51 Hits in 2.5 sec

SeMiner: A Flexible Sequence Miner Method to Forecast Solar Time Series

Sérgio Díscola Junior, José Cecatto, Márcio Merino Fernandes, Marcela Xavier Ribeiro
2018 Information  
X-rays emitted by the Sun can damage electronic devices of spaceships, satellites, positioning systems and electricity distribution grids. Thus, the forecasting of solar X-rays is needed to warn organizations and mitigate undesirable effects. Traditional mining classification methods categorize observations into labels, and we aim to extend this approach to predict future X-ray levels. Therefore, we developed the "SeMiner" method, which allows the prediction of future events. "SeMiner"
more » ... X-rays into sequences employing a new algorithm called "Series-to-Sequence" (SS). It employs a sliding window approach configured by a specialist. Then, the sequences are submitted to a classifier to generate a model that predicts X-ray levels. An optimized version of "SS" was also developed using parallelization techniques and Graphical Processing Units, in order to speed up the entire forecasting process. The obtained results indicate that "SeMiner" is well-suited to predict solar X-rays and solar flares within the defined time range. It reached more than 90% of accuracy for a 2-day forecast, and more than 80% of True Positive (TPR) and True Negative (TNR) rates predicting X-ray levels. It also reached an accuracy of 72.7%, with a TPR of 70.9% and TNR of 79.7% when predicting solar flares. Moreover, the optimized version of "SS" proved to be 4.36 faster than its initial version. Information 2018, 9, 8 2 of 23 grids, possibly causing blackouts. Consequently, because of those and other effects from X-ray fluxes on Earth, it is imperative to develop and enhance forecasting methods. There are two kinds of events related to solar flares: (1) the solar flares themselves; and (2) the increase of the X-ray background level. Solar Flares occur when there is a sudden variation on the level of X-ray emissions. On the other hand, a smooth increase in those emissions characterizes an "increase in the X-ray background level". Forecasting both events is essential because they may cause those impacts aforementioned. Solar flares can be more damaging than the increase of X-ray background level. However, an increase in background level can be an indication of an imminent occurrence of a more significant solar event. Recently, researchers have been increasing efforts to forecast solar flares using data mining techniques. Although necessary, works focussing on background level forecasting are relatively rare. The core of these methods resides in the preparation of raw data (also known as the pre-processing step) that are submitted to the classifiers. The forecasting methods follow the usual steps of a data mining process: acquisition and pre-processing of data, feature selection, classification, validation, and testing. They differ according to the solar parameters used, the preparation of both, training and testing datasets, and the adopted pre-processing and classification methods. They also differ on what is foreseen: one option is to forecast solar flares grouped under a set of categories, another produces a specific forecast for each class of solar flares. The classifiers used by forecasting methods were developed aiming to classify tuples with a given label, describing subjects or events. A subject label intends to describe the tuple, while an event label describes an event that occurred according to the tuple values. Then, the question that arises is: how to predict future events through traditional classifiers, since they label past tuples/events? One method found in the literature is to construct the learning model of a traditional classifier by labeling past tuples with future events. Hence, the vast majority of solar flare forecasting methods label a solar data tuple with the class "Positive", if a solar flare occurs up to 24 h from the observed tuple, and "Negative", if no solar flare occurs during the next 24 h. This labeling schema is too static because it does not consider the dynamics of solar data. In fact, the knowledge of a specialist (astrophysicist) is determinant to the success of a forecasting method based on data mining. In general, current forecasting systems do not allow the setup of specialized information from a specialist, such as: the most relevant solar features; the most relevant sub-series of solar data; the characteristics of the solar time series evolution that most significantly impact the forecasting results. Consequently, a pre-processing algorithm capable of including one's specialist knowledge to set up input parameters may improve forecasting results. In summary, the main open issues in forecasting solar flares using data mining are: • Few works consider the historical evolution of solar time series; • Few works explicitly employs astrophysicists knowledge in the actual forecasting process; Also, some requirements are crucial for the forecasting system in order to tackle those open issues:
doi:10.3390/info9010008 fatcat:f7rr6wxxy5cs3bsefozqwgtwea

A Software Framework to Create 3D Browser-Based Speech Enabled Applications

Ednaldo Brigante Pizzolato, Diego Daniel Duarte, Marcio Merino Fernandes
2009 Revista de Informática Teórica e Aplicada  
basic system just described is its intrinsic mono modal interaction 1 Universidade Federal de São Carlos Departamento de Computação São Carlos -SP -Brasil {,, marcio  ... 
doi:10.22456/2175-2745.8266 fatcat:2lwa4vk6w5edhjqtcikm7mo5oa

Automatic Generation of Custom Parallel Processors for Morphological Image Processing

Emerson Carlos Pedrino, Marcio Merino Fernandes
2014 2014 IEEE 26th International Symposium on Computer Architecture and High Performance Computing  
doi:10.1109/sbac-pad.2014.47 dblp:conf/sbac-pad/PedrinoF14 fatcat:qwhydqoqqvfr7ejgzdlg2mcqge

Handling Imbalanced Time Series Through Ensemble of Classifiers: A Multi-class Approach for Solar Flare Forecasting [chapter]

Sérgio Luisir Díscola Junior, José Roberto Cecatto, Márcio Merino Fernandes, Marcela Xavier Ribeiro
2019 Advances in Intelligent Systems and Computing  
doi:10.1007/978-3-030-14070-0_29 fatcat:deusqi22abcttmenjos3z5t4au

Ad Hoc Peer Reviewers of Articles of 2010 (Rev. Ambi-Agua volume 5, nº. 1, 2 e 3, 2010)

Getulio Teixeira Batista
2010 Revista Ambiente & Água  
Manoel Alonso Gan Manuel Eduardo Ferreira Marcelo dos Santos Targa Marcelo Zaiat Márcio J.  ...  Henriques Fernandes Paulo Roberto Meneses Regina Peralta Moreira Renato Fontes Guimarães Richarde Marques Silva Rodrigo Medeiros Ronaldo Teixeira Pelegrini Sérgio Marcos Sanches Servio Tulio Cassini  ... 
doi:10.4136/ambi-agua.557 doaj:310977c44ed346a28585bcfa72686be6 fatcat:xxpv3lxuyrefflyl7j3sz4guvq

Effects of Ibuprofen Use on Lymphocyte Count and Oxidative Stress in Elite Paralympic Powerlifting

Felipe J Aidar, Guacira S Fraga, Márcio Getirana-Mota, Anderson Carlos Marçal, Jymmys L Santos, Raphael Fabricio de Souza, Alexandre Reis Pires Ferreira, Eduardo Borba Neves, Aristela de Freitas Zanona, Alexandre Bulhões-Correia, Paulo Francisco de Almeida-Neto, Tulio Luiz Banja Fernandes (+7 others)
Paralympic Powerlifting (PP) training tends to promote fatigue and oxidative stress. To analyze the effects of ibuprofen use on performance and oxidative stress in post-training PP athletes. Ten national level PP athletes (age: 27.13 ± 5.57) were analyzed for oxidative stress in post-training. The study was carried out in three weeks, (1) familiarization and (2 and 3) evaluated the recovery with the use of a placebo (PLA) and ibuprofen (IBU), 800 mg. The Peak Torque (PT), Torque Development
more » ... (TDR), Fatigue Index (FI), reactive substances to thiobarbituric acid (TBARS) and sulfhydryl groups (SH) were evaluated. The training consisted of five sets of five repetitions (80-90%) 1-Repetition Maximum (1-RM) in the bench press. The IBU showed a higher PT (24 and 48 h, p = 0.04, ɳ2 p = 0.39), a lower FI (24 h, p = 0.01, ɳ2p = 0.74) and an increased lymphocyte count (p < 0.001; ɳ2p = 4.36). There was no change in oxidative stress. The use of IBU provided improvements in strength and did not protect against oxidative stress.
doi:10.3390/biology10100986 pmid:34681085 fatcat:g27fv4xynjb43ngdbcazrvbfmi

Viabilidade polínica como seleção assistida no programa de melhoramento genético de triticale

Maira Zanotto, Sandra Patussi Brammer, Alfredo do Nascimento Junior, Sandra Mansur Scagliusi
2009 Ciência e Agrotecnologia  
AGRADECIMENTOS Os autores desejam expressar seus agradecimentos ao colega Márcio Nicolau (Embrapa Trigo) pelas análises estatísticas realizadas.  ...  As revisões de Falcão et al. (1981) e Moraes-Fernandes (1982) , quanto aos aspectos citológicos e genéticos, destacam que inúmeras são as informações da literatura a respeito de associação entre fertilidade  ... 
doi:10.1590/s1413-70542009000700064 fatcat:bagfj6pb35ckneyprmn5rgjqey

Acknowledgement to Reviewers of Molecules in 2017

2018 Molecules  
Fernandes, Antony Fernandes, Caio Pinho Fernandes, Carla Fernandes, P.  ...  Fernandes, Pedro Fernandes-Ferreira, Manuel Fernández García, Elisabet Fernandéz, Carlos Fernández, Inmaculada Fernández, Marta Fernández, Roberto Fernández-Ballester, Gregorio Ferrante, Claudio  ... 
doi:10.3390/molecules23010138 fatcat:xsjptzyxynbv7ayla4kpzgmzpm

Acknowledgement to Reviewers of Biomolecules in 2019

Biomolecules Editorial Office
2020 Biomolecules  
, Tiera Márcio, Rodrigues Marcio Vinicius, Bertacine Dias Marco, Filice Marco, Nardini Marco, Giovine Marco, Jose Marco, Schiavone Marco, Confalonieri Marco, Abbatangelo Marco, Saler Marco A., Loza-Mejía  ...  Moreno Pavel, Semenyuk Pavel, Kopel Pavla, Bojarová Pavleta, Tzvetkova Pavlina, Dolashka Pavol, Farkaš Paweł, Bogdański Paweł, Konieczka Paweł, Sobczak Payel, Sil Pedro, Fernandes Pedro Alexander, Infante  ... 
doi:10.3390/biom10010145 fatcat:4efeacba7fckdfqe24hvzdoddu

Adriel Claro de Faria AUSTRÁLIA Go8

Amanda Aparecida, Padilha Dorta, Amanda Dela, Antonio Barbosa, Amanda Oliveira, Ana Beatriz, Siqueira Nicolau, Ariana Januario, Araujo Bruna, Larissa Maganhe, Bruna Maceiras, Astolfi Caio (+123 others)
CANDIDATURA DEFERIDAS PELAS UNIDADES E HOMOLOGADAS PELA USPAndre Progiante Brunna Gomes Re Claudio Marcio Cardoso Aires Fernanda da Silva Santos Luisa Facincani Camacho Marianne Junko Muramatsu Priscila  ...  Sergio da Silva Junior Priscila de Moura Queiroz Priscila dos Reis Cunha Priscilla Escudero Falsetti Renata Thina Yoshida Roberto Januszkiewicz Junior Robson Mengatti Pinheiros Stefhanie Costa Merino  ... 

Acknowledgement to Reviewers of Molecules in 2013

Molecules Editorial Office
2014 Molecules  
Fernand, Vivian Fernandes, K. F. Fernandez Megia, Eduardo Fernández-Alba, A. R. Fernández-Arroyo, Salvador Fernandez-Lafuente, Roberto Fernández-Miyakawa, M. E.  ...  Menaa, Farid Mencherini, Teresa Menezes, José Meng, Fan-Yi Merino, Pedro Mesías, Marta Messeguer, Angel Messori, Luigi Meyer, Matthew P. Meyer, R.  ... 
doi:10.3390/molecules19032707 fatcat:no3a4sb5afhvlcc2e6ycj5lvmq

Acknowledgment to Reviewers of Biomolecules in 2020

Biomolecules Editorial Office Biomolecules Editorial Office
2021 Biomolecules  
Fizeșan, Ionel Fernandes, João Paulo S. Florán, Benjamín Fernandes, Rosa Cristina Simoes Florek, Ewa Fernandes, Tiago G.  ...  Thummel, Ryan Tarasov, Andrei Thurnher, Martin Tarn, Woan-Yuh Tian, Sheng Tashima, Kimihito Tian, Ya-Chung Tashima, Toshihiko Tian, Yuan Tata, Ada Maria Ticconi, Carlo Tate, Shin-Ichi Tiera, Marcio  ... 
doi:10.3390/biom11020151 pmid:33503875 fatcat:dymribmmojagfccsgapnx47hri

Acknowledgement to Reviewers of Molecules in 2014

Molecules Editorial Office
2015 Molecules  
Mazutti, Marcio A. Mazzei, Franco Mazzoni, I. McAlpine, Shelli Mcanulty, Steve McCallum, Jason L. McCann, Mark J.  ...  Fernand Ge, Yubin Geary, Sean Gebicki, Janusz Gehrke, Sebastian S. Geraghty, Dominic P. Geronikaki, Athina Gerothanassis, Ioannis P.  ... 
doi:10.3390/molecules20010693 fatcat:nl44pswimvezdl6twscn2kx4iy

Obstructive sleep apnea and Parkinson's disease: characteristics and associated factors

Manoel Alves Sobreira-Neto, Márcio Alexandre Pena-Pereira, Emmanuelle Silva Tavares Sobreira, Marcos Hortes Nisihara Chagas, Carlos Maurício Oliveira de Almeida, Regina Maria França Fernandes, Vitor Tumas, Alan Luiz Eckeli
2019 Arquivos de Neuro-Psiquiatria  
With regard to excessive sleepiness, Merino-Andreu et al. documented the inadequate perception of the wake-sleep transition in PD patients, and this could be a possible explanation for the absence of a  ... 
doi:10.1590/0004-282x20190098 pmid:31553390 fatcat:dkivpvg2o5bdre36tvbzyu7kai

Acknowledgment to Reviewers of IJERPH in 2020

IJERPH Editorial Office IJERPH Editorial Office
2021 International Journal of Environmental Research and Public Health  
Fernandes, Francisco Fekete, Albert Fernandes, Gisele Aparecida Fekete, Alexander Fernandes, Hélder Miguel Fekete, Christine Fernandes, John F. T.  ...  Ribas Fernandes, Antonio Feinberg, Iris Fernandes, Cláudia Oliveira Feinman, Richard Fernandes, Cristina Feinn, Richard S.  ... 
doi:10.3390/ijerph18031259 fatcat:kqqzdz46tzf7nhqmf2ejn3n33y
« Previous Showing results 1 — 15 out of 51 results