The Irish Minister for Further and Higher Education, Research, Innovation and Science Simon Harris has today announced funding from Science Foundation Ireland for UCD’s Natural Computing Research & Applications Group led by Prof Michael O’Neill and Prof Fergal McCaffery (Director Regulated Software Research Centre (RSRC) in Dundalk Institute of Technology) for the Reg-Fr-AIMs project, which sets out to develop a Regulatory Compliance Framework for Trustworthy AI Medical Device Software. Alongside Prof O’Neill, the UCD team of researchers include Dr Miguel Nicolau and Dr Annunziata Esposito Amideo. The funding, awarded under SFI’s Frontiers for Partnerships Awards, is worth €1.29 Million, and will see the recruitment of a team of 2 postdoctoral researchers and 6 PhD students.
Our paper “Adaptive Athlete Training Plan Generation: An Optimal Control Systems Approach” has been published in the Journal of Science and Medicine in Sport, Volume 25 Issue 4.
We address the problem of automatically adapting athlete training plans using approaches from control systems theory and artificial intelligence, comparing a novel evolutionary computation approach, to proportional adjustment, and a pseudo-random control over simulations that replicate real-World training scenarios.
A collaboration between the UCD Natural Computing Research and Applications Group and STATSports has resulted in a journal publication introducing a novel method for mathematically optimising team sport training models using evolutionary computation.
Connor M., Fagan D., Watters B., McCaffery F., O’Neill M. (2021). Optimizing Team Sport Training With Multi-Objective Evolutionary Computation. International Journal of Computer Science in Sport, 20(1):92-105
Congratulations to Prof Michael O’Neill who was awarded the Lero Director’s Prize for Research Excellence 2021. The annual awards recognise the enormous commitment and contribution of Lero members to the research centre’s success.
On receiving the award Prof O’Neill said “Thank You to Lero, and thank you to everyone who contributed to our shared research success these 20+ years, especially all past and present members of the UCD Natural Computing Research and Applications Group, especially Tony Brabazon, the UCD School of Business, UCD School of Computer Science, UL School of Computer Science and Information Systems, and co-inventors of Grammatical Evolution, Conor Ryan and J.J. Collins who are joint winners of this award“.
10 years on from hosting GECCO 2011 in Dublin, Ireland, Mark Connor and Michael O’Neill presented an approach to optimising the Banister Dose-Response Fitness-Fatique model used in athlete training management (arxiv draft) at GECCO 2021…
Do you use the Banister Dose-Response/ Fitness-Fatigue Model? Well, chances are you might have been using it wrong all this time… we’ve just published some new research, so let’s talk ‘Parameters’ pic.twitter.com/AlNhk9Xbc5— Mark Connor (@MarkConradCon) July 12, 2021
Michael presented an invited talk on “Grammars, Evolutionary Computation and Intepretability” in a special session on Grammatical Evolution at DSSV-ECDA 2021 (7-9 July, 2021). The session was organised by Andreas Geyer-Schulz who spoke on “Architectural Design of a Unified GA/GP Package for R”, and Franz Rothlauf gave a talk on “Program Synthesis with Grammatical Evolution”.
Handcrafting mixed-integer linear programming (MILP) models can be a time-consuming and error-prone task. A novel algorithm, Grammatical Evolution for Constraint Synthesis (GECS), has been proposed which produces well-formed MILP models in the ZIMPL modelling language. GECS outperform state-of-the-art algorithms, and appears resistant to the curse of dimensionality. The research collaboration between Dr Tomasz Pawlak (Poznan University of Technology) and Prof Michael O’Neill (UCD Natural Computing Research & Applications Group) has been published in the journal Swarm and Evolutionary Computation.
Pawlak T., O’Neill M. (2021). Grammatical Evolution for Constraint Synthesis for Mixed-Integer Linear Programming. Swarm and Evolutionary Computation, 64:100896.
Stefano Mauceri and co-authors (James Sweeney, Miguel Nicolau and James McDermott) have published their latest research on a data-driven approach to feature extraction from time series for one-class classification in the journal Genetic Programming & Evolvable Machines. The approach, which uses Grammatical Evolution to automatically select both the features to extract and the sub-sequences from which to extract them, is demonstrated to lead to problem understanding and improved performance.
David Lynch and Michael O’Neill with NCRA alumnus James McDermott have been nominated for the Best Paper Award at the PPSN 2020 conference to be held in Leiden in September. The paper brings together the use of grammars and autoencoders in a novel approach to program synthesis.
Lynch D., McDermott J., O’Neill M. (2020). Program Synthesis in a Continuous Space using Grammars and Variational Autoencoders. The Sixteenth International Conference on Parallel Problem Solving from Nature (PPSN XVI). Springer LNCS.