Sebis Research News

Paper titled Paper titled Automatic Relation Extraction for Building Smart City Ecosystems using Dependency Parsing accepted at NL4AI.

Understanding and analysing rapidly changing and growing business ecosystems, like smart city and mobility ecosystems, becomes increasingly difficult. However, the understanding of these ecosystems is the key to being successful for all involved parties, like companies and public institutions. Modern Natural Language Processing technologies can help to automatically identify and extract relevant information from sources like online news and blog articles and hence support the analysis of complex ecosystems. In this paper, we present an approach to automatically extract directed relations between entities within business ecosystems from online news and blog articles by using dependency parsing.

In the era of digitalization, IT landscapes keep growing along with complexity and dependencies. This amplifies the need to determine the current elements of an IT landscape for the management and planning of IT landscapes as well as for failure analysis. The field of enterprise architecture documentation seeked for more than a decade for solutions to minimize the manual effort to build enterprise architecture models or automation. We summarize the approaches presented in the last decade in a literature survey. Moreover, we present a novel, machine-learning based approach to detect and to identify applications in an IT landscape.

In recent years, personalized connected care has become increasingly important due to the generally aging population and the rising cost pressures in the healthcare sector. Nevertheless, to the best of our knowledge, there are no off-the-shelf solutions available to provide open and adaptable information and communication technology (ICT) for connected care; the reasons for this may differ between use cases. Based on our case studies at hospitals in different European countries, we identified three main challenges of such for ICT solution: 1) the high diversity between hospital sites and treatments, 2) the embedding of information from existing information systems, and 3) the coordination and communication of the many different stakeholders. Our approach is to use a full stack modelbased solution that supports the integration, communication, and coordination of the pending work. Currently, our solution is being used for clinical trials. [link]

Integrated care approaches are becoming increasingly relevant with the current aging population. In the context of an integrated healthcare project, we developed a smart adaptive case management system for professionals that is currently being used for clinical trials. In this paper, we present the modeling requirements for integrated healthcare applications and use them to categorize and compare existing implementation approaches used in practice. [link]

Two paper from the chair have been accepted at this year's International Conference of Software Architecture in Seattle, USA:

• Manjunath A.; Bhat, M.; Shumaiev, K.; Biesdorf, A.; Matthes, F.: Decision making and cognitive biases in designing software architectures. 

• Bhat, M.; Shumaiev, K.; Koch K.; Hohenstein, U.; Biesdorf, A.; Matthes, F.: An expert recommendation system for design decision making - Who should be involved in making a design decision?