Automatic Cognitive Fatigue Detection Using Wearable fNIRS and Machine Learning

Abstract

Wearable sensors have increasingly been applied in healthcare to generate data and monitor patients unobtrusively. Their application for Brain-Computer Interfaces (BCI) allows for unobtrusively monitoring one's cognitive state over time. A particular state relevant in multiple domains is cognitive fatigue, which may impact performance and attention, among other capabilities. The monitoring of this state will be applied in real learning settings to detect and advise on effective break periods. In this study, two functional near-infrared spectroscopy (fNIRS) wearable devices were employed to build a BCI to automatically detect the state of cognitive fatigue using machine learning algorithms. An experimental procedure was developed to effectively induce cognitive fatigue that included a close-to-real digital lesson and two standard cognitive tasks: Corsi-Block task and a concentration task. Machine learning models were user-tuned to account for the individual dynamics of each participant, reaching classification accuracy scores of around 70.91 ± 13.67 %. We concluded that, although effective for some subjects, the methodology needs to be individually validated before being applied. Moreover, time on task was not a particularly determining factor for classification, i.e., to induce cognitive fatigue. Further research will include other physiological signals and human-computer interaction variables.

Keywords: brain–computer interface; cognitive fatigue; functional near-infrared spectroscopy; machine learning.

Figure 1

Board of the Corsi-Block task used during the experimental procedure. The yellow blocks would flash in blue by a specific order that the participants would have to memorise and then recall to click the blocks in the same order. The position of the blocks was adapted from [32].

Figure 2

Board of the concentration task. A pair of numbers would turn blue with the mouse hover. If that pair summed to 10, the participant would have to click with the mouse. Whenever they clicked, their positions would be marked in red. Board adapted from [28].

Figure 3

Schematic of the data acquisition protocol. The Corsi-Block task (yellow blocks) is performed 3 times, while the Concentration task (blue blocks) is performed only 2 times.

Figure 4

Confusion matrices of each participant, where each letter from A–J refers to each corresponding participant, respective to the results presented in Table 3.