Contactless WiFi Sensing and Monitoring for Future Healthcare - Emerging Trends, Challenges, and Opportunities

Ge, Yufeng; Taha, Ahmad; Shah, Syed Aziz; Dashtipour, Kia; Zhu, Shuyuan; Cooper, Jonathan M.; Abbasi, Qammer H.; Imran, Muhammad Ali

doi:10.1109/rbme.2022.3156810

Cited by 36 publications

(15 citation statements)

References 115 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Human-centric smart building applications are part of Industry 5.0 trends and target the real-time human body monitoring in indoor/outdoor areas [7], [8]. Passive sensing of people/workers and monitoring of their health conditions can be based on Wireless Local Area Network (WLAN) signal processing tools, as reviewed in [9]. For example, a devicefree fall detection algorithm, based on the analysis of ambient radio signals, is proposed in [10] by exploiting low-power IEEE 802.15.4 compliant devices already deployed in the monitored area for Machine-to-Machine (M2M) communication purposes.…”

Section: A Related Workmentioning

confidence: 99%

A Random Forest Approach to Body Motion Detection: Multisensory Fusion and Edge Processing

et al. 2023

View full text Add to dashboard Cite

Low-complexity and privacy-respecting human sensing is a challenging task in smart environments as it requires the orchestration of multiple sensors, low-impact Machine Learning (ML) methods, and resource-constrained IoT devices. Client/Serverbased architectures are typically employed to support sensor fusion. However, these architectures need data to be moved to/from the cloud or data centers which is contrary to the fundamental requirement of IoT applications to limit costs, complexity, memory footprint, processing and communication resources. In this paper, we propose the design and the implementation of an integrated edge device targeting human sensing for indoor smart spaces applications envisioned in Industry 5.0 applications. The proposed device implements the CUmulative SUM (CUSUM) method for data distillation from multiple sensors and adopts a lowcomplexity Random Forest Algorithm (RFA) to sense and classify body movements: in particular, the device integrates both infrared (IR) and ultrasonic sensors (US). The paper discusses the benefits of the combined use of CUSUM and RFA methods against classical ML approaches in terms of accuracy, complexity, computing time, and storage. The proposed architecture and processing steps are validated experimentally by targeting the fall detection problem in a smart space environment. RFA reduces the complexity by at least 3 times compared to classical ML tools based on the analysis of space and time features (Convolutional Neural Networks and Long-Short Term Memory). Processing time i.e., 0.1 seconds, is about 4 times faster, with good performance in terms of accuracy (94%).

show abstract

Section: A Related Workmentioning

confidence: 99%

A Random Forest Approach to Body Motion Detection: Multisensory Fusion and Edge Processing

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The CSI here covers the two main parameters that have been used for accurate sleep stages classification, namely the respiration and body movement information. More Information on the state-of-the-art advancements in health care and the future trends for the use of DFWS can be read through [62]- [64] and the review paper in [58].…”

Section: Applications In Health Carementioning

confidence: 99%

Channel State Information based Device Free Wireless Sensing for IoT Devices Employing TinyML

Hayajneh

Aldalahmeh

Zaidi

et al. 2022

2022 4th IEEE Middle East and North Africa COMMunications Conference (MENACOMM)

View full text Add to dashboard Cite

The channel state information (CSI) of the sub-carriers employed in orthogonal frequency division multiplexing (OFDM) systems has been employed traditionally for channel equalisation. However, the CSI intrinsically is a signature of the operational RF environment and can serve as a proxy for certain activities in the operational environment. For instance, the CSI gets influenced by scatterers and therefore can be an indicator of how many scatterers or if there are mobile scatterers etc. The mapping between the activities whose signature CSI encodes and the raw data is not deterministic. Nevertheless, machine learning (ML) based approaches can provide a reliable classification for patterns of life. Most of these approaches have only been implemented in lab environments. This is mainly because the hardware requirements for capturing CSI, processing it and performing signal-processing algorithms are too complex to be implemented in commercial devices. The increased proliferation of IoT sensors and the development of edge-based ML capabilities using the TinyML framework opens up possibilities for the implementation of these techniques at scale on commercial devices. Using RF signature instead of more invasive methods e.g. cameras or wearable devices provide ease of deployment, intrinsic privacy and better usability. The design space of device-free wireless sensing (DFWS) is complex and involves device, firmware and ML considerations. In this article, we present a comprehensive overview and key considerations for the implementation of such solutions. We also demonstrate the viability of these approaches using a simple case study.

show abstract

“…Indoor human activity recognition (HAR) has played a significant role in intelligent internet of things (IoT) controlling and healthcare monitoring. Device-free WiFi sensing in HAR is an emerging research trend for nearly a decade, which spawned various kinds of applications including vitals monitoring, human daily activity recognition, falling detection, and signs recognition [1], [2]. Compared to other equipment of radar-based device-free approaches, the WiFi devices objectively own higher cost-effective which is the better choice for general indoor cases implementation.…”

Section: Introductionmentioning

confidence: 99%

WiFi sensing of Human Activity Recognition using Continuous AoA-ToF Maps

Wang

et al. 2023

2023 IEEE Wireless Communications and Networking Conference (WCNC)

View full text Add to dashboard Cite

Joint communication and sensing technique has been adopted for smart home design and other applications recently. WiFi sensing, which utilizes mutually orthogonal channel response to monitor the changes in the medium, is regarded as one of key techniques in this field. Human activity recognition using wireless communication system is a key function of future internet of things system. The effective and inexpensive WiFi sensing system can help people for device-free controlling, healthcare monitoring without concern of image information leakage that uses camera system. In this article, we proposed a continuous angle of arrival and time of flight (AoA-ToF) maps based method that adopts multiple signals classification analysis on commercial and off-the-shelf WiFi devices to detect the human activities. The performance of our system achieves 85.6% accuracy in total with 8 activities among 5 users. Meanwhile, we investigated the performance of our system under different conditions, including direction and user identity. The results show the system's robustness for human activity recognition under such conditions.

show abstract

Contactless WiFi Sensing and Monitoring for Future Healthcare - Emerging Trends, Challenges, and Opportunities

Cited by 36 publications

References 115 publications

A Random Forest Approach to Body Motion Detection: Multisensory Fusion and Edge Processing

A Random Forest Approach to Body Motion Detection: Multisensory Fusion and Edge Processing

Channel State Information based Device Free Wireless Sensing for IoT Devices Employing TinyML

WiFi sensing of Human Activity Recognition using Continuous AoA-ToF Maps

Contact Info

Product

Resources

About