Modeling Mental Workload Via Rule-Based Expert System: A Comparison with NASA-TLX and Workload Profile

Abstract

In the last few decades several fields have made use of the construct of human mental workload (MWL) for system and task design as well as for assessing human performance. Despite this interest, MWL remains a nebulous concept with multiple definitions and measurement techniques. State-of-the-art models of MWL are usually ad-hoc, considering different pools of pieces of evidence aggregated with different inference strategies. In this paper the aim is to deploy a rule-based expert system as a more structured approach to model and infer MWL. This expert system is built upon a knowledge-base of an expert and translates into computable rules. Different heuristics for aggregating these rules are proposed and they are elicited using inputs gathered in an user study involving humans performing web-based tasks. The inferential capacity of the expert system, using the proposed heuristics, is compared against the one of two ad-hoc models, commonly used in psychology: the NASA-Task Load Index and the Workload Profile assessment technique. In detail, the inferential capacity is assessed by a quantification of two properties commonly used in psychological measurement: sensitivity and validity. Results show how some of the designed heuristics can over perform the baseline instruments suggesting that MWL modelling using expert system is a promising avenue worthy of further investigation.

Subjective Usability, Mental Workload Assessments and Their Impact on Objective Human Performance

“…Hence, designers who are interested in human or system performance require answers about operator workload at all stages of system design and operation so design alternatives can be explored and evaluated [20]. MWL is not a linear concept [30,43] but it can be intuitively defined as the volume of cognitive work necessary for an individual to accomplish a task over time. It is not 'an elementary property, rather it emerges from the interaction between the requirements of a task, the circumstances under which it is performed and the skills, behaviours and perceptions of the operator' [20].…”

Use of Dry Electrode Electroencephalography (EEG) to Monitor Pilot Workload and Distraction Based on P300 Responses to an Auditory Oddball Task

“…after take-off, cruising and landing. The NASA-TLX is a useful self-report measure to gauge participants' own opinion of how difficult the task is [12]. Participants were instructed to rate each of the six dimensions a score from 0-20 and the raw scores were used for analysis purposes.…”

Mental Workload in the Explanation of Automation Effects on ATC Performance

“…There are several scientifically valid methods for testing hypotheses in a dynamic task. An alternative to the methods designed to obtain empirical data to test the hypotheses that are derived from a theoretical model, is the method that has been called the 'computational method' [38,39], which consists of developing a computer model in which the psychological model is implemented. With this computer model, it is possible to run computer simulations where the hypothesis derived from the model can be tested.…”