No abstract

No abstract

In this letter, we present a neural network approach to the problem of finding the weights of one-(1-D) and two-dimensional (2-D) adaptive arrays. In modern cellular satellite mobile communications systems and in global positioning systems (GPS's), both desired and interfering signals change their directions continuously. Therefore, a fast tracking system is needed to constantly track the users and then adapt the radiation pattern of the antenna to direct multiple narrow beams to desired users and nulls interfering sources. In the approach suggested in this paper, the computation of the optimum weights is accomplished using three-layer radial basis function neural networks (RBFNN). The results obtained from this network are in excellent agreement with the Wiener solution.

No abstract

The problem of increasing the number of users in FDMA mobile satellite communication systems is addressed. An antenna array is used to estimate the AOA of desired and cochannel mobile users then the same array is used to allocate the maximum of the pattern to desired users while cochannel interference is nulled. This paper describes the use of the MUSIC algorithm for the DOA estimation. Pattern nulls are obtained using the Wiener Solution for the optimum array weights. It is shown that this approach allows closer proximity of the mobile users with same frequency thus increasing the channel capacity.