Seminar 16th September 2011 4 p.m. University of Southampton Building 58 (Social Sciences) Room 1039
Collective Decision Making in Immune-Inspired Ensembles: An Affective Study
Dr Julie Greensmith
The Intelligent Modelling & Analysis Research Group (IMA), University of Nottingham
- Web page
- http://ima.ac.uk/greensmith
- Categories
- Complex Systems
- Submitter
- Petrina Butler
Dr Julie Greensmith
Complex Systems Simulation Seminar Series (CS^4)
from the Institute for Complex Systems Simulation, the Complexity in Real-World Contexts USRG, and the Computational Modelling Group.
Speaker
Dr Julie Greensmith, The Intelligent Modelling & Analysis Research Group (IMA), University of Nottingham
Abstract
Artificial immune systems are a set computational intelligence techniques inspired by the function and behaviour of the human immune system. A number of different styles of have been developed over the past decade and have been applied with varying levels of success to a range of computational problems. However, it is believed that AIS have not yet reached their potential. One of the key properties of the human immune system, collective decision making, has not yet been capitalized on within AIS to any great extent. The research performed within our group is making headway into understanding the collective decision making aspects of immune systems and translating that into immune-inspired ensemble methods.
As with any decentralised complex algorithm, an equally dynamic and complex application is required in order to fully examine the efficacy and potential benefits of using an immune-inspired ensemble. Our example application lies in the domain of Affective Computing which is an emerging multidisciplinary field within computer science. The aim of affective computing is to incorporate emotions within computational systems. The nature of this incorporation can occur via the use of emotion data from users of such systems collected from wearable biosensor devices and through the subsequent classification of data into emotional categories. Equally it can represent the display of emotions by computational systems to enhance the experience of the user through the generation of an emotive dialogue. Affective computing is used as a testbed to further develop ensemble immune-inspired methods, and our current projects are presented.
Refreshments
Available from 3:30pm, lecture starts at 4pm.
Complex Systems Simulation Seminar Series
For the complete CS^4 schedule please click here: http://www.multidisciplinary.soton.ac.uk/cs4.html
Contact
Petrina Butler
Multidisciplinary Research Co-ordinator
University Strategic Research Groups
Research and Innovation Services
p.butler@soton.ac.uk
02380 593244