Effect of Mental Workload on Breathing Pattern and Heart Rate for a Working Memory Task: A Pilot Study

Area of Science:

• Physiology
• Cognitive Science
• Biomedical Engineering

Background:

• Mental workload, or cognitive load, is crucial for task performance and is typically measured qualitatively or via physiological signals.
• Research on assessing cognitive load using respiratory signals is limited, despite its potential.
• Physiological signals like peripheral blood volume (PPG) offer avenues for indirect respiratory analysis.

Purpose of the Study:

• To investigate the efficacy of respiratory features for assessing cognitive load.
• To explore the potential of combining respiratory and PPG features for enhanced cognitive load assessment.
• To identify respiratory features applicable to studying habituation effects.

Main Methods:

• A modified n-back memory test was employed to induce low and high cognitive load conditions.
• Breathing patterns were reconstructed from peripheral blood volume (PPG) signals.
• Morphological and statistical features were extracted from the reconstructed respiratory signals.
• A classifier was utilized to differentiate between low and high cognitive load states.

Main Results:

• Respiratory features alone achieved a classification accuracy of 76.8% for cognitive load.
• Combining time-domain PPG features with respiratory features yielded a maximum accuracy of 81.80%.
• The selected features demonstrated potential for analyzing habituation effects.

Conclusions:

• Respiratory signals provide a viable method for assessing cognitive load.
• Integrating PPG signal analysis with respiratory features significantly enhances cognitive load classification accuracy.
• The identified features offer a novel approach for cognitive load monitoring and habituation studies.