Insights from the Design Space Exploration of Flow-Guided Nanoscale Localization
Filip Lemic, Gerard Calvo Bartra, Arnau Brosa López, Jorge Torres Gómez, Jakob Struye, Falko Dressler, Sergi Abadal, Xavier Costa Perez
TL;DR
This paper addresses the challenge of flow-guided nanoscale localization in the human bloodstream, where energy constraints and severe THz attenuation hinder accurate event localization. It proposes a standardized, simulator-based evaluation framework and compares two representative approaches: an off-the-shelf NN-based classifier and a purpose-built in-house NN with regularization, under a design space that includes nanodevice count, sampling granularity, and detection threshold. The study provides objective, heterogeneous metric benchmarks (region accuracy, point accuracy, reliability) and reveals that, under realistic conditions, point localization remains challenging and region accuracy remains limited due to energy harvesting intermittency and communication unreliability, with substantial differences between the two solutions. The findings suggest that improvements will likely come from more powerful ML methods, especially graph neural networks, and from deploying additional anchors to better discriminate left-right body regions. Overall, the work offers a realistic roadmap for evaluating and advancing in-body localization technologies in THz-enabled nanonetworks.
Abstract
Nanodevices with Terahertz (THz)-based wireless communication capabilities are providing a primer for flow-guided localization within the human bloodstreams. Such localization is allowing for assigning the locations of sensed events with the events themselves, providing benefits along the lines of early and precise diagnostics, and reduced costs and invasiveness. Flow-guided localization is still in a rudimentary phase, with only a handful of works targeting the problem. Nonetheless, the performance assessments of the proposed solutions are already carried out in a non-standardized way, usually along a single performance metric, and ignoring various aspects that are relevant at such a scale (e.g., nanodevices' limited energy) and for such a challenging environment (e.g., extreme attenuation of in-body THz propagation). As such, these assessments feature low levels of realism and cannot be compared in an objective way. Toward addressing this issue, we account for the environmental and scale-related peculiarities of the scenario and assess the performance of two state-of-the-art flow-guided localization approaches along a set of heterogeneous performance metrics such as the accuracy and reliability of localization.