRS_ARR_TIME is 841, DISTANCE is 541, delay level is 1, after the RF regression model is trained, each tree finds out nodes meeting the task requirement to split and grow so as to predict the specific port-keeping delay time length, and the port-keeping delay time of the sample is predicted to be 25, as shown in figure 1.
Fifthly, predicting and assigning the attribute of the delay level of the test set of the RF regression task by using a trained RF classification model;
the fifth step is specifically as follows: and 3, predicting delay levels of samples in the RF regression model test set by using the model which is the trained RF (random forest) classification model in the step three, and taking the samples as a final test set for predicting specific delay time.
And step six, predicting the specific delay time of the flight by using the RF regression model to the test set for the RF regression task.
The sixth step is specifically as follows: and 3, predicting the specific delay time of the test set processed in the fifth step by using the RF regression model trained in the fourth step as shown in fig. 3. Specifically, the method comprises the following steps: the delay level is predicted first, and then the original data and the predicted delay level are combined to be used as the input of specific delay time prediction. And step five, predicting delay levels of the test set, wherein the step six combines the original data and the predicted delay levels to be used as the test set for predicting specific delay time.
The invention discloses a machine learning-based method for predicting flight harbor delay time, which predicts specific flight harbor delay time and can assist decision-making for civil aviation management departments. Firstly, defining delay levels of the flight harbor-keeping time (classifying by taking a specific time period as a unit), carrying out finer granularity division, constructing a data set of the flight harbor-keeping delay, and marking. And then, performing classification prediction training of delay levels by using an RF (random forest) classification model, restraining specific delay time by the delay levels to ensure that the prediction error of the delay time is smaller, and finally, inputting data containing the predicted delay levels into an RF regression model to predict the specific harbor delay time of the sample. The method has significantly smaller errors and higher efficiency than other methods in the current stage.
The foregoing is only a preferred embodiment of the invention, it being noted that: it will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the invention.
Claims (8)
1. A machine learning-based method for predicting a delay time of a flight harbor is characterized by comprising the following steps:
step one, classifying the delay time length of the flight harbor by sorting literature data of the civil aviation system and the prediction of the delay of the flight harbor, and determining delay grade parameters;
Step two, acquiring detailed information of flight delays of all airports, constructing a data set of the flight harbor delay and randomly dividing the data set into a training set and a testing set;
Step three, training for classifying the delay level of the flight by using an RF classification model;
Step four, predicting delay levels of samples of the test set by utilizing the RF classification model trained in the step three, inputting data containing the delay levels into the RF regression model, and combining the training set to learn regression tasks;
Fifthly, predicting and assigning the attribute of the delay level of the test set of the RF regression task by using a trained RF classification model;
And step six, predicting the specific delay time of the flight by using the RF regression model to the test set for the RF regression task.
2. The method for predicting delay time of a flight harbor based on machine learning according to claim 1, wherein the first step is specifically: by reading Guan Min documents classified by air transportation enterprise flight delay, aiming at the characteristics of the occurrence of the current civil aviation flight delay, analyzing the reason of the occurrence of the flight delay, selecting the attribute with important influence, classifying the delay time of the flight, and determining the time length parameter for distinguishing the delay grade;
The flight delay class is divided into the following five classes:
(A) 0 or more and less than 15 minutes, wherein: a view of 0 less than 0;
(B) 15 or more and less than 30 minutes;
(C) 30 minutes or more and less than 45 minutes;
(D) 45 or more and less than 60 minutes;
(E) 60 minutes or more;
A ranking parameter of the flight delay is then determined.
3. The method for predicting the delay time of a flight harbor based on machine learning according to claim 1, wherein the step two is specifically: and acquiring detailed information of flights on the internet, constructing a data set for predicting the delay time of the flights, randomly dividing the data set into a training set and a testing set, and marking delay grades.
4. A machine learning based method of predicting delay time for a flight to a harbor according to claim 3, wherein the step of labeling the delay level comprises:
(a) Preprocessing the acquired data, and cleaning to obtain data capable of being marked;
(b) Marking the delay grade of the data according to the known delay time of the port;
(c) The method is characterized in that the method is marked by integers, 0 represents delay time of 0-15 minutes, 1 represents delay time of 15-30 minutes, 2 represents delay time of 30-45 minutes, 3 represents delay time of 45-60 minutes, and 4 represents delay time of 60 minutes or more.
5. The method for predicting the delay time of a flight harbor based on machine learning according to claim 1, wherein the third step is specifically: and carrying out delay-level classification training on the training set by using an RF classification model, wherein the RF classification model finds the nonlinear relation of the data attribute.
6. The method for predicting the delay time of a flight harbor based on machine learning according to claim 1, wherein the fourth step is specifically: and carrying out regression training of specific delay time on the training set by using an RF regression model, wherein the RF regression model can carry out nonlinear combination on the attributes of the samples, predict the label of the flight delay time, and finally output the average value of the decision tree in the integrated model.
7. The method for predicting the delay time of a flight harbor based on machine learning according to claim 1, wherein the fifth step is specifically: and 3, predicting delay levels of samples in the RF regression model test set by using the model which is the trained RF classification model in the step three, and taking the samples as a final specific delay time prediction test set.
8. The method for predicting the delay time of a flight harbor based on machine learning according to claim 1, wherein the sixth step is specifically: and D, predicting the specific delay time of the test set processed in the fifth step by using the RF regression model trained in the fourth step.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111024195.XA CN113807579B (en) | 2021-09-02 | 2021-09-02 | Machine learning-based flight harbor-keeping delay time prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111024195.XA CN113807579B (en) | 2021-09-02 | 2021-09-02 | Machine learning-based flight harbor-keeping delay time prediction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113807579A CN113807579A (en) | 2021-12-17 |
| CN113807579B true CN113807579B (en) | 2024-06-14 |
Family
ID=78894587
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111024195.XA Active CN113807579B (en) | 2021-09-02 | 2021-09-02 | Machine learning-based flight harbor-keeping delay time prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113807579B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115691691A (en) * | 2022-12-03 | 2023-02-03 | 湖南大学 | New pollutant reactivity prediction method based on machine learning |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105956621A (en) * | 2016-04-29 | 2016-09-21 | 南京航空航天大学 | Flight delay early warning method based on evolutionary sub-sampling integrated learning |
| CN107818382A (en) * | 2017-10-27 | 2018-03-20 | 中航信移动科技有限公司 | Flight arrival time Forecasting Methodology |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111145596A (en) * | 2019-12-05 | 2020-05-12 | 阿里巴巴集团控股有限公司 | Method and device for predicting delay duration |
| CN110675007A (en) * | 2019-12-06 | 2020-01-10 | 南京萨利智能科技有限公司 | Flight delay prediction method and device and computer storage medium |
| CN112883640B (en) * | 2021-02-04 | 2023-06-09 | 西南交通大学 | Digital twin station system, job scheduling method based on system and application |
| CN113128769A (en) * | 2021-04-22 | 2021-07-16 | 上海工程技术大学 | Intelligent flight delay prediction method based on deep learning |
-
2021
- 2021-09-02 CN CN202111024195.XA patent/CN113807579B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105956621A (en) * | 2016-04-29 | 2016-09-21 | 南京航空航天大学 | Flight delay early warning method based on evolutionary sub-sampling integrated learning |
| CN107818382A (en) * | 2017-10-27 | 2018-03-20 | 中航信移动科技有限公司 | Flight arrival time Forecasting Methodology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113807579A (en) | 2021-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11367002B1 (en) | Method for constructing and training decentralized migration diagram neural network model for production process | |
| Utari et al. | Implementation of data mining for drop-out prediction using random forest method | |
| Pani et al. | A data mining approach to forecast late arrivals in a transhipment container terminal | |
| Koh et al. | Using simulation to preview plans of a container port operations | |
| Hasany et al. | Two-stage stochastic programming for the railroad blocking problem with uncertain demand and supply resources | |
| CN113807579B (en) | Machine learning-based flight harbor-keeping delay time prediction method | |
| Lin et al. | Airport baggage handling system simulation modeling using SysML | |
| Marcos et al. | A machine learning approach to air traffic route choice modelling | |
| Zhou et al. | A scalable vehicle assignment and routing strategy for real-time on-demand ridesharing considering endogenous congestion | |
| Sharma et al. | A Study on Decision‐Making of the Indian Railways Reservation System during COVID‐19 | |
| CN113221472B (en) | Passenger flow prediction method based on LSTM | |
| Jung et al. | A data-driven air traffic sequencing model based on pairwise preference learning | |
| Wang | A modelling framework for managing risk-based checkpoint screening systems with two-type inspection queues | |
| Huang et al. | Robust model for the assignment of outgoing flights on airport baggage unloading areas | |
| Yu et al. | Real-time decision making for train carriage load prediction via multi-stream learning | |
| CN113176873B (en) | Method and device for information management, electronic equipment and medium | |
| Li et al. | A bi-objective lane reservation problem considering dynamic traffic flow | |
| Poschmann et al. | Predicting estimated arrival times in logistics using machine learning | |
| JP7310459B2 (en) | Information processing method and information processing device | |
| Rahul et al. | Flight delay prediction using random forest classifier | |
| SAHADEVAN et al. | Prediction of gate in time of scheduled flights and schedule conformance using machine learning-based algorithms | |
| Cannas et al. | Delay prediction in container terminals: A comparison of machine learning methods | |
| Moll et al. | Predictive Analytics in Aviation Management: Passenger Arrival Prediction | |
| Thiagarajan et al. | Manufacturing flow time estimation using the model-tree induction approach in a dynamic job shop environment | |
| Moreno et al. | Prediction of air traffic complexity through a dynamic complexity indicator and machine learning models |
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 |