Advanced Extended Kohonen Mapping (EKM) modelling techniques for sensor actor networks
Christopher Chiu, ZC Chaczko, Perez Moses · UTS ePRESS (University of Technology Sydney) · 2009
This paper discusses the results of utilising advanced EKM modelling techniques to manage Sensor-Actor networks (SANETs) such as wireless sensor networks. EKMs allow a quantitative analysis of an algorithmic artificial neural network process by using an indirect-mapping EKM to self-organise from a given input space to administer SANET routing and clustering functions with a control parameter space. Results demonstrate that in comparison to linear approximation techniques, indirect mapping with EKMs provide fluid control and feedback mechanisms by operating in a continuous sensory control space. SANETs can be designed for a variety of sensory perceptive contexts where interactive detection and optimisation of events are required for real-time environments.