SNNLoc: an intelligent hierarchical spiking neural network for energy-efficient WiFi localization

Recent advances in artificial neural networks (ANNs) have greatly enhanced the accuracy of WiFi-based indoor localization. However, their high computational demand and energy consumption severely limit practical deployment in mobile and embedded environments. To overcome these limitations, we introduce SNNLoc, an intelligent, hierarchical localization framework built upon deep spiking neural networks (SNNs). Unlike traditional ANNs, SNNLoc adopts a biologically inspired, event-driven computation model in which neurons fire only when activation thresholds are reached, thereby drastically reducing unnecessary operations and improving energy efficiency. The proposed system integrates two learning stages: a building and floor recognition module that offers coarse-level spatial classification, followed by a position estimation module that delivers fine-grained localization using hierarchical reasoning. Both components are trained using received signal strength indicator data and are jointly optimized to balance precision and resource efficiency. Additionally, a dedicated hardware simulator is employed to evaluate and compare energy usage across architectures. Extensive experiments on two benchmark datasets validate the effectiveness of our method, demonstrating comparable or superior localization performance while achieving over 90% reduction in energy consumption. This research contributes to the development of neuromorphic, energy-aware intelligent systems for real-world ubiquitous computing scenarios.