| Autor: |
Amal Ourdou, Abdelghani Ghazdali, A. Metrane |
| Rok vydání: |
2021 |
| Předmět: |
|
| Zdroj: |
Springer Proceedings in Mathematics & Statistics ISBN: 9783030834418 |
| DOI: |
10.1007/978-3-030-83442-5_10 |
| Popis: |
The framework of this chapter is to introduce a new efficient Blind Source Separation (BSS) method that handles mixtures of noise contaminated independent/dependent sources. This approach is based on the minimization of a regularized criterion. Specifically, it consists in combining the total variation method to de-noise the observations, with the Kullbak-Leibler divergence between the copula densities to separate the mixtures. This algorithm has shown its effectiveness and efficiency toward the noisy dependent/independent sources and also surpassed the standard BSS algorithms through different experimental results. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
