An Unsupervised Multivariate Time Series Kernel Approach for Identifying Patients with Surgical Site Infection from Blood Samples.
Karl Øyvind MikalsenCristina Soguero-RuízFilippo Maria BianchiArthur RevhaugRobert JenssenPublished in: CoRR (2018)
Keyphrases
- multivariate time series
- physiological data
- blood pressure
- intensive care unit
- website
- multivariate time series data
- operating room
- temporal data
- risk factors
- supervised learning
- categorical data
- dimension reduction
- data sets
- support vector
- spatial structure
- unsupervised learning
- autoregressive
- intraoperative
- patient data
- training set
- feature space
- temporal patterns
- training data