AI for Aging Societies: From Basic Concepts to Practical Tools for AIFacilitated Cognitive Training

• Applicant: Professor Dr. Tonio Ball
• Subject Area: Image and Language Processing, Computer Graphics and Visualisation, Human Computer Interaction, Ubiquitous and Wearable Computing
• Term: since 2020
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 442666044

Today, around 50 million people worldwide suffer from dementia and there are almost 10 million new cases every year. Overcoming the challenges posed by ageing societies is therefore of paramount importance for Japan, France and Germany. The aim of this project is to exploit the potential of artificial intelligence (AI) approaches to promote healthy ageing. To this end, we will investigate objective machine learning driven biomarkers to evaluate cognitive interventions and support personalized therapies. We will develop novel, dedicated machine learning (ML) methods and adapt them to the specific signal types that can be picked up by the human brain. We will make our methods publicly available in an open source reference software package focusing on unattended learning, data multiplication, domain adaptation and interpretable machine learning models. Our main scientific goals are the optimization of decodable information about brain function, the identification of biomarkers indicating the risk for cognitive impairment and various forms of dementia, and the use of these improved methods to control AIcontrolled cognitive training. These joint efforts will be accompanied by a focus on ethical and societal aspects of AI related to ageing, coupled with participatory, transnational outreach activities to foster dialogue between our scientific community and the general public. This project combines complementary expertise from three groups in Germany, France and Japan: The group of M.Otake-Matsuura, Japan, has long experience in developing interventional technologies to improve the cognitive health of older adults and advanced EEG measurement and data analysis methods. The group of A. Gramfort d Inria, France has profound expertise in statistical machine learning algorithms for EEG data analysis and in the development and maintenance of internationally deployed open source software packages (Scikit learning for general machine learning and MNE for EEG data processing). The group of T. Ball, Freiburg, Germany, has many years of experience in translational neurotechnological and applied research with artificial intelligence.

• DFG Programme: Research Grants
• International Connection: France, Japan
• Partner Organisation: Agence Nationale de la Recherche / The French National Research Agency; Japan Science and Technology Agency; JST
• Cooperation Partners: Alexandre Gramfort, Ph.D.; Dr. Mihoko Otake-Matsuura