Navegando por Assunto "Machine Learning"

Agora exibindo 1 - 2 de 2

Acesso aberto (Open Access)
A machine learning framework for ECG biometric system
(Universidade Federal do Pará, 2020-02-28) SANTOS, Alex Barros dos; ROSÁRIO, Denis Lima do; http://lattes.cnpq.br/8273198217435163; CERQUEIRA, Eduardo Coelho; http://lattes.cnpq.br/1028151705135221; https://orcid.org/0000-0003-2162-6523
The new environment of IoT and the deployment of 5G networks have been generating a huge amount of data. Developers are creating new applications and redesigning other ones completely. Also, a society greater concern with health increases the demand for health services provided with the usage of wearable devices that are getting cheaper. Moreover, the applications require more data protection and privacy. Thus, biometrics has become one of the primary mechanisms for protecting information used by users in all kind of systems and applications. This work investigates the use of an ECG signal in biometrics systems approaching machine learning techniques. This signal is a new alternative not only to increase current safety standards by providing the individual’s continuous authentication but also to assess health with cardiac monitoring already well established in medicine by evaluations. In this context, this master’s thesis proposes some processing steps to data sets, improving its quality that allows it to be used as a reliable source of biometric data. We define techniques for extracting signal considering mobile application constraints and design a structure that allows the use of ECG as a biometric signal in a scalable and heterogeneous environment considering different machine learning techniques such as Support Vector Machine, Random Forest and Neural Networks. The set of our proposed feature extraction, processing steps of data set and a machine learning model are the main contributions of this work.
Acesso aberto (Open Access)
Três décadas de mudanças na planície costeira brasileira: O status dos manguezais, da aquicultura e salicultura a partir de séries temporais Landsat e técnicas de aprendizado de máquina
(Universidade Federal do Pará, 2020-03-31) DINIZ, Cesar Guerreiro; SOUZA FILHO, Pedro Walfir Martins e; http://lattes.cnpq.br/3282736820907252
Since the 1980s, land-use and land-cover (LULC) mapping has become a common scientific task. However, the systematic and continuous identification of any terrestrial use or cover, whether on a global or regional scale, demands large storage and processing capacities. This thesis presents two cloud computing pipelines to analyze: 1) the annual status of Brazilian mangroves from 1985 to 2018, along with a new spectral index, the Modular Mangrove Recognition Index (MMRI), which has been specifically designed to better discriminate mangrove forests from the surrounding vegetation, and 2) the annual status of the aquaculture and salt-culture over the Brazilian coastal plains. The mangrove cover showed two distinct occupation periods, 1985-1998 and 1999-2018. The first period shows an upward trend, which seems to be related more to the uneven distribution of Landsat data than to the regeneration of Brazilian mangroves. In the second period, a mangrove loss trend was registered, reaching up to 2% of the mangrove forest. On a regional scale, ~80% of Brazil's mangrove cover is located in the Amazon, Maranhao, Para, Amapa states. In terms of persistence, ~75% of the Brazilian mangroves remained unchanged for two decades or more, especially in the Brazilian Amazon. As for item 2, aquaculture and salt-culture are two of the most classical coastal land-uses worldwide. It isn't different in Brazil, where both land-uses are related to relevant economic activities in the Brazilian Coastal Zone (BCZ). However, to automatically discriminate such activities from other water-related covers/uses is not an easy task. Spectrally speaking, water is water and, unless it presents a high concentration of optically active compounds, not much can be done to dissociate a variety of water-related targets. In this sense, convolutional neural networks (CNN) have the advantage of predicting a given pixel's label by providing as input a local region (named patches or chips) around that pixel. Both the convolutional nature and the semantic segmentation capability allow the U-Net classifier, a type of CNN, to access the "context domain" instead of solely isolated pixel values. Backed by the context domain, the results obtained show that the BCZ aquaculture/saline ponds occupied ~356 km² in 1985 and ~544 km² in 2019, reflecting an area expansion of 52% (~185 km²), a rise of 1.5x in 35 years. From 1997 to 2015, the saline/aquaculture area grew by a factor of ~ 1.7, jumping from 349 km2 to 583 km2, a 67% increase. In 2019, the northeast sector concentrated 93% of the coastal aquaculture/salt-culture surface, 6% in Southeast and 1% in South. Interestingly, despite presenting extensive coastal zones and suitable conditions for developing different aquaculture products, the Amazon coast shows no relevant aquaculture infrastructure sign.