Ship type counterfeit monitoring method based on ensemble learning

An integrated learning and ship technology, applied in the field of ship type counterfeiting monitoring based on integrated learning, can solve the problems of aggravating the hidden dangers of water transportation safety, increasing the supervision difficulty of the maritime department, and low accuracy, achieving efficiency improvement, solving poor efficiency, The effect of fast monitoring speed

Active Publication Date: 2019-12-31
NANJING LES CYBERSECURITY & INFORMATION TECH RES INST CO LTD
View PDF11 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The counterfeiting of AIS types, mainly fishing boats, has undoubtedly greatly increased the difficulty of supervision by the maritime sector and aggravated the safety hazards of water transportation
In the face of counterfeiting of ship types, traditional maritime supervision methods can only estimate the position, speed, course and other information in the ship’s AIS message based on experience. This method is not only extremely inefficient, but also often has low accuracy

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Ship type counterfeit monitoring method based on ensemble learning
  • Ship type counterfeit monitoring method based on ensemble learning
  • Ship type counterfeit monitoring method based on ensemble learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] like figure 1 As shown, a ship type counterfeiting detection method based on ensemble learning includes the following steps:

[0048] (1) Cleaning and classification of ship historical track data;

[0049] (11) Set rules to clean historical data

[0050] like figure 2 As shown, first set the cleaning rules, including but not limited to the location should be within the responsibility area and cannot be on land, the speed cannot be negative, the course and heading cannot be negative and cannot be greater than 360 degrees, for the position and speed in the historical data , heading and other data items that conform to the outlier point cleaning rules are removed;

[0051] (12) Deduplication of historical data

[0052] Traverse the data, and remove the track points with the same time, position, and heading as duplicate points to prevent them from affecting the statistical results;

[0053] (13) Perform data type adjustment

[0054] For some ship types with naming ch...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a ship type counterfeit monitoring method based on ensemble learning. The ship type counterfeit monitoring method comprises: cleaning historical data of a ship and adjusting thetype; carrying out feature selection, carrying out format conversion, carrying out sliding window feature generation and carrying out feature normalization; carrying out selection and composition ofa classifier, and setting a classifier evaluation function; judging and monitoring a real-time ship target type. According to the invention, the historical ship track message can be utilized to trainand generate the model for judging and monitoring the ship type, judge and monitor the type of the real-time ship target, alarm the suspected type of counterfeit target, and help the maritime department to discover the type of counterfeit ship target in time.

Description

technical field [0001] The present invention relates to a ship type monitoring method, in particular to a ship type counterfeit monitoring method based on integrated learning Background technique [0002] With the development of my country's water production activities, the number of ships navigating in major ports and waterways is increasing. The increasing number of ships also brings with it an increasing risk of navigational accidents. Undoubtedly, the counterfeiting of AIS types mainly by fishing boats has greatly increased the difficulty of supervision by the maritime department and aggravated the safety hazards of water transportation. In the face of ship counterfeiting, traditional maritime supervision methods can only estimate based on experience based on information such as position, speed, and heading in the ship's AIS message. This method is not only extremely inefficient, but also often inaccurate. Early and better detection of type counterfeiting violations ca...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/33G06F16/35G06K9/62G06N20/20
CPCG06F16/334G06F16/355G06N20/20G06F18/24323
Inventor 段然隋远沈昌力王维圳白正
Owner NANJING LES CYBERSECURITY & INFORMATION TECH RES INST CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap