Modeling Human Emotions as Reactions to a Dynamical Virtual 3D Face

Abstract

Abstract. This paper introduces a comparison of one linear and two nonlinear one-step-ahead predictive models that were used to describe the relationship between human emotional signals (excitement, frustration, and engagement/boredom) and virtual dynamic stimulus (virtual 3D face with changing distance-between-eyes). An input-output model building method is proposed that allows building a stable model with the smallest output prediction error. Validation was performed using the recorded signals of four volunteers. Validation results of the models showed that all three models predict emotional signals in relatively high prediction accuracy.

Predictor-Based Control of Human Response to a Dynamic 3D Face Using Virtual Reality

“…is the Euclidean norm sign, γ 0 is a small and positive constant. When n 2 (stability domain for the model (2) is defined by linear inequations) factor γ calculation was given (Kaminskas et al, 2014) and when n 3 (stability domain is defined by linear and quadratic inequations) factor γ calculation was given (Kaminskas and Vidugirienė, 2016). Estimates of the model orders (m,n) are defined from the following conditions (Kaminskas and Vidugirienė, 2016):…”

“…Dependency between human excitement signal as a response to a virtual 3D face feature (distance-between-eyes) changes is described by linear input-output structure model (Kaminskas et al, 2014)…”

“…Predictive input-output structure models were proposed and investigated for exploring dependencies between virtual 3D face features and human reaction to them when dynamic virtual 3D face is observed without a virtual reality headset (Kaminskas et al, 2014;Kaminskas and Vidugirienė, 2016;Vaškevičius et al, 2014). Predictive models are necessary in the design of predictor-based control systems (Astrom and Wittenmark, 1997;Clarke, 1994;Kaminskas, 2007).…”

A Comparison of the Control Schemes of Human Response to a Dynamic Virtual 3D Face

“…Three types of 3D face features (distance-between-eyes, nose width and chin width) were used for human reaction elicitation and four EEG-based response signals (excitement, frustration, engagement/boredom and meditation) were observed and analyzed in previous research [46]. Analysis of the results has shown that all three types of the 3D face feature have triggered similar human reaction signals, accordingly distance-between-eyes was selected and used as a dynamic 3D face feature in further research [24], [26], [28]. From observed four EEG-based response signals, excitement is the most variable signal.…”

“…Linear and nonlinear predictive models of the input-output structure were proposed and investigated for exploring dependencies of the EEG-based emotion signals as a human response to a dynamic virtual 3D face features when a virtual 3D face is observed without a virtual reality headset [24], [26], [46]. The technique of dynamic systems identification which ensures stability of the models is applied to build these models [14].…”