Approaches to human activity recognition via passive radar

Christian Bresciani, Federico Cerutti, Marco Cominelli
10/31/2024
cs.LG

No official code found. Best implementation: christianbresciani/nscep-spiking-NN (1 star, MIT, last commit 2024-10-10).

Abstract

The thesis explores novel methods for Human Activity Recognition (HAR) using passive radar with a focus on non-intrusive Wi-Fi Channel State Information (CSI) data. Traditional HAR approaches often use invasive sensors like cameras or wearables, raising privacy issues. This study leverages the non-intrusive nature of CSI, using Spiking Neural Networks (SNN) to interpret signal variations caused by human movements. These networks, integrated with symbolic reasoning frameworks such as DeepProbLog, enhance the adaptability and interpretability of HAR systems. SNNs offer reduced power consumption, ideal for privacy-sensitive applications. Experimental results demonstrate SNN-based neurosymbolic models achieve high accuracy making them a promising alternative for HAR across various domains.

View on arXivView PDF

Code Implementations(1)

christianbresciani/nscep-spiking-NNCommunity100%
MIT
10Prolog, PythonMay 23, 20242 years agoMIT

Similar Papers

Contactless Human Activity Recognition using Deep Learning with Flexible and Scalable Software Define Radio

89% match2023

Hybrid Deep Learning Framework for CSI-Based Activity Recognition in Bandwidth-Constrained Wi-Fi Sensing

86% match2026

Data Augmentation Techniques for Cross-Domain WiFi CSI-based Human Activity Recognition

86% match1 repo62024

Evaluating BiLSTM and CNN+GRU Approaches for Human Activity Recognition Using WiFi CSI Data

85% match2025

Directional Antenna Systems for Long-Range Through-Wall Human Activity Recognition

83% match1 repo62024

Attention-Enhanced Deep Learning for Device-Free Through-the-Wall Presence Detection Using Indoor WiFi Systems

83% match2023

Cite this paper

@article{bresciani2024approaches,
  title  = {Approaches to human activity recognition via passive radar},
  author = {Christian Bresciani and Federico Cerutti and Marco Cominelli},
  year   = {2024},
  eprint = {2410.24166},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.24166v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.24166.svg)](https://codeofpaper.com/paper/2410.24166)

Discussion