Order Determination and Input Selection with Local Model Networks

Order Estimation and Model Selection

ICA model order selection of task co-activation networks

Independent component analysis (ICA) has become a widely used method for extracting functional networks in the brain during rest and task. Historically, preferred ICA dimensionality has widely varied within the neuroimaging community, but typically varies between 20 and 100 components. This can be problematic when comparing results across multiple studies because of the impact ICA dimensionalit...

A Multiband Multiple-input Multiple-output Antenna System for Long Term Evolution and Wireless Local Area Networks Handsets

A novel multiband multiple-input-multiple-output (MIMO) antenna system is proposed. The MIMO antenna system consists of two antenna elements, each of which comprises of three radiators: a driven monopole, an S-shaped strip and an inverted F-shaped strip and occupies footprint of 15x18.5x0.8 mm3 only. The driven monopole acts as a quarter-wave monopole and stimulate higher mode resonance. The tw...

Local Model Networks and Local Learning

The Local Model Networks (networks composed of locally accurate models, where the output is interpolated by smooth locally active basis functions) described in this paper provide a solid basis for practical modelling tasks. The architecture benefits from being able to incorporate Fuzzy, Neural Network and conventional System Identification methodology and experience. The advantages of the archi...

Bayesian model order determination and basis

Bayesian methods are developed for the seemingly unrelated regressions (SUR) model where the model order or structure is presumed random. In particular we consider the class of models that are linear in some basis space. This class includes standard linear regression as a special case, as well as those models that involve non-linear transformations of the explanatory variables through a set of ...