Matheus Gomes Cordeiro

Prof. Matheus Gomes Cordeiro

Center for Technological Sciences (CCT), Universidade de Fortaleza, Fortaleza, Ceará, Brazil
orcid
Assistant Professor | AI, Data Science & Quantum Computing

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2022 in Future Generation Computer Systems
Verified
Journal Article
Closed access
Matheus Gomes CordeiroMatheus Gomes Cordeiro
Matheus Gomes Cordeiro
CMCatherine Bezerra Markert
Catherine Bezerra Markert
SASayonara S. Araújo
Sayonara S. Araújo
NCNídia G.S. Campos
Nídia G.S. Campos
RGRubens Sonsol Gondim
Rubens Sonsol Gondim
ARAtslands Rego da Rocha
Atslands Rego da Rocha

1 January 2021
Verified
Conference Paper
Open access
NFNicksson A. de Freitas
Nicksson A. de Freitas
TSTiciana Coelho da Silva
Ticiana Coelho da Silva
JMJosé Fernandes de Macêdo
José Fernandes de Macêdo
LJLeopoldo Melo Junior
Leopoldo Melo Junior
Matheus Gomes CordeiroMatheus Gomes Cordeiro
Matheus Gomes Cordeiro

2 October 2022 in Sensors
Verified
Journal Article
Open access
PDF file
LCLívia Almada Cruz
Lívia Almada Cruz
TSTiciana L. Coelho Da Silva
Ticiana L. Coelho Da Silva
RMRegis Pires Magalhaes
Regis Pires Magalhaes
WMWilken Charles Dantas Melo
Wilken Charles Dantas Melo
Matheus Gomes CordeiroMatheus Gomes Cordeiro
Matheus Gomes Cordeiro
KZKarine Zeitouni
Karine Zeitouni
Representation learning seeks to extract useful and low-dimensional attributes from complex and high-dimensional data. Natural language processing (NLP) was used to investigate the representation learning models to extract words’ feature vectors using their sequential order in the text via word embeddings and language models that maintain their semantic meaning. Inspired by NLP, in this paper, we tackle the representation learning problem for trajectories, using NLP methods to encode external sensors positioned in the road network and generate the features’ space to predict the next vehicle movement. We evaluate the vector representations of on-road sensors and trajectories using extrinsic and intrinsic strategies. Our results have shown the potential of natural language models to describe the space of features on trajectory applications as the next location prediction.

1 October 2019
Verified
Conference Paper
Closed access
Matheus Gomes CordeiroMatheus Gomes Cordeiro
Matheus Gomes Cordeiro
PSPaulo Bruno S. Serafim
Paulo Bruno S. Serafim
YNYuri Lenon B. Nogueira
Yuri Lenon B. Nogueira
CVCreto A. Vidal
Creto A. Vidal
JNJoaquim Neto
Joaquim Neto
A large number of algorithms to generate behaviors of game agents have been developed in recent years. Most of them are based on artificial intelligence techniques that need a training stage. In this context, this paper proposes a minimal training strategy to develop autonomous virtual players using the NEAT neuroevolutionary algorithm to evolve an agent capable of playing the Flappy Bird game. NEAT was used to find the simplest neural network architecture that can perfectly play the game. The modeling of the scenarios and the fitness function were set to ensure adequate representation of the problem compared to the real game. The fitness function is a weighted average based on multiple scenarios and scenario-specific components. Coupling the minimal training strategy, a representative fitness and NEAT, the algorithm had a short convergence time (around 20 generations), with a low complexity network and achieved the perfect behavior in the game.

7 December 2020
Verified
Conference Paper
Closed access
PDF file
SBSandy Ferreira Bezerra
Sandy Ferreira Bezerra
Matheus Gomes CordeiroMatheus Gomes Cordeiro
Matheus Gomes Cordeiro
ARAtslands Rocha
Atslands Rocha
FDFlavia Delicato
Flavia Delicato
O paradigma da computação em névoa possibilita que os recursos computacionais sejam levados para a borda da rede, de forma que a latência e a largura de banda resultantes da computação em nuvem possam ser reduzidas. A combinação desse paradigma com técnicas de fusão de dados e processamento de eventos, a partir da aquisição de dados brutos, tem grande potencial de uso para gerar conhecimento de valor e ajudar a tomada de decisão em sistemas de IoT. Nesse contexto, foi proposta uma arquitetura de fusão de dados em três níveis (nó sensor, névoa e nuvem) que, aliada ao uso de técnicas de processamento de eventos complexos, promove a tomada de decisões com rapidez, enquanto reduz o custo de transmissão de dados na rede. Os experimentos mostram uma redução de 77% no tempo médio de envio de mensagens na rede e 82% de melhoria na vazão média com a utilização da arquitetura proposta.