This paper presents an approach that utilizes deep recurrent neural networks to predict body shape changes in individuals undergoing dietetic treatment. It contributes to computational body modelling by offering a reliable tool that assists healthcare professionals in tailoring recommendations and motivating individuals to achieve their body shape goals. The approach is focused on the regression of body shape parameters over time, which enables the prediction of shape changes using the individual body history. This method has been applied and evaluated using a dataset obtained from 80 individuals undergoing dietetic treatment over an 8-month period. The results demonstrate the effectiveness of the proposed model in accurately predicting body shape transformations resulting from dietetic treatment. The predictive capabilities of the model provide valuable insights for healthcare professionals, enabling them to tailor personalized recommendations for individuals.
CITATION STYLE
Garcia-D’Urso, N., Ramon-Guevara, P., Azorin-Lopez, J., Sebban, M., Habrard, A., & Fuster-Guillo, A. (2023). Predictive Modeling of Body Shape Changes in Individuals on Dietetic Treatment Using Recurrent Networks. In Lecture Notes in Networks and Systems (Vol. 842 LNNS, pp. 100–111). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-48642-5_10
Mendeley helps you to discover research relevant for your work.