• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Master's Dissertation
DOI
https://doi.org/10.11606/D.55.2008.tde-21012009-151233
Document
Author
Full name
Matheus Lorenzo dos Santos
Institute/School/College
Knowledge Area
Date of Defense
Published
São Carlos, 2008
Supervisor
Committee
Mello, Rodrigo Fernandes de (President)
Hruschka, Eduardo Raul
Macedo, Alessandra Alaniz
Title in Portuguese
Classificação e detecção de variações de comportamento: uma abordagem aplicada à identificação de perfis de usuários
Keywords in Portuguese
Cadeias de Markov
Classificação de comportamento
Entropia
Perfil
Abstract in Portuguese
Estudos comportamentais têm sido conduzidos, há séculos, por cientistas e filósofos, abordando assuntos tais como trajetórias de estrelas e planetas, organizações da sociedade, evolução dos seres vivos, comportamento e linguagem humana. Com o advento da computação, grandes quantidades de informação tornaram-se disponíveis, as quais geram novos desafios a fim de explorar e compreender variações comportamentais de interação com esses sistemas. Motivado por esses desafios e pela disponibilidade de informações, esta dissertação de mestrado propõe uma metodologia com objetivo de classificar, detectar e identificar padrões de comportamento. A fim de validar essa metodologia, modelou-se conhecimentos embutidos em informações relativas a interações de usuários durante a grafia digital de assinaturas (tais informações foram obtidas de uma base de dados do campeonato SVC2004 -- First International Signature Verification Competition). Os modelos de conhecimento gerados foram, posteriormente, empregados em experimentos visando o reconhecimento de assinaturas. Resultados obtidos foram comparados a outras abordagens propostas na literatura
Title in English
Classification and behavior variation detection: an approach applied to identify user profile
Keywords in English
Behavior classification
Entropy
Markov chain
Profile
Abstract in English
Throughout the centuries, behavioral studies have been conducted by scientists and philosophers, approaching subjects such as stars and planet trajectories, social organizations, living beings, human behavior and language. With the advent of computer science, large amounts of information have been made available, which brings out new challenges in the interactive behavior context. Such challenges have motivated this master thesis which proposes a methodology to classify, detect and identify behavioral patterns. A digital signature verification database, obtained from the First International Signature Verification Competition (SVC2004), was used to validate the proposed methodology. Knowledge models were obtained and, afterwards, employed in signature verification experiments. Results were compared to other approaches from the literature
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
dissertacao.pdf (4.79 Mbytes)
Publishing Date
2009-05-21
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2024. All rights reserved.