Browsing by Author "Dadgostar, F."

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    A formal model of emotional-response, inspired from human cognition and emotion systems
    (Massey University, 2006) Dadgostar, F.; Sarrafzadeh, A.
    In this paper, we used the formalisms of decision-making theory and theories in psychology, physiology and cognition to proposing a macro model of human emotional-response. We believe that using such formalism can fill the gap between psychology, cognitive science and AI, and can be useful in the design of human-like agents. This model can be used in a wide variety of applications such as artificial agents, user interface, and intelligent tutoring systems. Using the proposed model, we can provide for human behaviors like mood, personality and biological response in machines. This capability will enable such systems, to adapt their responses and behaviors. In situations where there are multiple ways for performing an action, this model can help with the decision making process.
  • Thumbnail Image
    Item
    Gesture recognition through angle space
    (Massey University, 2006) Dadgostar, F.; Sarrafzadeh, A.
    As the notion of ubiquitous computing becomes a reality, the keyboard and mouse paradigm become less satisfactory as an input modality. The ability to interpret gestures can open another dimension in the user interface technology. In this paper, we present a novel approach for dynamic hand gesture modeling using neural networks. The results show high accuracy in detecting single and multiple gestures, which makes this a promising approach for gesture recognition from continuous input with undetermined boundaries. This method is independent of the input device and can be applied as a general back-end processor for gesture recognition systems.