Navegando por Data de Publicação, começando com "2024-01-08"

Filtrar resultados por ano ou mês

Agora exibindo 1 - 2 de 2

Extração de características por transferência de aprendizado profundo no âmbito do monitoramento não Invasivo de cargas residenciais
(Universidade Federal de São Carlos, 2024-01-08) Cavalca, Diego Luiz; Fernandes, Ricardo Augusto Souza; https://lattes.cnpq.br/0880243208789454; https://lattes.cnpq.br/3677080775789758; https://orcid.org/0000-0002-7793-9425
The development of techniques that allow the efficient identification of loads, ideally in a nonintrusive way, is a key factor for the practical implementation of home energy management systems. Recently, the use of techniques based on deep learning has gained attention in different domains, such as signal and image processing, highlighting the models based on convolutional neural networks. However, the efficient training of these models is strongly dependent on the amount and balance of data, i.e., characteristics that are not normally found in nonintrusive load monitoring datasets. To deal with these challenges, this thesis proposes an approach based on three stages, which are: (i) transformation of time series into 2D images; (ii) feature extraction using deep transfer learning; and (iii) classification/labeling of loads. In this sense, it was considered five loads present in the Reference Energy Disaggregation Dataset. The results indicate that the proposed approach was able to obtain an average f1-score of 84.2%. Moreover, from the analysis of the results, it was also possible to observe a greater capacity of the proposed approach to infer and generalize its responses compared to other evaluated approaches, presenting a consistent result even in the face of unbalanced data.
Duas novas espécies de Priocharax dos lagos próximos à foz do rio Purus, Amazonas, Brasil (Teleostei: Characiformes)
(Universidade Federal de São Carlos, 2024-01-08) Lopez, Giovanna Guimarães da Silva; Mattox, George Mendes Taliaferro; https://lattes.cnpq.br/4453900943293186; https://orcid.org/0000-0003-4748-472X; https://lattes.cnpq.br/9442748801391006; https://orcid.org/0000-0001-5708-8777
Characiformes is one of the most diverse groups in Actinopterygii, representing the richest order in the Amazon basin. Among the genera distributed in this biome, we highlight Priocharax, currently with seven valid species of miniature fishes (i.e., reaching up to 26 mm Standard Length - SL), all of which retain the larval pectoral fin in the adults. Preliminary morphological, osteological and molecular data indicated the existence of new species of Priocharax in the region of river Purus, near its mouth. In this work, materials from this region previously deposited in ichthyological collections were examined in detail, based on meristic, morphometric and osteological data. Counts and measurements were taken under a stereomiscroscope connected to a computer, with the use of morphometric tools of the Zen software. Some specimens were cleared and stained for accessing the osteological characters. Comparative analyzes with other congeneric species were carried out through literature review and examination of additional material, including types. The results were analyzed together with DNA barcoding data in the context of the JP-FAPESP research project (2017/1970-4). The morphological data pointed to the existence of two undescribed species, one from lakes Ayapuá and Uauaçú (left bank), in the Reserva de Desenvolvimento Sustentável Piagaçu-Purus, and another, also corroborated by molecular information, from the right bank of the river Purus, originating from lake Xaviana. As with other species already recognized in Priocharax, both species treated here can be diagnosed from each other and from other species by the combination of meristic characters (i.e., number of teeth and number of anal-fin rays), morphometric (i.e., length of the base of the anal fin) and osteological (i.e., presence of postcleithra on the pectoral fin and presence of bones in the infraorbital series).