Skill Performance Estimation from cARdiac Signals

Descripción del proyecto

Aprovechar las señales cardíacas para un entrenamiento físico personalizado

En diferentes entornos de aprendizaje, las capacidades y motivaciones individuales varían, lo que pone en entredicho la eficacia de los métodos de formación estandarizados. La bibliografía científica destaca el potencial de las señales cardíacas (SC) para medir los estados cognitivo y físico, que son fundamentales para las experiencias de aprendizaje a medida. En este contexto, el proyecto SPEARS, financiado por el Consejo Europeo de Investigación, utilizará SC para la adaptación dinámica a los estados cognitivo y físico de los usuarios. Capitalizando el éxito del proyecto BrainConquest, que se centró en el entrenamiento personalizado a través de interfaces cerebro-ordenador, SPEARS pretende mejorar los algoritmos de aprendizaje automático y procesamiento de señales para, de este modo, predecir el rendimiento con datos de SC suministrados por sensores comerciales como los relojes inteligentes. El objetivo de SPEARS es integrar su tecnología predictiva en una aplicación de entrenamiento deportivo, ofreciendo soluciones de entrenamiento personalizados para deportistas de resistencia de todo el mundo.

Objetivo

In any learning situation, be it math education, language learning or sport training, different learners have different abilities, motivations and capacities at any given time. Thus, an optimal learning can only be achieved with personalized training solutions, dynamically adapted to each learner’s cognitive and/or physical states. The scientific literature showed that such states could be estimated from Cardiac Signals (CS). In ERC PoC SPEARS, we thus propose to redefine consumer training apps, by enabling them to propose personalized and adaptive training plans according to an estimation of their users’ cognitive and/or physical states from their CS measured with consumer grade sensors, e.g. smartwatches. The outcome of ERC project BrainConquest should enable us to tackle this challenge. Indeed, in BrainConquest we explored such a personalized training approach for users of Brain-Computer Interfaces (BCI). In doing so, we developed Machine Learning (ML) and Signal Processing (SP) algorithms to estimate users’ mental states and predict their upcoming performances from their brain and physiological signals, including CS. In SPEARS, we thus aim at adapting, improving and assessing BrainConquest ML & SP algorithms, initially designed for BCI performance prediction from research grade brain and CS sensors in the lab, to predict cognitive and physical performance from consumer grade CS sensors in the wild. Such algorithms could be used for adaptive training apps in education, cognitive training for healthy aging or sport training. We will then explore a commercial application of this technology for sport training in particular, in collaboration with the startup Flit Sport, which sells an app for providing personalized training exercises for endurance sport athletes, based on their past performances and ML. By integrating our CS-based prediction into Flit Sport training app, we should design optimally personalized training solutions for millions of runners worldwide.