In addition to Weibo, there is also WeChat
Please pay attention
WeChat public account
Shulou
2025-03-30 Update From: SLTechnology News&Howtos shulou NAV: SLTechnology News&Howtos > IT Information >
Share
Shulou(Shulou.com)11/24 Report--
Thanks to CTOnews.com netizen Xiaoxiang Langjun for your clue delivery! CTOnews.com, December 4, according to the News Network of China University of Science and Technology, Professor Chen Yan and researcher Sun Qibin, academician team of Wu Manqing of the University of Science and Technology of China, have made important progress in the research of wireless human perception, realizing real-time monitoring of non-contact human ECG based on millimeter wave radar, breaking through the limitation that ECG can only be obtained through contact sensors for more than a century.
According to reports, since its invention more than a hundred years ago, electrocardiogram (ECG) monitoring has been required to use body electrodes to measure changes in electrical activity on the body surface, resulting in uncomfortable user experience. Therefore, long-term continuous ECG monitoring in daily life is often difficult to implement, resulting in the loss of transient abnormal ECG records and delay the diagnosis of the disease.
Taking advantage of the fact that cardiac electrical activity and mechanical activity are homologous and different representations of cardiac activity, Professor Chen Yan and others use millimeter wave radar to measure cardiac mechanical activity on the body surface in a non-contact form, and extract four-dimensional cardiac mechanical activity signals. Then use the deep neural network model to model the nonlinear mapping relationship between cardiac mechanical activity and electrical activity, solve the domain transformation problem by data-driven method, and finally restore the ECG ECG waveform.
The working principle of ▲ non-contact ECG monitoring system this method is designed under the experimental design of 0.5m non-contact sensing distance, different physiological states and relative rest posture constraints of human body, and achieves the non-contact ECG monitoring performance of less than 14 milliseconds in time median accuracy and more than 90% in shape median accuracy for 35 subjects. The monitoring results of this method also support the stable monitoring of Rmurr R interval, which is the key index in the diagnosis of clinical arrhythmias, and its 90% error is less than 9 milliseconds, which further verifies the medical value of this method.
The performance analysis of time and morphological accuracy of ▲ system and the comparison of monitoring results under different heart rate states this study breaks through the physical perception limit of wireless signals in human perception tasks and provides a non-contact ECG monitoring method. In the process of use, the subjects do not need to wear electrodes or remove clothes, and complete ECG monitoring in a non-inductive way, which has high clinical value.
CTOnews.com learned that the first author of the paper is Chen Jinbo, a doctoral student of the University of Science and Technology of China, the correspondent author is Professor Chen Yan, and the University of Science and Technology of China is the only unit of the paper. The research was supported by the National Natural Science Foundation of China, Anhui Province and University of Science and Technology of China. The relevant research results were published in the IEEE Mobile Computing Compendium.
IEEE TMC article link:
Https://ieeexplore.ieee.org/document/9919401/
EEE SPECTRUM News links:
Https://spectrum.ieee.org/contactless-ecg
Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.
Views: 0
*The comments in the above article only represent the author's personal views and do not represent the views and positions of this website. If you have more insights, please feel free to contribute and share.
Continue with the installation of the previous hadoop.First, install zookooper1. Decompress zookoope
"Every 5-10 years, there's a rare product, a really special, very unusual product that's the most un
© 2024 shulou.com SLNews company. All rights reserved.