Support Vector machine and duration-aware conditional random field for identification of spatio-temporal activity patterns by combined indoor positioning and heart rate sensors.
Jan BehmannKathrin HendriksenUte MüllerWolfgang BüscherLutz PlümerPublished in: GeoInformatica (2016)
Keyphrases
- conditional random fields
- heart rate
- activity patterns
- support vector machine
- indoor positioning
- blood pressure
- graphical models
- crf model
- heart rate variability
- random fields
- hidden markov models
- probabilistic model
- markov random field
- dead reckoning
- generative model
- real time
- wifi
- information extraction
- moving objects
- sensor networks
- training data
- pairwise
- support vector
- feature vectors
- sensor data
- segmentation method
- global positioning system
- image sequences
- machine learning