An Analysis of Motion Transition in Subtle Errors using Inductive Logic Programming: A Case Study in Approaches to Mild Cognitive Impairment

Problem Representation

In this study, we held the experiments of everyday activities tasks of preparing breakfast on a virtual reality-based software called Virtual Kitchen (VK) (Martono, et. al., 2016). This study has the goal of generating rules on the nature of subtle errors (hereby called micro errors) by collecting finger movement and analyzing the basic transition patterns of study participants doing daily activity tasks in a virtual reality-based environment, using a machine learning approach. Another purpose is to explore the use of analyzing finger speed when micro errors occur. In this study, the micro errors that will be used in the analysis are limited to two types: Reach - Touch (RT) errors and Reach - No Touch (RNT) errors. The other type of micro-errors: reach with object is not considered in the study, because in doing the cognitive everyday activities task in the VK both errors are not applicable due to virtual reality software limitations. In this study, we will be working with the combination of qualitative and quantitative data as input information for the machine learning process. The challenges are how to generate such input that can be used to extract useful output from the learning.