Human Activity Recognition Using Place-Based Decision Fusion in Smart Homes - Archive ouverte HAL Access content directly
Conference Papers Year : 2017

Human Activity Recognition Using Place-Based Decision Fusion in Smart Homes

(1, 2) , (2) , (2) , (1)
1
2

Abstract

This paper describes the results of experiments where information about places is used in the recognition of activities in the home. We explore the use of place-specific activity recognition trained with supervised learning, coupled with a decision fusion step, for recognition of activities in the Opportunity dataset. Our experiments show that using place information to control recognition can substantially improve both the error rates and the computation cost of activity recognition compared to classical approaches where all sensors are used and all activities are possible. The use of place information for controlling recognition gives an F1 classification score of 92.70% ± 1.26%, requiring on average only 73 milliseconds of computing time per instance of activity. These experiments demonstrate that organizing activity recognition with place-based context models can provide a scalable approach for building context-aware services based on activity recognition in smart home environments .
Fichier principal
Vignette du fichier
paper_context.pdf (1.27 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01555334 , version 1 (04-07-2017)

Identifiers

Cite

Julien Cumin, Grégoire Lefebvre, Fano Ramparany, James L. Crowley. Human Activity Recognition Using Place-Based Decision Fusion in Smart Homes. 10th International and Interdisciplinary Conference, CONTEXT 2017, Jun 2017, Paris, France. pp.137 - 150, ⟨10.1145/1865987.1866010⟩. ⟨hal-01555334⟩
176 View
848 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More