Technical reports / Department Informatik
- MATINEE: A Quality-of-Service-aware Event Semantics Modeling Language (2014)
- Distributed event-based systems have risen in significance over the last few years across many different application domains. Still, the configuration of available communication middleware solutions remains an elaborate task driven by technical terms and manual performance optimization. We present the M2etis Quality-of-service-aware Semantics Modeling Language (MATINEE), a domain-specific language for modeling the QoS requirements and semantic properties of event-based systems in the terminology of the application domain. No knowledge of the technical terms of the underlying middleware solution is required by the application developers to conduct the configuration. Embedded in a novel configuration methodology provided by the M2etis project, MATINEE specifications are interpreted to automatically derive optimal middleware configurations without the need for manual optimization. The purpose of MATINEE is to provide a flexible language that can easily be adapted to different application domains. We focus on the language specification of MATINEE, briefly sketch our configuration methodology and present related language approaches.
- DEUS: Distributed Electronic Patient File Update System (2012)
- Inadequate availability of patient information is a major cause for medical errors and affects costs in healthcare. Traditional approaches to information integration in healthcare do not solve the problem. Applying a document-oriented paradigm to systems integration enables inter-institutional information exchange in healthcare. The goal of the proposed architecture is to provide information exchange between strict autonomous healthcare institutions, bridging the gap between primary and secondary care. In a long-term healthcare data distribution scenario, the patient has to maintain sovereignty over any personal health information. Thus, the traditional publish-subscribe architecture is extended by a phase of human mediation within the data flow. DEUS essentially decouples the roles of information author and information publisher into distinct actors, resulting in a triangular data flow. The interaction scenario will be motivated. The significance of human mediation will be discussed. DEUS provides a carefully distinguished actor and role model for mediated pub-sub. The data flow between the participants is factored into distinct phases of information interchange. The artefact model is decomposed into role-dependent constituent parts. Both a domain specific (healthcare) terminology and a generic terminology is provided. From a technical perspective, the system design is presented. The sublayer for network transfer will be highlighted as well as the subsystem for human-machine interaction.
- The Erlangen Glaucoma Registry: a Scientific Database for Longitudinal Analysis of Glaucoma (2011)
- Background: Due to the slow progression of the Glaucoma disease, a large study population and long-time observations are needed to gain insights into its long-term effects and progression rates. Since modalities can export data in machine-readable formats, statistical analyses of the large number of examinations is feasible. These data have been integrated in a central patient registry, the Erlangen Glaucoma Registry (EGR). Objectives: The primary focus of the EGR system design has been its fitness for analyses. It holds almost all the available research data for registered glaucoma patients. This allows for cross-sectional and longitudinal observations and for evaluation of prognostic validity of diagnostic procedures. Methods: An adequate technology for integration of data and flexibility in data analysis is a database management system (DBMS). Here, a careful schema design is mandatory. Adding new modalities leads to schema modifications which are supported by defining a core database schema and attaching all data to this core. On that basis, a large number of modalities have been connected to the EGR. Results: The registry contains data of 1,400 patients in the main longitudinal study. It has successfully helped in scientific research, as can be seen in a large number of published papers. For example, validation of new sensory physiological methods requires patients with reliable diagnoses. The existence of a well-documented patient collective facilitated finding such patients. Conclusions: The EGR holds a unique amount of available data gathered in large longitudinal studies. It was successful in terms of medical results obtained. Developed as an evolutionary system, it can easily be extended.