Name
Abstract | ||
|---|---|---|
Gaussian process models have some attractive advantages over parametric models and neural networks. They have a small number of tunable parameters, give a measure of the uncertainty of the model prediction, and obtain a relatively good model when only a small set of training data is available. In this study the theory of Gaussian process models has been applied to the neonatal seizure detection problem. Two measures are calculated from 1 second windows of EEG recordings; the variance (certainty) of a one step ahead prediction, and the ratio of the first model hyperparameter to the last. In ANOVA tests both measures show statistical difference in their values for nonseizure and seizure EEG. A comparison with a similar Autoregressive (AR) modelling approach shows that Gaussian Process model methods show great promise in real-time neonatal seizure detection. |
Year | Venue | Keywords |
|---|---|---|
2006 | SPPRA | gaussian process model method,seizure eeg,parametric model,gaussian process model,good model,eeg recording,real-time neonatal seizure detection,neonatal seizure detection problem,model prediction,model hyperparameter,gaussian process |
Field | DocType | ISBN |
Neonatal seizure,Autoregressive model,Parametric model,Pattern recognition,Hyperparameter,Computer science,Artificial intelligence,Gaussian process,Artificial neural network,Small set,Electroencephalography | Conference | 0-88986-580-9 |
Citations | PageRank | References |
1 | 0.37 | 5 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Stephen Faul | 1 | 148 | 8.21 |
| Gregor Gregorcic | 2 | 81 | 5.51 |
| Geraldine Boylan | 3 | 45 | 4.60 |
| William Marnane | 4 | 145 | 11.11 |
| Gordon Lightbody | 5 | 223 | 27.57 |
| Sean Connolly | 6 | 30 | 4.81 |