TLDia - Transfer Learning for Medical Diagnosis
Creation of automated classification of clinical documents with self-learning algorithms for coding of medical documentation and for medical automated risk analysis for insurances.
The project TLDia is a cooperation with THM Friedberg ans the company Minds-Medical. It has received a two-year funding from the Hessian„Landes-Offensive zur Entwicklung Wissenschaftlich-ökonomischer Exzellenz“ (LOEWE) under grant no. 701/19-21.
EVER 2 - Extraction and Processing of Procedural Experiential Knowledge in Workflows - Quality, Interactivity, and Transferability
The project examines new possibilities for the transfer of workflows from one well-known source domain in a new target domain, where the knowledge is sparse. In the first stage we investigate ontologies as a means for the transfer. The publication Ontology-based representation of workflows for transfer learning describes an approach for representing BPMN-workflows in an ontology. The next steps of the project comprise the automation of the suggested approach and the abstraction and generalization of workflows. These concepts should facilitate the transfer of knowledge in a new domain. One next project objective is the extension of the methods to various partner domains.
The project EVER 2 is funded by the Deutsche Forschungsgemeinschaft (DFG) under the number MI 1455/2-3. It is conducted in co-operation with the University of Trier during the period 2017-2020.
EVER - Extraction and Case-Based Processing of Experiential Knowledge from Internet Communities
Today’s Social Web allows people in a community of practice to post their own experiences in a diversity of content repositories such as blogs, forums, Q&A websites, etc. However, today there is no real support in finding and reusing these rich collections of personal experience. Current search functions available merely consider experience as text to be indexed as any other text and searched and found as any other document.
The objective of the project cluster Extraction and Case-Based Processing of Experiential Knowledge from Internet Communities is the analysis, the development, and the experimental application and evaluation of new knowledge-based methods, particularly from case-based reasoning (CBR), information extraction, and machine learning to extract and process experiences in Internet communities.
The project cluster consists of three projects led by the University of Marburg, the University of Trier, and the Goethe University Frankfurt. All have chosen the field of cooking as a joint application domain to demonstrate and to empirically evaluate the developed methods.
CAKE (Collaborative Agile Knowledge Engine) is a software system for workflow reasoning. Originating from the University of Trier, CAKE is developed further on in close cooperation with the University of Trier. The main components are a Web-based workflow design tool called CAKEflow, a workflow enactment service for the execution of agile workflows that might be changed during run-time, and a case-based reasoning component for the retrieval and adaptation of workflows.
CAKE serves as a platform for design-oriented research on business information systems, especially for experiments and further prototyping.