Metraipolis › archive › dc_fe980ba82b72

Towards Deployable Underwater Vessel Classification — arXiv:2609.29179

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29179
License (as archived)
CC0-1.0
Archived
2026-10-08T05:26:29.958Z
SHA-256 of the archived text
9575bf286da10c8b75a5e576ccec85d076f509d8c47ca31b901bb8d5f5965bab
Stable URL of this page
https://metraipolis.com/documento/dc_fe980ba82b72

How to cite

Towards Deployable Underwater Vessel Classification — arXiv:2609.29179 — arXiv (en), https://arxiv.org/abs/2609.29179 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fe980ba82b72 (Metraipolis archive dc_fe980ba82b72, sha256 9575bf286da10c8b75a5e576ccec85d076f509d8c47ca31b901bb8d5f5965bab)
BibTeX
@misc{dcfe980ba82b72,
  title = {Towards Deployable Underwater Vessel Classification — arXiv:2609.29179},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29179},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fe980ba82b72; sha256 9575bf286da10c8b75a5e576ccec85d076f509d8c47ca31b901bb8d5f5965bab},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29179. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We propose a compact underwater acoustic classification framework combining multi-representation feature engineering, temporal statistical pooling, and compact convolutional architectures designed for acoustic time-frequency and cochlear representations. We investigate multiple conventional and auditory-inspired representations and first evaluate lightweight classifiers and Conventional Neural Networks (CNNs) on ShipsEar dataset. On the provided split, a two-layer CNN achieves a macro F1 of 0.9918, while a Radial Basis Function Support Vector Machine (RBF-SVM) reaches 0.9883. However, source-recording provenance cannot be reconstructed, preventing verification of recording-independent generalisation. We therefore evaluate on DeepShip dataset using recording-level partitioning before segmentation. Under this protocol, a 157K-parameter compact CNN achieves a test macro F1 of 0.7226, while an 11.17M-parameter ResNet18 provides no improvement in validation performance under the matched setting. These results demonstrate the importance of representation-aware feature and model design, together with rigorous recording-level evaluation, for classification performance and deployability in compact underwater acoustic systems.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.LG).
Categorie arXiv: Sound (cs.SD) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.29179 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T04:50:39.610Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).