Identificação de Esforço Cognitivo com Auxílio de Dispositivos Vestíveis e Inteligência Artificial
Resumo
O esforço cognitivo pode ser identificado por meio de sinais psicofisiológicos como PPG, EDA e EEG. Este trabalho aplica duas abordagens: engenharia de características com SVM, KNN e GBDT, e aprendizado de ponta a ponta com CNN, FCN, LSTM e ResNet. Os modelos foram avaliados com dados de três voluntários para verificar sua capacidade de generalização. Os resultados mostram que dispositivos vestíveis comerciais, como o Samsung Galaxy Watch 4, podem obter desempenho semelhante ao de equipamentos clínicos, como o Empatica E4 (acurácia de 73% e AUC de 0,698 vs. 74,3% e 0,696). Esses achados reforçam o potencial de dispositivos acessíveis no monitoramento mental e na detecção de emoções.
Palavras-chave:
Esforço cognitivo, Sinais psicofisiológicos, Aprendizado de máquina, Dispositivos vestíveis, Detecção
Referências
Borisov, V., Kasneci, E., and Kasneci, G. (2021). Robust cognitive load detection from wrist-band sensors. Computers in Human Behavior Reports, 4.
Buja, A., Cook, D., Hofmann, H., Lawrence, M., Lee, E.-K., Swayne, D. F., and Wickham, H. (2009). Statistical inference for exploratory data analysis and model diagnostics. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 367(1906):4361–4383.
Cinaz, B. (2013). Monitoring of cognitive load and cognitive performance using wearable sensing.
Ding, Y., Cao, Y., Duffy, V. G., Wang, Y., and Zhang, X. (2020). Measurement and identification of mental workload during simulated computer tasks with multimodal methods and machine learning. Ergonomics, 63.
Ferreira, E., Ferreira, D., Kim, S., Siirtola, P., Röning, J., Forlizzi, J. F., and Dey, A. K. (2014). Assessing real-time cognitive load based on psycho-physiological measures for younger and older adults. In 2014 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB), pages 39–48. IEEE.
Fleming, H., Robinson, O. J., and Roiser, J. P. (2023). Measuring cognitive effort without difficulty. Cognitive, Affective, & Behavioral Neuroscience, 23(2):290–305.
Grzeszczyk, M. K., Blanco, R., Adamczyk, P., Kus, M., Marek, S., Prkecikowski, R., and Lisowska, A. (2023). Cogwear: Can we detect cognitive effort with consumer-grade wearables? Ismail Fawaz, H., Forestier, G., Weber, J., Idoumghar, L., and Muller, P.-A. (2019). Deep learning for time series classification: a review. Data Mining and Knowledge Discovery, 33(4):917–963.
Joseph, G., Joseph, A., Titus, G., Thomas, R. M., and Jose, D. (2014). Photoplethysmogram (ppg) signal analysis and wavelet de-noising. In 2014 Annual International Conference on Emerging Research Areas: Magnetics, Machines and Drives (AI-CERA/iCMMD), pages 1–5.
Kanjo, E., Younis, E. M., and Ang, C. S. (2019). Deep learning analysis of mobile physiological, environmental and location sensor data for emotion detection. Information Fusion, 49.
Longo, L., Wickens, C. D., Hancock, G., and Hancock, P. A. (2022). Human mental workload: A survey and a novel inclusive definition. Frontiers in psychology, 13:883321.
Paas, F., Tuovinen, J. E., Tabbers, H., and Gerven, P. W. V. (2003). Cognitive load measurement as a means to advance cognitive load theory. Educational Psychologist, 38.
Shu, L., Yu, Y., Chen, W., Hua, H., Li, Q., Jin, J., and Xu, X. (2020). Wearable emotion recognition using heart rate data from a smart bracelet. Sensors (Switzerland), 20.
Tukey, J. W. et al. (1977). Exploratory data analysis, volume 2. Springer.
Buja, A., Cook, D., Hofmann, H., Lawrence, M., Lee, E.-K., Swayne, D. F., and Wickham, H. (2009). Statistical inference for exploratory data analysis and model diagnostics. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 367(1906):4361–4383.
Cinaz, B. (2013). Monitoring of cognitive load and cognitive performance using wearable sensing.
Ding, Y., Cao, Y., Duffy, V. G., Wang, Y., and Zhang, X. (2020). Measurement and identification of mental workload during simulated computer tasks with multimodal methods and machine learning. Ergonomics, 63.
Ferreira, E., Ferreira, D., Kim, S., Siirtola, P., Röning, J., Forlizzi, J. F., and Dey, A. K. (2014). Assessing real-time cognitive load based on psycho-physiological measures for younger and older adults. In 2014 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB), pages 39–48. IEEE.
Fleming, H., Robinson, O. J., and Roiser, J. P. (2023). Measuring cognitive effort without difficulty. Cognitive, Affective, & Behavioral Neuroscience, 23(2):290–305.
Grzeszczyk, M. K., Blanco, R., Adamczyk, P., Kus, M., Marek, S., Prkecikowski, R., and Lisowska, A. (2023). Cogwear: Can we detect cognitive effort with consumer-grade wearables? Ismail Fawaz, H., Forestier, G., Weber, J., Idoumghar, L., and Muller, P.-A. (2019). Deep learning for time series classification: a review. Data Mining and Knowledge Discovery, 33(4):917–963.
Joseph, G., Joseph, A., Titus, G., Thomas, R. M., and Jose, D. (2014). Photoplethysmogram (ppg) signal analysis and wavelet de-noising. In 2014 Annual International Conference on Emerging Research Areas: Magnetics, Machines and Drives (AI-CERA/iCMMD), pages 1–5.
Kanjo, E., Younis, E. M., and Ang, C. S. (2019). Deep learning analysis of mobile physiological, environmental and location sensor data for emotion detection. Information Fusion, 49.
Longo, L., Wickens, C. D., Hancock, G., and Hancock, P. A. (2022). Human mental workload: A survey and a novel inclusive definition. Frontiers in psychology, 13:883321.
Paas, F., Tuovinen, J. E., Tabbers, H., and Gerven, P. W. V. (2003). Cognitive load measurement as a means to advance cognitive load theory. Educational Psychologist, 38.
Shu, L., Yu, Y., Chen, W., Hua, H., Li, Q., Jin, J., and Xu, X. (2020). Wearable emotion recognition using heart rate data from a smart bracelet. Sensors (Switzerland), 20.
Tukey, J. W. et al. (1977). Exploratory data analysis, volume 2. Springer.
Publicado
29/10/2025
Como Citar
FRANCESCHINA, Mateus Antonio; ZEISER, Felipe André; COSTA, Cristiano André da; ROEHE, Adriana Vial; ZEISER, Mateus Henrique.
Identificação de Esforço Cognitivo com Auxílio de Dispositivos Vestíveis e Inteligência Artificial. In: ESCOLA REGIONAL DE ENGENHARIA DE SOFTWARE (ERES), 9. , 2025, Chapecó/SC.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 109-118.
DOI: https://doi.org/10.5753/eres.2025.15429.
