Abstract
Assessing cognitive fatigue within the context of daily life is difficult due to the largely subjective nature of the condition and existing assessment approaches. Traditional methods of evaluation use self-assessment questionnaires delivered in a medical setting. Currently this is the most widely used approach, primarily due to the clinical supervision that is on hand for the duration of testing. The main drawback of this approach is the limiting factors of clinical evaluation, namely the constrained location, testing time and ability to account for external factors that can increase cognitive fatigue. Recent work has attempted to employ more objective cognitive tests as a way of evaluating cognitive fatigue. However, these tests are still predominantly delivered within a medical environment, limiting their utility.The primary focus of this work was to investigate how cognitive fatigue can be assessed in-situ, during everyday life. As a result of the research conducted, a cognitive fatigue assessment mythology was developed, by using a smartphone application, responding to the need of quick and accurate evaluation. This initial application assessment method was used as a basis for work carried out in subsequent chapters of the Thesis. Consequently, cognitive testing methods and contextual factors measurable though smartphone sensors were implemented in the application, improving the accuracy and enabling a higher degree of passive assessment. Building upon the pervasive capabilities of smartphones, facial feature capture and analysis was investigated to identify the validity of a completely passive, camera based approach. Classifier ensemble analysis of facial features and cognitive tests deployed though the mobile application were carried out, with a Rotation Forest ensemble providing the highest assessment accuracy of 82.2%. This smartphone approach was found to be comparative in accuracy to alternative multi camera based methods. These research findings display the potential of a mobile approach to in-situ cognitive fatigue assessment.
| Date of Award | May 2019 |
|---|---|
| Original language | English |
| Supervisor | George Moore (Supervisor) & L Galway (Supervisor) |