.png){kind=icon}
.png){kind=icon}
Return
Brain Source Localization Using Stochastic Gradient Descent
.png){kind=icon}
PRE
AI
DOI：10.1109/JSEN.2020.3047666.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The high temporal resolution of the electroencephalogram (EEG) makes it a useful modality to study the dynamic nature of cortical activity. The main objective of this work is to localize and track active sources on the surface of the cortex using EEG recordings. A stochastic gradient descent method is proposed, and the performance of this method is investigated on simulated data that models spatially fixed and spatially moving sources. Simulation results show that the proposed method is able to recover closely spaced sources and yields a localization accuracy similar to that of existing methods but with significantly reduced computational time. The proposed method is also applied on clinical data from epileptic patients, and the results are found to be compatible with the clinical reports.
Keywords:
Brain modeling
Electroencephalography
Lead
Inverse problems
Stochastic processes
Position measurement
Numerical models
Electroencephalography
source localization
stochastic gradient descent
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.5
Papers:
2.1W
Citations:
7.3W