Some Applications of Markov Network EDAs
Prof. John McCall
IDEAS Research Institute, The Robert Gordon University
DEI - Sala Seminari
3 Ottobre 2011
In recent years, Markov Network EDAs have begun to find application to a range of important scientific and industrial problems. In this talk we present some applications of Markov Network EDAs classified under the DEUM framework which estimates the overall distribution of fitness from bitstring populations. After a brief review of the main features of DEUM we describe applications to: chemotherapy optimisation; agricultural biocontrol; and case-based feature selection. We also present guidelines for further applications and future research.
John McCall is a Principal Member of the IDEAS Research Institute where he is responsible for the Digital Technologies theme.
He leads the Computational Intelligence research group, which he founded in 2003. John's research focuses on the study and analysis of a range of naturally-inspired metaheuristics (EA, EDA, PSO, ACO, ANN etc.) and their application to learning and optimisation problems. Originally a pure mathematician (algebraic topology), John has for many years now been interested in naturally-inspired computing.
Major themes of his research include medical treatment optimisation, particularly cancer-related, the development and analysis of novel metaheuristics, particularly markov-network EDAs, and probabilistic modeling for optimisation and learning. Application areas of this research include medical decision support, oil and gas operations, analysis of biological sequences, scheduling, image analysis and bio-control.
Area di ricerca:
Intelligenza artificiale, robotica e computer vision