Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Attending to Routers Aids Indoor Wireless Localization

Ayush Roy, Tahsin Fuad Hassan, Roshan Ayyalasomayajula, Vishnu Suresh Lokhande

TL;DR

By incorporating attention layers into a standard machine learning localization architecture, it is demonstrated, by incorporating attention layers into a standard machine learning localization architecture, that emphasizing the relevance of each router can substantially improve overall performance.

Abstract

Modern machine learning-based wireless localization using Wi-Fi signals continues to face significant challenges in achieving groundbreaking performance across diverse environments. A major limitation is that most existing algorithms do not appropriately weight the information from different routers during aggregation, resulting in suboptimal convergence and reduced accuracy. Motivated by traditional weighted triangulation methods, this paper introduces the concept of attention to routers, ensuring that each router's contribution is weighted differently when aggregating information from multiple routers for triangulation. We demonstrate, by incorporating attention layers into a standard machine learning localization architecture, that emphasizing the relevance of each router can substantially improve overall performance. We have also shown through evaluation over the open-sourced datasets and demonstrate that Attention to Routers outperforms the benchmark architecture by over 30% in accuracy.

Attending to Routers Aids Indoor Wireless Localization

TL;DR

By incorporating attention layers into a standard machine learning localization architecture, it is demonstrated, by incorporating attention layers into a standard machine learning localization architecture, that emphasizing the relevance of each router can substantially improve overall performance.

Abstract

Modern machine learning-based wireless localization using Wi-Fi signals continues to face significant challenges in achieving groundbreaking performance across diverse environments. A major limitation is that most existing algorithms do not appropriately weight the information from different routers during aggregation, resulting in suboptimal convergence and reduced accuracy. Motivated by traditional weighted triangulation methods, this paper introduces the concept of attention to routers, ensuring that each router's contribution is weighted differently when aggregating information from multiple routers for triangulation. We demonstrate, by incorporating attention layers into a standard machine learning localization architecture, that emphasizing the relevance of each router can substantially improve overall performance. We have also shown through evaluation over the open-sourced datasets and demonstrate that Attention to Routers outperforms the benchmark architecture by over 30% in accuracy.
Paper Structure (13 sections, 8 equations, 2 figures, 1 table)

This paper contains 13 sections, 8 equations, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. An Encoder-Decoder WiFi Localization
  3. Network Design.
  4. Loss Function.
  5. Channel-wise Attention for Router Importance Weighting
  6. Set-Invariant Functional Attention
  7. Computation of Attention Weights
  8. Feature Recalibration and Interpretability
  9. Experiments
  10. Localization Error in Easy and Hard Cases
  11. Weights of the Attention mechanism
  12. Localization Error CDF analysis
  13. Discussion

Figures (2)

  • Figure 1: The input heatmaps $\mathcal{H}$ are encoded by $\mathcal{E}$, processed by set-invariant attention $f$, and decoded by $\mathcal{D}$ to predict $y$, supervised with losses $\mathcal{L}_{\mathrm{Loc}}$ and $\mathcal{L}_{\mathrm{AoA}}$.
  • Figure 2: (a) Performance comparison between Vanilla and Attention models across case difficulty levels: The mean localization error (in cm) is reported for three difficulty tiers: Easy (bottom $30\%$), Medium (middle $40\%$), and Hard (top $30\%$) cases. (b) Spatial distribution of easy vs medium vs hard cases overlaid with AP locations: Easy (blue), Medium (orange) and Hard (red) samples are plotted with counts in the legend; APs are labeled and emphasized to show which access points are surrounded by high-error samples. (c) Router based Attention weight distribution: Shows the attention weights' distribution for each AP. We can clearly see tighter distributions for APs that provide equal attention to all samples like AP1, and at AP4 which has more skewed distribution demonstrating skewed attention across samples.