Generating Rules of Action Transition in Errors in Daily Activities from a Virtual Reality-Based Training Data

Developments in virtual reality (VR) have advanced numerous applications in clinical settings in the areas of learning and treatment in neuropsychology. Emerging VR applications today focus on the challenge of diagnosis and cognitive training of mild cognitive impairment (MCI) and dementia patients and address navigation and orientation, face recognition, cognitive functionality, and other instrumental activities of daily living (IADL). The information recorded and captured by VR-based technology is real-time and can be advantageous for further analysis of patients’ characteristics. The present study sought to utilize the data collected from VR-based software and a leap-motion device for learning in MCI cases to generate the rules for errors and action slips based on finger-action transitions when performing IADL. The finger motion was recorded as a time-series database, then an induction technique called Inductive Logic Programming (ILP), which uses logical and clausal language to represent the training data, was used to discover a concise classification rule using logical programming.