Electromagnetic evaluation of UHF-RFID Smartshelf in Healthcare Environments

Marina, Pablo; Suarez, Samuel; Hernández, J.A.; Febles, Victor M.; Rabassa, Luis E.; Ramos, Victoria

doi:10.1109/emceurope51680.2022.9901307

Cited by 2 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It plays a crucial role in enhancing remote patient monitoring, as evidenced by its application in post-surgical fall detection systems, which greatly benefit patient care [14]. Additionally, the technology has been instrumental in facilitating the real-time remote testing and programming of cardiac implantable electronic devices, marking a leap forward in cardiac care [15]. The coexistence of 5G C-Band with other wireless technologies in medical scenarios underscores its compatibility and effectiveness in a diverse technological environment [16].…”

Section: Introductionmentioning

confidence: 99%

An efficient monitoring of HELLP syndrome pre-eclampsia in wireless sensors networks

ullah,

Young,

khan

et al. 2023

Preprint

View full text Add to dashboard Cite

This paper explores the application of wireless sensing using 5G technology in the 4.8 GHz C-band, a significant step forward in healthcare innovation. It focuses on the application of wireless sensing to monitor HELLP syndrome in cases of pre-eclampsia, showcasing how Wireless Sensor Networks (WSNs), enhanced by 5G's high-speed capabilities, substantially improve real-time data transmission and healthcare decision-making. The integration of WSNs with 5G technology enables non-invasive, continuous patient monitoring, providing advanced solutions for remote health surveillance and efficient data management in critical healthcare situations. Specifically, the study highlights the use of a wireless transceiver in indoor environments to monitor various body movements, including those indicative of HELLP syndrome symptoms. These movements generate unique wireless data, thus enriching the understanding of wireless channel information. The research explores deep learning models such as ANN, CNN, and especially VGGNet, which achieved a notable 99.26% accuracy in classifying patient activities. Additionally, the paper discusses model optimization, emphasizing the need for adjustments in parameters such as batch sizes and hidden units to enhance performance. The study's outcomes, evaluated using metrics such as accuracy, recall, precision, specificity, and F-measure, demonstrate the superior performance of VGGNet compared to other classifiers. These findings underscore the potential of integrating advanced technologies like WSNs and 5G in healthcare, highlighting their role in creating more effective, reliable, and patient-centric healthcare systems

show abstract

Section: Introductionmentioning

confidence: 99%