ESR photo Research project "AI for dementia care" About the project Although the progress and severity of dementia varies depending on the underlying cause (e.g. Alzheimer´s disease) there are common symptoms between the manifestations. These symptoms include personality changes, which manifests itself in becoming subdued or withdrawn. By using machine learning in long-term emotional analysis, it should be possible to recognize patterns and thus determine personality changes. In order to assign the person´s mood correctly, it is necessary that the algorithms treat the emotions context aware. This means that the current situation and environment of the person is detected (e.g. by sensors or smartphone) which allows to determine whether certain emotions are only felt in company or alone. Some outcomes will be the development of new therapeutic intervention strategy, behaviour analysis based on 3D and 2D tracking data in order to detect changes in the health status, context aware recommendation for (music and dance) movements based on emotions and movement analysis, and empowerment of older people to increase the therapy effectiveness. Start date: March 2021 Progress of the project This project has conducted a state-of-the-art review of AI technologies for dementia care and has established two areas of work in which behavioural modelling using AI-based technologies is applied. The first area of work focuses on the development of an algorithm for assistance in daily activities for people with dementia, with a focus on the use of the algorithm. For this, a prototype has been developed that compares the activities the user is performing on the toilet using a depth sensor and provides guidance in case deviations from a predefined model are detected. From the very beginning, a collaboration with the DIANA project was established. Adapting the interaction for users with dementia is a key part of the success of this work, so a literature review in combination with focus groups with healthcare professionals has been carried out in collaboration with ESR15. The outcome of this was published in Pervasive Health 2021. A second phase of this project included experiments to validate the performance of the system, the results of which were published at the AHFE 2022 conference. The second area of work is dedicated to the detection of long-term behavioural changes in people with dementia using data from depth sensors as input data. As a first step, a review of the state of the art has been carried out together with a preliminary study to explore the possibilities of 3D coordinates as input data for the detection of behavioural changes. Secondly, a taxonomy of behaviours related to cognitive impairment to be measured has started to be defined and a collaboration with the AlgoCare project has been initiated. Both lines of work have been presented in the form of a research proposal in the proficiency evaluation together with a plan for future work. The proficiency evaluation consists of a presentation to an evaluation committee and is a prerequisite for a doctoral degree at the University of Vienna. The result was positive, and the recommendations of the evaluation committee are being taken into account for the further development of the project. Scientific publications Automated vision-based toilet assistance for people with dementia Irene Ballester, Martin Kampel Automated vision-based toilet assistance for people with dementia In: Matteo Zallio (eds) Human Factors in Accessibility and Assistive Technology. AHFE (2022) International Conference. AHFE Open Access, vol 37. AHFE International, USA, 2022. RITA: A privacy-aware toileting assistance designed for people with dementia Irene Ballester, Tamar Mujirishvili, Martin Kampel RITA: A privacy-aware toileting assistance designed for people with dementia EAI PervasiveHealth 2021 – 15th EAI International Conference on Pervasive Computing Technologies for Healthcare, December 6-8, Tel Aviv, Israel, 2021 Video of the presentation at the conference About the ESR Irene holds a BSc degree in Industrial Technology Engineering (2017) and an MSc degree in Industrial Engineering (2020), both from the University of Zaragoza, Spain. During the academic year 2019-2020, she was a Working Master Student at DLR in Munich where she wrote her Master’s thesis on Dynamic SLAM systems. Contact information Irene Ballester Campos Vienna University of Technology Computer Vision Lab Favoritenstr. 9/193-1 A-1040 Vienna, Austria Email address: iballester@cvl.tuwien.ac.at
Automated vision-based toilet assistance for people with dementia Irene Ballester, Martin Kampel Automated vision-based toilet assistance for people with dementia In: Matteo Zallio (eds) Human Factors in Accessibility and Assistive Technology. AHFE (2022) International Conference. AHFE Open Access, vol 37. AHFE International, USA, 2022.
RITA: A privacy-aware toileting assistance designed for people with dementia Irene Ballester, Tamar Mujirishvili, Martin Kampel RITA: A privacy-aware toileting assistance designed for people with dementia EAI PervasiveHealth 2021 – 15th EAI International Conference on Pervasive Computing Technologies for Healthcare, December 6-8, Tel Aviv, Israel, 2021 Video of the presentation at the conference