CN114492571A - Ship track classification method based on similarity distance - Google Patents
Ship track classification method based on similarity distance Download PDFInfo
- Publication number
- CN114492571A CN114492571A CN202111572146.XA CN202111572146A CN114492571A CN 114492571 A CN114492571 A CN 114492571A CN 202111572146 A CN202111572146 A CN 202111572146A CN 114492571 A CN114492571 A CN 114492571A
- Authority
- CN
- China
- Prior art keywords
- ship
- distance
- track
- similarity distance
- track points
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000012549 training Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 abstract description 2
- 230000002194 synthesizing effect Effects 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 239000003643 water by type Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a ship track classification method based on similarity distance, which comprises the steps of firstly, recording track point data of a ship, and selecting a reference ship; calculating the position similarity distance and the speed similarity distance between the reference ship and other ships, and synthesizing the two to calculate the final similarity distance; replacing the similarity distance in the KNN with the final similarity distance for training to obtain an optimal hyper-parameter; sequencing all the final similarity distances according to the numerical value, and counting the times of generating the MMSI values of the ships corresponding to the ship track points of the first K final similarity distance values; the vessel with the highest MMSI value is of the same type as the reference vessel. The classification method mainly aims at the problem that the traditional Euclidean distance is not suitable for marine ship track classification, and improves the accuracy and the rationality of ship track classification.
Description
Technical Field
The invention belongs to the technical field of ships, and particularly relates to a ship track classification method.
Background
To assist marine regulators in tracking ships and ensuring safe voyage, the International Maritime Organization (IMO) requires ships with a total tonnage of over 300, ships carrying cargo with a capacity of over 500 total tons, and passenger ships not in international waters during international voyage, which must be equipped with an Automatic Identification System (AIS). However, the ship trajectory received from the AIS is low in real-time and its time intervals are also irregular. Meanwhile, AIS data is occasionally lost due to communication reliability, which may cause vessel trajectory update to be suspended. For the seafarer, the better the integrity of the vessel data, the more adequate the response space and time to avoid the accident. Therefore, it is necessary to classify the movement locus of the ship to enhance the management of the ship. In recent years, data analysis and predictive modeling have become an emerging research topic.
However, the similarity distance designed in the conventional classification method, KNN (k-nearest neighbors) algorithm, is the euclidean distance, and this similarity distance calculation method is not suitable for the clustering between ship tracks. The reason is that the ship trajectory point data contains many influence factors and cannot be directly regarded as the distance between coordinate points. This results in poor performance of the KNN algorithm in classification of the vessel trajectory.
In conclusion, how to improve the actual effect of the ship track classification method has important research significance.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a ship track classification method based on similarity distance, which comprises the steps of firstly, recording track point data of a ship, and selecting a reference ship; calculating the position similarity distance and the speed similarity distance between the reference ship and other ships, and synthesizing the two to calculate the final similarity distance; replacing the similarity distance in the KNN with the final similarity distance for training to obtain an optimal hyper-parameter; sequencing all the final similarity distances according to the numerical value, and counting the times of generating the MMSI values of the ships corresponding to the ship track points of the first K final similarity distance values; the vessel with the highest MMSI value is of the same type as the reference vessel. The classification method mainly aims at the problem that the traditional Euclidean distance is not suitable for marine ship track classification, and improves the accuracy and the rationality of ship track classification.
The technical scheme adopted by the invention for solving the technical problem comprises the following steps:
step 1: recording track point data of all ships within a delta t time period, preprocessing the track point data, and deleting outliers and null values; selecting a ship as a reference ship;
step 2: selecting track points of a reference ship at the t moment in a delta t time period as reference track points; calculating the position similarity distance between the reference track point and all other ship track points in the delta t time period by adopting the formula (1):
Distance1=R*arccos[sin(λ1)sin(λ2)+cos(λ1)cos(λ2)cos(l1-l2)] (1)
wherein R is the mean radius of the earth, l1、l2Longitude, λ, of two points of the track respectively1、λ2Respectively the latitude of the two track points;
and step 3: selecting a ship SOG value at a time period t, and calculating the speed similarity distance between the reference track point and all other ship track points in the time period delta t by adopting a formula (2):
Distance2=v1-v2 (2)
wherein v is1、v2Respectively the navigational speeds of the two track points;
and 4, step 4: step 2 and step 3, obtaining position similarity distances and speed similarity distances of all ship track points to form a data set;
and 5: defining the final similarity distance:
D=a*Distance1+(1-a)*Distance2 (3)
wherein a is weight, and a belongs to [0,1 ];
step 6: determining the optimal hyper-parameter by using a leave-one method;
selecting 1 piece in the data set as a test set, and using the rest as a training set; replacing the similarity distance in the KNN with D for training to obtain optimal hyper-parameters K and a;
and 7: the value a is taken into the formula (3), the final similarity distance between the reference track point and all other ship track points in the delta t time period is calculated, and all the final similarity distances are sorted according to the numerical value;
and 8: selecting the first K values of the sorted final similarity distance list, and counting the MMSI value times of the ship corresponding to the ship track points generating the first K final similarity distance values;
and step 9: and returning the MMSI value of the ship with the most occurrence times, wherein the ship is the same as the reference ship.
The invention has the following beneficial effects:
the classification method mainly aims at the problem that the traditional Euclidean distance is not suitable for marine ship track classification, and improves the accuracy and the rationality of ship track classification.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
FIG. 2 shows the classification accuracy of the method under each parameter according to the embodiment of the present invention.
Fig. 3 is a graph illustrating the comparison between classification accuracy and effect provided by the embodiment of the present invention.
Detailed Description
The invention is further illustrated with reference to the following figures and examples.
According to the actual environment and ship track data, ships in a near port sea area are high in density, due to the fact that mutual influence factors exist among the ships, a classification algorithm based on similarity distance is suitable for the scenes, but similarity distances related to a traditional classification method, such as Euclidean distance and Manhattan distance, are not suitable for classification of ship track points on the sea, and similarity among the track points cannot be measured well, so that the method is based on a KNN method, improves the similarity distance, and classifies the ship track points.
As shown in fig. 1, a ship trajectory classification method based on similarity distance includes the following steps:
step 1: recording track point data of all ships within a delta t time period, preprocessing the track point data, and deleting outliers and null values; selecting a ship as a reference ship;
step 2: selecting track points of a reference ship at the t moment in a delta t time period as reference track points; calculating the position similarity distance between the reference track point and all other ship track points in the delta t time period by adopting the formula (1):
Distance1=R*arccos[sin(λ1)sin(λ2)+cos(λ1)cos(λ2)cos(l1-l2)] (1)
wherein R is the mean radius of the earth, l1、l2Longitude, λ, of two points of the track respectively1、λ2Respectively the latitude of the two track points;
and step 3: selecting a ship SOG value at a time period t, and calculating the speed similarity distance between the reference track point and all other ship track points in the time period delta t by adopting a formula (2):
Distance2=v1-v2 (2)
wherein v is1、v2Respectively the navigational speeds of the two track points;
and 4, step 4: step 2 and step 3, obtaining position similarity distances and speed similarity distances of all ship track points to form a data set;
and 5: defining the final similarity distance:
D=a*Distance1+(1-a)*Distance2 (3)
wherein a is weight, and a belongs to [0,1 ];
step 6: determining the optimal hyper-parameter by using a leave-one method;
selecting 1 piece in the data set as a test set, and using the rest as a training set; replacing the similarity distance in the KNN with D for training to obtain optimal hyper-parameters K and a;
and 7: the value a is taken into the formula (3), the final similarity distance between the reference track point and all other ship track points in the delta t time period is calculated, and all the final similarity distances are sorted according to the numerical value;
and 8: selecting the front K values of the sorted final similarity distance list, and counting the times of MMSI values of the ship corresponding to the ship track points for generating the front K final similarity distance values;
and step 9: and returning the MMSI of the ship with the most occurrence times, wherein the ship is the same as the reference ship.
FIG. 2 is a graph of classification accuracy of the method of the present invention using different values.
FIG. 3 is a graph showing the comparison between classification accuracy of the method of the present invention and that of the conventional KNN method.
As can be seen from the figure, the method of the invention achieves better effect.
Claims (1)
1. A ship track classification method based on similarity distance is characterized by comprising the following steps:
step 1: recording track point data of all ships within a delta t time period, preprocessing the track point data, and deleting outliers and null values; selecting a ship as a reference ship;
step 2: selecting track points of a reference ship at the t moment in a delta t time period as reference track points; calculating the position similarity distance between the reference track point and all other ship track points in the delta t time period by adopting the formula (1):
Distance1=R*arccos[sin(λ1)sin(λ2)+cos(λ1)cos(λ2)cos(l1-l2)] (1)
wherein R is the mean radius of the earth, l1、l2Longitude, λ, of two points of the track respectively1、λ2Respectively the latitude of the two track points;
and step 3: selecting a ship SOG value at a time period t, and calculating the speed similarity distance between the reference track point and all other ship track points in the time period delta t by adopting a formula (2):
Distance2=v1-v2 (2)
wherein v is1、v2Respectively the navigational speeds of the two track points;
and 4, step 4: step 2 and step 3, obtaining position similarity distances and speed similarity distances of all ship track points to form a data set;
and 5: defining the final similarity distance:
D=a*Distance1+(1-a)*Distance2 (3)
wherein a is weight, and a belongs to [0,1 ];
step 6: determining the optimal hyper-parameter by using a leave-one method;
selecting 1 piece in the data set as a test set, and using the rest as a training set; replacing the similarity distance in the KNN with D for training to obtain optimal hyper-parameters K and a;
and 7: the value a is taken into the formula (3), the final similarity distance between the reference track point and all other ship track points in the delta t time period is calculated, and all the final similarity distances are sorted according to the numerical value;
and 8: selecting the first K values of the sorted final similarity distance list, and counting the MMSI value times of the ship corresponding to the ship track points generating the first K final similarity distance values;
and step 9: and returning the MMSI value of the ship with the most occurrence times, wherein the ship is the same as the reference ship.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111572146.XA CN114492571B (en) | 2021-12-21 | 2021-12-21 | Ship track classification method based on similarity distance |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111572146.XA CN114492571B (en) | 2021-12-21 | 2021-12-21 | Ship track classification method based on similarity distance |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114492571A true CN114492571A (en) | 2022-05-13 |
CN114492571B CN114492571B (en) | 2024-03-01 |
Family
ID=81493958
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111572146.XA Active CN114492571B (en) | 2021-12-21 | 2021-12-21 | Ship track classification method based on similarity distance |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114492571B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021017577A1 (en) * | 2019-07-29 | 2021-02-04 | 南京莱斯网信技术研究院有限公司 | Ship-type-spoofing detection method employing ensemble learning |
CN113537386A (en) * | 2021-08-01 | 2021-10-22 | 大连海事大学 | Ship typical motion track self-adaptive mining method based on improved K-Medoids clustering |
-
2021
- 2021-12-21 CN CN202111572146.XA patent/CN114492571B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021017577A1 (en) * | 2019-07-29 | 2021-02-04 | 南京莱斯网信技术研究院有限公司 | Ship-type-spoofing detection method employing ensemble learning |
CN113537386A (en) * | 2021-08-01 | 2021-10-22 | 大连海事大学 | Ship typical motion track self-adaptive mining method based on improved K-Medoids clustering |
Non-Patent Citations (2)
Title |
---|
刘磊;初秀民;蒋仲廉;钟诚;张代勇;: "基于KNN的船舶轨迹分类算法", 大连海事大学学报, no. 03, 15 August 2018 (2018-08-15) * |
魏照坤;周康;魏明;史国友;: "基于AIS数据的船舶运动模式识别与应用", 上海海事大学学报, no. 02, 30 June 2016 (2016-06-30) * |
Also Published As
Publication number | Publication date |
---|---|
CN114492571B (en) | 2024-03-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103531043B (en) | Based on the boats and ships point-to-point hours underway evaluation method of course line coupling | |
CN109740494B (en) | Port identification method based on ship track big data | |
CN112906830B (en) | Automatic generation method of ship optimal route based on AIS big data | |
CN113312438B (en) | Marine target position prediction method integrating route extraction and trend judgment | |
CN113553682B (en) | Data-driven multi-level ship route network construction method | |
CN110309383A (en) | Ship trajectory clustering analysis method based on improved DBSCAN algorithm | |
CN110175633B (en) | Fishing boat track abnormity detection method based on Beidou satellite transmission data | |
CN112699315B (en) | AIS data-based ship abnormal behavior detection method | |
CN113537386B (en) | Ship typical motion trail self-adaptive mining method based on improved K-Medoids clustering | |
CN113283653B (en) | Ship track prediction method based on machine learning and AIS data | |
CN111240229B (en) | Fault information processing system based on intelligent ship berthing-off simulation test | |
CN115050214B (en) | AIS data-based ship collision risk prediction method | |
Xu et al. | Trajectory clustering for SVR-based Time of Arrival estimation | |
CN113988213A (en) | Ship in-dock repair identification method and system | |
Xu et al. | Improved vessel trajectory prediction model based on stacked-bigrus | |
CN115457300A (en) | Ship abnormal behavior detection method based on distance measurement and isolation mechanism | |
CN114492571A (en) | Ship track classification method based on similarity distance | |
CN101957384A (en) | Ship speed reciprocating measurement method | |
WO2020161843A1 (en) | Ship behavior analyzing device, ship behavior analyzing method, and non-transitory computer-readable medium | |
CN117312891A (en) | Track prediction method based on ship data | |
CN115587308A (en) | Method and device for determining navigation channel, electronic equipment and storage medium | |
CN112350733B (en) | Rapid track compression method based on effective distance | |
CN113525626A (en) | Ship predicted track correction method based on sea-land constraint | |
KR102631383B1 (en) | Predicting method for operating variable of ship based on artificial intelligence and computer readable recording medium for the same | |
Cai et al. | Development of a vision-based ship behavior characteristics extraction approach and comparison with K-means clustering |
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 |