Study On The Player Fatigue Model Of Body-controlled Games Based On Physiological Signals

Body-controlled games are a new kind of computer games, in which the physical movements and actions of players are exploited to design the interactions of games. Since the gaming experience of body-controlled games is radically different from traditional computer games, such games have achieved great success in the market. In recent years, body-controlled games have been studied extensively, and different actions of players were exploited to design the interaction of these games. Due to the physical nature of body-controlled games, playing such games would affect the physiological signals of players, and utilizing the physiological context of players in body-controlled games is a promising design method. This study used two experiments to study the physiological state of the players during playing the body-controlled games in two different ways. The experiment one was conducted to obtain the heart rate (HR) and heart rate variability (HRV) of twelve healthy participants (mean age: 26.6, SD: 1.62) while playing a body-controlled game. The results indicate that HR and some of frequency domain HRV parameters, obtained at different physiological states (rest, fitness, and fatigue), show a statistically significant change (p<0.05). Moreover, a discriminant model was built based on Fisher linear discriminant analysis, which can be used to classify the physiological states of players. Self-validation and cross-validation were used to evaluate the model, and the correct rates of the two validation schemes are higher than 75%. games. The physiological signals, including pulse rate, skin temperature, saturation of peripheral oxygen (SpO2), and galvanic skin response (GSR), of eleven healthy participants were recorded while playing body-controlled games. Based on the results of the experiment, we propose a discriminant model to predict the fatigue state of players. Our model can identify non-fatigue with 78.90% accuracy and fatigue with 82.76% accuracy. This model can be used with biofeedback hardware to continuously predict players'fatigue state and to improve the adaptation design of body-controlled games. The results show that: physiological signals can be used to objectively reflect the state of the player during playing the body-controlled games; assessment to the state of the players using the physiological signals is consistent with the subjective reports; physiological signals can be used to model the state of the players during playing the body-controlled games.