Project description
Personalised cognitive and motor learning for the aged
For those who require it, motor sequence learning in the elderly is crucial for improvement of their motor function. However, existing motor learning programmes neglect individual cognitive and motor differences, resulting in significantly varied improvements in motor function. The EU-funded ICOME project aims to offer a management solution to the ageing demographic in the EU. It will create an efficient method that provides a personalised approach to motor sequence learning in the elderly. The project will address historical and existing theoretical topics, establish an inclusive neurocognitive model of motor learning representation using advanced machine learning methods, and create a personalised intervention. The findings will contribute to improving health management policies and future applications of advanced brain-computer interfaces.
Objective
This project aims to create a method with high efficacy aimed at providing an individualised approach to motor sequence learning in elder adults. The current problem is that the provision of motor learning programs have little/no consideration of individual cognitive and motor differences, and therefore varying levels of improvements. The innovation is to provide a management solution to the ageing demographics across Europe by creating an evidence-based approach targeting cognitive and motor learning parameters for elder adults to improve their overall motor function using an ecological dancelike sequence learning task. We propose a three-stage approach to investigate and provide a viable solution. In the first stage, we will address historical and current theoretical issues with the quantification of motor learning development in elder adults. Addressing topics such as dynamical systems and the aggregation of performance analyses in the face of a large range of baseline physical differences in the elderly will shed new light in a theoretically driven perspective. In the second stage, we will create an integrated neurocognitive model of motor learning representation for the elderly using advanced supervised machine learning with real EEG and behavioural data. Lastly, we will create and pilot an individualised intervention based on the model in the second stage, that targets cognitive control using meditation, and physical parameters with progressive chunk scaling approaches to drive greater learning outcomes in a shorter timeframe for the elderly. The results from this project have the potential to change health management policies and future applications of advanced brain computer interfaces.
Fields of science
Keywords
Programme(s)
Funding Scheme
MSCA-IF - Marie Skłodowska-Curie Individual Fellowships (IF)Coordinator
7522 NB Enschede
Netherlands