Search

Your search keyword '"Guido, Rodrigo Capobianco"' showing total 218 results
Start Over Author "Guido, Rodrigo Capobianco"
218 results on '"Guido, Rodrigo Capobianco"'

1. Trusting Language Models in Education

Author

Neto, Jogi Suda, Deng, Li, Raya, Thejaswi, Shahbazi, Reza, Liu, Nick, Venkatesh, Adhitya, Shah, Miral, Khosla, Neeru, and Guido, Rodrigo Capobianco

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence
Abstract

Language Models are being widely used in Education. Even though modern deep learning models achieve very good performance on question-answering tasks, sometimes they make errors. To avoid misleading students by showing wrong answers, it is important to calibrate the confidence - that is, the prediction probability - of these models. In our work, we propose to use an XGBoost on top of BERT to output the corrected probabilities, using features based on the attention mechanism. Our hypothesis is that the level of uncertainty contained in the flow of attention is related to the quality of the model's response itself.

Published
2023

2. Metaheuristic Algorithms for Enhancing Multicepstral Representation in Voice Spoofing Detection: An Experimental Approach

Author

Contreras, Rodrigo Colnago, Heck, Gustavo Luiz, Viana, Monique Simplicio, dos Santos Bongarti, Marcelo Adriano, Zamani, Hoda, Guido, Rodrigo Capobianco, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Tan, Ying, editor, and Shi, Yuhui, editor

Published
2024
Full Text
View/download PDF

3. Massive Conscious Neighborhood-Based Crow Search Algorithm for the Pseudo-Coloring Problem

Author

Simplicio Viana, Monique, Contreras, Rodrigo Colnago, Pessoa, Paulo Cavalcanti, Bongarti, Marcelo Adriano dos Santos, Zamani, Hoda, Guido, Rodrigo Capobianco, MorandinJunior, Orides, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Tan, Ying, editor, and Shi, Yuhui, editor

Published
2024
Full Text
View/download PDF

5. An Experimental Analysis on Mapping Strategies for Cepstral Coefficients Multi-projection in Voice Spoofing Detection Problem

Author

Contreras, Rodrigo Colnago, Viana, Monique Simplicio, Guido, Rodrigo Capobianco, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Rutkowski, Leszek, editor, Scherer, Rafał, editor, Korytkowski, Marcin, editor, Pedrycz, Witold, editor, Tadeusiewicz, Ryszard, editor, and Zurada, Jacek M., editor

Published
2023
Full Text
View/download PDF

22. Genetic Algorithm for Feature Selection Applied to Financial Time Series Monotonicity Prediction: Experimental Cases in Cryptocurrencies and Brazilian Assets.

Author

Contreras, Rodrigo Colnago, Xavier da Silva, Vitor Trevelin, Xavier da Silva, Igor Trevelin, Viana, Monique Simplicio, Santos, Francisco Lledo dos, Zanin, Rodrigo Bruno, Martins, Erico Fernandes Oliveira, and Guido, Rodrigo Capobianco

Subjects
MACHINE learning, GENETIC algorithms, TIME series analysis, CRYPTOCURRENCIES, FEATURE selection, INVESTORS, ASSETS (Accounting)
Abstract

Since financial assets on stock exchanges were created, investors have sought to predict their future values. Currently, cryptocurrencies are also seen as assets. Machine learning is increasingly adopted to assist and automate investments. The main objective of this paper is to make daily predictions about the movement direction of financial time series through classification models, financial time series preprocessing methods, and feature selection with genetic algorithms. The target time series are Bitcoin, Ibovespa, and Vale. The methodology of this paper includes the following steps: collecting time series of financial assets; data preprocessing; feature selection with genetic algorithms; and the training and testing of machine learning models. The results were obtained by evaluating the models with the area under the ROC curve metric. For the best prediction models for Bitcoin, Ibovespa, and Vale, values of 0.61, 0.62, and 0.58 were obtained, respectively. In conclusion, the feature selection allowed the improvement of performance in most models, and the input series in the form of percentage variation obtained a good performance, although it was composed of fewer attributes in relation to the other sets tested. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

42. SETCom

Author

Guido, Rodrigo Capobianco, Moschim, Edson, 1953-2017, Ricarte, Ivan Luiz Marques, Drummond, Rogério, Universidade Estadual de Campinas. Faculdade de Engenharia Elétrica e de Computação, Programa de Pós-Graduação em Engenharia Elétrica, and UNIVERSIDADE ESTADUAL DE CAMPINAS

Subjects
Sistemas de telecomunicação, Internet, Educação, Computação, Métodos de simulação
Abstract

Orientador: Edson Moschim Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Eletrica e de Computação Resumo: Este trabalho tem por objetivo descrever o SETCom - Um ambiente planejado para fornecer, através da Internet, cursos de telecomunicações. Para tanto, foram desenvolvidos um simulador sistêmico para uso como laboratório virtual, chamado de SETComSim, um plotador de curvas, chamado de SETComPlot, usado para visualizar qualquer tipo de função necessária para apoio ao texto, uma Base de Informações chamada de SETComBln, onde são agregadas as informações de texto, vídeo e as bibliotecas usuais para o SETComSim e SETComPlot. Outras ferramentas comuns da Internet, como e-maU e chat, foram também agregadas ao sistema. Neste trabalho apresenta-se a modelagem do sistema como um todo, a construção dos elementos mencionados acima e, por fim, uma situação-exemplo é desenvolvida Abstract: This work aims describing the SETCom - an environment built to provide, through Internet, courses of telecommunications. With this purpose, it were developed, a system simulator to be used as a virtual laboratory, called SETComSim, a p]otter of curves, called SETComPlot, used to view any sort of function to aid the class, a Information Base, called SETComBln other Internet ordinary resources as e-mail, chat and so on. The system model and components are presented, followed by an example of its use Mestrado Telecomunicações e Telemática Mestre em Engenharia Elétrica

Published
2021

44. Análise de Área de Cobertura de Dispositivo IoT para Monitoramento em Smart Farm

Author

Escola,João Paulo Lemos, Guido,Rodrigo Capobianco, Silva,Ivan Nunes da, and Soares,Lucas Exposto

Subjects
Agricultura 4.0, Cigarras, Internet das Coisas
Abstract

Resumo A melhoria do processo de monitoramento de insetos-praga em área agrícola é um desafio para os cientistas. A cigarra é um inseto-praga da lavoura de café que tem como característica marcante a emissão de som. Um dispositivo capaz de auxiliar o agricultor no manejo desses insetos pode ser de grande auxílio no manejo desses insetos. O presente trabalho busca aprimorar o processo de monitoramento automatizado de cigarras em lavoura de café analisando o alcance do dispositivo capaz de detetar a presença das cigarras no campo. Os resultados mostraram promissores, encorajando os pesquisadores na continuidade dos estudos.

Published
2021

45. Análise de área de cobertura de dispositivo iot para monitoramento em smart farm

Author

Escola, João Paulo Lemos, Guido, Rodrigo Capobianco [UNESP], da Silva, Ivan Nunes, Soares, Lucas Exposto, Instituto Federal de São Paulo (IFSP), Universidade Estadual Paulista (UNESP), and Universidade de São Paulo (USP)

Subjects
Internet of things, Cicadas, Agriculture 4.0
Abstract

Made available in DSpace on 2022-05-01T11:07:20Z (GMT). No. of bitstreams: 0 Previous issue date: 2021-06-01 Improving the process of monitoring pest insects in agricultural areas is a challenge for scientists. The cicada is an insect-pest of the coffee crop that has a distinctive feature of sound emission. A device capable of assisting the farmer in the management of these insects can be of great help in the management of these insects. This work seeks to improve the process of automated monitoring of cicadas in coffee fields by analyzing the range of the device capable of detecting the presence of cicadas in the field. The results showed promising results, encouraging researchers to continue their studies. Instituto Federal de São Paulo (IFSP) Instituto de Biociências Letras e Ciências Exatas Universidade Estadual Paulista (UNESP) Escola de Engenharia de São Carlos Universidade de São Paulo (USP) Instituto de Biociências Letras e Ciências Exatas Universidade Estadual Paulista (UNESP)

Published
2021

47. Wavelet-based cepstrum calculation

Author

Sanchez, Fabrício Lopes, Barbon, Sylvio, Júnior, Vieira, Lucimar Sasso, Guido, Rodrigo Capobianco, Fonseca, Everthon Silva, Scalassara, Paulo Rogério, Maciel, Carlos Dias, Pereira, José Carlos, and Chen, Shi-Huang

Published
2009
Full Text
View/download PDF

48. Wavelet-based dynamic time warping

Author

Barbon, Sylvio, Jr., Guido, Rodrigo Capobianco, Vieira, Lucimar Sasso, Silva Fonseca, Everthon, Sanchez, Fabrício Lopes, Scalassara, Paulo Rogério, Maciel, Carlos Dias, Pereira, José Carlos, and Chen, Shi-Huang

Published
2009
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results