Perceptron ann control of array sensors and transmitters with different activation functions for 5G wireless systems

Successful development of a fast, low memory Perceptron Artificial Neural Network (ANN) based electromagnetic signal processor for array sensors has spurred the interest in embedding the electromagnetic signal processor in highly portable (e.g. to be attached to a drone) Arduino as well as in fast parallel Graphic processing Unit (GPU) based systems. In this paper we report the initial results on the embedded system, while also improving on the perceptron based array beam forming with effective activation functions. The paper also explores the effectiveness of different geometrical arrangements of the array system for different applications from wireless communication, medical EEG data acquisition and analysis to power cable condition monitoring and diagnosis.