APPLICATION OF ARTIFICIAL NEURAL NETWORKS IN ESTIMATING CORE BODY TEMPERATURE
DOI:
https://doi.org/10.24867/33BE15PavkovicKeywords:
Artificial neural networks, core body temperature, data processingAbstract
This thesis addresses the estimation of core body temperature using non-invasive physiological signals. Machine-learning models based on different artificial neural-network architectures were developed to estimate temperature. After data preprocessing and normalization, the models were trained and tested, and their accuracy assessed with standard regression metrics.
References
[1] P. N. Stuart Russell, Artifical Intelligence: A Modern Approach, Pearson, 2016..
[2] Y. B. G. H. Yann LeCun, "Deep Learning," Nature, 2015.
[3] H. B. Youngjoo Kim, Introduction to Kalman Filter and Its Applications, InTechOpen, 2018.
[4] S. S. K. G. M. F. Shahin Tasoujian, Real-Time Cubature Kalman Filter Parameter Estimation of Blood Pressure Response Characteristics Under Vasoactive Drugs Administration, IEEE, 2020.
[5] W. J. T. S. N. C. S. J. M. R. W. K. J. C. W. A. L. W. S. R. M. R. O. C. J. R. W. H. Mark J Buller 1, Estimation of human core temperature from, PubMed, 2013.
[6] E. W. S. A. A. P. S. D. R. M. R. Reto Niedermann 1, "Prediction of human core body temperature using non-invasive," Springer Nature Link, 2013.
