Approaches to human activity recognition via passive radar
This addresses privacy concerns in HAR for applications like smart homes or healthcare by providing a less invasive method, though it appears incremental as it builds on existing CSI and neurosymbolic approaches.
The thesis tackled human activity recognition by using passive radar with Wi-Fi CSI data and spiking neural networks integrated with symbolic reasoning, achieving high accuracy as a non-intrusive alternative.
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.