On-line Human Activity Recognition from Audio and Home Automation Sensors: comparison of sequential and non-sequential models in realistic Smart Homes

Abstract : Automatic human Activity Recognition (AR) is an important process for the provision of context-aware services in smart spaces such as voice-controlled smart homes. In this paper, we present an on-line Activities of Daily Living (ADL) recognition method for automatic identification within homes in which multiple sensors, actuators and automation equipment coexist, including audio sensors. Three sequence-based models are presented and compared: a Hidden Markov Model (HMM), Conditional Random Fields (CRF) and a sequential Markov Logic Network (MLN). These methods have been tested in two real Smart Homes thanks to experiments involving more than 30 participants. Their results were compared to those of three non-sequential models: a Support Vector Machine (SVM), a Random Forest (RF) and a non-sequential MLN. This comparative study shows that CRF gave the best results for on-line activity recognition from non-visual, audio and home automation sensors.
Document type :
Journal articles
Liste complète des métadonnées

Cited literature [83 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01336552
Contributor : Michel Vacher <>
Submitted on : Thursday, June 23, 2016 - 11:54:58 AM
Last modification on : Friday, April 5, 2019 - 3:16:13 PM
Document(s) archivé(s) le : Saturday, September 24, 2016 - 11:27:47 AM

File

2016_JAISE_Chahuara_auteur.pdf
Files produced by the author(s)

Identifiers

Citation

Pedro Chahuara, Anthony Fleury, François Portet, Michel Vacher. On-line Human Activity Recognition from Audio and Home Automation Sensors: comparison of sequential and non-sequential models in realistic Smart Homes. JAISE - Journal of Ambient Intelligence and Smart Environments, IOS Press, 2016, 8 (4), pp.399-422. ⟨http://content.iospress.com/journals/journal-of-ambient-intelligence-and-smart-environments/8/4⟩. ⟨10.3233/AIS-160386⟩. ⟨hal-01336552⟩

Share

Metrics

Record views

473

Files downloads

1082