Main target of fast care is the development of a real-time capable sensor data analysis framework for intelligent assistive systems in the field of Ambient Assisted Living, eHealth, Tele Rehabilitation, and Tele Care. The aim is to provide a medically valid integrated situation model based on a distributed, ad-hoc connected, energy-efficient sensor infrastructure suitable for daily use. The integrated situation model combining physiological, cognitive, and kinematic information about the patient is grounded on the intelligent fusion of heterogeneous sensor data on different levels. The model can serve as a tool for quickly identifying risk and hazards as well as enable medical assistance systems to autonomously intervene in real-time and actively give telemedical feedback.
The central task at the University of Rostock is to create an integrated probabilistic situation model as well as the development and prototypical realization of real-time capable distributed inference methods. The integrated situation model here not only contains kinematic parameters, physiological measurements, or activity labels, but "depending on the requirements of the application" has to mirror a preferably holistic picture of a person's state within his/her environment. It will be represented by a probabilistic generative state space model (state of the environment, location, motion state, physiological parameters, cognitive and emotional state, activity goals) and can be realized for example in form of a Dynamic Bayesian Network. Because of the real-time requirement of the application it is crucial to efficiently make use of the underlying computing platform as much as possible.
In summary the following targets can be identified:
- Requirement analysis of hard- and software for distributed real-time capable inference methods
- Probabilistic generative system model
- Observation model for heterogeneous noisy sensor data
- Energy reduction and synchronization approaches for heterogeneous on-body sensor networks
- Real-time capable distribution of inference algorithms
- Example application with real-time feedback for people with cognitive impairments
- Project title: fast care: Real-time Sensor Data Analysis Framework for Intelligent Assistance Systems
- Sub-project at MMIS: Distributed Inference Methods on Multi-Sensor Platforms
- Project homepage: https://de.fast-zwanzig20.de/gesundheit/fast-care/
- Runtime: Aug. 2016 / Jul. 2019 (our subproject: Nov. 2016 - Jul. 2019)
- Sponsor: German Federal Ministry of Education and Research (BMBF), grant number 03ZZ0519D
- Reference number: 03ZZ0519D
- A. Hein, F. Grützmacher, C. Haubelt, and T. Kirste, “Fast care – real-time sensor data analysis framework for intelligent assistance systems,” Current Directions in Biomedical Engineering, vol. 3, no. 2, pp. 743-- 748, Jan. 2017.