Speakers

SGAI

Contact

If you have any questions about Real Artificial Intelligence, you can contact the organisers by email on
realai@bcs-sgai.org

 

BCS

Real Artificial Intelligence - Speakers

Details of the speakers and their presentations are given below.

Feargal Timon

Managing Director, CIM Ireland

Dynamic Simulation Modelling of Telco Field Force

Large systems can be complex. They have many variables interacting dynamically. It can be difficult to predict how they will perform. Eircom (The main provider of telephone services in Ireland) is such a system. Fault reports and Customer orders volumes can vary by 50% from one week to another. It is complex to balance conflicting demands; to reduce resources, and maintain customer service. The approach was to builds a dynamic simulation model imitating Eircom’s field force demands and decision making processes. The model effectively predicted the number and location of field technicians while delivering a high service level for all products. A dynamic simulation model can imitate a reasonable degree of intelligence by; combining the basic decision making, and the dynamic simulation of the interactions of the object in the system.

Feargal Timon builds workflow simulation models, having graduated from the Nation University of Ireland in Galway with a BE and MEng .Sc. in 1989. Feargal worked in the university for 6 years in association with the University current president Prof Jimmy Brown. Currently, Feargal is the Managing Director of CIM Ireland, a company that provides Simulation Modelling expertise’s to Irish, UK and US companies. He setup the company in 1994 and since then has worked with companies such as Intel, Coke, HP, Bausch and Lomb, Boston Scientific, Honewell, and more recently with telco companies such as Eircom.

 

Phil Bull

Chief Researcher, BT

AI in Practice – a Commercial Perspective

AI saw a boom in popularity during the late 1980s and through the 1990s. Phil has led research and delivery of a number of systems using AI techniques that have both used commercial tools and been built from scratch. He will present a view of the practical challenges and benefits of applying AI in a commercial environment, as well as some thoughts on where we are today with using these technologies.

Phil Bull is a Chief Researcher in BT, currently leading a research programme on advanced automated test and diagnostics techniques, with a particular interest in broadband services. Diagnosing faults can be difficult because the problem space is complex or information about symptoms is uncertain. The research challenge is to develop techniques that understand which information is relevant and perform the interpretation automatically with a high level of confidence. A mixture of techniques such as machine-learning, artificial intelligence and signature analysis are used. Phil, who graduated in Electronic Engineering, has extensive R&D experience in a wide range of domains, including intelligent network design tools, pervasive networks, smart homes and smart energy metering.

David Nicholson

Executive Scientist, BAE Systems Advanced Technology Centre

Industrial Applications of Multi-Agent Data Fusion Systems

Multi-agent data fusion systems provide a decentralised framework for enabling situation awareness and coordinated decision-making in uncertain, partially observed, and hazardous environments. Such environments are characteristic of a range of industrial applications, e.g. defence, disaster response. BAE Systems and EPSRC funded the Autonomous Learning Agents for Decentralised Data and Information Networks (ALADDIN) project from 2005-2010. This talk will present a number of examples of how fundamental multi-agent systems research, developed in ALADDIN, was matured and transferred into applications of interest to BAE Systems. The talk will then move on to describe ORCHID, a new project that builds on ALADDIN by introducing the human dimension to consider human-agent collectives. Applications of ORCHID technology in future energy and disaster response systems will be presented.

David Nicholson is an Executive Scientist with BAE Systems Advanced Technology Centre. He undertakes research with academic partners in the main areas of information fusion, decision making, and control. David led the technology transfer work theme for the ALADDIN project and oversaw the transfer of a number of multi-agent system methods into BAE Systems applications. He is currently serving as the Knowledge Transfer Officer for the ORCHID project, charged with ensuring the transfer of new human-agent collective technology into commercial and defence industry applications.

   

Simon Lucas

Professor of Computer Science, University of Essex

Monte Carlo Tree Search: Insights and Applications

Monte Carlo Tree Search has revolutionised the world of Computer Go, where it has achieved amazing success on this challenging game; beyond this it is already being applied to a variety of games and also applications beyond games. This talk will cover the main elements MCTS, offer some insights into its strengths and weaknesses, and show how it can be tailored to a particular application.

Simon Lucas (SMIEEE) is a professor of Computer Science at the University of Essex (UK) where he leads the Game Intelligence Group. His main research interests are games, evolutionary computation, and machine learning, and he has published widely in these fields with over 150 peer-reviewed papers. He is the inventor of the scanning n-tuple classifier, and is the founding Editor-in-Chief of the IEEE Transactions on Computational Intelligence and AI in Games.

Raphael Dorne

Principal Consultant, R&D Innov

Integrating an AI solution for automating work allocation of a Telco in the Middle East

I will talk about a recent deployment of an AI work allocation solution for a customer in the Middle East. I will begin by reviewing the high level challenges the project team faced in designing the solution. I will also outline the different steps we followed in order to successfully deliver this solution to the customer. Our solution comprises an optimisation engine responsible for automatically allocating work to technicians. I will also talk about how we integrated the optimisation engine with the customer’s operational support systems.

Raphael Dorne holds a PhD in Computer Science-Artificial Intelligence from the University of Montpellier (France). He worked one year as a research engineer in the LGI2P research Lab in Nimes, France before joining in August 1999 the Research Department of British Telecom. During his time in British Telecom, he occupied different positions from Senior Researcher to Team Leader of the Optimisation Group of BT I&D. From 2009 until now, Raphael has worked as a Principal Consultant on different R&D projects applying advanced AI techniques to telecom network design and field technician management.

 

 

David Lesaint

Professor of Computer Science, University of Angers

Supply Chain Planning in the Consumer Electronics industry

Supply Chain Planning (SCP) is concerned with the planning of production and transportation activities in a supply chain with the objective of optimally balancing demand and supply. From a problem solving perspective, SCP encompasses different aspects such as order handling, activity planning and routing, stock management, resource allocation and task scheduling. This talk will introduce a concrete example in the Consumer Electronics industry which is characterized by rich ontologies, large-scale instances and complex optimization requirements. We will discuss in particular the benefits of using hybrid Optimisation/AI solutions built upon configurable Constraint Programming models.

David Lesaint holds a PhD in Artificial Intelligence from the Ecole Nationale Supérieure de L'Aéronautique et de L'Espace (Toulouse, France). David joined BT's research labs in 1995 where he helped to design advanced optimisation solutions for problems ranging from fieldforce scheduling and network planning to call control and service personalisation. He was instrumental in developing BT's fieldforce scheduling system which was rolled-out nationally in the late 90s and received the Franz Edelman 1999 finalist award from the Institute for Operations Research and Management Sciences. David joined Dynadec in 2010 - a startup specialised in engineering and marketing optimisation solutions based on CometTM - before being appointed professor at the University of Angers in 2011.

[Real AI] [Programme] [Speakers] [Registration]