ANN Prediction Models for Outdoor SIMO Millimeter Band System
This paper presents the prediction propagation paths of angle of arrivals (AoAs) of a Smart Antenna System in an outdoor environment utilizing Artificial Neural Networks (ANN). The proposed models consist of a Multilayer Perceptron and a Generalized Regression Neural Network trained with measurements of an antenna system consisted of a Single Input Single Output (SISO) system in the millimeter wave band. For comparison purposes the theoretical Gaussian scatter density model was investigated for the derivation of the power angle profile. The proposed models utilize the characteristics of the environment for prediction of the angle of arrivals of each one of the propagation paths and can be applicable for the derivation of SIMO (Single Input Single Output) parameters, such as system capacity. The results are presented towards the average error, standard deviation and mean square error compared with the measurements and they are capable for the derivation of accurate prediction models for the case of AoA in an outdoor millimeter wave propagation environment.
KeywordsArtificial Neural Network Hide Layer Radial Basis Function Neural Network Generalize Regression Neural Network Band System
- 7.S. Haykin, Neural Networks: A Comprehensive Foundation, IEEE Press (McMillan College Publishing Co., 1994).Google Scholar
- 9.A. Kanatas, N. Moraitis, G. Pantos, and P. Constantinou, Time delay and coherence bandwidth evaluation in urban environment for PCS microcells, in Proc. IST’02, 508–512, (2002).Google Scholar
- 10.C. Christodoulou, and M. Georgiopoulos, Applications of Neural Networks in Electromagnetics (Artech House, 2001).Google Scholar