Therapies customization by emotion recognition in biosignals
DOI:
https://doi.org/10.59681/2175-4411.v16.iEspecial.2024.1266Keywords:
Emotion-Focused Therapy, Music Therapy, Artificial IntelligenceAbstract
Goal: This study aimed to develop a hybrid artificial neural network architecture to recognize mood states in biosignals from elderly individuals, including those with mild to moderate dementia, to support the personalization of therapies. Method: The study employed Wavelet Transform to convert signals into images, used as input for a hybrid architecture comprising a pre-trained convolutional neural network of LeNet type for feature extraction, and a Random Forest algorithm with 450 trees for classification. The performance of the proposed algorithm was evaluated on publicly available databases of electroencephalography and voice signals, and subsequently validated on an in-house database of elderly individuals with and without dementia. Results: The achieved accuracy ranged from 71% to 73%. Conclusion: This technology can be integrated into human-machine interfaces to personalize various therapies, such as music therapy.
References
Vivas EN, Rocha SF. The Brazilian population aging and its contemporary challenges. MOJ Gerontol Ger. 2020;5(5):165-8. DOI: https://doi.org/10.15406/mojgg.2020.05.00251
Bloom DE, Canning D, Lubet A. Global population aging: Facts, challenges, solutions & perspectives. Daedalus. 2015;144(2):80-92. DOI: https://doi.org/10.1162/DAED_a_00332
Silva-Júnior JD. Memórias Autobiográficas e Música em Idosos. Campinas: Editora Alínea. 2018.
Peixoto CT da S. Saúde mental: um enfoque voltado à prevenção da demência de alzheimer. JHMReview [Internet]. 2021;7(3). Disponível em: https://ijhmreview.org/ijhmreview/article/view/276
Santana MA, Lima CL, Torcate AS, Fonseca FS, Santos WP. Affective computing in the context of music therapy: a systematic review. RSD [Internet]. 2021;10(15): e392101522844. Disponível em: https://rsdjournal.org/index.php/rsd/article/view/22844 DOI: https://doi.org/10.33448/rsd-v10i15.22844
Veltmeijer EA, Gerritsen C, Hindriks KV. Automatic emotion recognition for groups: a review. IEEE Transactions on Affective Computing. 2021;14(1):89-107. DOI: https://doi.org/10.1109/TAFFC.2021.3065726
Dupré D, Krumhuber EG, Küster D, McKeown GJ. A performance comparison of eight commercially available automatic classifiers for facial affect recognition. Plos one. 2020;15(4):e0231968. DOI: https://doi.org/10.1371/journal.pone.0231968
Mallat SG. Multifrequency channel decompositions of images and wavelet models. IEEE Transactions on Acoustics, speech, and signal processing. 1989;37(12):2091-110. DOI: https://doi.org/10.1109/29.45554
Eaton JW, Bateman D, Hauberg S. GNU Octave version 3.0. 1 manual: a high-level interactive language for numerical computations. Whales: Network Theory Ltd. 2007.
Witten IH, Frank E, Hall MA. Data Mining: Practical machine learning tools and techniques. Burlington: Morgan Kaufmann Publishers. 2011.
Soleymani M, Lichtenauer J, Pun T, Pantic M. A multimodal database for affect recognition and implicit tagging. IEEE transactions on affective computing. 2011;3(1):42-55. DOI: https://doi.org/10.1109/T-AFFC.2011.25
Livingstone SR, Russo FA. The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS): A dynamic, multimodal set of facial and vocal expressions in North American English. PloS one. 2018;13(5):e0196391. DOI: https://doi.org/10.1371/journal.pone.0196391
McHugh ML. Interrater reliability: the kappa statistic. Biochemia medica. 2012;22(3):276-82. DOI: https://doi.org/10.11613/BM.2012.031
Almeida OP. Mini exame dos estado mental e o diagnóstico de demência no Brasil. Arquivos de Neuro-psiquiatria. 1998;56:605-12. DOI: https://doi.org/10.1590/S0004-282X1998000400014
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Submission of a paper to Journal of Health Informatics is understood to imply that it is not being considered for publication elsewhere and that the author(s) permission to publish his/her (their) article(s) in this Journal implies the exclusive authorization of the publishers to deal with all issues concerning the copyright therein. Upon the submission of an article, authors will be asked to sign a Copyright Notice. Acceptance of the agreement will ensure the widest possible dissemination of information. An e-mail will be sent to the corresponding author confirming receipt of the manuscript and acceptance of the agreement.
