Mental workload prediction based on attentional resource allocation and information processing

Abstract

Abstract.Mental workload is an important component in complex human-machine systems. The limited applicability of empirical workload measures produces the need for workload modeling and prediction methods. In the present study, a mental workload prediction model is built on the basis of attentional resource allocation and information processing to ensure pilots' accuracy and speed in understanding large amounts of flight information on the cockpit display interface. Validation with an empirical study of an abnormal attitude recovery task showed that this model's prediction of mental workload highly correlated with experimental results. This mental workload prediction model provides a new tool for optimizing human factors interface design and reducing human errors.

Pilots’ mental workload prediction based on timeline analysis

“…The multi-factor mental workload prediction based on attention resource allocation [17] is triggered by two decisive factors: external task demand and internal resource allocation of mental workload, integrating the information amount H i , time pressure T i , visual coding C i , and attention resource allocation f i .…”

“…E i indicates the effort that the vision system needs to pay to acquire the i-th AOI, and V i is the information importance attribute associated with the assignment task. [17] is the visual coding comprehensive performance eigenvalue, with 0 < C i < 0.1. w j i is the weight coefficient corresponding to the j-th visual coding in the i-th AOI, which is obtained by the G1 method through expert evaluation. v j i is the comprehensive performance eigenvalue of the j-th visual coding obtained by meta-analysis, and is the fuzzy weighted average operator.…”

“…However, these models do not consider the influencing factors of mental workload in the aviation field, nor do they take into account the impact of different task types on mental workload. Xiao et al [17] comprehensively adopted factors such as information amount, time pressure, visual coding, and attention resource allocation to establish a multi-factor mental workload prediction model. However, the model does not consider the conflicts within task types and dynamic time effect.…”

“…On account of the dynamic concept of mental workload, the timeline task analysis method was used to decompose complex tasks into several task units and simple behaviors that changed dynamically with time and employed the McCracken-Aldrich scale [5] to divide and assign each simple behavior. A dynamic prediction model of mental workload based on timeline analysis was established according to the mental workload prediction based on attentional resource allocation and information processing [17]. The model was verified by carrying out an ergonomic experiment on the civil cockpit simulator.…”

Human-based dynamics of mental workload in complicated systems

“…On the other hand, the balance in the workload reduces the human error and increases the task performance of operators (Xie and Salvendy, 2000[ 36 ]; Yu et al, 2016[ 40 ]; Zhao et al, 2016[ 41 ]). Therefore, the concept of mental workload and mechanism of its effect on task performance in different human-machine systems is considered by practitioners and researchers in a variety of cognitive activities, such as conventional driving (Allahyari et al, 2014[ 1 ]; Hassanzadeh-Rangi et al, 2014[ 18 ]; Yan et al, 2019[ 37 ]), automated driving (Ko and Ji, 2018[ 22 ]), train driving (Balfe et al, 2017[ 6 ]), nuclear power plants (Choi et al, 2018[ 12 ]), advanced surgery programs (Cavuoto et al, 2017[ 9 ]), air traffic monitoring (Dasari et al, 2017[ 14 ]), control rooms (Melo et al, 2017[ 24 ]), workplace activities (Chen et al, 2017[ 11 ]), information technologies (Buettner, 2017[ 7 ]) and other complex human-machine systems (Xiao et al, 2015[ 35 ]). Few conceptual frameworks are available for understanding mental workload mechanism based on the static relationship extracted from traditional statistics (Xie and Salvendy, 2000[ 36 ]).…”