dorsal/arxiv
View SchemaMonte Carlo Algorithm for Least Dependent Non-Negative Mixture Decomposition
| Authors | Sergey A. Astakhov, Harald Stögbauer, Alexander Kraskov, Peter Grassberger |
|---|---|
| Categories | |
| ArXiv ID | physics/0601161 |
| URL | https://arxiv.org/abs/physics/0601161 |
| DOI | 10.1021/ac051707c |
| Journal | Analytical Chemistry; 2006; 78(5) pp 1620 - 1627 |
Abstract
We propose a simulated annealing algorithm (called SNICA for "stochastic non-negative independent component analysis") for blind decomposition of linear mixtures of non-negative sources with non-negative coefficients. The de-mixing is based on a Metropolis type Monte Carlo search for least dependent components, with the mutual information between recovered components as a cost function and their non-negativity as a hard constraint. Elementary moves are shears in two-dimensional subspaces and rotations in three-dimensional subspaces. The algorithm is geared at decomposing signals whose probability densities peak at zero, the case typical in analytical spectroscopy and multivariate curve resolution. The decomposition performance on large samples of synthetic mixtures and experimental data is much better than that of traditional blind source separation methods based on principal component analysis (MILCA, FastICA, RADICAL) and chemometrics techniques (SIMPLISMA, ALS, BTEM) The source codes of SNICA, MILCA and the MI estimator are freely available online at http://www.fz-juelich.de/nic/cs/software
{
"annotation_id": "b0e9df14-8198-4eec-9496-ac74eeb6cbc3",
"date_created": "2026-03-02T18:01:04.404000Z",
"date_modified": "2026-03-02T18:01:04.404000Z",
"file_hash": "f5ba920ee56ee9f24a0c5c644c90dad98ce8955b3bddaf61a0e8c912200b59bd",
"private": false,
"record": {
"abstract": "We propose a simulated annealing algorithm (called SNICA for \"stochastic\nnon-negative independent component analysis\") for blind decomposition of linear\nmixtures of non-negative sources with non-negative coefficients. The de-mixing\nis based on a Metropolis type Monte Carlo search for least dependent\ncomponents, with the mutual information between recovered components as a cost\nfunction and their non-negativity as a hard constraint. Elementary moves are\nshears in two-dimensional subspaces and rotations in three-dimensional\nsubspaces. The algorithm is geared at decomposing signals whose probability\ndensities peak at zero, the case typical in analytical spectroscopy and\nmultivariate curve resolution. The decomposition performance on large samples\nof synthetic mixtures and experimental data is much better than that of\ntraditional blind source separation methods based on principal component\nanalysis (MILCA, FastICA, RADICAL) and chemometrics techniques (SIMPLISMA, ALS,\nBTEM)\n The source codes of SNICA, MILCA and the MI estimator are freely available\nonline at http://www.fz-juelich.de/nic/cs/software",
"arxiv_id": "physics/0601161",
"authors": [
"Sergey A. Astakhov",
"Harald St\u00f6gbauer",
"Alexander Kraskov",
"Peter Grassberger"
],
"categories": [
"physics.chem-ph",
"cond-mat.stat-mech",
"cs.IT",
"math.IT",
"math.PR",
"math.ST",
"physics.comp-ph",
"physics.data-an",
"stat.TH"
],
"doi": "10.1021/ac051707c",
"journal_ref": "Analytical Chemistry; 2006; 78(5) pp 1620 - 1627",
"title": "Monte Carlo Algorithm for Least Dependent Non-Negative Mixture Decomposition",
"url": "https://arxiv.org/abs/physics/0601161"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "b13fa618-1726-4d27-a013-7c8880e8b647",
"id": "arXiv Dataset IDs",
"type": "Model",
"variant": "snapshot-2026-03-01",
"version": "0.1.0"
},
"user_id": 1000002
}