My main research topic deals with the identification of human activities in pervasive environments. In particular, my main focus is the use of contextual information (such as locations of sensors and people) to improve machine learning models for such tasks.
Smart homes and smart offices are the major application domains of my work. Nevertherless, my contributions can be applied to other pervasive environments where human context understanding is important.
Future works include working on situations of multi-human activities. That is, situations where multiple people perform different activities simultaneously in the same environment. We are also interested in recognizing group activities, which implies interactions between subjects.
Other future subjects include exploiting a priori knowledge of context information (such as locations of sensors) to allow unsupervised discovery of human activity-related information.
Through Juan Vazquez-Rodriguez’s thesis, we are interested in recognizing human emotion from multimodal data sources, such as physiological, visual, and audio data.
One of our major goals is to propose new attention-based models such as Transformers, that can deal with multimodal data while still being pre-trainable from different data sets.
Orange4Home is a dataset of routines of daily living captured in Amiqual4Home’s smart home environment, from January 30th, 2017 to February 24th, 2017.
This dataset is the result of a joint work between Orange and Inria. The experiment was conducted by Julien Cumin, Grégoire Lefebvre, Fano Ramparany and James L. Crowley, with technical and organisational help from Nicolas Bonnefond and Stan Borkowski
More information about the dataset is available on Amiqual4Home’s website.
This dataset is openly available, simply contact me by email to ask for access to the dataset. Any use of this dataset in publications must cite the following publication:
Julien Cumin, Grégoire Lefebvre, Fano Ramparany, James L. Crowley. A dataset of routine daily activities in an instrumented home. In 11th international conference on ubiquitous computing and ambient intelligence (UCAmI), 2017.