# Multi-Band Wi-Fi Sensing with Matched Feature Granularity

arXiv: https://arxiv.org/abs/2112.14006 · HTML: https://mlsanity.com/paper/2112.14006/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 81 references that are in the map.
- First posted on arXiv 28 Dec 2021.

## Builds on (most cited first, 9 of 9)

- [Person-in-WiFi: Fine-grained Person Perception using WiFi](https://mlsanity.com/paper/1904.00276/) (2019)
- [CSI-based Fingerprinting for Indoor Localization: A Deep Learning Approach](https://mlsanity.com/paper/1603.07080/) (2016)
- [Joint Activity Recognition and Indoor Localization with WiFi Fingerprints](https://mlsanity.com/paper/1904.04964/) (2019)
- [Recurrent Neural Networks For Accurate RSSI Indoor Localization](https://mlsanity.com/paper/1903.11703/) (2019)
- [CSI-Based Multi-Antenna and Multi-Point Indoor Positioning Using Probability Fusion](https://mlsanity.com/paper/2009.02798/) (2020)
- [CRISLoc: Reconstructable CSI Fingerprintingfor Indoor Smartphone Localization](https://mlsanity.com/paper/1910.06895/) (2019)
- [Robust Sub-meter Level Indoor Localization - A Logistic Regression Approach](https://mlsanity.com/paper/1902.06226/) (2019)
- [BeSense: Leveraging WiFi Channel Data and Computational Intelligence for Behavior Analysis](https://mlsanity.com/paper/1907.06005/) (2019)
- [Robust Sub-Meter Level Indoor Localization With a Single WiFi Access Point-Regression Versus Classification](https://mlsanity.com/paper/1911.08563/) (2019)

## Built on by (most cited first, 2 of 2)

- [Multi-Modal Recurrent Fusion for Indoor Localization](https://mlsanity.com/paper/2203.00510/) (2022)
- [Adversarial Bi-Regressor Network for Domain Adaptive Regression](https://mlsanity.com/paper/2209.09943/) (2022)

## Abstract (arXiv)

Complementary to the fine-grained channel state information (CSI) from the physical layer and coarse-grained received signal strength indicator (RSSI) measurements, the mid-grained spatial beam attributes (e.g., beam SNR) that are available at millimeter-wave (mmWave) bands during the mandatory beam training phase can be repurposed for Wi-Fi sensing applications. In this paper, we propose a multi-band Wi-Fi fusion method for Wi-Fi sensing that hierarchically fuses the features from both the fine-grained CSI at sub-6 GHz and the mid-grained beam SNR at 60 GHz in a granularity matching framework. The granularity matching is realized by pairing two feature maps from the CSI and beam SNR at different granularity levels and linearly combining all paired feature maps into a fused feature map with learnable weights. To further address the issue of limited labeled training data, we propose an autoencoder-based multi-band Wi-Fi fusion network that can be pre-trained in an unsupervised fashion. Once the autoencoder-based fusion network is pre-trained, we detach the decoders and append multi-task sensing heads to the fused feature map by fine-tuning the fusion block and re-training the multi-task heads from the scratch. The multi-band Wi-Fi fusion framework is thoroughly validated by in-house experimental Wi-Fi sensing datasets spanning three tasks: 1) pose recognition; 2) occupancy sensing; and 3) indoor localization. Comparison to four baseline methods (i.e., CSI-only, beam SNR-only, input fusion, and feature fusion) demonstrates the granularity matching improves the multi-task sensing performance. Quantitative performance is evaluated as a function of the number of labeled training data, latent space dimension, and fine-tuning learning rates.