Background: Interactive smart home systems are particularly useful for people with cognitive impairment. Objective: To investigate the long-term effects of Assistive Technology (AT) combined with tailored non-pharmacological interventions for people with cognitive impairment. Methods: 18 participants (12 with mild cognitive impairment and 6 with Alzheimer's disease) took part in the study that we evenly allocated in one of three groups: 1) experimental group (EG), 2) control group 1 (CG1), and 3) control group 2 (CG2). EG received the system installed at home for 4 to 12 months, during which they received tailored non-pharmacological interventions according to system observations. CG1 received tailored interventions for the same period, but only according to state-of-the-art self-reporting methods. Finally, CG2 neither had a system installation nor received interventions. All groups underwent neuropsychological assessment before and after the observational period. Results: After several months of continuously monitoring at home and deployment of tailored interventions, the EG showed statistically significant improvement in cognitive function, compared to the CG1 and CG2. Moreover, EG participants, who received the sensor-based system, have shown improvement in domains such as sleep quality and daily activity, as measured by the multi-sensor system. In addition, the feedback collected from the participants concludes that the long-term use of the multi-sensor system by people with cognitive impairment can be both feasible and beneficial. Conclusion: Deploying a sensor-based system at real home settings of people with cognitive limitations living alone and maintaining its use long-term is not only possible, but also beneficial for clinical decision making in order to tackle cognitive, functional, and behavioral related problems.

Stress is a common problem that affects most people with dementia and their caregivers. Stress symptoms for people with dementia are often measured by answering a checklist of questions by the clinical staff who work closely with the person with the dementia. This process requires a lot of effort with continuous observation of the person with dementia over the long term. This article investigates the effectiveness of using a straightforward method, based on a single wristband sensor to classify events of “Stressed” and “Not stressed” for people with dementia. The presented system calculates the stress level as an integer value from zero to five, providing clinical information of behavioral patterns to the clinical staff. Thirty staff members participated in this experiment, together with six residents suffering from dementia, from two nursing homes. The residents were equipped with the wristband sensor during the day, and the staff were writing observation notes during the experiment to serve as ground truth. Experimental evaluation showed relationships between staff observations and sensor analysis, while stress level thresholds adjusted to each individual can serve different scenarios.

Real-time collection of tweets about the COVID-19 pandemic in highly affected Italy• Automatic geotagging of tweets and detection of showing faces in their visual content• Further analysis of tweets to detect trending topics, user communities, and events• An online platform that visualises the analysed tweets in multi-level aspects• An interactive map and a visual analytics dashboard to monitor the pandemic crisis