Saved in:
Bibliographic Details
Main Authors: Tella, Dhanush, Tiriveedhi, Chandra Teja, Rishe, Naphtali, Tamir, Dan E., Tamir, Jonathan I.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.20054
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917818472071168
author Tella, Dhanush
Tiriveedhi, Chandra Teja
Rishe, Naphtali
Tamir, Dan E.
Tamir, Jonathan I.
author_facet Tella, Dhanush
Tiriveedhi, Chandra Teja
Rishe, Naphtali
Tamir, Dan E.
Tamir, Jonathan I.
contents We consider the task of classifying trajectories of boat activities as a proxy for assessing maritime threats. Previous approaches have considered entropy-based metrics for clustering boat activity into three broad categories: random walk, following, and chasing. Here, we comprehensively assess the accuracy of neural network-based approaches as alternatives to entropy-based clustering. We train four neural network models and compare them to shallow learning using synthetic data. We also investigate the accuracy of models as time steps increase and with and without rotated data. To improve test-time robustness, we normalize trajectories and perform rotation-based data augmentation. Our results show that deep networks can achieve a test-set accuracy of up to 100% on a full trajectory, with graceful degradation as the number of time steps decreases, outperforming entropy-based clustering.
format Preprint
id arxiv_https___arxiv_org_abs_2410_20054
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Evaluating Neural Networks for Early Maritime Threat Detection
Tella, Dhanush
Tiriveedhi, Chandra Teja
Rishe, Naphtali
Tamir, Dan E.
Tamir, Jonathan I.
Machine Learning
Artificial Intelligence
We consider the task of classifying trajectories of boat activities as a proxy for assessing maritime threats. Previous approaches have considered entropy-based metrics for clustering boat activity into three broad categories: random walk, following, and chasing. Here, we comprehensively assess the accuracy of neural network-based approaches as alternatives to entropy-based clustering. We train four neural network models and compare them to shallow learning using synthetic data. We also investigate the accuracy of models as time steps increase and with and without rotated data. To improve test-time robustness, we normalize trajectories and perform rotation-based data augmentation. Our results show that deep networks can achieve a test-set accuracy of up to 100% on a full trajectory, with graceful degradation as the number of time steps decreases, outperforming entropy-based clustering.
title Evaluating Neural Networks for Early Maritime Threat Detection
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2410.20054