Polygraph , Lie Detection

Researchers in medicine and psychology have studied emotions and the way they influence human thinking and behaviour for decades. Recently computer scientists have realised the importance of emotions in human interactions with the environment and a considerable amount of research has been directed towards the identification and utilisation of affective information. Particular interest exists in the detection of emotional states with the intention of improving both human-machine interaction and artificial human-like inference models. Emotion detection has also been employed to explore applications that relate emotional states, habits and ambient conditions inside inhabited environments. Valuable information can be obtained by analysing the way affective states that influence behaviour are altered by environmental changes. In this paper an analysis of the properties of four physiological signals employed in emotion recognition is presented. Class separation analysis was used for determining the best physiological parameters (among those from a list chosen a priori) to use for recognizing emotional states. Results showed that the masseter electromyogram was the best attribute when distinguishing between neutral and non-neutral emotional states. Using Autoassociative Neural Networks for improving cluster separation the gradient of the skin conductance provided the best results when discriminating between positive and negative emotions.

The development of systems capable of recognizing and categorising emotions is of interest to researchers in various scientific areas including artificial intelligence. The traditional notion that emotions and rationality are two separate realms has gradually been challenged. The work of neurologists has shown the strong relationship between emotional episodes and the way humans think and act. Furthermore, emotions not only regulate human decisions but could also contribute to a more satisfactory response to the environment, i.e., faster and more precise actions. In this paper an analysis of physiological signals employed in real-time emotion detection is presented in the context of Intelligent Inhabited Environments (IIE). Two studies were performed to investigate whether physical exertion has a significant effect on bodily signals stemming from emotional episodes with subjects having various degrees of affect intensity: 1) a statistical analysis using the Wilcoxon Test, and 2) a cluster analysis using the Davies- Bouldin Index. Preliminary results demonstrated that the heart rate and skin resistance consistently showed similar changes regardless of the physical stimuli while blood volume pressure did not show a significant change. It was also found that neither physical stress nor affect intensity played a role in the separation of neutral and non-neutral emotional states.