Savvidou Foteini, Tegos Sotiris A, Diamantoulakis Panagiotis D, Karagiannidis George K
Department of Electrical and Computer EngineeringAristotle University of Thessaloniki 54124 Thessaloniki Greece.
Artificial Intelligence & Cyber Systems Research CenterLebanese American University Beirut 03797751 Lebanon.
IEEE Open J Eng Med Biol. 2024 Jun 28;5:700-706. doi: 10.1109/OJEMB.2024.3420747. eCollection 2024.
Continuous and unobtrusive monitoring of daily human activities in homes can potentially improve the quality of life and prolong independent living for the elderly and people with chronic diseases by recognizing normal daily activities and detecting gradual changes in their conditions. However, existing human activity recognition (HAR) solutions employ wearable and video-based sensors, which either require dedicated devices to be carried by the user or raise privacy concerns. Radar sensors enable non-intrusive long-term monitoring, while they can exploit existing communication systems, e.g., Wi-Fi, as illuminators of opportunity. This survey provides an overview of passive radar system architectures, signal processing techniques, feature extraction, and machine learning's role in HAR applications. Moreover, it points out challenges in wireless human activity sensing research like robustness, privacy, and multiple user activity sensing and suggests possible future directions, including the coexistence of sensing and communications and the construction of open datasets.
对家庭中人类日常活动进行持续且不引人注意的监测，通过识别正常日常活动并检测老年人和慢性病患者状况的逐渐变化，有可能提高他们的生活质量并延长其独立生活时间。然而，现有的人类活动识别（HAR）解决方案采用可穿戴和基于视频的传感器，这要么需要用户携带专用设备，要么会引发隐私问题。雷达传感器能够实现非侵入式长期监测，同时还可以利用现有的通信系统，如Wi-Fi，作为机会照明器。本综述概述了无源雷达系统架构、信号处理技术、特征提取以及机器学习在HAR应用中的作用。此外，它指出了无线人类活动传感研究中的挑战，如鲁棒性、隐私和多用户活动传感，并提出了可能的未来方向，包括传感与通信的共存以及开放数据集的构建。
