Abnormality detection using molecular communications based nano-scale sensor networks

Abnormality detection is one of the most highly anticipated application areas of Molecular Communication (MC) based nanonetworks. .is task entails sensing, detection, and reporting of abnormal changes in a fluid medium that may characterize a disease or disorder using a network of collaborating nanoscale sensors. Such distributed detection (DD) problems are of paramount interest in applications of nanonetworks. For the first time in literature, we proposed to employ sequential probability ratio test (SPRT) to decision fusion (DF). .e proposed approach yields considerable gains in the average number of samples required for the decision resulting in significant improvement in decision delay, which is one of the main challenges encountered in a molecular communications based sensor network. Existing strategies for such distributed collaborative detection problems require a complete statistical characterization of the underlying communication channel between the sensors and the fusion centre (FC), with the assumption of perfectly-known or accurately estimated channel parameters. .is assumption is usually impractical both due to mathematical intractability of the analytical channel models for MC except in a few ideal cases, and the slow and dispersive signal propagation characteristics that make the channel estimation a difficult task even in these ideal cases. .is work, for the first time in the literature, proposes to employ a machine learning (ML) approach to this task and shows that this approach provides the robustness and flexibility required for practical implementation. We focus on detection based on deep learning, specifically on a feed-forward neural network and a recurrent neural network structure that learn the underlying model from data. .is study shows that the proposed DF strategy can perform well without any knowledge of the communication channel.