Aplicação da Máquina de Aprendizagem Mínima na Análise Emocional de Sinais Cerebrais
Comparação com Redes Neurais Artificiais e Máquinas de Vetores
DOI:
https://doi.org/10.5752/P.2316-9451.e2026140103Palavras-chave:
Emoções humanas, Sinais EEG, Máquina de Aprendizagem Mínima, Reconhecimento de padrõesResumo
Sistemas Brain-Computer Interface (BCI) utilizam sinais de eletroencefalografia (EEG) para traduzir padrões cerebrais em comandos computacionais. Contudo, a classificação desses sinais depende do ajuste de hiperparâmetros. Neste estudo, avaliou-se o desempenho da Minimal Learning Machine (MLM) no reconhecimento de emoções humanas a partir de sinais de EEG, comparando-a aos modelos Multilayer Perceptron (MLP) e Support Vector Machine (SVM). Foram conduzidos três experimentos computacionais, dos quais os resultados mostraram que a MLM superou MLP e SVM em dois experimentos, alcançando acurácia máxima de 96,7%. Conclui-se que a MLM é uma alternativa eficaz e flexível para aplicações em sistemas BCI.
Downloads
Referências
ABIRI, Reza et al. A comprehensive review of EEG-based brain–computer interface paradigms. Journal of Neural Engineering, IOP Publishing, v. 16, n. 1, p. 011001, 2019.
ALZAHAB, Nibras Abo et al. Hybrid Deep Learning (hDL)-Based Brain-Computer Interface (BCI) Systems: A Systematic Review. Brain Sciences, v. 11, n. 1, 2021. ISSN 2076-3425. Disponível em: https://www.mdpi.com/2076-3425/11/1/75.
BASHASHATI, Hossein et al. Comparing different classifiers in sensory motor brain computer interfaces. PloS One, Public Library of Science, v. 10, n. 6, p. e0129435, 2015.
BHATTI, Adnan Mehmood et al. Human emotion recognition and analysis in response to audio music using brain signals. Computers in Human Behavior, Elsevier, v. 65, p. 267–275, 2016. Disponível em: https://www.sciencedirect.com/science/article/pii/S0747563216305945?via%3Dihub.
BIRD, Jordan J. et al. A deep evolutionary approach to bioinspired classifier optimisation for brain-machine interaction. Complexity, Hindawi, v. 2019, 2019.
BIRD, Jordan James et al. Mental emotional sentiment classification with an EEG-based brain-machine interface. In: Proceedings of the International Conference on Digital Image and Signal Processing (DISP’19). United Kingdom: St Hugh’s College, Oxford University, 2019. p. 75–78. ISBN 978-1-912532-05-6. Anais: https://imm.dtu.dk/~alan/DISP2019_proceedings.pdf. Disponível em: https://jordanjamesbird.com/publications/Mental-Emotional-Sentiment-Classification-with-an-EEG-based-Brain-machine-Interface.pdf.
CAPARELLI, Thiago Bruno et al. Projeto e desenvolvimento de um sistema multicanal de biotelemetria para detecção de sinais ECG, EEG e EMG. 2007. Dissertação (Mestrado em Engenharia Elétrica) — Universidade Federal de Uberlândia, Uberlândia, 2007.
DIAS, Madson Luiz Dantas et al. Opposite neighborhood: a new method to select reference points of minimal learning machines. In: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning 2018. Bruges: ESANN, 2018. p. 201–206. ISBN 978-287587047-6. Anais: https://www.esann.org/proceedings/2018.
FACELI, Katti et al. Inteligência artificial: uma abordagem de aprendizado de máquina. Barueri: LTC, 2021. ISBN 9788521637349.
FERNÁNDEZ-DELGADO, Manuel et al. Do we need hundreds of classifiers to solve real world classification problems? The Journal of Machine Learning Research, JMLR.org, v. 15, n. 1, p. 3133–3181, 2014. Disponível em: http://jmlr.org/papers/v15/delgado14a.html.
FLORÊNCIO, José A. V. et al. A fuzzy c-means-based approach for selecting reference points in minimal learning machines. In: North American Fuzzy Information Processing Society Annual Conference. Fortaleza: Springer, Cham, 2018. p. 398–407.
GARDNER, Matt W.; DORLING, Stephen R. Artificial neural networks (the multilayer perceptron): a review of applications in the atmospheric sciences. Atmospheric Environment, Elsevier, v. 32, n. 14-15, p. 2627–2636, 1998.
GOMES, João Paulo Pordeus et al. A cost sensitive minimal learning machine for pattern classification. In: International Conference on Neural Information Processing. Montréal: Springer, Cham, 2015. p. 557–564. Anais: https://link.springer.com/book/10.1007/978-3-319-26532-2. Disponível em: https://doi.org/10.1007/978-3-319-26532-2_61.
GU, Xiaotong et al. EEG-based brain-computer interfaces (BCIs): A survey of recent studies on signal sensing technologies and computational intelligence approaches and their applications. IEEE/ACM Transactions on Computational Biology and Bioinformatics, IEEE, 2021.
HUANG, H. et al. An EEG-based brain computer interface for emotion recognition and its application in patients with Disorder of Consciousness. IEEE Transactions on Affective Computing, IEEE, 2021.
JALILIFARD, Amir; PIZZOLATO, Ednaldo Brigante; ISLAM, Md Kafiul. Emotion classification using single-channel scalp-EEG recording. In: 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Florida: IEEE, 2016. p. 845–849. Anais: https://ieeexplore.ieee.org/xpl/conhome/7580725/proceeding. Disponível em: https://ieeexplore.ieee.org/document/7590833.
JÚNIOR, Amauri Holanda de Souza. Regional models and minimal learning machines for nonlinear dynamical system identification. 2014. Tese (Doutorado em Engenharia de Teleinformática) — Universidade Federal do Ceará, Fortaleza, 2014.
JUNIOR, Amauri Holanda de Souza et al. Minimal learning machine: a novel supervised distance-based approach for regression and classification. Neurocomputing, Elsevier, v. 164, p. 34–44, 2015.
JÚNIOR, Amauri Holanda de Souza et al. Extending the Minimal Learning Machine for Pattern Classification. In: 2013 BRICS Congress on Computational Intelligence and 11th Brazilian Congress on Computational Intelligence. Ipojuca: IEEE, 2013. p. 236–241.
KAYIKCIOGLU, Temel; AYDEMIR, Onder. A polynomial fitting and k-NN based approach for improving classification of motor imagery BCI data. Pattern Recognition Letters, Elsevier, v. 31, n. 11, p. 1207–1215, 2010.
KUMAR, M. Keerthi et al. Comparative analysis to identify efficient technique for interfacing BCI system. IOP Conference Series: Materials Science and Engineering, IOP Publishing, v. 925, n. 1, p. 012062, set. 2020. Disponível em: https://dx.doi.org/10.1088/1757-899X/925/1/012062.
LELIS, Atahualpa Bastos; FILHO, Jarbas Cabral. Utilização de Ondas Cerebrais para Controle de Componentes Eletrônicos. Semana Acadêmica, Fortaleza, v. 1, n. 52, 2014.
LI, Jing et al. Using permutation entropy to measure the changes in EEG signals during absence seizures. Entropy, Multidisciplinary Digital Publishing Institute, v. 16, n. 6, p. 3049–3061, 2014.
LINJA, Joakim et al. Do Randomized Algorithms Improve the Efficiency of Minimal Learning Machine? Machine Learning and Knowledge Extraction, Multidisciplinary Digital Publishing Institute, v. 2, n. 4, p. 533–557, 2020.
LOTTE, F. et al. A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update. Journal of Neural Engineering, IOP Publishing, v. 15, n. 3, p. 031005, 2018.
MARKOULIDAKIS, I. et al. Multiclass confusion matrix reduction method and its application on net promoter score classification problem. Technologies, Multidisciplinary Digital Publishing Institute, v. 9, n. 4, p. 81, 2021.
MESQUITA, Diego Parente Paiva; GOMES, Joao Paulo Pordeus; JUNIOR, Amauri H. Souza. Ensemble of efficient minimal learning machines for classification and regression. Neural Processing Letters, Springer, v. 46, n. 3, p. 751–766, 2017. Disponível em: https://doi.org/10.1007/s11063-017-9587-5.
MESQUITA, Diego Parente Paiva; GOMES, Joao Paulo Pordeus; JUNIOR, Amauri Holanda Souza. Ensemble of minimal learning machines for pattern classification. In: International Work-Conference on Artificial Neural Networks. Palma de Mallorca: Springer, 2015. p. 142–152. Anais: https://link.springer.com/book/10.1007/978-3-319-19222-2. Disponível em: https://doi.org/10.1007/978-3-319-19222-2_12.
OUYANG, Gaoxiang et al. Ordinal pattern based similarity analysis for EEG recordings. Clinical Neurophysiology, Elsevier, v. 121, n. 5, p. 694–703, 2010.
PRODANOV, C. C.; FREITAS, E. C. Metodologia do trabalho científico: métodos e técnicas da pesquisa e do trabalho acadêmico. 2. ed. Novo Hamburgo: Feevale, 2013.
RASHID, Mamunur et al. Current status, challenges, and possible solutions of EEG-based brain-computer interface: a comprehensive review. Frontiers in Neurorobotics, Frontiers, v. 14, p. 25, 2020.
SOKOLOVA, Marina; LAPALME, Guy. A systematic analysis of performance measures for classification tasks. Information Processing & Management, Elsevier, v. 45, n. 4, p. 427–437, 2009.
VELASCO-ALVAREZ, Francisco et al. Audio-cued motor imagery-based brain–computer interface: Navigation through virtual and real environments. Neurocomputing, Elsevier, v. 121, p. 89–98, 2013.
WANG, Xiao-Wei; NIE, Dan; LU, Bao-Liang. Emotional state classification from EEG data using machine learning approach. Neurocomputing, Elsevier, v. 129, p. 94–106, 2014.
WEBB, Andrew R. Statistical Pattern Recognition. San Francisco: John Wiley & Sons, 2003.
Downloads
Publicado
Como Citar
Edição
Seção
Licença
Os autores dos artigos detêm o copyright sem restrições e mantêm direitos de publicação nos termos da licença Creative Common 4.0.
Licença Creative Common 4.0 - CC BY
Este obra está licenciado com uma Licença Creative Commons Atribuição 4.0 Internacional. CC BY
Português
English
