Automatic recognition of jellyfish with artificial intelligence

Automatic recognition of jellyfish with artificial intelligence

jellyfish

Aequorea victoria. Image credit: Sierra Blakely/Wikipedia.

Jellyfish spotting app MedusApp has recently incorporated artificial intelligence (AI) to automatically recognize different species of jellyfish. So far, this app has only required users to select the species of jellyfish from a provided directory; now the user can upload photos and have the species automatically identified before uploading them to the app for publication.

MedusApp, which is freely available in Spanish and English for both Android and iPhone, has been developed by researchers from the University of Alicante (UA) and two computer scientists from the Polytechnic University of Valencia (UPV), in collaboration with CIBER of Diseases (CIBERES) and Immunoallergy Laboratory at the Fundación Jiménez Díaz Health Research Institute (IIS-FJD). Since its launch in 2018, the platform has accumulated more than 100,000 downloads and 6,000 jellyfish observations. “Thanks to the cooperation of citizens and their observations, we have been able to train the AI ​​software with several thousand real photos to generate a mathematical model with a total of 25 species, which will ultimately help the app automatically recognize the most common jellyfish,” a news update highlighted by UPV programmers Eduardo Blasco and Ramón Palacios.

Other news

In addition to the automatic recognition of jellyfish thanks to AI, the app has incorporated other novelties such as the “no observations” option, to report if a beach is free of jellyfish or, in addition, a function that allows observations to be made via transects, “This new the option, intended for sailors, divers or fishermen, allows you to include an image of possible jellyfish sightings found during a boat trip,” the authors write.

“The application is constantly being improved and is intended to improve and expand our knowledge of the health effects of jellyfish stings, as well as to better understand aspects of their biology and ecology (spatial and temporal distribution),” explains Professor César Bordehore from the Department of Marine Ecology at the UA. The scientific-medical data on the registered stings, which already exceeds 970 reported stings, is managed and analyzed by a multidisciplinary scientific team consisting of the researchers César Bordehore (principal researcher) and Eva S. Fonfría, from the Multidisciplinary Institute for the Study of the Environment (IMEM ) and the UA department, as well as doctors Victoria del Pozo and Mar Fernández Nieto, from CIBER for Respiratory Diseases (CIBERES) and the Immunoallergy Laboratory-Jiménez Díaz Foundation Health Research Institute (IIS-FJD).

Another useful feature of the app is an interactive guide on what to do in the event of being stung accompanied by information on the level of risk posed by different jellyfish. “If a sting occurs, the most important thing is to remove the remains of the tentacles with tweezers or a plastic card, without rubbing the area, and then proceed to inactivate the stinging cells that may remain on the skin with a mixture of baking soda and seawater. About the species of jellyfish is known, the app contains more specific medical protocols that can improve the recovery phase, we always want to highlight that freshwater (and urine) should never be used as this can worsen the effects of the sting, says Bordehore.

MedusApp has become an open, simple and fast tool for citizen science that has already attracted the interest of research teams in Mexico. “Specialists and colleagues working in centers in Latin America have requested permission to use the app and make use of scientific-medical data,” says the UA researcher.

The MedusApp team has developed training videos that are available in open source to facilitate the use, knowledge and optimization of all tools offered by MedusApp. All information is available through the app and on the web located at: medusapp.net/.


What you need to know about jellyfish stings


Provided by the Universitat Politècnica de València

Quote: Automatic Recognition of Jellyfish with Artificial Intelligence (2022, July 27) Retrieved July 27, 2022, from https://phys.org/news/2022-07-automatic-recognition-jellyfish-artificial-intelligence.html

This document is subject to copyright. Except for any fair trade for the purpose of private study or research, no part may be reproduced without written permission. The content is provided for informational purposes only.


#Automatic #recognition #jellyfish #artificial #intelligence

Leave a Comment

Your email address will not be published.