Towards a cognitive system for the identification of sleep disorders

Abstract

Alzheimer’s disease (AD) is the most common type of dementia. Patients with AD may show anomalous behaviors such as sleeping disorders. Due to the increasing attention focused on these kinds of behaviors, activities like monitoring and identification are becoming critical. In order to meet these requirements, we propose a cognitive approach based on a combination of machine learning algorithms and a prior knowledge base for the identification of anomalous behaviors during sleep. The results show an improvement in the identification of sleeping disorders of more than 10%.