To recognize emotions using less obtrusive wearable sensors, we present a novel emotion recognition method that uses only pupil diameter (PD) and skin conductance (SC). Psychological studies show that these two signals are related to the attention level of humans exposed to visual stimuli. Based on this, we propose a feature extraction algorithm that extract correlation-based features for participants watching the same video clip. To boost performance given limited data, we implement a learning system without a deep architecture to classify arousal and valence. Our method outperforms not only state-of-art approaches, but also widely-used traditional and deep learning methods.

Abstract-Measuring the experience of audience of arts events is

Abstract:Accurately measuring the audience response during a performance is a difficult task. This is particularly the case for connected performances. In this paper, we staged a connected performance in which a remote audience enjoyed the performance in real-time. Both objective (galvanic skin response and behaviours) and subjective (interviews) responses from the live and remote audience members were recorded. To capture galvanic skin response, a group of self-built sensors was used to record the electrical conductance of the skin. The results of the measurements showed that both the live and the remote audience members had a similar response to the connected performance even though more vivid artistic artefacts had a stronger effect on the live audience. Some technical issues also influenced the experience of the remote audience. In conclusion we found that the remoteness had little influence on the connected performance.

No abstract

No abstract