O Programa de Pós Graduação em Ciência da Computação tem a honra de convidar toda a comunidade acadêmica para participar das  Defesas de  Dissertações de Mestrado abaixo relacionadas:

DEFESAS DE MESTRADO: 

1) Aluno: Fábio Rocha de Araújo

Matrícula: 201720070004.
Titulo: "ESBA: Hybrid Energy-Saving Vídeo Bitrate Adaptation Algorithm To Deliver Videos With High Quality Of Experience and Energy-Efficiency For Mobile Users ".  

Orientador: Prof. Dr. Denis Lima do Rosário
Data: 29/04/2019.

Hora:13:00 h

Local: Auditório da Faculdade de Matemática.

Banca Examinadora:

1.    Prof. Dr. Denis Lima do Rosário - Orientador (PPGCC/UFPA)

2.    Prof. Dr. Eduardo Coelho Cerqueira - Co-Orientador (PPGCC/UFPA)

3.    Pesquisador Thais Lira Tavares dos Santos - Membro Externo (UFPA)

RESUMO

The number of mobile devices that use video streaming applications has been steadily rising year after year. Platforms responsible for providing multimedia service face great challenges in delivering high-quality content for mobile users due to frequent disconnections, often caused by user movements and heavily energy-dependence of mobile devices. A video adaptation approach with Quality of Experience (QoE) and Energy-saving support is a key issue to mitigate these problems, enhancing user QoE, as well as reducing the energy consumption in mobile devices. In this master thesis, we propose a hybrid Energy-Saving video Bitrate Adaptation algorithm (ESBA) to deliver videos with high QoE and energy-efficiency for mobile users. In addition, we consider an Artificial Neural Network (ANN) approach for individual network throughput prediction. Simulation results show the efficiency of ESBA compared to existing adaptation video bitrate algorithms, reducing the number and duration of player stalls, as well as saving energy of mobile devices. Moreover, observing results, we notice that the ANN approach overcomes current throughput prediction approaches present in literature in specific scenarios, permitting the adaptation algorithm to respond more efficiently to network changes. 

Palavras-chave: Energy, HAS, OoE

2) Aluno: Felipe Rocha de Araújo

Matrícula: 201720070003.
Titulo: "Mobility Prediction Based on Markov Model With User Similarity Using Location-Based Social Networks Data".  

Orientador: Prof. Dr.  Eduardo Coelho Cerqueira  
Data: 29/04/2019.

Hora:16:00 h

Local: Auditório da Faculdade de Matemática.

Banca Examinadora:

1.    Prof. Dr. Eduardo Coelho Cerqueira   - Orientador (PPGCC/UFPA)

2.    Prof. Dr. Denis Lima do Rosário - Co-Orientador (PPGCC/UFPA)

3.    Pesquisador Thais Lira Tavares dos Santos - Membro Externo (UFPA)

         RESUMO

The increasing availability of location-acquisition technology, e.g., embed GPS in smartphones, has created a new specificity of social networks, known as Location-Based Social Networks (LBSNs). It enables users to add a location dimension to existing online social networks in a variety of ways. In this context, LBSNs users stopped being only consumers to become data producers, offering various research opportunities such as mobility prediction and recommendation systems. In addition, LBSN data contains spatial, temporal, and social features of user activity, providing valuable information that is currently available on a large scale and low-cost form via traditional data collection methods. Several models have been proposed for mobility prediction based on LBSN, where most of them use historical records to identify user and group movements. In this sense, Markov Chain (MC) is one of the statistical models used in user mobility prediction, which aims to find the probability of an event happening given $n$ past events conforming to the order of the model. In this master thesis, we introduce the TEmporal Markov Model with User Similarity (TEMMUS) mobility prediction model. It considers an MC of variable order based on the day of the week (weekday or weekend) and the user similarity to predict the user's future location. The results highlight a higher performance of TEMMUS compared to other predictors.

Palavras-chave: PSN, mobility, prediction