Title :
Digital Ecosystems: Optimisation by a distributed intelligence
Author :
Briscoe, Gerard ; Wilde, Philippe De
Author_Institution :
Dept. of Media & Commun., London Sch. of Econ. & Political Sci., London
Abstract :
Can intelligence optimise Digital Ecosystems? How could a distributed intelligence interact with the ecosystem dynamics? Can the software components that are part of genetic selection be intelligent in themselves, as in an adaptive technology? We consider the effect of a distributed intelligence mechanism on the evolutionary and ecological dynamics of our Digital Ecosystem, which is the digital counterpart of a biological ecosystem for evolving software services in a distributed network. We investigate Neural Networks (NNs) and Support Vector Machines (SVM) for the learning based pattern recognition functionality of our distributed intelligence. Simulation results imply that the Digital Ecosystem performs better with the application of a distributed intelligence, marginally more effectively when powered by SVM than NNs. These results suggest that a distributed intelligence can contribute to optimising the operation of our Digital Ecosystem.
Keywords :
learning (artificial intelligence); neural nets; object-oriented programming; pattern recognition; peer-to-peer computing; software architecture; support vector machines; biological ecosystem; digital ecosystem dynamics; distributed intelligence mechanism; distributed network; ecological dynamic; evolutionary dynamic; neural network; pattern recognition; peer-to-peer network; software component; software service-oriented architecture; support vector machine; Application software; Biological system modeling; Ecosystems; Genetics; Intelligent networks; Learning systems; Machine learning; Neural networks; Pattern recognition; Support vector machines; distributed; ecosystem; evolution; intelligence;
Conference_Titel :
Digital Ecosystems and Technologies, 2008. DEST 2008. 2nd IEEE International Conference on
Conference_Location :
Phitsanulok
Print_ISBN :
978-1-4244-1489-5
Electronic_ISBN :
978-1-4244-1490-1
DOI :
10.1109/DEST.2008.4635157
