This is an open-source project that employs deep learning to enhance indoor positioning using WiFi Channel State Information (CSI). This project aims to harness the detailed data from CSI, such as signal amplitude, phase, and environmental properties, to accurately locate devices inside buildings where GPS is ineffective.
Mean Teacher-based Cross-Domain Activity Recognition using WiFi Signals, IoTJ 2023
🔭 See through walls with the Wi-Fi router you already own. Open-source passive radar fusing Wi-Fi CSI + acoustic chirps. Edge-only, privacy-first.
ESP32 Wi‑Fi CSI radar for human presence & movement detection. Privacy‑first — no cameras, no sensors, just Wi-Fi signal jitter. Real‑time WEB UI dashboard with live RSSI/jitter charts, auto‑calibration, GPIO/LED outputs.
基于 ESP32 系列 SoC 的 Wi-Fi CSI 数据采集与分析框架。集成信号预处理、特征提取及边缘端 AI 推理，实现手势识别、人体身份识别及环境感知/An ESP32-based Wi-Fi CSI sensing framework integrating data acquisition, signal preprocessing, feature extraction, and edge AI inference for gesture recognition, human identification, and environmental perception.
ESP32-S3 WiFi CSI Human Activity Recognition system with real-time RF sensing, ML inference, and live visualization dashboard.
Secure WiFi CSI sensing research hub with collaboration wiki for adversarial robustness, aging-in-place sensing, benchmark evaluation, and safety-aware metrics.
An innovative smart home application that leverages Wi-Fi CSI for presence detection and gesture recognition, and enables uses to automate tasks, control devices, and monitor their home’s environment.
TFG: Sistema de Reconocimiento de Actividad Humana mediante Wi-Fi CSI | CSITransformer F1=0.826 | 4 modelos + GUI 6 pestañas + 73 tests
A real time hybrid application for Human Activity Sensing using Wi-Fi Channel State Information (CSI). It ingests raw IQ subcarrier packets from an ESP32-S3, processes them via PCA/STFT, and classifies physical activities using PyTorch.
Built-in WiFi monitor mode (and nexmon CSI groundwork) for Raspberry Pi 4 on Pi OS Bookworm with kernel 6.12. Includes a modified brcmfmac driver, ported from nexmon 6.6.y to kernel 6.12, plus pre-built firmware and helper scripts.
A deep learning-based system for human activity recognition using Wi-Fi CSI signals, enabling device-free sensing. It combines CNNs, BiLSTMs, and a custom attention layer to capture spatial and temporal patterns.
A Docker-based cross-compilation build system for generating bootable Gentoo Linux
AI-powered Safety System using WiFi CSI for Elderly Care (Fall Detection) and Industrial Safety.
Passive camera-free human presence detection using WiFi CSI on ESP32 — privacy-preserving sensing for patient & elderly monitoring
Detect human activity and room occupancy in real-time using raw Wi-Fi CSI data from an ESP32-S3 and Scikit-Learn.
Unilateral WiFi CSI as an Entropy Source: A Preliminary SP 800-90B Assessment (Preprint 2026)
Add a description, image, and links to the wifi-csi topic page so that developers can more easily learn about it.
To associate your repository with the wifi-csi topic, visit your repo's landing page and select "manage topics."