Deep Neural Networks for Human Activity Recognition With Wearable Sensors: Leave-One-Subject-Out Cross-Validation for Model Selection.
Davoud GholamiangonabadiNikita KiselovKatarina GrolingerPublished in: IEEE Access (2020)
Keyphrases
- cross validation
- model selection
- human activity recognition
- activity recognition
- human activities
- hyperparameters
- variable selection
- sample size
- generalization error
- daily life
- information criterion
- visual surveillance
- error estimation
- selection criterion
- motion segmentation
- gaussian process
- machine learning
- mixture model
- feature selection
- sensor data
- unsupervised learning
- human computer interaction
- training set
- leave one out cross validation