Source Number Estimation via Entropy Estimation of Eigenvalues (EEE) in Gaussian and Non-Gaussian Noise
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2013
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917762695168000 |
|---|---|
| author | Asadi, Hamid Seyfe, Babak |
| author_facet | Asadi, Hamid Seyfe, Babak |
| contents | In this paper, a novel method based on the entropy estimation of the observation space eigenvalues is proposed to estimate the number of the sources in Gaussian and Non-Gaussian noise. In this method, the eigenvalues of correlation matrix of the observation space will be divided by two sets: eigenvalues of signal subspace and eigenvalues of noise subspace. We will use estimated entropy of eigenvalues to determine the number of sources. In this method we do not need any a priory information about signals and noise. The advantages of the proposed algorithm based on the performance is compared with the existing methods in the presence of Gaussian and Non-Gaussian noise. We have shown that our proposed method outperforms those methods in the literature, for different values of observation time and Signal to Noise Ratio, i. e. SNR. It is shown that the algorithm is consistent and also its probability of false alarm and probability of missed detection tend to zero for long observation time. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_1311_6051 |
| institution | arXiv |
| publishDate | 2013 |
| record_format | arxiv |
| spellingShingle | Source Number Estimation via Entropy Estimation of Eigenvalues (EEE) in Gaussian and Non-Gaussian Noise Asadi, Hamid Seyfe, Babak Applications In this paper, a novel method based on the entropy estimation of the observation space eigenvalues is proposed to estimate the number of the sources in Gaussian and Non-Gaussian noise. In this method, the eigenvalues of correlation matrix of the observation space will be divided by two sets: eigenvalues of signal subspace and eigenvalues of noise subspace. We will use estimated entropy of eigenvalues to determine the number of sources. In this method we do not need any a priory information about signals and noise. The advantages of the proposed algorithm based on the performance is compared with the existing methods in the presence of Gaussian and Non-Gaussian noise. We have shown that our proposed method outperforms those methods in the literature, for different values of observation time and Signal to Noise Ratio, i. e. SNR. It is shown that the algorithm is consistent and also its probability of false alarm and probability of missed detection tend to zero for long observation time. |
| title | Source Number Estimation via Entropy Estimation of Eigenvalues (EEE) in Gaussian and Non-Gaussian Noise |
| topic | Applications |
| url | https://arxiv.org/abs/1311.6051 |