Phoenix - INRIA Research Group

Two new papers accepted at ASSETS 2014 - The 16th International ACM SIGACCESS Conference on Computers and Accessibility

Verification of Daily Activities of Elders: A Simple, Non-Intrusive, Low-Cost Approach

Loïc Caroux, Charles Consel, Lucile Dupuy, Hélène Sauzéon

Abstract: This paper presents an approach to verifying the activities of daily living of elders at their home. We verify activities, instead of inferring them, because our monitoring approach is driven by routines, initially sketched by users in their environment. Monitoring is supported by a lightweight sensor infrastructure, comprising non-intrusive, low-cost, wireless devices. Verification is performed by applying a simple formulae to sensor log data, for each activity of interest. The result value determines whether an activity has been performed. We have conducted an experimental study to validate our approach. To do so, four participants have been monitored during five days at their home, equipped with sensors. When applied to the log data, our formulas were able to automatically verify that a list of activities were performed. They produced the same interpretations, using Signal Detection Theory, as a third party, manually analyzing the log data.

Tablet-Based Activity Schedule for Children with Autism in Mainstream Environment

Charles Fage, Léonard Pommereau, Charles Consel, Emilie Balland, Hélène Sauzéon

Abstract: Including children with Autism Spectrum Disorders (ASD) in mainstreamed environments creates a need for new interventions whose efficacy must be assessed in situ. This paper presents a tablet-based application for activ- ity schedules that has been designed following a partic- ipatory design approach involving mainstream teachers, special-education teachers and school aides. This appli- cations addresses two domains of activities: classroom routines and verbal communications. We assessed the efficiency of our application with a study involving 10 children with ASD in mainstream inclusion (5 children are equipped and 5 are not equipped). We show that (1) the use of the application is rapidly self- initiated (after two months for almost all the partici- pants) and that (2) the tablet-supported routines are differently executed over time according to the activity domain conditions. Importantly, compared to the con- trol children, the equipped children exhibited more class- room and communication routines correctly performed after three month of intervention.