Cookies
Usamos cookies para melhorar nosso site e a sua experiência. Ao continuar a navegar no site, você aceita a nossa política de cookies. Ver mais
Fechar
  • Menu
Sobre
Download foto HD

Sobre

Professor Adjunto no Departamento de Engenharia Informática da ESTG-Leiria (Instituto Politécnico de Leiria) e investigador no CRACS.

É doutorado em Ciência dos Computadores pela Universidade do Porto; mestre em Informática, ramo de sistemas e redes, também pela Universidade do Porto; licenciado em Engenharia Informática pelo Instituto Superior de Engenharia do Porto.

Coordena atualmente a Pós-Graduação em Informática de Segurança e Computação Forense a decorrer no IPLeiria e é responsável pela lecionação de unidades curriculares na área das redes de computadores, administração de sistemas e redes, tecnologias de cloud e infraestruturas de datacenters.

As principais áreas de investigação incluem os algoritmos imuno-inspirados para a deteção automática de anomalias, algoritmos de classificação e deteção usando ensembles, aprendizagem em sistemas dinâmicos e com base temporal.

Detém igualmente experiência empresarial como gestor de projetos TI e administrador de sistemas.

Tópicos
de interesse
Detalhes

Detalhes

  • Nome

    Mário João Antunes
  • Cluster

    Informática
  • Cargo

    Investigador Sénior
  • Desde

    01 janeiro 2009
Publicações

2019

Boosting dynamic ensemble’s performance in Twitter

Autores
Costa, J; Silva, C; Antunes, M; Ribeiro, B;

Publicação
Neural Computing and Applications

Abstract
Many text classification problems in social networks, and other contexts, are also dynamic problems, where concepts drift through time, and meaningful labels are dynamic. In Twitter-based applications in particular, ensembles are often applied to problems that fit this description, for example sentiment analysis or adapting to drifting circumstances. While it can be straightforward to request different classifiers' input on such ensembles, our goal is to boost dynamic ensembles by combining performance metrics as efficiently as possible. We present a twofold performance-based framework to classify incoming tweets based on recent tweets. On the one hand, individual ensemble classifiers' performance is paramount in defining their contribution to the ensemble. On the other hand, examples are actively selected based on their ability to effectively contribute to the performance in classifying drifting concepts. The main step of the algorithm uses different performance metrics to determine both each classifier strength in the ensemble and each example importance, and hence lifetime, in the learning process. We demonstrate, on a drifted benchmark dataset, that our framework drives the classification performance considerably up for it to make a difference in a variety of applications. © 2019, Springer-Verlag London Ltd., part of Springer Nature.

2019

Ncryptr: a symmetric and asymmetric encryption application

Autores
Ribeiro, G; Grabovschi, M; Antunes, M; Frazao, L;

Publicação
2019 14TH IBERIAN CONFERENCE ON INFORMATION SYSTEMS AND TECHNOLOGIES (CISTI)

Abstract
Each person carries digital devices that communicate with other person's devices and may transmit sensitive data. When the transmitted data is sensitive, it becomes necessary to implement secure mechanisms to hide the information and thus avoid it from being analyzed by third parties. This paper aims to present Ncryptr, a web-based application that allows its users to exchange encrypted instant messages in real time. Outside parties are unable to extract the contents of the messages exchanged between two or more users. Ncryptr allows its users to choose the type of encryption employed, being this a major distinction with others already existing instant messaging applications. The performance analysis is made by comparing the efficiency and latency time of different encryption methods, showing the pros and cons of using each one.

2019

Performance of Hash Functions in Blockchain Applied to IoT Devices

Autores
Ferreira, J; Zhygulskyy, M; Antunes, M; Frazao, L;

Publicação
2019 14TH IBERIAN CONFERENCE ON INFORMATION SYSTEMS AND TECHNOLOGIES (CISTI)

Abstract
The IoT (Internet of Things) is a network composed of several devices (things) connected to the Internet and to each other. IoT services are increasingly growing and are allowing companies to deploy scalable solutions with reduced costs and instantaneous data access. These solutions require seamless authentication, data privacy, security, robustness against attacks, easy deployment, and self- maintenance. Such requirements can be given to a company's IoT solution by applying blockchain technology. This paper analyzes the blockchain technology and the advantages and challenges behind its implementation in an IoT environment. A blockchain in IoT scenario was developed to evaluate the performance of different cryptographic hash functions in the IoT device RaspberryPi. Conclusions were drawn when it comes to the viability of some hash functions mainly based on the low resource characteristic shared by the IoT devices, which compromises the performance of the hash function.

2018

Adaptive Learning Models Evaluation in Twitter’s Timelines

Autores
Costa, J; Silva, C; Antunes, M; Ribeiro, B;

Publicação
2018 International Joint Conference on Neural Networks (IJCNN)

Abstract

2018

An Automated System for Criminal Police Reports Analysis

Autores
Carnaz, G; Nogueira, VB; Antunes, M; Fonseca Ferreira, NM;

Publicação
Proceedings of the Tenth International Conference on Soft Computing and Pattern Recognition (SoCPaR 2018) - Advances in Intelligent Systems and Computing

Abstract

Teses
supervisionadas

2017

Uma implementação open source de um serviço de cloud do tipo IaaS

Autor
João Vitoria Santos

Instituição
IPLeiria

2017

Using telemedicine WebRTC tests in hospital environment

Autor
Dário Gabriel da Cruz Santos

Instituição
IPLeiria