Navegando por Data de Publicação, começando com "2022-02-11"

Filtrar resultados por ano ou mês

Agora exibindo 1 - 3 de 3

Fuzzy approach for classification and novelty detection in data streams
(Universidade Federal de São Carlos, 2022-02-11) Cristiani, André Luis; Camargo, Heloisa de Arruda; https://lattes.cnpq.br/0487231065057783; https://lattes.cnpq.br/3601289671291571
Learning in data streams (DS) is a research area that seeks to extract knowledge from a large amount of continuously generated data in a short period of time. The novelty detection (ND) is responsible for identifying the emergence of new concepts and changes in known concepts. The true labels of the instances can be used so that the algorithms adapt to the concept evolution and concept drift. The time between the classification of an instance and the arrival of its true label is called latency. Most applications consider that these true labels will never be available. Others are more optimistic and assume that the true label will be available shortly after the instance has been classified. Another way is to consider that, after a certain time, the true labels will be available, which is applicable in most real-world scenarios. The use of concepts from fuzzy set theory makes it possible to make learning adaptable to possible inaccuracies in the data. However, few approaches use the concepts of fuzzy set theory and consider intermediate latency to obtain the labels. Therefore, this work proposes a method for classifying multiclass ND in DS for intermediate and extreme latency scenarios based on ECSMiner and PFuzzND algorithms. The results obtained show that the proposed algorithm obtained good accuracy in the classification and detection of multiclass novelties, classifying outliers that approaches that use crisp clustering were not able to classify. In addition, improvements were presented in relation to the algorithm initialization parameters, which reduce the complexity of its use, maintaining good results.
Desinformação e Esquerda Brasileira: o discurso por trás das fake news
(Universidade Federal de São Carlos, 2022-02-11) Quessada, Miguel; Andrade, Thales Haddad Novaes de; https://lattes.cnpq.br/5882842888759363; https://lattes.cnpq.br/7016464811045412
Fake news came up with the post-truth and had the Trump’s election and Brexit as the main examples of its indiscriminate use. Brazil did not come out unscathed and here they also had repercussions, mainly during the electoral period, in which all sorts of misinformation has been resurrected and became public again. Although the use of lies in politics is not recent, the fake news phenomenon is associated to the technological apparatus of the information society in which we live. As usual, the term fake news has become complex and the literature has preferred the term disinformation for being more comprehensive and able to understand all kinds of rumors. The present study aims to investigate the discourse propagated against the Brazilian left, proposing a typology of fake news used in order to understand which themes were part of the political schedule in the period studied by cataloging the disinformation that was denied by the agencies/sites. Checking and analysis of its content and discourse. Fake news is proposed by a subject interested in bringing specific topics to the political debate. propagated, they inflate the imagination of the subjects involved in the communication process. Methodologically, the work adopts Discourse Analysis to understand this phenomenon and applies Semiolinguistic Analysis as a form of analysis.
Algoritmos quânticos para resolução de equações diferenciais: análise de complexidade e aplicabilidade
(Universidade Federal de São Carlos, 2022-02-11) Akamatsu, Daniel Yoshio; Villas-Bôas, Celso Jorge; https://lattes.cnpq.br/5700887540085418; https://lattes.cnpq.br/4457174341992705
This work consists in a complexity analysis of an algorithm for solving differential equations, which shares common characteristics with other algorithms designed for the same task. Operations such as state preparation, implementation of multiple q-bit gates and controlled gates are found in several algorithms and their complexity, whose details are sometimes neglected when new algorithms are analyzed, are approached with details, intending to do an analysis as consistent with the reality as possible. It is possible to conclude that neglecting these operations can lead to a wrong complexity analysis with aid of practical examples.