Dra. E. Gabriela Barrantes Sliesarieva

Dra. E. Gabriela Barrantes Sliesarieva

Descripción: 

Reconocimientos

  • Fondos de investigación para seguridad por diversificación, Santa Fe Institute, U.S.A., Marzo 2005 - Febrero 2007.
  • Disertación de Doctorado defendida con distinción, Departamento de Ciencias de la Computación, Universidad de Nuevo México, Febrero 2005.
  • Beca Fulbright-LASPAU, De agosto 2000 a julio 2002
  • Presidente de la Rama Costa Rica de la Computer Society (IEEE), 2000.
Es estudiante: 
No

Formación académica

  • Ph.D. Ciencias de la Computación, The University of New Mexico, Albuquerque, Nuevo México, Estados Unidos, 2005. Disertación: Automated Methods for Creating Diversity in Computer Systems Área: Seguridad Computacional
  • M.Sc. Ingeniería de la Computación, Florida Atlantic University, Boca Raton, Florida, Estados Unidos, 1995.
  • Bachillerato en Computación e Informática, Universidad de Costa Rica, San José, Costa Rica, 1990.

Experiencia laboral

  • Profesora Catedrática, Escuela de Ciencias de la Computación e Informática, Universidad de Costa Rica.  2009 a la actualidad.
  • Directora, Escuela de Ciencias de la Computación e Informática, Universidad de Costa Rica. Del 1ero de julio de 2009 al 30 de junio de 2013.
  • Directora, Programa de Posgrado en Computación e Informática, Universidad de Costa Rica. Del 1ero de julio de 2008 al 31 de julio de 2009.
  • Profesora, Escuela de Ciencias de la Computación e Informática, Universidad de Costa Rica.  1993 a la actualidad.

Proyectos

Publicaciones

Emotions Classifier based on Facial Expressions

Descripción:

Emotion recognition is important in the context of smart buildings and IoT, because it allows the environment to have a better notion of the mood of the humans who are present. With a view to developing such projects, in this article we analyze the performance of an emotion classifier that uses a convolutional neural network. Specifically, we focus on analyzing the impact of the epochs and batch size hyperparameters. To do this, we propose an experimental design with the following hypothesis: "The number of epochs that the model trains and the size of the batch given by iteration in each epoch influence the accuracy of an emotion classifier built from networks. convolutional neurons using the VGG16 architecture".

Tipo de publicación: Conference Paper

Publicado en: 2021 IEEE V Jornadas Costarricenses de Investigación en Computación e Informática (JoCICI)

Asynchronous Detection of Slowloris Attacks Via Random Forests

Descripción:

An asynchronous classifier of network flows was developed to detect Slowloris attacks. This classifier was implemented using random forests and its effectiveness was measured by the area under the ROC curve. These random forests were trained from a public dataset. We sought to minimize the number of necessary features that are required to analyze the flows satisfactorily. Finally, it was shown that the chosen features can be used individually to obtain reliable detections in the classifier, with two of the three individual features having an area under the curve greater than 0.95.

Tipo de publicación: Conference Paper

Publicado en: 2021 IEEE V Jornadas Costarricenses de Investigación en Computación e Informática (JoCICI)

Recognizing daily-life activities using sensor-collected data in a kitchen

Descripción:

This paper focuses on the recognition and classification of Activities of Daily Living (ADLs) that are carried out in a kitchen. To do this, a Recurrent Neural Network architecture of the Long-Short Term Memory (LSTM) type is implemented as a classifier. The ARAS dataset is used for training and evaluation. A classifier is obtained with an average value in the F1 metric of 95.33% for the chosen data set.

Tipo de publicación: Conference Paper

Publicado en: 2021 IEEE V Jornadas Costarricenses de Investigación en Computación e Informática (JoCICI)

Tor Traffic Classification using Decision Trees

Descripción:

The amount of users interested in protecting their data and privacy on the Internet has increased lately. This has augmented the popularity of anonymization services such as Tor. However, the anonymization and the complication of being tracked provided by Tor has also been used for illintended purposes, such as evading security policies and controls. In this work, we implemented and evaluated an offline Tor traffic detector using white-box machine learning algorithms such as decision trees and random forests. On the one hand, our classifier achieves precision levels above 99 %. On the other hand, our approach is the first one to allow understanding and interpreting the classifier, thus understanding which variables play a significant role in the classification. We show that TCP window size, packet size and some time-related features can be used to identify Tor traffic.

Tipo de publicación: Conference Paper

Publicado en: 2023 XLIX Latin American Computer Conference (CLEI)