Component isolation for multi-component signal analysis using a non-parametric gaussian latent feature model

Component isolation for multi-component signal analysis using a non-parametric gaussian latent feature model

A challenge in analysing non-stationary multi-component signals is to isolate nonlinearly time-varying signals especially when they are overlapped in time and frequency plane. In this paper, a framework integrating time-frequency analysis-based demodulation and a non-parametric Gaussian latent feature model is proposed to isolate and recover components of such signals. The former aims to remove...

Non-Gaussian Component Analysis: a Semi-parametric Framework for Linear Dimension Reduction

We propose a new linear method for dimension reduction to identify nonGaussian components in high dimensional data. Our method, NGCA (non-Gaussian component analysis), uses a very general semi-parametric framework. In contrast to existing projection methods we define what is uninteresting (Gaussian): by projecting out uninterestingness, we can estimate the relevant non-Gaussian subspace. We sho...

COUPLING MODEL FOR MULTI-COMPONENT GAS PERMEATION PROCESS

A gas permeation model (Coupling Model) has been developed which has the flexibility to be used for different membrane module configurations. The aim of this work is to predict the performance of a single stage gas separation process using membranes and provide a comprehensive description of process parameters like flow rates, composition, stage cut and stream pressure. The significant feature ...

Independent Component Analysis using Gaussian Mixture Models

This paper discusses a method for performing independent component analysis exploiting Gaussian mixture models (GMMs). Previously most techniques that combine these methods have used GMMs to model the source signals. This paper considers a parsimonious method for modelling the observed signals. The GMM is fitted to the observed data using a modified version of the expectation maximisation algor...

Preliminary-summation-based principal component analysis for non-Gaussian processes