Sökning: "Erik Lindén"
Hittade 2 avhandlingar innehållade orden Erik Lindén.
1. Calibration in deep-learning eye tracking
Sammanfattning : Personal variations severely limit the performance of appearance-based gaze tracking. Adapting to these variations using standard neural network model adaptation methods is difficult. The problems range from overfitting, due to small amounts of training data, to underfitting, due to restrictive model architectures. LÄS MER
2. Markers of hemodynamic state and heart failure as predictors for outcome in cardiac surgery : with special reference to mixed venous oxygen saturation and natriuretic peptides
Sammanfattning : Postoperative heart failure or low cardiac output syndrome is the major cause for morbidity and mortality in cardiac surgery. Unfortunately commonly used methods to assess hemodynamic state and heart failure are not well documented with regard to outcome. LÄS MER