Nilay Ozge Yalcin
Building from a background in Cognitive Science, Nilay’s PhD research focuses on the role of emotions and especially empathy in multi-modal human to machine communication. She uses an interdisciplinary approach that combines computer science methods with the theories of psychology, linguistics and sociology to understand and explore the mechanisms of human communication and dialog. Nilay is working to develop an Affective Intelligent Agent system which acts as an interactive assistant for language-based communication. She is investigating the social, emphatetic and affective behavior as well as the notion of personality in artificial agents and their effects on human-agent interaction. She also works on achieving computational abstraction techniques for anonymization without losing emotional content.
She is involved in two projects at iVizLab and is a teaching assistant for COGS100 course.
Our lab has extensive experience in using different sensing technology including eye tracking and facial emotion recognition (DiPaola et al 2013), as well as gesture tracking and heart rate and EDA bio sensing (Song & DiPaola, 2015) to affect generative computer graphics systems.
Bringing together an interdisciplinary team, we created a wholly new AI technique to anonymize interview subjects and scenes in regular and 360 videos to create a technique that would be much better at conveying emotional and knowledge information than current anonymization techniques.
Using Cognitive Science as a basis for our work, we attempt to model aspects of human creativity in AI. Specially we are using Neural Networks (and evolutionary systems) in the form of Deep Learning, CNNs, RNNs and other modern techniques to model aspects of human expression and creativity.
Embodied Interactions with a Sufi Dhikr Ritual: Negotiating Privacy and Transmission of Intangible Cultural Heritage in “Virtual Sama”
Conference Proceedings: Electronic Visualisation and the Arts, British Computer Society, July 2017
pp. 365-372, DOI: https://dx.doi.org/10.14236/ewic/EVA2017.73
British Computer Society