Giter Site home page Giter Site logo

shipsear-an-unofficial-train-test-split's Introduction

ShipsEar-An-Unofficial-Train-Test-Split

An unofficial train-test split for ShipsEar: An underwater vessel noise database

Background

The ShipsEar dataset (https://doi.org/10.1016/j.apacoust.2016.06.008) is widely used in the field of underwater acoustics as one of the most commonly utilized underwater noise databases.

However, the official train-test split is unavailable, which hinders fair comparisons across various works.
This repository aims to address this limitation by providing an unofficial training-test split, enabling works to achieve fair comparisons and credible benchmarks.

We hope that by providing this training-test split, it will contribute to the growth and advancement of the academic community in the field of underwater acoustics.

Train-Test Split

This repository offers two train-test splits for the following tasks:

  1. 9-class recognition involving "Dredger, Fishboat, Motorboat, Musselboat, Naturalambientnoise, Oceanliner, Passengers, RORO, Sailboat." The remaining three categories (Pilotship, Trawler, Tugboat) are excluded due to the limited number of recordings available.
  2. 12-class recognition encompassing "Dredger, Fishboat, Motorboat, Musselboat, Naturalambientnoise, Oceanliner, Passengers, Pilotship, RORO, Sailboat, Trawler, Tugboat."

To prevent the model from overfitting to specific test data, distinct train-test splits are provided for 9-class and 12-class recognition. If the model demonstrates promising performance in both 9-class and 12-class recognition, it substantiates its generalization ability.

Notably, 12-class recognition poses a greater challenge as it evaluates the model's few-shot learning capabilities. Conversely, 9-class recognition is relatively simpler due to the relatively sufficient amount of data available in each class.

Based on your approach, you can select the appropriate task (or both) and utilize the corresponding train-test split.

Existing work using this Train-Test Split

Work Task Accuracy 30s-level Repo DOI
SIR & LMR 9-class 83.45 - https://doi.org/10.1016/j.oceaneng.2023.114926
CMoE 9-class 86.21 CMoE_code https://doi.org/10.1016/j.eswa.2024.123431
M3-TSE 9-class 87.07±2.43 - https://doi.org/10.1121/10.0026481
AMTNet 12-class 80.95±0.84 - https://doi.org/10.1121/10.0026598

Citation

If you have utilized the training-test split provided by this repository, we kindly request that you reference the following article in your work:

# IF YOU USE 9-CLASS SPLIT, PLEASE CITE:
@article{xie2024unraveling,
  title={Unraveling complex data diversity in underwater acoustic target recognition through convolution-based mixture of experts},
  author={Xie, Yuan and Ren, Jiawei and Xu, Ji},
  journal={Expert Systems with Applications},
  pages={123431},
  year={2024},
  publisher={Elsevier}
}

@article{xie2024advancing,
  title={Advancing robust underwater acoustic target recognition through multitask learning and multi-gate mixture of experts},
  author={Xie, Yuan and Ren, Jiawei and Li, Junfeng and Xu, Ji},
  journal={The Journal of the Acoustical Society of America},
  volume={156},
  number={1},
  pages={244--255},
  year={2024},
  publisher={AIP Publishing}
}

# IF YOU USE 12-CLASS SPLIT, PLEASE CITE:
@article{xie2024adversarial,
  title={Adversarial multi-task underwater acoustic target recognition: Toward robustness against various influential factors},
  author={Xie, Yuan and Xu, Ji and Ren, Jiawei and Li, Junfeng},
  journal={The Journal of the Acoustical Society of America},
  volume={156},
  number={1},
  pages={299--313},
  year={2024},
  publisher={AIP Publishing}
}


# Also, do not forget to cite:
@article{santos2016shipsear,
  title={ShipsEar: An underwater vessel noise database},
  author={Santos-Dom{\'\i}nguez, David and Torres-Guijarro, Soledad and Cardenal-L{\'o}pez, Antonio and Pena-Gimenez, Antonio},
  journal={Applied Acoustics},
  volume={113},
  pages={64--69},
  year={2016},
  publisher={Elsevier}
}


Train-Test Split for 9 classes

Category Training set Test set
Dredger Dredger_80__04_10_12_adricristuy.wav
Dredger_93__A__Draga_1.wav
Dredger_94__A__Draga_2.wav
Dredger_96__A__Draga_4.wav
Dredger_95__A__Draga_3.wav
Fishboat Fishboat_73__23_07_13_H3_pesqMariCarmen.wav
Fishboat_74__23_07_13_H3_pesqSaladinoPrimero.wav
Fishboat_76__23_07_13_H3_pesquero2.wav
Fishboat_75__23_07_13_H3_pesquero1.wav
Motorboat Motorboat_21__18_07_13_lanchaMotora.wav
Motorboat_26__19_07_13_Lancha.wav
Motorboat_33__19_07_13_lanchaDuda_Sale.wav
Motorboat_39__19_07_13_lanchaMotora_Entra.wav
Motorboat_45__19_07_13_yate_Sale.wav
Motorboat_51__23_07_13_H3_lancha2_interf.wav
Motorboat_52__23_07_13_H3_lancha3_interf.wav
Motorboat_70__23_07_13_H2_yatePeq.wav
Motorboat_77__23_07_13_H3_Planeadora.wav
Motorboat_79__23_07_13_H3_zodiac.wav
Motorboat_27__19_07_13_Lancha2.wav
Motorboat_50__23_07_13_H3_lancha1.wav
Motorboat_72__23_07_13_H3_lancha2.wav
Musselboat Musselboat_46__23_07_13_H3_bateero1.wav
Musselboat_47__23_07_13_H2_bateero2.wav
Musselboat_49__23_07_13_H1_bateero4.wav
Musselboat_66__23_07_13_H3_Pesquerito2_Velero.wav
Musselboat_48__23_07_13_H3_bateero3_interf.wav
Naturalambientnoise Naturalambientnoise_81__25_09_13_H3_corriente.wav
Naturalambientnoise_82__27_09_13_H3_lluvia.wav
Naturalambientnoise_84__27_09_13_H3_viento.wav
Naturalambientnoise_85__E__1L.wav
Naturalambientnoise_86__E__2M.wav
Naturalambientnoise_88__E__4L.wav
Naturalambientnoise_89__E__5M.wav
Naturalambientnoise_90__E__6H.wav
Naturalambientnoise_91__E__7H_N.wav
Naturalambientnoise_83__27_09_13_H3_oleaje.wav
Naturalambientnoise_87__E__3H.wav
Naturalambientnoise_92__E__8H_N.wav
Oceanliner Oceanliner_16__10_07_13_mscOpera_InicioSalida.wav
Oceanliner_22__19_07_13_adventure_maniobra.wav
Oceanliner_23__19_07_13_adventure_parado.wav
Oceanliner_25__19_07_13_adventureOfTheSea_llegando.wav
Oceanliner_69__23_07_13_H2_costaVoyager.wav
Oceanliner_24__19_07_13_adventureFrenando_duda.wav
Oceanliner_71__23_07_13_H3_Discovery_UK_DUDA.wav
Passengers Passengers_6__10_07_13_marDeCangas_Entra.wav
Passengers_7__10_07_13_marDeCangas_Espera.wav
Passengers_8__10_07_13_marDeOnza_Entra.wav
Passengers_10__10_07_13_marDeOnza_Sale.wav
Passengers_11__10_07_13_minhoUno_Entra.wav
Passengers_12__10_07_13_minhoUno_Sale.wav
Passengers_14__10_07_13_piraCies_Espera.wav
Passengers_17__10_07_13_visionSub_Entra.wav
Passengers_32__19_07_13_Arroios_llega.wav
Passengers_34__19_07_13_MarDeOnza_Llega.wav
Passengers_36__19_07_13_MinoUno_Sale.wav
Passengers_38__19_07_13_Arroios_Sale_2entran.wav
Passengers_40__19_07_13_MarDeCangas_Llega_Interf.wav
Passengers_41__19_07_13_MinoUno_Entra.wav
Passengers_43__19_07_13_PirataDeCies_Llega_Interf.wav
Passengers_53__23_07_13_H3_PirataSalvora_Llega1.wav
Passengers_54__23_07_13_H3_PirataSalvora_SALE1.wav
Passengers_59__23_07_13_H2_MarDeMouro.wav
Passengers_60__23_07_13_H3_MarDeCangas_LLEGA.wav
Passengers_61__23_07_13_H3_MarDeCangas_SALE-2.wav
Passengers_63__23_07_13_H3_MarDeOnza_LLEGA.wav
Passengers_64__23_07_13_H3_MarDeOnza_SALE.wav
Passengers_67__23_07_13_H3_PirataCiesSale.wav
Passengers_9__10_07_13_marDeOnza_Espera.wav
Passengers_13__10_07_13_piraCies_Entra.wav
Passengers_35__19_07_13_MarDeOnza_sale.wav
Passengers_42__19_07_13_PirataCies_Sale.wav
Passengers_55__23_07_13_H3_PirataSalvora_SALE2.wav
Passengers_62__23_07_13_H3_MarDeCangas_SALE.wav
Passengers_65__23_07_13_H3_MinhoUno_LLEGA.wav
RORO RORO_18__18_07_13_AutoPrideEntra.wav
RORO_19__18_07_13_AutoprideMarchaAtras.wav
RORO_58__23_07_13_H2_EimskipReefer_Pesquerito1.wav
RORO_20__18_07_13_AutopridePrepManiobra.wav
RORO_78__23_07_13_H3_vikingChance.wav
Sailboat Sailboat_37__19_07_13_Velero_Sale.wav
Sailboat_56__23_07_13_H3_velero1.wav
Sailboat_68__23_07_13_H3_veleroMarisol.wav
Sailboat_57__23_07_13_H3_velero2.wav
---- ---- ----
Total Number 64 recordings 21 recordings

Train-Test Split for 12 classes

Category Training set Test set
Dredger Dredger_80__04_10_12_adricristuy.wav
Dredger_94__A__Draga_2.wav
Dredger_96__A__Draga_4.wav
Dredger_93__A__Draga_1.wav
Dredger_95__A__Draga_3.wav
Fishboat Fishboat_73__23_07_13_H3_pesqMariCarmen.wav
Fishboat_74__23_07_13_H3_pesqSaladinoPrimero.wav
Fishboat_76__23_07_13_H3_pesquero2.wav
Fishboat_75__23_07_13_H3_pesquero1.wav
Motorboat Motorboat_27__19_07_13_Lancha2.wav
Motorboat_33__19_07_13_lanchaDuda_Sale.wav
Motorboat_39__19_07_13_lanchaMotora_Entra.wav
Motorboat_45__19_07_13_yate_Sale.wav
Motorboat_50__23_07_13_H3_lancha1.wav
Motorboat_52__23_07_13_H3_lancha3_interf.wav
Motorboat_70__23_07_13_H2_yatePeq.wav
Motorboat_72__23_07_13_H3_lancha2.wav
Motorboat_77__23_07_13_H3_Planeadora.wav
Motorboat_79__23_07_13_H3_zodiac.wav
Motorboat_21__18_07_13_lanchaMotora.wav
Motorboat_26__19_07_13_Lancha.wav
Motorboat_51__23_07_13_H3_lancha2_interf.wav
Musselboat Musselboat_47__23_07_13_H2_bateero2.wav
Musselboat_48__23_07_13_H3_bateero3_interf.wav
Musselboat_49__23_07_13_H1_bateero4.wav
Musselboat_46__23_07_13_H3_bateero1.wav
Musselboat_66__23_07_13_H3_Pesquerito2_Velero.wav
Naturalambientnoise Naturalambientnoise_82__27_09_13_H3_lluvia.wav
Naturalambientnoise_83__27_09_13_H3_oleaje.wav
Naturalambientnoise_84__27_09_13_H3_viento.wav
Naturalambientnoise_86__E__2M.wav
Naturalambientnoise_87__E__3H.wav
Naturalambientnoise_89__E__5M.wav
Naturalambientnoise_90__E__6H.wav
Naturalambientnoise_91__E__7H_N.wav
Naturalambientnoise_92__E__8H_N.wav
Naturalambientnoise_81__25_09_13_H3_corriente.wav
Naturalambientnoise_85__E__1L.wav
Naturalambientnoise_88__E__4L.wav
Oceanliner Oceanliner_16__10_07_13_mscOpera_InicioSalida.wav
Oceanliner_23__19_07_13_adventure_parado.wav
Oceanliner_25__19_07_13_adventureOfTheSea_llegando.wav
Oceanliner_69__23_07_13_H2_costaVoyager.wav
Oceanliner_71__23_07_13_H3_Discovery_UK_DUDA.wav
Oceanliner_22__19_07_13_adventure_maniobra.wav
Oceanliner_24__19_07_13_adventureFrenando_duda.wav
Passengers Passengers_6__10_07_13_marDeCangas_Entra.wav
Passengers_8__10_07_13_marDeOnza_Entra.wav
Passengers_9__10_07_13_marDeOnza_Espera.wav
Passengers_10__10_07_13_marDeOnza_Sale.wav
Passengers_11__10_07_13_minhoUno_Entra.wav
Passengers_12__10_07_13_minhoUno_Sale.wav
Passengers_13__10_07_13_piraCies_Entra.wav
Passengers_17__10_07_13_visionSub_Entra.wav
Passengers_32__19_07_13_Arroios_llega.wav
Passengers_34__19_07_13_MarDeOnza_Llega.wav
Passengers_36__19_07_13_MinoUno_Sale.wav
Passengers_38__19_07_13_Arroios_Sale_2entran.wav
Passengers_41__19_07_13_MinoUno_Entra.wav
Passengers_42__19_07_13_PirataCies_Sale.wav
Passengers_53__23_07_13_H3_PirataSalvora_Llega1.wav
Passengers_55__23_07_13_H3_PirataSalvora_SALE2.wav
Passengers_59__23_07_13_H2_MarDeMouro.wav
Passengers_60__23_07_13_H3_MarDeCangas_LLEGA.wav
Passengers_62__23_07_13_H3_MarDeCangas_SALE.wav
Passengers_63__23_07_13_H3_MarDeOnza_LLEGA.wav
Passengers_64__23_07_13_H3_MarDeOnza_SALE.wav
Passengers_65__23_07_13_H3_MinhoUno_LLEGA.wav
Passengers_67__23_07_13_H3_PirataCiesSale.wav
Passengers_7__10_07_13_marDeCangas_Espera.wav
Passengers_14__10_07_13_piraCies_Espera.wav
Passengers_35__19_07_13_MarDeOnza_sale.wav
Passengers_40__19_07_13_MarDeCangas_Llega_Interf.wav
Passengers_43__19_07_13_PirataDeCies_Llega_Interf.wav
Passengers_54__23_07_13_H3_PirataSalvora_SALE1.wav
Passengers_61__23_07_13_H3_MarDeCangas_SALE-2.wav
Pilotship Pilotship_29__19_07_13_practico.wav Pilotship_30__19_07_13_practico2.wav
RORO RORO_18__18_07_13_AutoPrideEntra.wav
RORO_19__18_07_13_AutoprideMarchaAtras.wav
RORO_58__23_07_13_H2_EimskipReefer_Pesquerito1.wav
RORO_20__18_07_13_AutopridePrepManiobra.wav
RORO_78__23_07_13_H3_vikingChance.wav
Sailboat Sailboat_37__19_07_13_Velero_Sale.wav
Sailboat_57__23_07_13_H3_velero2.wav
Sailboat_68__23_07_13_H3_veleroMarisol.wav
Sailboat_56__23_07_13_H3_velero1.wav
Trawler Trawler_28__19_07_13_NuevoRiaAldan.wav [15-125 second] Trawler_28__19_07_13_NuevoRiaAldan.wav [125-163 second]
Tugboat Tugboat_15__10_07_13_radaUno_Pasa.wav Tugboat_31__19_07_13_RemolcadorArrancaPara.wav
---- ---- ----
Total Number 65 recordings 26 recordings

It is worth mentioning that the ``Trawler'' category has only one recording, so when dividing the training and test sets, this recording is divided into two non-overlapping segments, which can be downloaded at:
https://github.com/xy980523/ShipsEar-An-Unofficial-Train-Test-Split/releases/download/main/Trawler_28__19_07_13_NuevoRiaAldan_train.wav
https://github.com/xy980523/ShipsEar-An-Unofficial-Train-Test-Split/releases/download/main/Trawler_28__19_07_13_NuevoRiaAldan_test.wav

shipsear-an-unofficial-train-test-split's People

Contributors

xy980523 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar

Forkers

wxt808823

shipsear-an-unofficial-train-test-split's Issues

Can you send me the full database?

Can you send me the full database? Thank you very much. I sent an email to the address at the bottom of the web page to ask for full database but have not received anything yet.

你好

请问您用的ShipsEar数据集是全的吗?还是不完整的?谢谢

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.