Evaluating Neural Networks for Early Maritime Threat Detection
This work addresses maritime security by improving threat detection, but it is incremental as it compares existing neural network methods to entropy-based approaches on synthetic data.
The paper tackled the problem of classifying boat trajectories for maritime threat detection by evaluating neural networks against entropy-based clustering, achieving up to 100% test-set accuracy on full trajectories with performance degrading gracefully as time steps decreased.
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.