Tools and Methods for Achieving Wi-Fi Sensing in Embedded Devices

Abstract

Wi-Fi sensing has emerged as a powerful approach to Human Activity Recognition (HAR) by utilizing Channel State Information (CSI). However, current implementations face two significant challenges: reliance on firmware-modified hardware for CSI collection and dependence on GPU/cloud-based deep learning models for inference. To address these limitations, we propose a two-fold embedded solution: a novel CSI collection tool built on low-cost microcontrollers that surpass existing embedded alternatives in packet rate efficiency under standard baud rate conditions and an optimized DenseNet-based HAR model deployable on resource-constrained edge devices without cloud dependency. In addition, a new HAR dataset is presented. To deal with the scarcity of training data, an Empirical Mode Decomposition (EMD)-based data augmentation method is presented. With this strategy, it was possible to enhance model accuracy from 59.91% to 97.55%. Leveraging this enhanced dataset, a compact DenseNet variant is presented. An accuracy of 92.43% at 232 ms inference latency is achieved when implemented on an ESP32-S3 microcontroller. Using as little as 127 kB of memory, the proposed model offers acceptable performance in terms of accuracy and privacy-preserving HAR at the edge; it also represents a scalable and low-cost Wi-Fi sensing solution.