Establishing Ground Truth on Pyschophysiological Models for Training Machine Learning Algorithms: Options for Ground Truth Proxies

摘要

One of the core aspects of human-human interaction is the ability to recognize and respond to the emotional and cognitive states of the other person, leaving human-computer interaction systems, at their core, to perform many of the same tasks. This can take the form of robotic interaction systems that respond to 'anger' [33], instructional systems that take different actions according to 'confusion' [27], and intelligent aiding systems which dynamically adjust levels of autonomy (i.e. task allocation to the human or the system) depending on continuously changing levels of 'workload' [9]. A well-designed system responds to information about the user, tailoring the experience for the purposes of enjoyment, effectiveness, or both. The emphasis of this paper focuses on understanding that emotional state to maximize human performance.