Loading...
Research Project
Untitled
Funder
Authors
Publications
Low-cost internet of things and snapshot geolocation pipeline in marine sensing
Publication . Pinto, Pedro José Gouveia; Radeta, Marko; Quintal, Filipe
Biologging and biotelemetry are commonly used as methods to assess marine biodiversity pop ulation. However, current state-of-the-art devices (commonly referred to as tags) remain at the
greater cost of production while geolocation and georeferencing methods use proprietary satellite
constellations, remain expensive and are prone to greater battery usage. This dissertation enhances
such state-of-the-art devices, providing affordable tags for multipurpose usage. Dissertation contri bution is two-fold. In first, it describes the design of low-cost telecommunication system comprised
from tag emitters and land receivers, evaluated during the sea-vessel field trips in pelagic area of
Madeira island. In second, it also describes the software pipeline for deducing the position of tags,
leveraging the raw signal from obtained GPS receivers.
MAR Gate: augmented reality for attracting wider audience to marine concerns
Publication . Teles, Jocelyne Estefania Pestana; Radeta, Marko
As condições nos ambientes marinhos permanecem angustiantes, pois as atividades humanas afetam
a qualidade de vida das espécies marinhas. Uma das espécies que sente tais consequências é a Baleia
Franca do Atlântico Norte, cuja saúde está em declíneo devido a ameaças passadas e presentes.
Uma forma de chamar a atenção para os problemas ambientais marinhos é educando as pessoas,
conectando-as a tais espécies, conscientizando-as e fazendo-as refletir sobre ações futuras. Esta
dissertação apresenta a aplicação móvel de realidade aumentada, alavancando a interação sobre
as Baleias Francas do Atlântico Norte (BFAN), educando os utilizadores sobre a sua contribução
para ambientes marinhos, ameaças e curiosidades com essa interação. A dissertação relata o uso de
tecnologias imersivas e aprendizagem móvel, fornecendo informações sobre as BFANs. Três estudos
foram conduzidos em diferentes etapas do desenvolvimento da aplicação, em ambientes internos,
externos e em praças públicas, estudando: (i) como a Realidade Aumentada pode influenciar os
utilizadores, (ii) como o público entende as interações e (iii) quão eficaz é a AR para aprender
em espaços públicos. Os estudos revelaram as seguintes respostas: (i) a Realidade Aumentada
tem um impacto emocional nos utilizadores que pode ser positivo dependendo do tema abordado.
A imersão e a absorção são elementos cruciais, e o ambiente externo, seja com sombra ou não,
pode não influenciar significativamente na experiência. (ii) Os infográficos sem textos podem ser
entendidos pelo público considerando dois factores: a clareza dos desenhos que representam os
dados e o conjunto de conhecimentos da população-alvo. (iii) AR demonstra resultados positivos
na educação dos utilizadores sobre as Baleias Francas do Atlântico Norte em espaços públicos.
Interactive geodesic structures for attracting wider audience to marine concerns
Publication . Abreu, Pedro Miguel Cabral; Radeta, Marko
Recent surveys indicate that there is a greater emotional disconnect between the
European population and Europe’s aquatic environments [1]. Although a wider
audience recognizes anthropogenic issues (i.e. litter pollution, overfishing, noise
pollution, etc) where most people can feel connected to nature, however, they
do not exhibit pro-environmental behaviors towards them. Interactive environ ments, which depict marine concerns, remain passive and informative, i.e. not
being able to engage with the audience, failing to provide a long-term positive
effect. This thesis explores the usage of geodesic structures in depicting marine
concerns, exploring possible interactive environments among them in effort to
increase the awareness of marine concerns. Dissertation performs five geodesic
dome iterations and validations. In first, it studies the role of the open and
porous geodesic structure, resembled as four marine species (seabird, sea turtle,
dolphin and whale). In second, it enhances the first with the covers, studying
more immersive experiences. Third setup contributed to the scaling-down of the
geodesic dome marine species. Fourth setup showcased its deployment in wider
public spaces. Fifth setup streamlined further the structures, so they can be used
at diverse public spots. Two additional Augmented Reality modalites were used,
with the former with interaction with the sea turtle and the latter, interacting
with the whale.
Marine biodiversity assessments using aquatic internet of things
Publication . Martins, Carlos Diogo Félix; Radeta, Marko; Quintal, Filipe Magno de Gouveia
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.
Dashboard for collecting and depicting the marine megafauna presence
Publication . Aguiar, Paulo Filipe Nunes; Radeta, Marko; Quintal, Filipe Magno Gouveia
While more and more technologies and software are being created and applied for the ocean setting,
most of them still remain at high cost, and hinder the data to wider public. Understanding the
marine biodiversity can be achieved through numerous ways, however, there is a lack of consensus
and operability when depicting the marine megafauna population. Moreover, Deep Learning (DL)
techniques are becoming accessible to wider population, and there is a potential of exposing them
to the marine biologists, involving them to participate in public web-based dashboards, depicting
those data.
This dissertation addresses such issues, by providing an interactive dashboard, capable of fa cilitating the classification, prediction and deeper analysis of marine species. Using the State of
Art (SoA) Machine Learning (ML) techniques for image vision, and providing the interactive vi sualizations, this thesis seeks to provide a less cumbersome apparatus for marine biologists, who
can participate further in data gathering, labelling, depicting, ecological modelling, and potential
calls for action.
In further, this dissertation document provides the aquatic dashboard functionality using
Human-Computer Interaction (HCI) techniques and interactive means to ease the upload, clas sification, and visualization of collected marine taxa, with a case study on marine megafauna
imagery (e.g. whales, dolphins, sea birds, seals and turtles). As it will be hereinafter described,
marine biologists, as end users, will evaluate of the proposed dashboard.
Organizational Units
Description
Keywords
Contributors
Funders
Funding agency
Fundação para a Ciência e a Tecnologia
Funding programme
3599-PPCDT
Funding Award Number
PTDC/CCI-CIF/32474/2017