Modeling nano-communication networks using neurocomputing algorithm

In this paper, a novel practical neurocomputing algorithm is introduced and elaborated in order to design and implement a nano-communication network for various applications such as medical and industrial signal processing. Firstly, the idea of artificial neural network (ANN) for data processing is explained and feasibility of modeling a nano-scale network by an optimized neurocomputing algorithm is discussed using binary neuro-modeling. Moreover, it is stressed how nano-scaling increases the complexity of the communication network considering the existing constraints on computation resources, and accuracy of the proposed networking algorithm, either for communication or computation. Furthermore, the developed nano-scale networking technique is more optimized in order to assist the so-called neural nano-machines, to conduct the simple nano-nodes working more effectively and collaboratively. To experiment the performance of the presented bio-inspired nano-network, a practical test scenario is implemented on Imote2 sensor nodes to compare the accuracy of data processing techniques, showing how a large-scale network is replaced by an efficient nano-scale networking algorithm. Finally, the obtained results are illustrated and more elaborated to provide a complete procedure for future developments of the bio-inspired networking in nano-scale.