Use of ECDF-based features and ensemble of classifiers to accurately detect mobility activities of people using accelerometers.
Megha VijVinayak NaikVenkata M. V. GunturiPublished in: COMSNETS (2017)
Keyphrases
- multiple classifiers
- feature set
- ensemble learning
- ensemble classifier
- decision tree classifiers
- individual features
- training data
- final classification
- extracted features
- feature ranking
- detection method
- weak learners
- svm classifier
- training set
- classifier ensemble
- random forest
- decision trees
- train a support vector machine
- linear svm
- majority voting
- ensemble pruning
- neural network
- weak classifiers
- classification models
- feature vectors
- feature space
- support vector
- feature extraction
- classification process
- feature selection algorithms
- feature values
- feature subset
- activity recognition
- class labels
- mobile agents
- classification accuracy
- feature extractors
- feature selection