RT Conference Proceedings
T1 Grammatical Evolutionary Techniques for Prompt Migraine Prediction
A1 Pagán Ortiz, Josué
A1 Risco Martín, José Luis
A1 Moya, José M.
A1 Ayala Rodrigo, José Luis
AB The migraine disease is a chronic headache presenting symptomatic crisis that causes high economic costs to the national health services, and impacts negatively on the quality of life of the patients. Even if some patients can feel unspecific symptoms before the onset of the migraine, these only happen randomly and cannot predict the crisis precisely. In our work, we have proved how migraine crisis can be predicted with high accuracy from the physiological variables of the patients, acquired by a non-intrusive Wireless Body Sensor Network. In this paper, we derive alternative models for migraine prediction using Grammatical Evolution techniques. We obtain prediction horizons around 20 minutes, which are sufficient to advance the drug intake and avoid the symptomatic crisis. The robustness of the models with respect to sensor failures has also been tackled to allow the practical implementation in the ambulatory monitoring platform. The achieved models are non linear mathematical expressions with low computing overhead during the run-time execution in the wearable devices.
SN 978-1-4503-4206-3
YR 2016
FD 2016
LK https://hdl.handle.net/20.500.14352/94869
UL https://hdl.handle.net/20.500.14352/94869
LA eng
NO Josué Pagán, José L. Risco-Martín, José M. Moya, and José L. Ayala. 2016. Grammatical Evolutionary Techniques for Prompt Migraine Prediction. In Proceedings of the Genetic and Evolutionary Computation Conference 2016 (GECCO '16). Association for Computing Machinery, New York, NY, USA, 973–980. https://doi.org/10.1145/2908812.2908897
NO Ministerio de Economía y Competitividad (España)
DS Docta Complutense
RD 7 abr 2025