• Non ci sono risultati.

A neural network approach for pixel unmixing in hyperspectral data

N/A
N/A
Protected

Academic year: 2021

Condividi "A neural network approach for pixel unmixing in hyperspectral data"

Copied!
1
0
0

Testo completo

(1)

ABSTRACT

The paper is about the performance of neural networks to perform nonlinear spectral unmixing when applied to hyperspectral data. A pixel-based classification algorithm is considered and implemented via a Multi-Layer Perceptron (MLP) neural network scheme. The experimental set-up consists of multi-temporal and multi-angular CHRIS-PROBA satellite imagery. The results obtained have been compared with those yielded by Linear Spectral Unmixing (LSU), up to date one of the most frequently used approach for dealing with the unmixing problems.

Riferimenti

Documenti correlati

Radio frequency identification systems consists of readers and transponders, that is RFID tags or contactless cards, containing an electronic circuit attached to an

This neglect of time is expressed by the emphasis on actor preferences instead of substantive policy change (i.e. European University Institute. Available Open Access on

[r]

DSFT: Digit Span Forward Test; RAVLT: Rey Auditory Verbal Learning Test; IR: immediate recall; DR: delayed recall; ROCF: figura complessa di Rey-Osterrieth; DSBT: Digit Span

There are only two studies, one on the effect of rosemary and sage tea extract on BA production in Sardina pilchardus fillets [14], and the other on the effect of icing with

The approach presented in this thesis produces abstract maps resembling the traditional geographic ones and thus allows users to reuse their cognitive skills and prior knowledge

Some examples are: (1) cognitive modelling [ 4 , 5 ] which formally accounts for the generative cognitive processes which are assumed to produce the observed data; (2)

Herein we identify the nonhistone architectural nuclear proteins High Mobility Group A1 (HMGA1), whose overexpression is a feature of several human malignancies and has a key role