Daily activity recognition based on acoustic signals and acceleration signals estimated with Gaussian process.
Masafumi NishidaNorihide KitaokaKazuya TakedaPublished in: APSIPA (2015)
Keyphrases
- acoustic signals
- gaussian process
- daily activities
- acoustic signal
- activity recognition
- gaussian processes
- bayesian framework
- gaussian process regression
- model selection
- regression model
- hyperparameters
- human activities
- latent variables
- gaussian process models
- semi supervised
- cross validation
- image reconstruction
- decision trees
- smart home
- action recognition
- maximum likelihood
- learning process