Condução de experimentos para o treinamento de modelos de Rede Neurais Artificiais em tarefas de inferência de expressões faciais em um ambiente Testbed

• Ítalo J. da S. Melo UFPA
• Edson M. da C. Filho UFPA
• Alana M. Medeiros UFPA
• Yomara P. Pires UFPA
• Saulo W. da S. Costa UFPA
• Marcos C. da R. Seruffo UFPA

DOI: https://doi.org/10.5753/wtestbeds.2023.230558

Abstract

Advances in the field of Artificial Intelligence (AI) in recent times have allowed the development of technologies and research present in our daily lives, an example of the area of affective computing in the recognition of advanced expressions. However, carrying out experiments in this area requires allocation of resources and a controllable test environment for training neural models capable of inferring emotions. This article reports the use of Testbeds for training an Artificial Neural Network (ANN) model for emotion inference tasks through facial expression recognition. For this, the Teachable Machine tool was used to compose the neural network model. The test environment used was Testbeds from the National Teaching and Research Network (RNP). The obtained results indicate that the use of the Teachable Machine in a TestBeds enables the creation of accurate and efficient facial recognition models.

References

Bhandari, A. (,2020). Everything you should know about confusion matrix for machine learning. analytics vidhya, 2020. Disponível em: [link]. Acesso em 2023-03-20.

Bukhari, N., Hussain, S., Ayoub, M., Yu, Y., and Khan, A. (2022). Deep learning based framework for emotion recognition using facial expression. Pakistan Journal of Engineering and Technology, 5(3):51–57.

Costa, S. W. D. S., Pires, Y. P., De Sousa, A. L., Costa, F. A. R., De Oliveira, E., Araújo, F. P., and Seruffo, M. C. D. R. (2021). Whot, a novel tool to assist women victims of violence: a case study in the brazilian amazon. IEEE Access, 9:95046–95060.

Domingos, D. A., Cortes, O. A. C., and Lobato, F. M. F. (2022). Evoluindo redes neurais convolucionais na detecção de emoções usando micro ags. Anais do Computer on the Beach, 13:266–273.

Heck, L., Künas, C., and Padoin, E. (2020). Análise de desempenho e efetividade de redes neurais convolucionais em plataformas de gpu e cpu aplicadas ao reconhecimento de emoções através de expressões faciais em seres humanos. In Anais Estendidos do XXI Simpósio em Sistemas Computacionais de Alto Desempenho, pages 8–13, Porto Alegre, RS, Brasil. SBC.

Kuruvayil, S. and Palaniswamy, S. (2022). Emotion recognition from facial images with simultaneous occlusion, pose and illumination variations using meta-learning. Journal of King Saud University-Computer and Information Sciences, 34(9):7271–7282.

MEDEIROS, A. M. et al. (2022). Uma revisão sistemática sobre estudos de detecção de expressões faciais a partir do emprego de modelos de inteligência artificial.

Oguine, O. C., Oguine, K. J., Bisallah, H. I., and Ofuani, D. (2022). Hybrid facial expression recognition (fer2013) model for real-time emotion classification and prediction. arXiv preprint arXiv:2206.09509.

Passos, L. F. C. (2022). Métodos de regularização no aprendizado de máquinas: Ridge e lasso.

Wong, J. J. N. and Fadzly, N. (2022). Development of species recognition models using google teachable machine on shorebirds and waterbirds. Journal of Taibah University for Science, 16(1):1096–1111.