Automatic 1D convolutional neural network-based detection of artifacts in MEG acquired without electrooculography or electrocardiography

Medicine & Life Sciences

• Electrooculography 89%
• Magnetoencephalography 80%
• Artifacts 60%
• Electrocardiography 50%
• Electrodes 40%
• Eye 38%
• Sensitivity and Specificity 23%
• Functional Neuroimaging 18%
• Patient Comfort 18%
• Magnetic Fields 17%
• Thorax 10%
• Muscles 9%

Engineering & Materials Science

• Electrooculography 100%
• Magnetoencephalography 93%
• Electrocardiography 60%
• Convolutional neural networks 56%
• Electrodes 35%
• Functional neuroimaging 27%
• Independent component analysis 17%
• Muscle 14%
• Magnetic fields 13%
• Imaging techniques 11%
• Decomposition 11%
• Classifiers 10%