Resources   Research   Professional Activities   Teaching   Publications   Contact Details

Jim Smith

Who am I?

Resources

• The supporting Web site of our book: A.E. Eiben and J.E. Smith, Introduction to Evolutionary Computing can be found here.
• IPAT (Interactive Parameter Adaptation Tool) [Caleb-Solly& Smith 2002,2004,2007, Pauplin, Caleb-Solly and Smith 2008,2010] is an application that has been designed to provide an effective and efficient graphical interface to find optimal image segmentation parameters to segment regions of interests (ROI) on images from users’ knowledge. It can also be extended to many types of other problem where AI-based systems can help users develop solutions to their problems without the need for continual dialogue with technical experts. Read more…
• You can find various resources such as data sets, software,  and papers relating to my work on Statistical Disclosure Control here
  

Research

Most of my research concerns computer-based systems which are able to learn to do useful things by repeated interactions with their environment. The environment could be the real world (e.g. robotics applications), people (e.g. interactive learning) or a computer model of part of the world we are interested in (e.g. various applications in planning, scheduling, and design optimisation). This learning falls into two broad areas:

• Optimisation - in other words finding problems to "difficult" problems that cannot easily be tackled  via  conventional mathematical approaches.
• Machine Learning / Classification -  in other words learning to discover patterns in data,  often used for learning to automatically classify things such as images.

• Systems that "learn how to learn" - for example by discovering useful features in data,  or by changing the way in which they come up with new solutions.  Within this fall topics such  as the adaptation of search operators in evolutionary algorithms,  and of the types and frequency of "memes"   - which can be thought of as the equivalent of different styles of learning that individuals use to improve theirselves over their lifespan.
• Systems that learn to do things from interactions with people - for example providing intelligent support that lets users "teach" software so that it can then act on its own.  There's a wide range of topics here ranging across psychology, the design of human-computer interfaces, and fundamental research into the supporting AI methods.

Whilst conducting these more theoretical studies,I have attempted to keep my feet on the ground by applying these technologies to a number of difficult "real world" problems, such as Statistical Disclosure Control, VLSI Design Verification, Adaptive Image Segmentation and Classification,  Computer Vision systems for Production Quality Control, Lot-sizing and scheduling, and bio-informatics problems such as Protein Structure Prediction and Protein Structure Comparison.

Some of my current and recently completed projects include:

• an EU funded "Knowledge Escalator" project with CX Partners and Pure Useability to take thre IPAT tools describe dabove and apply them to web-page customisation.
• The EU-FP6 funded project DynaVis (2005-2008), which applied Machine Learning techniques to create dynamically reconfigurable machine vision systems for manufacturing quality control. As well as developing classificstion systems, my team was  particularly looking at "human" aspects which affect the training provided to the machiones - such as differences between operators,  and the effects of fatigue and lack of confidence. We also developed systems that gave feedback to the users as to how well the systems were learning under their guidance, and how well they might be expected to learn from further input.
• Research collaborations with the UK Office of National Statistics to investigate the use of Evolutionary Algorithms for Statistical Disclosure Control. This concerns how to protect confidentiality in publicly available datasets (e.g. census, industrial outputs) while maximising the usefulness of what is published.
• EPSRC research project investigating mathematical modelling of statistical disclosure control with ONS 2007-2011.
• Higher Education Academy project to create on-line self-assessment material for teaching Artificial Intelligence 2008. These resources can be downloaded from the HEA website here .
• Principal Investigator for UWE as part of consortium in JISC funded project "Open Educational Resources in Computer Science 2009-2010. the resources developed can be accsssed from Jorum here.
• Higher education academy project teaching ai with pacman and netlogo. 2009-2010 these resources will be made available from the hea website once completed.
• Co-investigator with Alistair Clark: Extenses industriais ao problema de planejamento e Programacao da Producao (ref. 005/09), funded by "Fundacao Coordenacao de Aperfeicoamento de Pessoal De N’vel Superior"(CAPES), Ministry of Education, Brazil, under its "Programa Geral de Cooperacao Internacional Brasil-Inglaterra", October 2009 to October 2011. See PPExt project for details.
• Co-investigator with Alistair Clark: Industrial Extensions to Production Planning and Scheduling (PPExt) funded under the EU Framework 7 Programme "Marie Curie International Research Staff Exchange Scheme (IRSES)", with partner universities from Portugal and Brazil ( Faculdade de Engenharia da Universidade do Porto, Universidade de Sao Paulo, Universidade Federal de Sao Carlos, Universidade Estadual Paulista - UNESP) March 2010 - Feb 2013.  This project concerns the development of improved techniques to help industries improve efficiency in areas such as lot sizing and scheduling,  cutting and packing.

Professional Activities

• External PhD examiner at Birmingham University, University of Chester, Nanyang Technological University, Singapore, University College London, University of Nottingham.
• Internal examiner for numerous PhD students at UWE.
• Member of IEEE SMC Society Technical Committee on Soft Computing.
• Member of IEEE Computational Intelligence Society Emerging Technologies Task Force on  Memetic Computing
• Member of Editorial Boards of the journals Evolutionary Computation (MIT Prress) and Memetic Computing (Springer)
• Project proposal reviewer: EPSRC, Leverhulme Trust, Research Council for Culture and Society at the Academy of Finland
• Member of the Council of Authors of the International Society of Genetic and Evolutionary Computation
• GA Track Chair Genetic and Evolutionary Computation Conference (GECCO 2011)
• Programme Co-Chair for Parallel Problem Solving from Nature 8 held in Birmingham, UK, 18th-22nd September 2004.
• Founder and Organiser (with Natalio Krasnogor and Bill Hart ) of the annual International  Workshops on Memetic Algorithms (WOMA) which have been co-located with the GECCO (2000,2001,2003) and PPSN  (2002, 2004 )conferences.
• Member of the Training Committee and the Management Committee of Evonet and EvoNet II , the European Network of Excellence in Evolutionary Computing,
• Member of the Education Committee of COIL (the EU funded Computation Intelligence CLuster)
• Guest Editor of Journal of Evolutionary Computation, Volume 12, number 3, Special Issue on Memetic Algorithms
• Reviewer for the journals Theoretical Computer Science, Evolutionary Computation, IEEE Transactions on Evolutionary Computation, IEEE Transactions on Systems, Man and Cybernetics, IEEE Transactions on Neural Networks, Journal of Theoretical Biology, Image and Vision Computing, EURASIP Journal on Applied Signal Processing, Journal of Heuristics, Evolutionary Intelligence and several others.
• Programme Committee member for Parallel Problem Solving from Nature (PPSN), IEEE Congress on Evolutionary Computation (IEEE CEC), Genetic and Evolutionary Computing Conference (GECCO), Evonet Workshops on Evolutionary Signal Processing,  Memetic Theory in Artificial Systems and Societies, Foundations of Genetic Algorithms, Nature Inspired Co-operative Optimisation, EvoCOP, and various others.

Teaching

Undergraduate and Masters

• I am Module Leader for the level one module UFCE3H-20-1 Introduction to Artificial Intelligence.
• I was award leader for BSc. Artificial Intelligence with Information Systems, and lead the validation of the award BSc. Data Mining.
• I was previously module leader for: UFCE3P-15-M, Evolutionary Computing; UFCE3Y-60-M, Master's Dissertation (Computer Science); and UFCEL4-15-M, Generic Skills for Research Students.
• I also supervise final year undergraduate projects: a list of project ideas can be found here.

Current and Past Research Students

• Kashif Hameed has completed his PhD on: "Aspect-Oriented Software Fault-Tolerance for Mission Critical Systems".
• Masoumeh Mahdie is studying hybrids of mathematical programming and evolutionary heuristics for scheduling and planning applications.
• Martin Serpell has just successfully defended  his PhD on "Mathematical Modelling and Artificial Intelligene Applied to Statistical Disclosure Control".
• Natalio Krasnogor has completed his PhD on "Studies on the Theory and Design Space of Memetic Algorithms".
• Michal Steuer has completed his PhD. “A Modified Neocognitron for Pattern Recognition with an Application to Respiratory Signal Classification".
• Praminda Caleb-Solly has completed her PhD on the use of adaptive computing techniques for image processing and classification, focussing on interactive evolutionary systems for building on-line systems to detect and classify defects in hot-rolled steel.
• Chris Stone has completed his PhD. on the use of Learning Classifier Systems for learning financial trading rules.
• Niraj Updahayaya has completed his PhD. studying the methods for implementing global shard memory within clustered linux processors.
• Yong Yang has completed his PhD.  “Efficient parallel genetic algorithms applied to numerical optimisation".
• Andrea Staggemeier has completed her PhD "Metaheuristics in a Production Lot-Sizing and Scheduling Problem"

Publications

Stuff I've written that others seem to like ...

• Eiben, A.E. and Smith, J.E: Introduction to Evolutionary Computing, Springer, 2003. (2019 citations).
• Krasnogor, N. and Smith, J.E.: A Tutorial for Competent Memetic Algorithms: Model, Taxonomy and Design Issues. IEEE Transactions on Evolutionary Computation, 2005.    (322 citations).
• Smith, J.E. and Fogarty T.C: Operator and Parameter Adaptation in Genetic Algorithms,  Soft Computing, 1997. (146 citations).
• Smith, J.E. & Fogarty, T.C. :Self Adaptation of Mutation Rates in a Steady State Genetic Algorithm. Proceedings of IEEE International Conference on Evolutionary Computing 1996. (134 citations).
• Krasnogor, N., and Smith J. : A Memetic Algorithm With Self-adaptive Local Search: TSP as a case study. Proceedings of  GECCO 2000.  (120 citations).
• Krasnogor, N., Hart, W., Smith, J.E. & Pelta, D.: Protein Structure Prediction With Evolutionary Algorithms.  Proceedings of GECCO 1999.   (120 citations).
• Eiben, A.E., Michalewicz, Z., Schoenauer, M and Smith, J.E.: Parameter Control in Evolutionary Algorithms. in "Parameter Setting in Evolutionary Algorithms", Springer, 2007. (101 citations).
• J.E. Smith. Co-evolving Memetic Algorithms: A review and progress report. 2007. IEEE Transactions in Systems, Man and Cybernetics, part B, 37(1):6--17. (79 citations).
Krasnogor, N, and Smith, J.E. : Emergence of Profitable Search strategies Based on a Simple Inheritance Mechanism" Proceedings of GECCO 2001. (79 citations).
• Smith, J.E. & Fogarty,T.C.:Recombination Strategy Adaptation via Evolution of Gene Linkage"  in Proceedings of IEEE International Conference on Evolutionary Computing 1996.  (62 citations).

Contact Details

• Room Number : 3P1
• E-mail address : XXJames.Smith@uwe.ac.uk (remove the XX)
• Phone Number : +44 (0) 117 3283161
• Fax Number : +44 (0) 117 9750416
• Mail Address :

  Dr. J.E. Smith

  Faculty of Environment and Technology,

  The University of the West of England,

  Bristol

  BS16 1QY, United Kingdom.

This page created by Jim Smith. Last updated May 4th 2011.