作者: Pedro Chahuara , Anthony Fleury , François Portet , Michel Vacher
DOI: 10.1007/978-3-642-34898-3_12
关键词:
摘要: This paper presents the application of Markov Logic Networks(MLN) for recognition Activities Daily Living (ADL) in a smart home. We describe procedure that uses raw data from non visual and wearable sensors order to create classification model leveraging logic formal representation probabilistic inference. SVM Naive Bayes methods were used as baselines compare performance our implementation, they have proved be highly efficient tasks. The evaluation was carried out on real home where 21 participants performed ADLs. Results show not only appreciable capacities MLN classifier, but also its potential easily integrable into knowledge framework.