Towards Mobile Cognitive Fatigue Assessment as Indicated by Physical, Social, Environmental, and Emotional Factors

Edward Price, George Moore, Leo Galway, Mark Linden

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)
36 Downloads (Pure)


Background: Cognitive fatigue can result in multiple detrimental physical and cognitive effects, including loss of concentration, difficulty in planning and reduced memory capabilities. The assessment of cognitive fatigue is inherently difficult due the lack of obvious and easily measurable biological markers. Therefore, any assessment typically takes place within a clinical environment, making use of self-assessment questionnaires, which can be time consuming and costly
Objectives: This research sought to establish which in-situ measures of cognitive fatigue, physical activity, social interaction, location, emotional state and facial landmarks, made using a bespoke smartphone application, could be used to indicate episodes of cognitive fatigue, as measured using our previously validated approach.
Methods: This assessment is realised using: cognitive tests (assessing memory, attention, reaction time, information processing speed and executive function), self-assessment, recording of contextual factors and facial feature analysis. The paper also proposes the use of an ensemble algorithm for the classification of cognitive fatigue utilising facial features and a Rotation Forest approach. During a two-week study, 28 participants used the application once a day to assess their levels of cognitive fatigue, with a daily adherence rate of 37%.
Results: Self-assessment of cognitive fatigue through single item scales on a smartphone was shown to directly correlate with reaction time through a Psychomotor Vigilance Task (r=.643, p=.000), and self-reported increases in the level of social activity (r=.377, p=.000). Facial feature analysis revealed dominant emotions of sadness and anger when participants were more cognitively fatigued. It also showed several underlying facial cues that indicated higher levels of cognitive fatigue, including expressions of negative valence, lower attention and Facial Action Coding System units of increased brow furrow, increased eye lid tightening and increased lip suck. In addition, a Principle Component Analysis based Rotation Forest ensemble with a ternary output (i.e. low, normal, high) demonstrated a cognitive fatigue classification accuracy of 82.17%.
Conclusion: The findings presented in this paper indicate that the inclusion of data relating to surrounding cognitive, social, physical and emotional factors can improve the accuracy of in-situ cognitive fatigue assessment using our previously validated smartphone-based cognitive fatigue assessment approach. In addition, the findings further suggest gross-level fatigue status may be potentially classified to a reasonable degree of accuracy using facial features, which may give rise to personalised in-situ fatigue detection
Original languageEnglish
Number of pages15
JournalIEEE Access
Publication statusPublished - 15 Aug 2019


Dive into the research topics of 'Towards Mobile Cognitive Fatigue Assessment as Indicated by Physical, Social, Environmental, and Emotional Factors'. Together they form a unique fingerprint.

Cite this