SLIDE 1
Medical domain
§ Physicians are inference systems § Physicians working together, means exchanging data But…. § Physicians really don’t like uncertainty!!
Scalable Uncertainty Management
Handling Probabilistic Data Ander de Keijzer Scalable Uncertainty - - PowerPoint PPT Presentation
Handling Probabilistic Data Ander de Keijzer Scalable Uncertainty - - PowerPoint PPT Presentation
Handling Probabilistic Data Ander de Keijzer Scalable Uncertainty Management Medical domain Physicians are inference systems Physicians working together, means exchanging data But. Physicians really dont like uncertainty!!
SLIDE 2
SLIDE 3
Brief overview of uncertain data
§ Data has an associated probability
Scalable Uncertainty Management
Patient (name, diagnosis*) Amy, (Epilepsy || Parkinson)
SLIDE 4
Brief overview of uncertain data
§ Data has an associated probability § Granularity of uncertainty depends on level with which the probability is associated
Scalable Uncertainty Management
Patient (name, diagnosis*) Amy, (Epilepsy || Parkinson) Patient (name, diagnosis*) Amy, (Epilepsy:.8 || Parkinson:.2)
SLIDE 5
Brief overview of uncertain data
§ Data has an associated probability § Granularity of uncertainty depends on level with which the probability is associated
Scalable Uncertainty Management
Patient (name, diagnosis*) Amy, (Epilepsy || Parkinson) Patient (name, diagnosis*) Amy, (Epilepsy:.8 || Parkinson:.2)
EEGFeatures(patient, feature) Amy, FocalBurst AccelData(patient, feature) Amy, ShortStride
? ?
SLIDE 6
Brief overview of uncertain data
§ Data has an associated probability § Granularity of uncertainty depends on level with which the probability is associated
Scalable Uncertainty Management
Patient (name, diagnosis*) Amy, (Epilepsy:.8 || Parkinson:.2)
EEGFeatures(patient, feature) Amy, FocalBurst AccelData(patient, feature) Amy, ShortStride
? ?
10 20
λ(30,1)= 10; λ(30,2)=20
30
SLIDE 7
Or…
§ Probabilities given as conditional dependence probabilities, which incorporate lineage.
Scalable Uncertainty Management
ShortStride
Epilepsy Falling
FocalBurst Parkinson
SLIDE 8
Or…
Scalable Uncertainty Management
. Accel FocalBurst Falling ShortStride α 1- α EEG
SLIDE 9
Discussion
Scalable Uncertainty Management
SLIDE 10
Discussion
§ Where do the initial probabilities come from?
Scalable Uncertainty Management
SLIDE 11
Discussion
§ Where do the initial probabilities come from? § Are they even probabilities?? Or is it confidence scores?
Scalable Uncertainty Management
SLIDE 12
Discussion
§ Where do the initial probabilities come from? § Are they even probabilities?? Or is it confidence scores? § Lineage…or provenance….or inference rules?? § How to represent the data to end users? § Database researchers usually ignore this one! § Is uncertainty (in databases) only useful with large amounts of data? § Can we scale? § What is large scale?
Scalable Uncertainty Management