Banca de QUALIFICAÇÃO: AMANDA LUCENA GERMANO

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
DISCENTE : AMANDA LUCENA GERMANO
DATA : 13/12/2016
HORA: 09:00
LOCAL: Sala 2 do DCA
TÍTULO:

Outliers detection in data stream

PALAVRAS-CHAVES:

Outliers detection, data stream, data anomalies.

PÁGINAS: 32
GRANDE ÁREA: Engenharias
ÁREA: Engenharia Elétrica
SUBÁREA: Eletrônica Industrial, Sistemas e Controles Eletrônicos
ESPECIALIDADE: Automação Eletrônica de Processos Elétricos e Industriais
RESUMO:

Recent advances in software and hardware technologies allowed the various systems
and their components to be monitored and measured, generating a rapid growth in the
flow of information and especially the size of the databases. With this avalanche of data,
the traditional model of treating data as persistent relationships proved to be inadequate
by limiting the size of databases. To meet the new needs, the data flow model, which consists
of an ordered sequence of points that can only be read only once or a few times, has
arisen. This area has grown a lot in recent years, mainly due to the large number of systems
that needed to work with this type of data, which includes financial data, telephone
records, web transactions, medical data, sensor networks or even multimedia data. However,
among the numerous data, there are rare events in which the points present deviations
from the others, called outliers or anomalies. These anomalous data have important information
about the abnormal behavior of the system. Thus, outliers detection has become a
major problem in the areas of credit card fraud detection, medical care, public safety, industry
damage detection, image processing, sensor/video network surveillance, intrusion
detection etc. Given the importance of this topic, the area has grown a lot in recent years,
and despite the numerous proposed algorithms for detection of outliers, many of them
become inadequate when working with data flow. In this way, this work approaches the
main themes related to these two areas that has been expanding in the last years, besides
employing and analyzing the different algorithms for detecting anomalies.

MEMBROS DA BANCA:
Presidente - 1153006 - LUIZ AFFONSO HENDERSON GUEDES DE OLIVEIRA
Interno - 2885532 - Ivanovitch Silva
Externo ao Programa - 1555898 - DIEGO RODRIGO CABRAL SILVA