Bleaching Detection in Coral Reef using Deep Convolutional Autoencoder based Model

The coral reefs have been considered as an essential component of the marine ecosystem as they help ecologically as well as toward the development of medicine related to the severe diseases such as HIV infections, heart disease, etc. The Coral bleaching phenomenon has been found as the main cause th...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:The ... CSI International Symposium on Artificial Intelligence & Signal Processing (Online) s. 01 - 05
Hlavní autoři: Gautam, Neeraj Kumar, Mishra, Mayank, Pati, Umesh C.
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 26.10.2024
Témata:
Accuracy
Artificial intelligence
Autoencoder
Autoencoders
Biological system modeling
Bleached Coral Reefs
Bleaching
Classification
Convolution
Convolutional neural networks
Coral reefs
Deep CNN
Diseases
Feature extraction
Marine vegetation
ISSN:2640-5768
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The coral reefs have been considered as an essential component of the marine ecosystem as they help ecologically as well as toward the development of medicine related to the severe diseases such as HIV infections, heart disease, etc. The Coral bleaching phenomenon has been found as the main cause that increases the worldwide dying out risk of coral reefs. The Artificial Intelligence (AI) based approach can become an essential way of early detection of coral reefs bleaching. This work has proposed a Deep Convolution Autoencoder (DCAE) based model to detect the bleaching of the coral reefs. The Proposed DCAE model has been utilized to extract the deep feature image from the underwater image of coral reefs, which can be further utilize for the bleaching detection. The Kaggle repository of coral reef health dataset comprising the underwater images of healthy corals and bleached corals have been taken for the experimention. The proposed DCAE approach has achieved an accuracy of 76.60%, sensitivity of 80%, precision of 73.46%, and F1-Score of 76.59% in detecting the bleaching of coral reefs.
ISSN:2640-5768
DOI:10.1109/AISP61711.2024.10870660