|
" Deep tissue monitoring enabled by wearable ultrasonic devices and machine learning "
Zhang, Zhuorui
Xu, Sheng
| Document Type
|
:
|
Latin Dissertation
|
| Language of Document
|
:
|
English
|
| Record Number
|
:
|
897336
|
| Doc. No
|
:
|
TL7f895421
|
| Main Entry
|
:
|
Brahinsky, Joshua
|
| Title & Author
|
:
|
Deep tissue monitoring enabled by wearable ultrasonic devices and machine learning\ Zhang, ZhuoruiXu, Sheng
|
| Date
|
:
|
2019
|
| student score
|
:
|
2019
|
| Abstract
|
:
|
Benefiting from the development of wearable electronic devices, various physiological signals, such as body temperature, hydration, glucose/lactate levels, and local field potentials, can already be monitored continuously and noninvasively. Among all physiological signals, those deeply beneath the skin, including central blood pressure, blood flow and activities of major organs, are particularly important since they are directly related to the subject’s life-sustaining capability. However, there is a lack of devices that could give continuous and reliable readings of these vital signs. Their common limitations can be summarized as: limited penetration depth and operator dependence. Herein, we use human carotid artery as an example and demonstrate wearable ultrasonic devices supported by control electronics and adaptive algorithms to achieve automatic deep tissue monitoring. To eliminate the operator dependence of ultrasound technology, machine learning-based algorithms were developed addressing the blood vessel positioning and wall tracking tasks.
|
| Added Entry
|
:
|
Zhang, Zhuorui
|
| Added Entry
|
:
|
UC San Diego
|
| |