| Sumario: | Purpose SafEE (Safe and Easy Environment for Alzheimer's disease) is a French-Taiwanese collaborative project on technologies for health and autonomy aimed at improving safety, autonomy, and quality of life for older people diagnosed with Alzheimer's disease and related disorders. More specifically the SafEE project: (i) focuses on specific clinical targets in three domains: behavior, motricity, and cognition; (ii) merges assessment and non-pharmacological help/intervention; and (iii) proposes easy ICT device solutions for end users. Method French partners within SafEE are designing an ICT system combining event automatic video recognition with actigraphy components. This system is detects, recognizes, and assesses daytime (such as agitation) and night-time (such as sleep disturbances) behavioral patterns (BEHAVIOR), walking/balancing capabilities (MOTRICITY), orientation, and procedural memory (COGNITION). Event models combine a priori knowledge of the scene (3D geometric and semantic information, such as contextual zones and equipments) with moving objects (e.g., a Person) detected by the monitoring system. The event models follow a generic ontology based on natural language, which allows domain experts to easily adapt them for a variety of tasks. The framework's novelty relies on combining multiple sensors at the decision (event) level, and handling conflicts using a probabilistic approach. The proposed approach for event conflict handling computes the event reliability for each sensor, and then combines them using probabilistic assessment with an alternative combination rule. The proposed framework is evaluated using multi-sensor recording of the instrumental daily living activities (e.g., watching TV, writing a check, preparing tea, organizing week intake of prescribed medication) of participants of a clinical trial for Alzheimer's disease. Results & Discussion Preliminary results show that the automated monitoring system can accurately detect activities, characteristic behavioral patterns, and motricity capabilities. We have evaluated the activity recognition algorithm on a large dataset containing 38 elderly participants undertaking instrumental activities of daily living (IADL) during 15 minutes (570 min. in total). The recordings took place in the observation room of the Memory Center of Nice hospital using a video camera. A summary of the recognized activities (e.g., duration, frequency) was produced at the end of the monitoring task and provided to the participants' doctor as a basis for assessing patient performance on IADL.
|
|---|