ARTÍCULO
TITULO

Analyzing the Performance of Transformers for the Prediction of the Blood Glucose Level Considering Imputation and Smoothing

Edgar Acuna    
Roxana Aparicio and Velcy Palomino    

Resumen

In this paper we investigate the effect of two preprocessing techniques, data imputation and smoothing, in the prediction of blood glucose level in type 1 diabetes patients, using a novel deep learning model called Transformer. We train three models: XGBoost, a one-dimensional convolutional neural network (1D-CNN), and the Transformer model to predict future blood glucose levels for a 30-min horizon using a 60-min time series history in the OhioT1DM dataset. We also compare four methods of handling missing time series data during the model training: hourly mean, linear interpolation, cubic interpolation, and spline interpolation; and two smoothing techniques: Kalman smoothing and smoothing splines. Our experiments show that the Transformer performs better than XGBoost and 1D-CNN when only continuous glucose monitoring (CGM) is used as a predictor, and that it is very competitive against XGBoost when CGM and carbohydrate intake from the meal are used to predict blood glucose level. Overall, our results are more accurate than those appearing in the literature.

 Artículos similares

       
 
Julián Pulecio-Díaz, Miguel Sol-Sánchez and Fernando Moreno-Navarro    
Roller-compacted concrete (RCC) pavements have been the subject of studies focused on their increasing deterioration over time due to the influence of vehicular loading and ambient factors in humidity and temperature conditions ranging from medium to low... ver más
Revista: Infrastructures

 
Lea Dasallas, Junghwan Lee, Sungphil Jang and Suhyung Jang    
Smart water cities (SWCs) use advanced technologies for efficient management and preservation of the urban water cycle, strengthening sustainability and improving the quality of life of the residents. This research aims to develop measurement and evaluat... ver más
Revista: Water

 
Jakob Benisch, Björn Helm, Xin Chang and Peter Krebs    
The European Union Water Framework Directive (2000/60/EC; WFD) aims to achieve a good ecological and chemical status of all bodies of surface water by 2027. The development of integrated guidance on surface water chemical monitoring (e.g., WFD Guidance D... ver más
Revista: Water

 
Imane El Bouazzaoui, Oumaima Lamhour, Yassine Ait Brahim, Adam Najmi and Blaïd Bougadir    
In most parts of the world, groundwater is the main source of their water supply, particularly during periods of drought when surface water is scarce. As a result, groundwater drought is among the most worrying problems of our time. In order to shed ligh... ver más
Revista: Water

 
Lijun Ma, Meng Sun and Yunlong Zhang    
In order to facilitate waste glass recycling and enable the monitoring of concrete structures, this study prepares a new type of self-sensing engineered cementitious composite (ECC) via the use of glass sand instead of silica sand. The health monitoring ... ver más
Revista: Buildings