Sensing Cognitive Responses Through a Non-Invasive Brain-Computer Interface

The main objective of this study is to investigate the influence of cognitive stress (mental workload) on some physiological parameters and reactions of a set of experimental subjects. The aim is to check whether these indicators, observed simultaneously, can distinguish the state of rest from the state of mental tension and whether they can distinguish tasks of different difficulty. An assessment of the state of rest in the study protocol is also performed. The experiments implemented a multimodal, non-invasive BCI for tracking physiological responses during cognitive task performance. Five parallel measured parameters are used: electroencephalography (EEG), heart rate (HR), galvanic skin response (GSR), facial surface temperature, and oxygen saturation (SpO₂). The results show that HR is a fast and reliable marker for detecting psychological load, the normalized phase GSR is good for detecting higher loads, EEG α/θ can be used for central validation, facial temperature is shown to be a slowly changing but reliable context indicator and SpO₂ preservation can be used as a measure of stability.