Jay Paul Morgan – Research

Dr. Jay Paul Morgan

Bâtiment X
Université de Toulon
Campus de La Garde
83041 - TOULON
FRANCE

jay.morgan@univ-tln.fr
Google Scholar
Github

Active Projects

  • The Development of an Accessible, Diverse and Inclusive Digital Visual Language – Icons, symbols, and signs represent a visual language that facilitates communication because it conveys large amounts of information in single units intended to be understood by everyone irrespective of culture or language. The development of a visual language of icons and symbols that is accessible, inclusive, diverse and neutral is of paramount importance now that the number of digital interfaces that use such language keep expanding at a global level. The proposed project is the first to gather evidence from a diverse population that will be, by default inclusive, and create web application to make those evidence-based guidelines easily accessible to all. This knowledge will be disseminated to a wider audience to promote better use of icon design that is inclusive to a wider audience; one that includes different cultures and languages. From research outputs of the first stage of the project, with the help of the RA we will design and build a machine learning model to learn how icons are rated across groups based on their 7 key properties. This machine learning model will provide the classification and usability scores that will form the basis of an online searchable database for all the key icon characteristics, thereby removing the obstacles for developers to use good icons based on research-backed principles.
    • Project Name: The Development of an Accessible, Diverse and Inclusive Digital Visual Language
    • Awarded: August 2022
    • Awarding Body: Morgan Advanced Studies Institute (MASI)
  • PREdicting Solar Activity using machine learning on heteroGEneous data (PRESAGE) – Our project concerns itself with the activity of the Sun, those events (e.g. flares, coronal mass ejections (CME)) are dynamical phenomena that may have strong impacts on the solar-terrestrial environment. Events of solar activity seem to be strongly associated with the evolution of solar structures (e.g. active regions, filaments), which are objects of the solar atmosphere that differ from the “quiet Sun” and which appear, evolve, and disappear over a period of days to months. The exact mechanisms of solar activity, and the links between solar structures and activity events, are still ill-understood.
    • Project Name: PREdicting Solar Activity using machine learning on heteroGEneous data (PRESAGE)
  • Developing Resilience against Online Grooming (DRaOG) – The grant application was based on the research outputs of `Integrating linguistic knowledge into DNNs: Application to online grooming detection'. This work and its outputs were included in a grant application to further collaborate with police forces and social workers in the UK. This grant is a collaborative effort between the Department of Computer Science, and College of Law, Swansea, and Université de Toulon, France. More information about the grant and the funding body can be found on the End Violence Against Children website at https://www.end-violence.org/grants/swansea-university and at the Project's website: https://www.swansea.ac.uk/project-dragon-s/
    • Project Name: DRAGON-S
    • Awarded: January 2021
    • Awarding Body: End Violence Against Children (EVAC)

Articles

  • Crook, T., Morgan, J., Pauly, A., & Roggenbach, M. (2021). A Computable Analysis perspective on (Verified) Machine Learning. arXiv preprint preprint. arXiv:2102.06585 [URL].
  • Morgan, J., Paiement, A., Pauly, A., & Seisenberger, M. (2021). Adaptive Neighbourhoods for the Discovery of Adversarial Examples. arXiv preprint arXiv:2101.09108 [URL].
  • Morgan, J., Paiement, A., Lorenzo-Dus, L., Kinzel, A., Di Cristofaro, M. (2020) Integrating linguistic knowledge into DNNs: Application to online grooming detection. Paper under review.
  • Morgan, J., Paiement, A., & Klinke, C. (2020). VIMPNN: A physics informed neural network for estimating potential energies of out-of-equilibrium systems. Paper under review
  • Morgan, J., Paiement, A., Seisenberger, M., Williams, J., & Wyner, A. (2018). A chatbot framework for the children’s legal centre. Frontiers in Artificial Intelligence and Applications, 313, 205–209 [URL].

Talks

  • 2021-07-06 - Computability in Europe (CiE) 2021, Ghent University, Belgium - A Computability Perspective on (Verified) Machine Learning, Tonicha Crook, Jay Morgan, Arno Pauly, and Markus Roggenbach - Talk presented by Tonicha Crook. Talk was awarded best poster talk by Springer.
  • 2021-03-30 - British Colloquium for Theoretical Computer Science (BCTCS) 2021, Liverpool, United Kingdom - Trustable Machine Learning Systems. https://blog.morganwastaken.com/2021-03-29/BCTCS-2021-Presentation
  • 2020-12-07 - Bio-Ontology Research Group (BORG) Seminar, King Abdulla University of Science and Technology (KAUST), Jeddah, Saudi Arabia - Using Logic to Predict Protein Sequence Functions
  • 2019-04-09 - Edinburgh Science Festival 2019 - Developing Resilience against Online Grooming
  • 2019-01-08 - Japan Advanced Institute of Science and Technology (JAIST) Research Seminar, Nomi, Japan - Verification of Machine Learning Models
  • 2018-12-13 - International Conference on Legal Knowledge and Information Systems (JURIX) Conference 2018, Groningen, Netherlands - A Chatbot Framework for the Children's Legal Centre

Author: Jay Morgan

Created: 2023-04-01 Sat 16:50

Validate