An Artificial Neural Network Model for Eficient Estimation of the Number of Mobile Stochastic EM Sources in a Space Sector




Abstract:
Information on the total number of radiation sources that are currently observed in the physical sector may be of use in procedures dealing with efficient DoA (Direction of Arrival) estimation of stochastic radiation source. This paper introduces an artificial neural model based on MLP (Multi-Layer Perceptron) network, that is based on a value of the spatial correlation matrix signal, which is sampled in the far zone of radiation, and can determine in real time, the number of mobile stochastic sources (up to five sources) with mutually uncorrelated radiation that are currently present in the given sector in the azimuthal plane. This model is an upgrade MLP model that previously had implementation for a maximum of three sources in the sector. Training neural model was carried out on the samples of the spatial correlation matrix obtained by using Green’s functions. Authors observe the case when the number of sources in the sector variable in time and when the sources during the movement in the given sector may be located in another arbitrary distance.

CITATION:

IEEE format

Z. Stanković, I. Milovanović, “An Artificial Neural Network Model for Eficient Estimation of the Number of Mobile Stochastic EM Sources in a Space Sector,” in Sinteza 2016 - International Scientific Conference on ICT and E-Business Related Research, Belgrade, Singidunum University, Serbia, 2016, pp. 87-93. doi:10.15308/Sinteza-2016-87-93

APA format

Stanković, Z., Milovanović, I. (2016). An Artificial Neural Network Model for Eficient Estimation of the Number of Mobile Stochastic EM Sources in a Space Sector. Paper presented at Sinteza 2016 - International Scientific Conference on ICT and E-Business Related Research. doi:10.15308/Sinteza-2016-87-93

BibTeX format
Download

RefWorks Tagged format
Download