Enhancing Grammatical Evolution Through Data Augmentation: Application to Blood Glucose Forecasting
Currently, Diabetes Mellitus Type 1 patients are waiting hopefully for the arrival of the Artificial Pancreas (AP) in a near future. AP systems will control the blood glucose of people that suffer the disease, improving their lives and reducing the risks they face everyday. At the core of the AP, an algorithm will forecast future glucose levels and estimate insulin bolus sizes. Grammatical Evolution (GE) has been proved as a suitable algorithm for predicting glucose levels. Nevertheless, one the main obstacles that researches have found for training the GE models is the lack of significant amounts of data. As in many other fields in medicine, the collection of data from real patients is very complex. In this paper, we propose a data augmentation algorithm that generates synthetic glucose time series from real data. The synthetic time series can be used to train a unique GE model or to produce several GE models that work together in a combining system. Our experimental results show that, in a scarce data context, Grammatical Evolution models can get more accurate and robust predictions using data augmentation.
KeywordsGrammatical Evolution Diabetes Time series forecasting Data augmentation Combining systems
This research is supported by the Spanish Minister of Science and Innovation (TIN2014-54806-R).
The authors would like to thank the staff in the Principe de Asturias Hospital at Alcala de Henares for their support and assistance with this project. Special thanks also go to Maria Aranzazu Aramendi Zurimendi and Remedios Martinez Rodriguez.
- 2.Nicolao, G.D., Magni, L., Man, C.D., Cobelli, C.: Modeling and control of diabetes: towards the artificial pancreas. In: 18th IFAC World Congress of the IFAC Proceedings Volumes, vol. 44, no. 1, pp. 7092–7101 (2011)Google Scholar
- 4.Tanner, M.A., Wong, W.H.: From EM to data augmentation: the emergence of MCMC Bayesian computation in the 1980s, April 2011. arXiv e-prints arXiv:1104.2210
- 5.Yadav, M., Malhotra, P., Vig, L., Sriram, K., Shroff, G.: ODE - augmented training improves anomaly detection in sensor data from machines. CoRR (2016). arXiv:1605.01534
- 8.Messori, M., Toffanin, C., Favero, S.D., Nicolao, G.D., Cobelli, C., Magni, L.: Model individualization for artificial pancreas. Comput. Methods Programs Biomed. (2016, in press). http://dx.doi.org/10.1016/j.cmpb.2016.06.006
- 9.Kastorini, C.-M., Papadakis, G., Milionis, H.J., Kalantzi, K., Puddu, P.-E., Nikolaou, V., Vemmos, K.N., Goudevenos, J.A., Panagiotakos, D.B.: Comparative analysis of a-priori and a-posteriori dietary patterns using state-of-the-art classification algorithms: a case/case-control study. Artif. Intell. Med. 59(3), 175–183 (2013)CrossRefGoogle Scholar
- 11.Yu, C., Zhao, C.: Rapid model identification for online glucose prediction of new subjects with type 1 diabetes using model migration method. In: IFAC World Congress of the IFAC Proceedings Volumes, vol. 47, no. 3, pp. 2094–2099 (2011)Google Scholar
- 13.Pelikan, M., Mühlenbein, H.: Marginal distributions in evolutionary algorithms. In: Proceedings of the International Conference on Genetic Algorithms Mendel, vol. 98, pp. 90–95. Citeseer (1998)Google Scholar