Detecção Automática da Depressão Assistida por Stacking DNNs em Dados de Descritores de Características Visuais

  • Filipe F. de Almeida UFMA
  • André C. B. Soares UFPI
  • Laurindo de S. B. Neto UFPI
  • Kelson R. T. Aires UFPI

Resumo


Pessoas vivenciam cada vez mais sentimentos de angústia, ansiedade e tristeza. Esses apontam, entre outras patologias, à depressão e, pior, pensamentos de ideação suicida. Posto isso, técnicas computacionais capazes de apontar tal transtorno precocemente se tornam indispensáveis. O presente trabalho apresenta um modelo baseado em Stacking Deep Neural Networks para análise de expressões faciais e subsequente detecção automática da depressão. Os resultados obtidos indicam um avanço promissor quanto à detecção automática da depressão. O modelo Stacking DNNs atinge, na base de teste, 78,5% de Recall e 62,8% de F1-Score. Tais valores são 22% e 17% superiores, respectivamente, a modelos unimodais que aplicam métodos semelhantes.

Referências

Akbar, H., Dewi, S., Rozali, Y. A., Lunanta, L. P., Anwar, N., and Anwar, D. (2021). Exploiting facial action unit in video for recognizing depression using metaheuristic and neural networks. In 2021 1st International Conference on Computer Science and Artificial Intelligence (ICCSAI), volume 1, pages 438–443. IEEE.

Baltrušaitis, T., Robinson, P., and Morency, L.-P. (2016). Openface: an open source facial behavior analysis toolkit. In 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), pages 1–10. IEEE.

Chawla, N. V., Bowyer, K. W., Hall, L. O., and Kegelmeyer, W. P. (2002). Smote: synthetic minority over-sampling technique. Journal of artificial intelligence research, 16:321–357.

Cohn, J. F., Ambadar, Z., and Ekman, P. (2007). Observer-based measurement of facial expression with the facial action coding system. The handbook of emotion elicitation and assessment, 1(3):203–221.

Colab, G. (2022). Google colaboratory. url: https://colab.research.google.com/.

Cortes, C. and Vapnik, V. (1995). Support-vector networks. Machine learning, 20:273–297.

de Melo, W. C., Granger, E., and Lopez, M. B. (2021). Mdn: A deep maximization-differentiation network for spatio-temporal depression detection. IEEE Transactions on Affective Computing.

Durstewitz, D., Koppe, G., and Meyer-Lindenberg, A. (2019). Deep neural networks in psychiatry. Molecular psychiatry, 24(11):1583–1598.

Farias, M., Gusmão, R., and Gusmão, C. (2020). Mineração de dados aplicada à saúde mental de estudantes universitários: Uma revisão sistemática. Anais do XX Simpósio Brasileiro de Computação Aplicada à Saúde, pages 49–59.

Ghorbani, R. and Ghousi, R. (2020). Comparing different resampling methods in predicting students’ performance using machine learning techniques. IEEE Access, 8:67899–67911.

Gratch, J., Artstein, R., Lucas, G., Stratou, G., Scherer, S., Nazarian, A., Wood, R., Boberg, J., DeVault, D., Marsella, S., et al. (2014). The distress analysis interview corpus of human and computer interviews. Technical report, UNIVERSITY OF SOUTHERN CALIFORNIA LOS ANGELES.

Guo, Y., Zhu, C., Hao, S., and Hong, R. (2022). Automatic depression detection via learning and fusing features from visual cues. arXiv preprint arXiv:2203.00304.

Haque, A., Guo, M., Miner, A. S., and Fei-Fei, L. (2018). Measuring depression symptom severity from spoken language and 3d facial expressions. arXiv preprint arXiv:1811.08592.

Kroenke, K., Strine, T. W., Spitzer, R. L., Williams, J. B., Berry, J. T., and Mokdad, A. H. (2009). The phq-8 as a measure of current depression in the general population. Journal of affective disorders, 114(1-3):163–173.

Li, M., Soltanolkotabi, M., and Oymak, S. (2020). Gradient descent with early stopping is provably robust to label noise for overparameterized neural networks. In International conference on artificial intelligence and statistics, pages 4313–4324. PMLR.

Maćkiewicz, A. and Ratajczak, W. (1993). Principal components analysis (pca). Computers & Geosciences, 19(3):303–342.

Mienye, I. D. and Sun, Y. (2022). A survey of ensemble learning: Concepts, algorithms, applications, and prospects. IEEE Access, 10:99129–99149.

Moon, J., Jung, S., Rew, J., Rho, S., and Hwang, E. (2020). Combination of short-term load forecasting models based on a stacking ensemble approach. Energy and Buildings, 216:109921.

Morales, M. R. (2018). Multimodal depression detection: An investigation of features and fusion techniques for automated systems. City University of New York.

Nasir, M., Jati, A., Shivakumar, P. G., Nallan Chakravarthula, S., and Georgiou, P. (2016). Multimodal and multiresolution depression detection from speech and facial landmark features. In Proceedings of the 6th international workshop on audio/visual emotion challenge, pages 43–50.

Nguyen, H. M., Cooper, E. W., and Kamei, K. (2011). Borderline over-sampling for imbalanced data classification. International Journal of Knowledge Engineering and Soft Data Paradigms, 3(1):4–21.

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830.

Song, S., Shen, L., and Valstar, M. (2018). Human behaviour-based automatic depression analysis using hand-crafted statistics and deep learned spectral features. In 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018), pages 158–165. IEEE.

Taschereau-Dumouchel, V., Michel, M., Lau, H., Hofmann, S. G., and LeDoux, J. E. (2022). Putting the “mental” back in “mental disorders”: a perspective from research on fear and anxiety. Molecular Psychiatry, 27(3):1322–1330.

Valstar, M., Gratch, J., Schuller, B., Ringeval, F., Lalanne, D., Torres Torres, M., Scherer, S., Stratou, G., Cowie, R., and Pantic, M. (2016). Avec 2016: Depression, mood, and emotion recognition workshop and challenge. In Proceedings of the 6th international workshop on audio/visual emotion challenge, pages 3–10.

Wang, Y., Ma, J., Hao, B., Hu, P., Wang, X., Mei, J., and Li, S. (2020). Automatic depression detection via facial expressions using multiple instance learning. In 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), pages 1933–1936. IEEE.

Wei, P.-C., Peng, K., Roitberg, A., Yang, K., Zhang, J., and Stiefelhagen, R. (2022). Multi-modal depression estimation based on sub-attentional fusion. arXiv preprint arXiv:2207.06180.

WHO (2022). World health organization depression. url: https://bityli.com/EqHbyv.

Zou, X., Hu, Y., Tian, Z., and Shen, K. (2019). Logistic regression model optimization and case analysis. In 2019 IEEE 7th international conference on computer science and network technology (ICCSNT), pages 135–139. IEEE.
Publicado
27/06/2023
ALMEIDA, Filipe F. de; SOARES, André C. B.; B. NETO, Laurindo de S.; AIRES, Kelson R. T.. Detecção Automática da Depressão Assistida por Stacking DNNs em Dados de Descritores de Características Visuais. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 23. , 2023, São Paulo/SP. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2023 . p. 150-161. ISSN 2763-8952. DOI: https://doi.org/10.5753/sbcas.2023.229573.

##plugins.generic.recommendByAuthor.heading##