On-line human activity recognition from audio and home automation sensors: Comparison of sequential and non-sequential models in realistic Smart Homes¹

Issue title: Human-centric computing and intelligent environments

Guest editors: Gordon Hunter, Tiina Kymäläinen and Raúl Herrera-Acuña

Article type: Research Article

Authors: Chahuara, Pedro^{a; b; *} | Fleury, Anthony^{c; d} | Portet, François^{a; b; **} | Vacher, Michel^{a; b}

Affiliations: [a] Université Grenoble Alpes, LIG, F-38000 Grenoble, France | [b] CNRS, LIG, F-38000 Grenoble, France. E-mails: [email protected], [email protected], [email protected] | [c] Université Lille, F-59000 Lille, France | [d] Mines Douai, IA, F-59508 Douai Cedex, France. E-mail: [email protected]

Correspondence: [**] Corresponding author. Tel.: +33476514879; E-mail: [email protected].

Note: [1] This work is part of the Sweet-Home project founded by the French National Research Agency (Agence Nationale de la Recherche/ANR-09-VERS-011).

Note: [*] Pedro Chahuara is now at European Commission Joint Research Centre, Ispra, Italy.

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. This paper presents 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.

Keywords: Activity recognition, Markov Logic Network, Statistical Relational Learning, Smart Home, Ambient Assisted Living

DOI: 10.3233/AIS-160386

Journal: Journal of Ambient Intelligence and Smart Environments, vol. 8, no. 4, pp. 399-422, 2016