SimDem A Multi-agent Simulation Environment to Model Persons with Dementia and their Assistance
This work addresses the problem of data scarcity for AI developers in dementia care, though it appears incremental as it builds on existing synthetic data tools.
The paper tackles the challenge of training AI assistive systems for Persons with Dementia (PwD) by proposing SimDem, a multi-agent simulation environment that models cognitive impairments to generate synthetic data, addressing ethical and logistical issues in data collection.
Developing artificial intelligence based assistive systems to aid Persons with Dementia (PwD) requires large amounts of training data. However, data collection poses ethical, legal, economic, and logistic issues. Synthetic data generation tools, in this regard, provide a potential solution. However, we believe that already available such tools do not adequately reflect cognitive deficiencies in behavior simulation. To counter these issues we propose a simulation model (SimDem ) that primarily focuses on cognitive impairments suffered by PwD and can be easily configured and adapted by the users to model and evaluate assistive solutions.