While the term task load (TL) refers to external task demands, the amount of work, or the number of tasks to be performed, mental workload (MWL) refers to the individual’s effort, mental capacity, or cognitive resources utilized while performing a task. MWL in multitasking scenarios is often closely linked with the quantity of tasks a person is handling within a given timeframe. In this study, we challenge this hypothesis from the perspective of electroencephalography (EEG) using a deep learning approach. We conducted an EEG experiment with 50 participants performing NASA Multi-Attribute Task Battery II (MATB-II) under 4 different task load levels. We designed a convolutional neural network (CNN) to help with two distinct classification tasks. In one setting, the CNN was used to classify EEG segments based on their task load level. In another setting, the same CNN architecture was trained again to detect the presence of individual MATB-II subtasks. Results show that, while the model successfully learns to detect whether a particular subtask is active in a given segment (i.e., to differentiate between different subtasks-related EEG patterns), it struggles to differentiate between the two highest levels of task load (i.e., to distinguish MWL-related EEG patterns). We speculate that the challenge comes from two factors: first, the experiment was designed in a way that these two highest levels differed only in the quantity of work within a given timeframe; and second, the participants’ effective adaptation to increased task demands, as evidenced by low error rates. Consequently, this indicates that under such conditions in multitasking, EEG may not reflect distinct enough patterns to differentiate higher levels of task load.

The disruptive deployment of collaborative robots, named cobots, in Industry 5.0 has brought attention to the safety and ergonomic aspects of industrial human–robot interaction (HRI) tasks. In particular, the study of the operator’s mental workload in HRI activities has been the research object of a new branch of ergonomics, called neuroergonomics, to improve the operator’s wellbeing and the efficiency of the system. This study shows the development of a combinative assessment for the evaluation of mental workload in a comparative analysis of two assembly task scenarios, without and with robot interaction. The evaluation of mental workload is achieved through a combination of subjective (NASA TLX) and real-time objective measurements. This latter measurement is found using an innovative electroencephalogram (EEG) device and the characterization of the cognitive workload through the brainwave power ratio β/α, defined after the pre-processing phase of EEG data. Finally, observational analyses are considered regarding the task performance of the two scenarios. The statistical analyses show how significantly the mental workload diminution and a higher level of performance, as the number of components assembled correctly by the participants, are achieved in the scenario with the robot.

The literature features a variety of tasks and methodologies to induce mental workload (MWL) and to assess the performance of MWL estimation models. Because no standardized benchmark task or set of tasks exists, the comparison of different machine learning (ML) solutions in this field is difficult, as their performance is significantly dependent on these factors. In this paper, we present the first comprehensive examination of ML models' performance in EEG-based MWL classification across task types. To achieve this, we categorized ML studies based on the task type used in their experiments and compared models' performances across these categories. Notably, a significant drop in MWL classification accuracy was observed among the best-performing models in multitasking studies where MWL was rated based on quantitative task load, compared to those in single-tasking studies and studies where MWL was subjectively rated. This points to the inherent challenges associated with estimating MWL in more complex tasks such as multitasking. This is particularly relevant for practical applications, as real-world tasks typically involve some degree of multitasking. By comparing ML models' performances across task types, this review provides valuable insights into the state-of-the-art of EEG-based MWL estimation, highlights existing gaps in the field, and points to open questions for further research.

Background/Objectives: This study addresses the gap in methodological guidelines for neuroergonomic attention assessment in safety-critical tasks, focusing on validating EEG indices, including the engagement index (EI) and beta/alpha ratio, alongside subjective ratings. Methods: A novel task-embedded reaction time paradigm was developed to evaluate the sensitivity of these metrics to dynamic attentional demands in a more naturalistic multitasking context. By manipulating attention levels through varying secondary tasks in the NASA MATB-II task while maintaining a consistent primary reaction-time task, this study successfully demonstrated the effectiveness of the paradigm. Results: Results indicate that both the beta/alpha ratio and EI are sensitive to changes in attentional demands, with beta/alpha being more responsive to dynamic variations in attention, and EI reflecting more the overall effort required to sustain performance, especially in conditions where maintaining attention is challenging. Conclusions: The potential for predicting the attention lapses through integration of performance metrics, EEG measures, and subjective assessments was demonstrated, providing a more nuanced understanding of dynamic fluctuations of attention in multitasking scenarios, mimicking those in real-world safety-critical tasks. These findings provide a foundation for advancing methods to monitor attention fluctuations accurately and mitigate risks in critical scenarios, such as train-driving or automated vehicle operation, where maintaining a high attention level is crucial.

Despite significant advancements in Electroencephalography (EEG)-based Mental Workload (MWL) assessment facilitated by deep learning, challenges such as subject-independent MWL estimation persist. Addressing this challenge is crucial for the widespread adoption of the technology in practical, real-world settings. It could facilitate the deployment of neuroadaptive systems across various users without the need for individual calibration, significantly reducing setup time and complexity, and enhancing the scalability. This study explores subject-independent MWL estimation under realistic conditions of a typical assembly line workplace, as opposed to the idealized settings typical of existing research. We employed a convolutional neural network (CNN) to classify 10s EEG segments into two MWL categories, based on different complexity of visual instructions for manual assembly. The results in subject-dependent and subject-independent cases were compared. The findings reveal only a marginal decrease in classification accuracy when transitioning from subject-dependent (92.2 ^% ) to subject-independent scenarios (90.8%). The study demonstrates the feasibility of using deep learning models for EEG-based MWL estimation under realistic conditions, paving the way for broader applications of this technology across diverse industrial environments.