首页|Hardware real-time individualised blood glucose predictor generator based on grammars and cartesian genetic programming
Hardware real-time individualised blood glucose predictor generator based on grammars and cartesian genetic programming
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Springer Nature
In this paper, we introduce a novel grammar-guided technique based on genetic programming for on-chip, real-time, configurable hardware design of model generators on an FPGA. The technique integrates grammar-based design, Cartesian Genetic Programming, and a (1+λ) Evolutionary Strategy and is demonstrated through the implementation of a wearable hardware predictor for blood glucose prediction. People with diabetes need to manage their blood glucose levels to prevent life-threatening situations and long-term complications. Effective glucose management requires accurate blood glucose predictions, yet most existing methods rely on heuristic estimators. This system enables the training and testing of personalized models using real patient data. We validated the approach by generating and evaluating models for 30- and 60-min forecasting predictions on ten patients, creating a total of 200 models. The system achieved state-of-the-art results, with 98% and 90% of predictions falling within clinically acceptable regions according to Clarke error grid analysis, for 30- and 60-min horizons, respectively. Unlike software implementations, our technique does not suffer from hardware limitations and provides an efficient, adaptable solution through wearable hardware with minimal errors and low power consumption. This is the first demonstration of combining Cartesian Genetic Programming with a hardware implementation for grammar-based blood glucose prediction, potentially enabling real-time embedded systems for portable devices.
Departamento de Arquitectura de Computadores y Automatica, Universidad Complutense de Madrid, Calle del Prof. Jose Garcia Santesmases, 28040 Madrid, Comunidad de Madrid, Spain
NETL
NSTL
Springer Nature
