Matches in Nanopublications for { ?s ?p ?o <https://w3id.org/np/RAEEWZakGEYasyLtGIutveyXyO0iEV7q5XCcUItPwUSeI/assertion>. }
- 66f444e7-3dd4-45e4-ba98-b4e391865ea8 type Concept assertion.
- 79d05959-407f-4a39-a318-fb91bd8fb55b type Concept assertion.
- 814949bc-4842-44f7-81f1-36038bb181b8 type Concept assertion.
- 86f2dde1-a2f7-4522-9cfa-176ea018fafe type Phrase assertion.
- 89348c0d-c0dc-4cd9-b15f-78e7375e2229 type Organization assertion.
- 89cf8c4d-e1f0-42eb-98e3-b6d9eeee65ed type Sentence assertion.
- 89f3b193-bdb9-4c95-a318-ebb3680c4e91 type Lemma assertion.
- 8c4689d8-c414-4fc6-b146-5116be29b610 type FieldOfResearch assertion.
- 8d1e60f3-c584-4c46-8b02-17721be0432d type Concept assertion.
- 94586186-05a5-4196-bfdf-e435435eb686 type Lemma assertion.
- 9cfe1dc2-fa7f-4e38-bad8-2bb134d4c849 type Concept assertion.
- a60e1260-04e0-416b-9cbf-4c20c5879209 type Concept assertion.
- adf9ae93-b583-4926-af0d-24582dc923e4 type IPTC assertion.
- b06cbca1-f427-4bb3-bbb8-74f6bc52c810 type Concept assertion.
- c052e832-c5d2-4ce8-9c11-eedfcfb9ab4e type Concept assertion.
- ce0477be-634d-495f-a61c-c2ea805e3574 type Concept assertion.
- cea696a5-37aa-40e2-b1c3-4dac165bf713 type Concept assertion.
- d10e2676-8df4-4ad2-841c-d74c2e1fd006 type Phrase assertion.
- defd14f6-e79a-4cb4-ad0d-23f7f7c539b3 type Sentence assertion.
- e8c52532-a63e-4a48-895f-fc65557746ec type Lemma assertion.
- f1a3d801-1c37-42e8-9ac9-114d3cea7dbe type NASA assertion.
- 3949 type DefinedTerm assertion.
- 5171f956-448b-4fd8-9a79-f091e53c4a0f type GeoCoordinates assertion.
- bd12751b-5767-4c6b-89ad-d851a797a11b type GeoCoordinates assertion.
- db43eb51-8abc-4a9b-acf8-b77434119670 type Place assertion.
- e6bb65bf-c136-4a7f-be68-894c5ed9ca21 type Place assertion.
- 5c2b7b95-a99c-4489-b0ac-f656a65b90f7 copyrightNotice "© MAELSTROM - Smart technology for MArinE Litter SusTainable RemOval and Management funded by the European Union, Programme H2020-EU.3.2.5.1. Grant agreement No 101000832. https://doi.org/10.3030/101000832." assertion.
- 5c2b7b95-a99c-4489-b0ac-f656a65b90f7 archivedAtTime "2025-06-16 11:46:27.588074+00:00" assertion.
- 5c2b7b95-a99c-4489-b0ac-f656a65b90f7 archivedBy 0000-0003-2388-0744 assertion.
- 5c2b7b95-a99c-4489-b0ac-f656a65b90f7 hasArchive 5c2b7b95-a99c-4489-b0ac-f656a65b90f7 assertion.
- 5c2b7b95-a99c-4489-b0ac-f656a65b90f7 isArchiveOf 5c2b7b95-a99c-4489-b0ac-f656a65b90f7 assertion.
- 5c2b7b95-a99c-4489-b0ac-f656a65b90f7 isFinalized "True" assertion.
- document description "The multiplication of publicly available datasets makes it possible to develop Deep Learning models for many real-world applica tions. However, some domains are still poorly explored, and their related datasets are often small or inconsistent. In addition, some biases linked to the dataset construction or labeling may give the impression that a model is particularly efficient. Therefore, evaluating a model requires a clear understanding of the database. Moreover, a model often reflects a given dataset’s performance and may deteriorate if a shift exists between the training dataset and real-world data. In this paper, we derive a more consistent and balanced version of the TrashCan [6] image dataset, called UNO, to evaluate models for de tecting non-natural objects in the underwater environment. We pro pose a method to balance the number of annotations and images for cross-evaluation. We then compare the performance of a SOTA object detection model when using TrashCAN and UNO datasets. Addition ally, we assess covariate shift by testing the model on an image dataset for real-world application. Experimental results show significantly better and more consistent performance using the UNO dataset. The UNO database and the code are publicly av https://github.com/CBarrelet/balanced_kfold" assertion.
- 13952176 description "Three underwater macro-litter image datasets for object detection in YOLO format: UNO dataset: All details are available in From TrashCan to UNO: Deriving an Underwater Image Dataset to Get a More Consistent and Balanced Version, C.Barrelet et al, ICPR 2022 MORGANE dataset: Images taken in shallow water in the harbors near Montpellier, France VENICE dataset: Images taken during the MAELSTROM experiments in Venice, Italy" assertion.
- 14929590 description "Petrizzo, A., MOSCHINO, V., Madricardo, F., Ghezzo, M., Galvez, D., Rodriguez, M., & ferrari, . nicola . (2022). D5.1 Report on site identification and installation of the Seabed Cleaning System in Venice. MAELSTROM Project. https://doi.org/10.5281/zenodo.14929590" assertion.
- 14929678 description "Gouttefarde, M., & Barrelet, C. (2024). D3.3 Preliminary report on the Cable robot autonomous control using Machine learning for litter identification. MAELSTROM Project. https://doi.org/10.5281/zenodo.14929678" assertion.
- 14930072 description "Ehrhorn, P., Iglesias, I., Vieira, L., & Sousa Pinto, I. (2021). D5.3 Definition of location for surface/water column removal device in the Porto region, Portugal. MAELSTROM Project. https://doi.org/10.5281/zenodo.14930072" assertion.
- 14931001 description "Rodriguez, M., & Gouttefarde, M. (2022). D3.1 Report on the cable robot design and teleoperated control. MAELSTROM Project. https://doi.org/10.5281/zenodo.14931001" assertion.
- 14931140 description "Gouttefarde, M., & Barrelet, C. (2024). D3.2 Report and videos about the cable robot control with shared autonomy. MAELSTROM Project. https://doi.org/10.5281/zenodo.14931140" assertion.
- 15544106 description "Iglesias, I., Vieira, L., Antunes, S., Kett, G., Fantinati, D. del O. A., Nogueira, S., Bio, A., Sousa-Pinto, I., Buschman, F. A., Mira Veiga, J., Pessoa, A., Zingariello, D., & Mule'Stagno, L. (2025). D5.4 Final Report on operation of the surface and water column removal technology in the Porto region. MAELSTROM Project. https://doi.org/10.5281/zenodo.15544106" assertion.
- 15546289 description "Ferrari, N., Fantin, A., Rodríguez Mijangos, M., Sallé, D., Herve, P.-E., Gorrotxategi, J., Oyarzabal, A., Culla, D., Gouttefarde, M., Creuze, V., Barrelet, C., Temperini, H. O., Petrizzo, A., MOSCHINO, V., Mesghez, S., Lahami, T., Lorenzetti, G., & Madricardo, F. (2025). D5.2 Final report on operation of the Seabed Cleaning System in Venice. MAELSTROM Project. https://doi.org/10.5281/zenodo.15546289" assertion.
- cdd7e89f-7013-45cd-9d15-00c4d7fe19fa description "The robotic seabed cleaning platform developed by TECNALIA, CNRS- LIRMM and “Servizi Tecnici”, consists in a floating platform which, through cables and winches, the seabed cleaning robot is attached. The structure is equipped with a set of sensors for underwater perception to control the robot and detect & identify the marine litter to be removed. Moreover, the robotic platform is characterized by two different tools that allow to collect the ML on the seabed: a drudge to suck up smaller litter and a gripper to grasps larger items like tires, parts of boats, fishing nets etc." assertion.
- document description "As a contribution to the development of new techniques to remove marine litter from the seabed of sees and oceans, the Robotic Seabed Cleaning Platform has been designed, built and experimented in the framework of the European Union project MAELSTROM. It es sentially consists of a oating platform that supports the base elements of a 6 degree-of-freedom cable-driven parallel robot actuated by eight winches. The mobile platform of this robot can work underwater and is equipped with sensors to control its underwater motions and to detect & identify marine litter. To achieve e cient and selective litter removal, an aspiration system and a gripper are installed on the CDPR underwater mobile platform." assertion.
- 5c2b7b95-a99c-4489-b0ac-f656a65b90f7 description "This objective supports the implementation of the UN SDG 14 Life Below Water, by addressing two major challenges: (i)Surface and Upper Water Column litter: Floating plastics carried by rivers and harbours currents must be intercepted and captured before they enter the oceans and either sink to the seabed or create gyres MAELSTROM will deploy an automated air-bubbles barrier installed in optimized locations to retrieve these floating items, and also contribute to the re-oxygenation of the rivers, harbours and lagoons. (ii)Seabed and Lower Water Column: For ML hotspots in coastal waters, MAELSTROM will provide a robotized cable robot capable of high efficiency removal of small and large debris on seabed and in the lower water column." assertion.
- 3949 description "" assertion.
- 5c2b7b95-a99c-4489-b0ac-f656a65b90f7 contentLocation db43eb51-8abc-4a9b-acf8-b77434119670 assertion.
- 5c2b7b95-a99c-4489-b0ac-f656a65b90f7 contentLocation e6bb65bf-c136-4a7f-be68-894c5ed9ca21 assertion.
- 5c2b7b95-a99c-4489-b0ac-f656a65b90f7 contentSize "0" assertion.
- e14484df-b757-4415-abed-a252d35e24d4 contentSize "222726" assertion.
- 5c2b7b95-a99c-4489-b0ac-f656a65b90f7 contributor mailto:antonio.petrizzo@cnr.it assertion.
- 5c2b7b95-a99c-4489-b0ac-f656a65b90f7 contributor mailto:taha.lahami@ve.ismar.cnr.it assertion.
- 5c2b7b95-a99c-4489-b0ac-f656a65b90f7 contributor 0000-0002-3489-268X assertion.
- document dateCreated "2025-06-11 11:05:31.499118+00:00" assertion.
- 16k3-Bp4FCI dateCreated "2025-05-28 13:10:01.014718+00:00" assertion.
- 13952176 dateCreated "2025-06-11 10:55:01.395983+00:00" assertion.
- 14929590 dateCreated "2025-06-12 10:23:32.031487+00:00" assertion.
- 14929678 dateCreated "2025-06-12 10:22:16.970677+00:00" assertion.
- 14930072 dateCreated "2025-06-12 10:24:29.134034+00:00" assertion.
- 14931001 dateCreated "2025-06-12 10:21:15.235065+00:00" assertion.
- 14931140 dateCreated "2025-06-12 10:21:47.620450+00:00" assertion.
- 15544106 dateCreated "2025-06-12 10:24:57.022797+00:00" assertion.
- 15546289 dateCreated "2025-06-12 10:24:01.634152+00:00" assertion.
- watch?v=3lUl9FOVGGE dateCreated "2025-05-28 13:14:36.270632+00:00" assertion.
- watch?v=YKN2yoXyXHY dateCreated "2025-05-28 13:11:24.109127+00:00" assertion.
- cdd7e89f-7013-45cd-9d15-00c4d7fe19fa dateCreated "2025-06-11 09:21:53.348421+00:00" assertion.
- document dateCreated "2025-06-11 11:00:03.950011+00:00" assertion.
- 0jEVO73Z_YY dateCreated "2025-05-28 13:16:18.836651+00:00" assertion.
- 1EVQm-0yyRY dateCreated "2025-05-28 13:13:34.331104+00:00" assertion.
- QGbCNkvaSL0 dateCreated "2025-05-28 13:12:35.558107+00:00" assertion.
- jTs3cgio3hU dateCreated "2025-05-28 13:15:22.339834+00:00" assertion.
- 5c2b7b95-a99c-4489-b0ac-f656a65b90f7 dateCreated "2025-05-28 09:48:38.233944+00:00" assertion.
- e14484df-b757-4415-abed-a252d35e24d4 dateCreated "2025-05-28 09:51:57.401950+00:00" assertion.
- db43eb51-8abc-4a9b-acf8-b77434119670 geo bd12751b-5767-4c6b-89ad-d851a797a11b assertion.
- e6bb65bf-c136-4a7f-be68-894c5ed9ca21 geo 5171f956-448b-4fd8-9a79-f091e53c4a0f assertion.
- 5c2b7b95-a99c-4489-b0ac-f656a65b90f7 hasGeometry a50b65b6-5682-46cf-b6d5-46e60513c545 assertion.
- 5c2b7b95-a99c-4489-b0ac-f656a65b90f7 creation_mode "MANUAL" assertion.
- 0000-0002-3489-268X orcid "0000-0002-3489-268X" assertion.
- 5c2b7b95-a99c-4489-b0ac-f656a65b90f7 cite-as "Fantina Madricardo, Vanessa Moschino, ANTONIO PETRIZZO, Taha Lahami, and Valentina Grande. "MAELSTROM Objective 2: ML Removal from seabed and both lower and upper water column - archive." ROHub. May 28 ,2025. https://doi.org/10.24424/ddnx-hs06." assertion.
- 002bd400-c49a-4dad-aae4-6b81e069e482 normScore "12.268518518518519" assertion.
- 02eb8421-e600-4f59-a5d8-18adca5bf10b normScore "100.0" assertion.
- 05d9d826-c13d-470a-9e57-4453339aded7 normScore "9.8989898989899" assertion.
- 0c1d437c-a4ea-470e-963d-07b307c30655 normScore "5.439814814814816" assertion.
- 0e42e4ba-ec98-4a42-9af4-0965ef9804cd normScore "5.555555555555556" assertion.
- 1b376855-ef8d-435b-96a6-a18e19f8d651 normScore "14.214046822742475" assertion.
- 1c73a2d9-dc9d-4437-9617-3cd048a5a074 normScore "12.207357859531772" assertion.
- 21d80121-a9e1-48b6-80d6-0a6a573dda82 normScore "35.28428093645485" assertion.
- 2394fa09-d9ce-42f4-a95b-2b61fb0d78b6 normScore "100.0" assertion.
- 24d533ef-f565-455f-a22e-0d8434f1cd67 normScore "16.363636363636363" assertion.
- 276c7d70-293f-41e2-99d1-d9705fb3b1f3 normScore "19.7979797979798" assertion.
- 2a81a0ad-b9c3-4cfa-ad07-3e2871d1b466 normScore "100.0" assertion.
- 2de52d97-b538-43fc-b657-95e5cd645a35 normScore "13.131313131313131" assertion.
- 31578e2f-a639-4a4f-b790-7e572e6fef6c normScore "29.92992992992993" assertion.
- 66f444e7-3dd4-45e4-ba98-b4e391865ea8 normScore "4.0509259259259265" assertion.
- 79d05959-407f-4a39-a318-fb91bd8fb55b normScore "9.375000000000002" assertion.
- 814949bc-4842-44f7-81f1-36038bb181b8 normScore "7.060185185185186" assertion.
- 86f2dde1-a2f7-4522-9cfa-176ea018fafe normScore "25.75250836120401" assertion.
- 89cf8c4d-e1f0-42eb-98e3-b6d9eeee65ed normScore "45.745745745745744" assertion.
- 89f3b193-bdb9-4c95-a318-ebb3680c4e91 normScore "17.171717171717173" assertion.
- 8c4689d8-c414-4fc6-b146-5116be29b610 normScore "100.0" assertion.
- 8d1e60f3-c584-4c46-8b02-17721be0432d normScore "15.856481481481483" assertion.