Outputs (452)
Dynamic control and information processing in the Belousov-Zhabotinsky reaction using a coevolutionary algorithm (2008)
Journal Article
We propose that the behavior of nonlinear media can be controlled dynamically through coevolutionary systems. In this study, a light-sensitive subexcitable Belousov-Zhabotinsky reaction is controlled using a heterogeneous cellular automaton. A checke... Read More about Dynamic control and information processing in the Belousov-Zhabotinsky reaction using a coevolutionary algorithm.
Towards designing collision based chemical logic gates with adaptive computing (2008)
Presentation / Conference Contribution
Shape estimation using polarization and shading from two views (2007)
Journal Article
This paper presents a novel method for 3D surface reconstruction that uses polarization and shading information from two views. The method relies on polarization data acquired using a standard digital camera and a linear polarizer. Fresnel theory is... Read More about Shape estimation using polarization and shading from two views.
A photometric stereo approach to face recognition (2007)
Thesis
Face recognition has received much interest in the last decade, as the need for reliable personal identification security has become ever more critical. At present for face recognition to be a viable personal identification method an accurate low cos... Read More about A photometric stereo approach to face recognition.
Whiskerbot: A robotic active touch system modeled on the rat whisker sensory system (2007)
Journal Article
The Whiskerbot project is a collaborative project between robotics engineers, computational neuroscientists and ethologists, aiming to build a biologically inspired robotic implementation of the rodent whisker sensory system. The morphology and mech... Read More about Whiskerbot: A robotic active touch system modeled on the rat whisker sensory system.
A genetic approach to search for glider guns in cellular automata (2007)
Presentation / Conference Contribution
Accuracy-based learning classifier system ensembles with rule-sharing (2007)
Journal Article
Learning Classifier Systems (LCS) are a method of evolving compact rule-sets using reinforcement learning. This paper presents an investigation into exploiting the population-based nature of LCS for their use within highly-parallel systems, such as... Read More about Accuracy-based learning classifier system ensembles with rule-sharing.
Implementing spiking neural networks for real-time signal-processing and control applications: A model-validated FPGA approach (2007)
Journal Article
In this paper, we present two versions of a hardware processing architecture for modeling large networks of leaky-integrate-and-fire (LIF) neurons; the second version provides performance enhancing features relative to the first. Both versions of the... Read More about Implementing spiking neural networks for real-time signal-processing and control applications: A model-validated FPGA approach.
Fuzzy-XCS: A Michigan genetic fuzzy system (2007)
Journal Article
The issue of finding fuzzy models with an interpretability as good as possible without decreasing the accuracy is one of the main research topics on genetic fuzzy systems. When they are used to perform online reinforcement learning by means of Michig... Read More about Fuzzy-XCS: A Michigan genetic fuzzy system.
Object surface recovery using a multi-light photometric stereo technique for non-Lambertian surfaces subject to shadows and specularities (2007)
Journal Article
This paper presents a new multi-light source photometric stereo system for reconstructing images of various characteristics of non-Lambertian rough surfaces with widely varying texture and specularity. Compared to the traditional three-light photomet... Read More about Object surface recovery using a multi-light photometric stereo technique for non-Lambertian surfaces subject to shadows and specularities.
Super computer heterogeneous classifier meta-ensembles (2007)
Journal Article
Using the XCS classifier system for multi-objective reinforcement learning problems (2007)
Journal Article
We investigate the performance of a learning classifier system in some simple multi-objective, multi-step maze problems, using both random and biased action-selection policies for exploration. Results show that the choice of action-selection policy c... Read More about Using the XCS classifier system for multi-objective reinforcement learning problems.
Unconventional computing 2007 (2007)
Book
A learning classifier system approach to the identification of cellular automata (2007)
Journal Article
Learning classifier system ensembles with rule-sharing (2007)
Journal Article
This paper presents an investigation into exploiting the population-based nature of learning classifier systems (LCSs) for their use within highly parallel systems. In particular, the use of simple payoff and accuracy-based LCSs within the ensemble m... Read More about Learning classifier system ensembles with rule-sharing.
Design of integrated sensor-actuator ionic polymer-metal devices (2006)
Presentation / Conference Contribution
Active indoor localisation of mobile robots using infra-red (2006)
Presentation / Conference Contribution
Installation and first results of a solar assisted heat pump system (2006)
Presentation / Conference Contribution
The importance of renewable energy resources are growing because of many reasons including the increasing costs of fossil fuels and the growing awareness of sustainability and environmental concerns. There are many different possibilities to use rene... Read More about Installation and first results of a solar assisted heat pump system.