A. Carneiro, L. S. Nascimento, M. A. Noernberg, C. S. Hara, A. T. R. Pozo
{"title":"Social media image classification for jellyfish monitoring","authors":"A. Carneiro, L. S. Nascimento, M. A. Noernberg, C. S. Hara, A. T. R. Pozo","doi":"10.1007/s10452-023-10078-y","DOIUrl":null,"url":null,"abstract":"<div><p>The Portuguese man-of-war is responsible for the most common and severe stings worldwide. Jellyfish monitoring is essential to manage stings, and social media is a valuable data source for obtaining observations of this species. This study reports on using Convolutional Neural Networks for Portuguese man-of-war image classification extracted from social media posts. We created a suitable dataset and trained three different neural networks: VGG-16, ResNet50, and InceptionV3, with and without a pre-trained step with the ImageNet dataset. The pre-trained ResNet50 network presented the best results, obtaining 94% accuracy and 95% precision, recall, and F1 score. We conclude that Convolutional Neural Networks can be very effective for recognizing Portuguese man-of-war images from social media, helping in obtaining data about its occurrence and distribution.</p></div>","PeriodicalId":8262,"journal":{"name":"Aquatic Ecology","volume":"58 1","pages":"3 - 15"},"PeriodicalIF":1.7000,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10452-023-10078-y.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Aquatic Ecology","FirstCategoryId":"93","ListUrlMain":"https://link.springer.com/article/10.1007/s10452-023-10078-y","RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ECOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
The Portuguese man-of-war is responsible for the most common and severe stings worldwide. Jellyfish monitoring is essential to manage stings, and social media is a valuable data source for obtaining observations of this species. This study reports on using Convolutional Neural Networks for Portuguese man-of-war image classification extracted from social media posts. We created a suitable dataset and trained three different neural networks: VGG-16, ResNet50, and InceptionV3, with and without a pre-trained step with the ImageNet dataset. The pre-trained ResNet50 network presented the best results, obtaining 94% accuracy and 95% precision, recall, and F1 score. We conclude that Convolutional Neural Networks can be very effective for recognizing Portuguese man-of-war images from social media, helping in obtaining data about its occurrence and distribution.
期刊介绍：
Aquatic Ecology publishes timely, peer-reviewed original papers relating to the ecology of fresh, brackish, estuarine and marine environments. Papers on fundamental and applied novel research in both the field and the laboratory, including descriptive or experimental studies, will be included in the journal. Preference will be given to studies that address timely and current topics and are integrative and critical in approach. We discourage papers that describe presence and abundance of aquatic biota in local habitats as well as papers that are pure systematic.
The journal provides a forum for the aquatic ecologist - limnologist and oceanologist alike- to discuss ecological issues related to processes and structures at different integration levels from individuals to populations, to communities and entire ecosystems.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
