ABSTRACT
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.
ABSTRACT
The industry increasingly insists on academic cooperation to solve the identified problems such as workers' performance, wellbeing, job satisfaction, and injuries. It causes an unsafe and unpleasant working environment that directly impacts the quality of the product, workers' productivity, and effectiveness. This study aimed to give a specialized solution for tests and explore possible solutions to the given problem in neuroergonomics and human-robot interaction. The designed modular and adaptive laboratory model of the industrial assembly workstation represents the laboratory infrastructure for conducting advanced research in the field of ergonomics, neuroergonomics, and human-robot interaction. It meets the operator's anatomical, anthropometric, physiological, and biomechanical characteristics. Comparing standard, ergonomic, guided, and collaborative work will be possible based on workstation construction and integrated elements. These possibilities allow the industry to try, analyze, and get answers for an identified problem, the condition, habits, and behavior of operators in the workplace. The set-up includes a workstation with an industry work chair, a Poka-Yoke system, adequate lighting, an audio 5.0 system, containers with parts and tools, EEG devices (a cap and smartfones), an EMG device, touchscreen PC screen, and collaborative robot. The first phase of the neuroergonomic study was performed according to the most common industry tasks defined as manual, monotonous, and repetitive activities. Participants have a task to assemble the developed prototype model of an industrial product using prepared parts and elements, and instructed by the installed touchscreen PC. In the beginning, the participant gets all the necessary information about the experiment and gets 15 min of practice. After the introductory part, the EEG device is mounted and prepared for recording. The experiment starts with relaxing music for 5 min. The whole experiment lasts two sessions per 60 min each, with a 15 min break between the sessions. Based on the first experiments, it is possible to develop, construct, and conduct complex experiments for industrial purposes to improve the physical, cognitive, and organizational aspects and increase workers' productivity, efficiency, and effectiveness. It has highlighted the possibility of applying modular and adaptive ergonomic research laboratory experimental set-up to transform standard workplaces into the workplaces of the future.
