Julien Cumin - Recognizing and predicting activities in smart homes

Julien Cumin


Lieu de soutenance :

Orange Labs, 28 ch. du Vieux Chêne Meylan - Grand amphithéatre

Jury :

  • James Crowley, professeur, Université Grenoble Alpes, directeur de thèse
  • Grégoire Lefebvre, ingénieur de recherche, Orange Labs, codirecteur de thèse
  • Fano Ramparany, ingénieur de recherche, Orange Labs, codirecteur de thèse
  • Daniel Roggen, associate professor, University of Sussex, examinateur
  • Gaëlle Calvary, professeur des universités, Université Grenoble Alpes, examinatrice
  • Albrecht Schmidt, professeur des universités, University of Stuttgart, rapporteur
  • Patrick Brézillon, professeur des universités, Université Pierre et Marie Curie, rapporteur
  • Jean-Yves Tigli, maître de conférences, Université de Nice Sophia Antipolis, examinateur

Understanding the context of a home is essential in order to provide services to occupants that fit their situations and thus fulfil their needs. One example of service that such a context-aware smart home could provide is that of a communication assistant, which can for example advise correspondents outside the home on the availability for communication of occupants. In order to implement such a service, it is indeed required that the home understands the situations of occupants, in order to derive their availability. 

In this thesis, we first propose a definition of context in homes. We argue that one of the primary context dimensions necessary for a system to be context-aware is the activity of occupants. As such, we then study the problem of recognizing activities, from ambient smart home sensors. We propose a new supervised place-based approach which both improves activity recognition accuracy as well as computing times compared to standard approaches. 

Smart home services, such as our communication assistance example, may often need to anticipate future situations. In particular, they need to anticipate future activities of occupants. Therefore, we design a new supervised activity prediction model, based on previous state-of-the-art work. We propose a number of extensions to improve prediction accuracy based on the specificities of smart home environments. 

Finally, we study the problem of inferring the availability of occupants for communication, in order to illustrate the feasibility of our communication assistant example. We argue that availability can be inferred from primary context dimensions such as place and activity (which can be recognized or predicted using our previous contributions), and by taking into consideration the correspondent initiating the communication as well as the modality of communication used. We discuss the impact of the activity recognition step on availability inference. 

We evaluate those contributions on various state-of-the-art datasets, as well as on a new dataset of activities and availabilities in homes which we constructed specifically for the purposes of this thesis: Orange4Home. Through our contributions to these 3 problems, we demonstrate the way in which an example context-aware communication assistance service can be implemented, which can advise on future availability for communication of occupants. More generally, we show how secondary context dimensions such as availability can be inferred from other context dimensions, in particular from activity. Highly accurate activity recognition and prediction are thus mandatory for a smart home to achieve context awareness.