Oukrich Nadia, Maach Abdelilah, Sabri ElMehdi, Mabrouk ElMahdi et Bouchard Kévin. (2016). Activity recognition using back-propagation algorithm and minimum redundancy feature selection method. Dans 2016 4th IEEE International colloquium on information science and technology (CiSt). (p. 818-823). Piscataway, New Jersey : IEEE.
Le texte intégral n'est pas disponible pour ce document.
URL officielle: http://dx.doi.org/doi:10.1109/CIST.2016.7805000
Résumé
In this paper, we use multilayer Perceptron model and a supervised learning technique called backpropagation to train a neural network in order to recognize human activity inside smart home, and select useful features according to minimum redundancy maximum relevance. The results show that different feature datasets and different number of neurons of hidden layer of neural network yield different activity recognition accuracy. The selection of suitable feature datasets increases the activity recognition accuracy and reduces the time of execution. Furthermore, neural network using back-propagation algorithm and multilayer Perceptron model has relatively better human activity recognition performances.
| Type de document: | Chapitre de livre |
|---|---|
| Date: | 2016 |
| Lieu de publication: | Piscataway, New Jersey |
| Identifiant unique: | 10.1109/CIST.2016.7805000 |
| Sujets: | Sciences naturelles et génie > Sciences mathématiques > Informatique |
| Département, module, service et unité de recherche: | Départements et modules > Département d'informatique et de mathématique |
| Liens connexes: | |
| Mots-clés: | activity recognition, smart home, multilayer perceptron, back-propagation, feature selection, mutual information |
| Déposé le: | 15 févr. 2021 16:37 |
|---|---|
| Dernière modification: | 15 févr. 2021 16:37 |
Éditer le document (administrateurs uniquement)
Altmetric
Altmetric