Evaluation of cognitive workload finds its application in many areas, from educational program assessment through professional driver health examination to monitoring the mental state of people carrying out jobs of high responsibility, such as pilots or airline traffic dispatchers. Estimation of multilevel cognitive workload is a task usually realized in a subject-dependent way, while the present research is focused on developing the procedure of subject-independent evaluation of cognitive workload level. The aim of the paper is to estimate cognitive workload level in accordance with subject-independent approach, applying classical machine learning methods combined with feature selection techniques. The procedure of data acquisition was based on registering the EEG signal of the person performing arithmetical tasks divided into six intervals of advancement. The analysis included the stages of preprocessing, feature extraction, and selection, while the final step covered multiclass classification performed with several models. The results discussed show high maximal accuracies achieved: ~91% for both the validation dataset and for the cross-validation approach for kNN model.

The paper is focussed on the assessment of cognitive workload level using selected machine learning models. In the study, eye-tracking data were gathered from 29 healthy volunteers during examination with three versions of the computerised version of the digit symbol substitution test (DSST). Understanding cognitive workload is of great importance in analysing human mental fatigue and the performance of intellectual tasks. It is also essential in the context of explanation of the brain cognitive process. Eight three-class classification machine learning models were constructed and analysed. Furthermore, the technique of interpretable machine learning model was applied to obtain the measures of feature importance and its contribution to the brain cognitive functions. The measures allowed improving the quality of classification, simultaneously lowering the number of applied features to six or eight, depending on the model. Moreover, the applied method of explainable machine learning provided valuable insights into understanding the process accompanying various levels of cognitive workload. The main classification performance metrics, such as F1, recall, precision, accuracy, and the area under the Receiver operating characteristic curve (ROC AUC) were used in order to assess the quality of classification quantitatively. The best result obtained on the complete feature set was as high as 0.95 (F1); however, feature importance interpretation allowed increasing the result up to 0.97 with only seven of 20 features applied.

An improvement in ecological validity is one of the significant challenges for 21st-century neuroscience. At the same time, the study of neurocognitive processes in real-life situations requires good control of all variables relevant to the results. One possible solution that combines the capability of creating realistic experimental scenarios with adequate control of the test environment is virtual reality. Our goal was to develop an integrative research workspace involving a CW-fNIRS and head-mounted-display (HMD) technology dedicated to offline and online cognitive experiments. We designed an experimental study in a repeated-measures model on a group of BCI-naïve participants to verify our assumptions. The procedure included a 3D environment-adapted variant of the classic n-back task (2-back version). Tasks were divided into offline (calibration) and online (feedback) sessions. In both sessions, the signal was recorded during the cognitive task for within-group comparisons of changes in oxy-Hb concentration in the regions of interest (the dorsolateral prefrontal cortex-DLPFC and middle frontal gyrus-MFG). In the online session, the recorded signal changes were translated into real-time feedback. We hypothesized that it would be possible to obtain significantly higher than the level-of-chance threshold classification accuracy for the enhanced attention engagement (2-back task) vs. relaxed state in both conditions. Additionally, we measured participants′ subjective experiences of the BCI control in terms of satisfaction. Our results confirmed hypotheses regarding the offline condition. In accordance with the hypotheses, combining fNIRS and HMD technologies enables the effective transfer of experimental cognitive procedures to a controlled VR environment. This opens the new possibility of creating more ecologically valid studies and training procedures.

Cognitive workload, being a quantitative measure of mental effort, draws significant interest of researchers, as it allows to monitor the state of mental fatigue. Estimation of cognitive workload becomes especially important for job positions requiring outstanding engagement and responsibility, e.g., air-traffic dispatchers, pilots, car or train drivers. Cognitive workload estimation finds its applications also in the field of education material preparation. It allows to monitor the difficulty degree for specific tasks enabling to adjust the level of education materials to typical abilities of students. In this study, we present the results of research conducted with the goal of examining the influence of various fuzzy or non-fuzzy aggregation functions upon the quality of cognitive workload estimation. Various classic machine learning models were successfully applied to the problem. The results of extensive in-depth experiments with over 2000 aggregation operators shows the applicability of the approach based on the aggregation functions. Moreover, the approach based on aggregation process allows for further improvement of classification results. A wide range of aggregation functions is considered and the results suggest that the combination of classical machine learning models and aggregation methods allows to achieve high quality of cognitive workload level recognition preserving low computational cost.

The study is focused on applying ex-Gaussian parameters of eye-tracking and cognitive measures in the classification process of cognitive workload level. A computerised version of the digit symbol substitution test has been developed in order to perform the case study. The dataset applied in the study is a collection of variables related to eye-tracking: saccades, fixations and blinks, as well as test-related variables including response time and correct response number. The application of ex-Gaussian modelling to all collected data was beneficial in the context of detection of dissimilarity in groups. An independent classification approach has been applied in the study. Several classical classification methods have been invoked in the process. The overall classification accuracy reached almost 96%. Furthermore, the interpretable machine learning model based on logistic regression was adapted in order to calculate the ranking of the most valuable features, which allowed us to examine their importance.

In the modern world fast and efficient processing of non-digital (handwritten or typed) texts is the task of extreme importance. Similar to many other fields, optical character recognition (OCR) benefits from appliance of machine learning (ML) which allows to develop effective and accurate...