US-12626179-B2 - System and methods for monitoring marine vessels using topic model to determine probabilistic maritime scenarios

US12626179B2US 12626179 B2US12626179 B2US 12626179B2US-12626179-B2

Abstract

A system is for monitoring marine vessels that generate automatic identification system (AIS) message data. The system may include a memory and a processor cooperating therewith to train a maritime scenario topic model using training textual data having known corresponding maritime scenarios associated therewith. The training textual data may include AIS message data. The processor operate the trained maritime scenario topic model on new textual data having unknown corresponding maritime scenarios to determine probabilistic maritime scenarios corresponding to the new textual data, where the new textual data includes new AIS message data. The processor may further generate an alert based upon the probabilistic maritime scenarios.

Inventors

John L. Delay
Mark D. Rahmes
DAVID A. MOTTARELLA
SAMER M. ABIFAKER

Assignees

EAGLE TECHNOLOGY, LLC

Dates

Publication Date: 20260512
Application Date: 20190627

Claims (14)

1 . A system for monitoring marine vessels that generate automatic identification system (AIS) message data, the system comprising: a memory and a processor cooperating therewith to process open source internet (OSINT) data from a plurality of different sources generated or consumed by passengers on the marine vessels to extract OSINT topic vectors therefrom correlated with at least one location of interest using a first infer topics module applying min/max normalization, and store the OSINT topic vectors in a columnar format in at least one binary data file within a data lake, process AIS message data from the marine vessels to extract AIS topic vectors therefrom correlated with the at least one location of interest using a second infer topics module applying min/max normalization, and store the AIS topic vectors in the columnar format in the at least one binary data file within the data lake, query the OSINT topic vectors and the AIS topic vectors from the at least one binary data file using on-line analytical processing (OLAP) and aggregation, operate an accuracy assessment module to train a maritime scenario topic model based upon a game theoretic optimization using a reward matrix to select between a plurality of different classification models using training textual data having known corresponding maritime scenarios associated therewith, the training textual data comprising the AIS topic vectors and the OSINT topic vectors, the accuracy assessment module performing the training to an accuracy level based upon an accuracy assessment of the topic vectors relative to truth topic vectors using a receiver operating characteristic (ROC) curve, operate the trained maritime scenario topic model on new textual data comprising OSINT topic vectors and AIS message vectors having unknown corresponding maritime scenarios to determine probabilistic maritime scenarios corresponding to the new textual data, the new textual data comprising new AIS topic vectors and the OSINT topic vectors, and generate an alert based upon the probabilistic maritime scenarios.
2 . The system of claim 1 wherein the accuracy assessment module performs the training further by performing singular value decomposition (SVD) on the topic vectors.
3 . The system of claim 2 wherein the accuracy assessment module performs the training further by determining correlation scores for the topic vectors using cosine similarity after performing SVD.
4 . The system of claim 3 wherein the accuracy assessment module performs the training further by performing an accuracy assessment of the topic vectors based upon the correlation scores using the ROC curve.
5 . The system of claim 1 wherein the processor operates the trained maritime scenario topic model based upon a thesaurus corresponding to maritime scenarios of interest.
6 . The system of claim 1 wherein the plurality of different classification models comprises at least some of nearest neighbor, Bayes, classification and prediction tree, multiple linear regression, and neural network models.
7 . A system for monitoring marine vessels that generate automatic identification system (AIS) message data, the system comprising: a memory and a processor cooperating therewith to process open source internet (OSINT) data from a plurality of different sources generated or consumed by passengers on the marine vessels to extract OSINT topic vectors therefrom correlated with at least one location of interest using a first infer topics module applying min/max normalization, and store the OSINT topic vectors in a columnar format in at least one binary data file within a data lake, process AIS message data from the marine vessels to extract AIS topic vectors therefrom correlated with the at least one location of interest using a second infer topics module applying min/max normalization, and store the AIS topic vectors in the columnar format in the at least one binary data file within the data lake, query the OSINT topic vectors and the AIS topic vectors from the at least one binary data file using on-line analytical processing (OLAP) and aggregation, operate an accuracy assessment module to train a maritime scenario topic model based upon a game theoretic optimization using a reward matrix to select between a plurality of different classification models from the training textual data generated using singular value decomposition (SVD) AIS topic vectors and OSINT topic vectors having known corresponding maritime scenarios associated therewith, the accuracy assessment module performing the training to an accuracy level based upon an accuracy assessment of the topic vectors relative to truth topic vectors using a receiver operating characteristic (ROC) curve, operate the trained maritime scenario topic model on new textual data comprising OSINT topic vectors and AIS message vectors having unknown corresponding maritime scenarios based upon a thesaurus corresponding to maritime scenarios of interest to determine probabilistic maritime scenarios of interest corresponding to the new textual data, the new textual data comprising new AIS topic vectors and the OSINT topic vectors, and generate an alert based upon the probabilistic maritime scenarios.
8 . The system of claim 7 wherein the accuracy assessment module performs the training further by determining correlation scores for the topic vectors using cosine similarity after performing SVD.
9 . The system of claim 7 wherein the processor trains the maritime scenario topic model based upon a plurality of different classification models comprising at least some of nearest neighbor, Bayes, classification and prediction tree, multiple linear regression, and neural network models.
10 . A method for monitoring marine vessels that generate automatic identification system (AIS) message data, the method comprising: processing open source internet (OSINT) data from a plurality of different sources generated or consumed by passengers on the marine vessels to extract OSINT topic vectors therefrom correlated with at least one location of interest using a first infer topics module applying min/max normalization, and store the OSINT topic vectors in a columnar format in at least one binary data file within a data lake, using a computer, processing AIS message data from the marine vessels to extract AIS topic vectors therefrom correlated with the at least one location of interest using a second infer topics module applying min/max normalization, and storing the AIS topic vectors in the columnar format in the at least one binary data file within the data lake, using the computer, querying the OSINT topic vectors and the AIS topic vectors from the at least one binary data file using on-line analytical processing (OLAP) and aggregation, operating an accuracy assessment module for training a maritime scenario topic model with the computer based upon a game theoretic optimization using a reward matrix to select between a plurality of different classification models using training textual data having known corresponding maritime scenarios associated therewith, the training textual data comprising the AIS topic vectors and the OSINT topic vectors, the accuracy assessment module performing the training to an accuracy level based upon an accuracy assessment of the topic vectors relative to truth topic vectors using a receiver operating characteristic (ROC) curve; operating the trained maritime scenario topic model with the computer on new textual data comprising OSINT topic vectors and AIS message vectors having unknown corresponding maritime scenarios to determine probabilistic maritime scenarios corresponding to the new textual data, the new textual data comprising new AIS topic vectors and the OSINT topic vectors; and generating an alert with the computer based upon the probabilistic maritime scenarios.
11 . The method of claim 10 wherein operating the accuracy assessment module further comprises operating the accuracy assessment module for performing singular value decomposition (SVD) on the topic vectors.
12 . The method of claim 11 wherein operating the accuracy assessment module further comprises operating the accuracy assessment module for determining correlation scores for the topic vectors using cosine similarity after performing SVD.
13 . The method of claim 10 wherein operating the trained maritime scenario topic model comprises operating the trained maritime scenario topic model based upon a thesaurus corresponding to maritime scenarios of interest.
14 . The method of claim 10 wherein operating the maritime scenario topic model comprises operating the trained maritime scenario topic model based upon a plurality of different classification models comprising at least some of nearest neighbor, Bayes, classification and prediction tree, multiple linear regression, and neural network models.

Description

TECHNICAL FIELD The present disclosure relates to marine vessel tracking systems, and, more particularly, to systems for monitoring marine vessels that send Automatic Identification System (AIS) signals and related methods. BACKGROUND The Automatic Identification System (AIS) is a tracking system for identifying and locating marine vessels by electronically exchanging data with other nearby vessels, AIS base stations, and satellites. AIS information may be used in conjunction with marine radar to help avoid collision with other vessels. AIS transmissions include information such as vessel identifiers, position, course, and speed. AIS not only allows oncoming vessels to know each other's locations, but it also allows maritime authorities to track and monitor vessel movements as well. AIS devices utilize information from satellite positioning systems (e.g., GPS), as well as other electronic navigation sensors, and communicate the AIS data via a very high frequency (VHF) transceiver. U.S. Pat. Pub. No. 2009/0161797 to Cowles et al. discloses a system for detecting and decoding Automatic Identification System (AIS) signals which includes a plurality of orbital satellites. Each orbital satellite has at least one antenna with at least one antenna polarization for receiving a radio frequency signal. Each orbital satellite also has a communication module for accepting the radio frequency signal, converting the radio frequency signal into sampled packetized data for insertion into a raw data stream, inserting a plurality of signal parameters into the raw data stream, and transmitting the raw data stream and a telemetry data stream to at least one ground station. A processor located at the ground station receives and processes the raw data stream to identify one or more candidate AIS message signals. Despite the existence of such systems, further advancements in marine vessel monitoring may be desirable in certain applications. SUMMARY A system is for monitoring marine vessels that generate automatic identification system (AIS) message data. The system may include a memory and a processor cooperating therewith to train a maritime scenario topic model using training textual data having known corresponding maritime scenarios associated therewith. The training textual data may comprise AIS message data. The processor may also operate the trained maritime scenario topic model on new textual data having unknown corresponding maritime scenarios to determine probabilistic maritime scenarios corresponding to the new textual data, where the new textual data includes new AIS message data. The processor may further generate an alert based upon the probabilistic maritime scenarios. More particularly, the processor may train the maritime scenario topic model by generating topic vectors from the training textual data. For example, the processor may train the maritime scenario topic model further by performing singular value decomposition (SVD) on the topic vectors. Additionally, the processor may train the maritime scenario topic model further by determining correlation scores for the topic vectors using cosine similarity after performing SVD. Moreover, the processor may train the maritime scenario topic model further by performing an accuracy assessment of the topic vectors based upon the correlation scores using a receiver operating characteristic (ROC) curve. In an example embodiment, the processor may operate the trained maritime scenario topic model based upon a thesaurus corresponding to maritime scenarios of interest. Additionally, the processor may train the maritime scenario topic model based upon a plurality of different classification models. By way of example, the plurality of different classification models may comprise at least some of nearest neighbor, Bayes, classification and prediction tree, multiple linear regression, and neural network models. Furthermore, the processor may use a reward matrix to select between the different classification models for the training textual data. In accordance with another example implementation, the processor may train the maritime scenario topic model also using open source social media data having known corresponding maritime scenarios associated therewith. A related method is for monitoring marine vessels that generate AIS message data. The method may include training a maritime scenario topic model with a computer using training textual data having known corresponding maritime scenarios associated therewith, with the training textual data comprising AIS message data. The method may include operating the trained maritime scenario topic model with the computer on new textual data having unknown corresponding maritime scenarios to determine probabilistic maritime scenarios corresponding to the new textual data, where the new textual data includes new AIS message data. The method may further include generating an alert with the computer based upon the probabilistic maritime scena