Immuno-neural network for spectrum prediction

Abstract

The artificial neural network is an important machine learning algorithm for secondary users (SUs) in cognitive radio networks. An SU equipped with an ANN is able to perform predictive modelling using input samples acquired for a channel sensed to be idle. This input samples are acquired incurring an input sample acquisition time (ISAT) that reduces the data transmission time (DTT) and throughput of SUs in the network. The reduction of the ISAT is therefore important for enhanced throughput. This paper addresses this issue by proposing the addition of a Kullback Leibler divergence (KLD) layer to the neural network based on inspiration from artificial immune systems theory. This layer computes the dissimilairites between previous and current inputs and reduces ISAT. We examine the performance of the neural network with the added KLD layer in three scenarios that consider the achievable SU throughput. The throughput performance of SUs are examined for three scenarios for single and dual mode SUs equipped with ANN and dual mode SUs equipped with recurrent ANNs in the first, second and third scenarios respectively. Performance analysis shows that the addition of the KLD layer improves the DTT and the SU throughput compared to existing scheme.

5G Message Service System Based on Artificial Immune Dynamic Adaptive Mechanism

“…In recent years, the international research on the application of artificial immune system in communication system has gradually become a hot spot, and literature [8] studies the potential of artificial immune system in solving the problem of wireless communication channel allocation. Literature [9], based on the inspiration of artificial immunity, reduces the data transmission time and increases the data throughput of the trunked communication system. Literature [10] used the artificial immune algorithm based on clonal selection theory to maximize the total throughput of the radio system and reduce its interference to the main users.…”