Evolutionary Computation & Interactive Evolution

A set of commonly used algorithms for complex optimisation tasks are derived from the field of evolutionary computation (EC). Evolutionary Algorithms are a class of stochastic population-based search heuristics loosely modelled on Darwinian Evolution and genetics.

current research

My main research is in the area of interactive evolutionary computation which was the focus of my PhD - An Interactive Evolutionary Approach for Configuring Machine Vision Systems

An increasingly frequent application of machine vision technologies is in automated surface inspection for the detection of defects in manufactured products. Such systems offer significant benefits in terms of cost, detection rates, and user-satisfaction over conventional human inspection systems. However they usually require significant investment of expert time to set up, are “brittle” in the sense of being highly specialised to the task for which they are tuned, and consequently are sensitive to changes in operating conditions or product specifications. This raises problems within an industrial setting, where operating conditions or requirements may change, and the end-users are experts in the manufacturing field, but not in image processing.

My PhD was aimed at the development of a methodology for rapidly reconfigurable systems. In these systems, the users’ tacit knowledge and requirements are elicited via a process of Interactive Evolution, tuning the image processing parameters to achieve the required goals without any need for specialised knowledge of the machine vision system.

My focus now is on enhancing user experience and ease of interaction which are vital to ensure the applicability of these algorithms in real-world scenarios.

My research has also included the application of adaptive non-linear learning algorithms to a range of medically related problems.

publications

Tahir, M. A., Smith, J. and Caleb-Solly, P (2008); “A Novel Feature Selection based Semi-Supervised method for Image Classification”. Proceedings of 6th International Conference on Computer Vision Systems, 484-493.

Sannen, D., Nuttin, M., Smith, J., Caleb-Solly, Tahir, M. A., Eitzinger , C., Lughofer, E. (2008), An On-Line Interactive Self-Adaptive Image Classification Framework. Proceedings of 6th International Conference on Computer Vision Systems, 171-180.

Pauplin, O., Caleb-Solly, P. and Smith, J.E. (2008), Interactive Parameter Adaptation Tool for Image Segmentation. IADIS, Computer Graphics and Visualization 2008 (CGV 2008) Conference. Amsterdam, July 2008. Winner of the Best Paper Award.

Caleb-Solly, P. and Smith, J., (2007) Adaptive Surface Inspection via Interactive Evolution, Journal of Image and Vision Computing, Special Issue on Machine Vision, vol. 25:7, 1058—1072.

Caleb-Solly, P. and Smith, J. (2005) Incorporation of Adaptive Mutation Based on Subjective Evaluation in an Interactive Evolution Strategy. Proc. IEEE Congress on Evolutionary Computation. IEEE press, 979-986,

Caleb-Solly, P. and Smith, J., (2004) Interactive Evolutionary Strategy Based Discovery of Image Segmentation Parameters, Adaptive Computing in Design and Manufacture VI, Springer, 2004, 209-219

Caleb-Solly, P. and Smith, J., (2002) Adaptive Image Segmentation based on Visual Interactive Feedback Learning, Proceedings of the Fifth International Conference on Adaptive Computing in Design and Manufacturing.

M. Steuer and P. Caleb-Solly and J. Smith, (2001) Modified Neocognitron Network for Medical Signal Classification, Proceedings of the Fourth International Conference on Neural Networks and Expert Systems in Medicine and Healthcare, 34-40.

Steuer, M. & Caleb-Solly, P. & Smith, J. (2001) An Alternative Approach for the Evaluation of the Neocognitron. Proc. European Symposium on Artificial Neural Networks, Brugges, Belgium, 125-130, (2001).

Caleb, P., M.Steuer, (2000) Classification of Surface Defects on Hot Rolled Steel Using Adaptive Learning Methods. Proceedings of the KES'2000 Fourth International Conference on Knowledge-Based Intelligent Engineering Systems & Allied Technologies, Vol. I, 103-108, 0-7803-6400-7 IEEE.

Steuer, M., P. Caleb, GB. Drummond, AMS. Black, (2000) Visualisation and Categorisation of Respiratory Mechanism using Self Organising Maps. IEE Proc.- Science, Measurement and Technology, Vol. 147, No. 6, 339 – 344, IEE.

Steuer M, Caleb P, Sharpe PK, Drummond GB, Black AMS, (2000) Graphical Analysis of Respiration in Postoperative Patients Using Self Organising Maps. Proceedings of the ANNIMAB conf., the International Conference on Artificial Neural Networks In Medicine And Biology, 149-154; Series: Perspectives in Neural Computing, Springer Verlag.

previous projects

EU FP6, DynaVis, development of machine learning methods for machine vision systems in production and manufacturing to achieve dynamically reconfigurable systems.

LloydsTSB funded project for modelling subsidence claims reserves and unemployment claims forecasting

ECSC funded project for Improvement of Automatic Surface Inspection in Flat Steel Products. British Steel.

IRISS, a Eureka High Performance Parallel Computing / Software Engineering Applications project.

PCFC funded, Co-operative Decision Making project.

research

Evolutionary Computation & Interactive Evolution

IPAT