Marine biodiversity assessments using aquatic internet of things

• Autor(a) principal: Martins, Carlos Diogo Félix
• Data de Publicação: 2021
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10400.13/3430
• topic: Ubiquitous computing; Aerial assessments; Wildlife monitoring; Machine learning; Internet of things; Informatics Engineering; .; Faculdade de Ciências Exatas e da Engenharia; Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática

While Ubiquitous Computing remains vastly applied in urban environments, it is still scarce in oceanic environments. Current equipment used for biodiversity assessments remain at a high cost, being still inaccessible to wider audiences. More accessible IoT (Internet of Things) solutions need to be implemented to tackle these issues and provide alternatives to facilitate data collection in-the-wild. While the ocean remains a very harsh environment to apply such devices, it is still providing the opportunity to further explore the biodiversity, being that current marine taxa is estimated to be 200k, while this number can be actually in millions. The main goal of this thesis is to provide an apparatus and architecture for aerial marine biodiversity assessments, based on low-cost MCUs (Microcontroller unit) and microcomputers. In addition, the apparatus will provide a proof of concept for collecting and classifying the collected media. The thesis will also explore and contribute to the latest IoT and machine learning techniques (e.g. Python, TensorFlow) when applied to ocean settings. The final product of the thesis will enhance the state of the art in technologies applied to marine biology assessments.