Neural networks for blind-source separation of Stromboli explosion quakes

Picking up the hydrothermal whisper at Ischia Island in the Covid-19 lockdown quiet

In this paper, we analyse the seismic noise at Ischia Island (Italy) with the objective of detecting the hydrothermal source signals taking advantage of the Covid-19 quiescence due to lockdown (strong reduction of anthropogenic noise). We compare the characteristics of the background noise in pre-, during and post-lockdown in terms of spectral content, energy release (RMS) and statistical moments. The continuous noise is decomposed into two independent signals in the 1-2 Hz and 2-4 Hz frequency bands, becoming sharpened around 1 Hz and 3 Hz respectively in lockdown. We propose a conceptual model according to which a dendritic system of fluid-permeated fractures plays as neighbour closed organ pipes, for which the fundamental mode provides the persistent whisper and the first higher mode is activated in concomitance with energy increases. By assuming reasonable values for the sound speed in low vapor-liquid mass fraction for a two-phase fluid and considering temperatures and pressures of the shallow aquifer fed by sea, meteoric and deep hydrothermal fluids, we estimate pipe lengths in the range 200-300 m. In this scheme, Ischia organ-like system can play both continuous whisper and transients, depending on the energy variations sourced by pressure fluctuations in the hydrothermal fluids.

A 3-d surface reconstruction approach based on postnonlinear ICA model

Photometric stereo technique deals with the reconstruction of three-dimensional (3-D) shape of an object by using several images of the same surface taken from the same viewpoint but under illuminations from different directions. In this paper, we propose a new photometric stereo scheme based on a new reflectance model and the postnonlinear (PNL) independent components analysis (ICA) method. The proposed nonlinear reflectance model consists of diffuse components and specular components for modeling the surface reflectance of a stereo object in an image. Unlike the previous approaches, these two components are not separated and processed individually in the proposed model. An unsupervised learning adaptation algorithm is developed to estimate the reflectance model based on image intensities. In this algorithm, the PNL ICA method is used to obtain the surface normal on each point of an image. Then, the 3-D surface model is reconstructed based on the estimated surface normal on each point of image by using the enforcing integrability method. Two experiments are performed to assess the performance of the proposed approach. We test our algorithm on synthetically generated images for the reconstruction of surface of objects and on a number of real images captured from the Yale Face Database B. These testing images contain variability due to illumination and varying albedo in each point of surface of human faces. All the experimental results are compared to those of the existing photometric stereo approaches tested on the same images. The results clearly indicate the superiority of the proposed nonlinear reflectance model over the conventional Lambertian model and the other linear hybrid reflectance model.

Complexity of time series associated to dynamical systems inferred from independent component analysis

A not trivial problem for every experimental time series associated to a natural system is to individuate the significant variables to describe the dynamics, i.e., the effective degrees of freedom. The application of independent component analysis (ICA) has provided interesting results in this direction, e.g., in the seismological and atmospheric field. Since all natural phenomena can be represented by dynamical systems, our aim is to check the performance of ICA in this general context to avoid ambiguities when investigating an unknown experimental system. We show many examples, representing linear, nonlinear, and stochastic processes, in which ICA seems to be an efficacious preanalysis able to give information about the complexity of the dynamics.

Overview of independent component analysis technique with an application to synthetic aperture radar (SAR) imagery processing

We present an overview of independent component analysis, an emerging signal processing technique based on neural networks, with the aim to provide an up-to-date survey of the theoretical streams in this discipline and of the current applications in the engineering area. We also focus on a particular application, dealing with a remote sensing technique based on synthetic aperture radar imagery processing: we briefly review the features and main applications of synthetic aperture radar and show how blind signal processing by neural networks may be advantageously employed to enhance the quality of remote sensing data.