We are involved in many projects of the EU, the BMBF (Germany's Federal Ministry of Education and Research), the BMWi (Germany's Federal Ministry of Economy and Energy) and the DFG (German Research Foundation). Our main projects are listed below.
FWLeck - Detection and localisation of leakages in district heating networks applying model-based and data-driven approaches
Funding: BMWi (FKZ 03ET1236B) Duration: November 2018 - October 2021
The project partners develop different approaches for a method to detect and subsequently localise leakages within district heating networks. All partial methods are based on pressure and flow measurement devices already available in the district heating network. The development of the following partial methods is planned: a stationary district heating network model which estimates all pressure and flow values of the network and performs the leakage detection and localisation based on the estimation results; a data-mining model which recognises leakages based on sample data sets of both the damagefree and the damaged case; and a method for the recognition and evaluation of pressure waves resulting from leakages which propagate through the district heating network. The single methods are to be examined with respect to possible synergy effects and shall be combined into a total method. The purpose is to localise the leakage in operation to at least an exclusion area so that the network provider is able to take countervailing measures to maintain the operation of the network.
Project partners: Stadtwerke München; Institut für Information Engineering, Ostfalia-Hochschule Wolfenbüttel; Institut für Automatisierungstechnik, Universität Bremen; Entwicklungsbüro für physikalische Technik Christian Lukas.
MEMoRIAL-M1.10 | Deep learning for interventional C-arm CT
Funding: EU - ESF Sachsen-Anhalt Duration: November 2018 - April 2022
The CT reconstruction task, addressing the determination of an underlying 3D volume from a series of projections, corresponds to the solution of a huge system of linear equations. Modern deep-learning methods provide an effective tool to perform such tasks. To date, CT scans always acquire a complete set of x-ray projections of the examination object disregarding the fact, that it might be about one and the same patient being multiply and/or repeatedly screened. Moreover, complete CT scans result in identically high doses of ionising radiation as well as long scan durations.
Prior knowledge e.g. including generalisable information on human anatomy or even the availability of individual data based on previous, patient-specific scans is presently not taken into account. This holds particularly true for image-guided interventions such as inserting a needle into a tumour for the purpose of ablation. The associated exposures only differ with respect to the needle's position - an information being derivable also from a single projection within the scope of a suitable setting. The aim of this sub-project is to study, whether CT reconstruction by means of deep learning methods allows for the imaging and detection of very small changes of the scene based on a number of relevant projections as minimal as possible. If applicable, significantly reduced radiation doses linked to shorter scan times may result, enabling the real-time imaging during interventions.
Characterization and Modelling of Information Seeking Dialogues (as part of IAIS)
Funding: EU - EFRE Sachsen-Anhalt Duration: January 2018 - December 2020
Intention-based, anticipatory, interactive systems (IAIS) utilize from signal data derived action- and system intentions as well as the user’s affective condition. Via anticipation of the user’s further actions and intentions, solutions are interactively negotiated. A sequence of successive interaction steps can be considered as a dialogue between the user and the system. The goal is to design the dialogue in a way that a positive user experience can be achieved. Dialogues that have to leave the premeditated progression due to a missing gap of information, that has to be closed, are particularly challenging but for problem solving, such information-seeking dialogues are a fundamental process and hence a crucial aspect of IAIS.
Within the sub project "Characterization and Modelling of Information Seeking Dialogues" information-seeking dialogues are investigated with an emphasis on exploratory search. Here the user has initially no distinct objective and can formulate his (complex) information needs only vague. During the dialogue with the system the objectives can be specified. This requires the system to methodically adapt the interface to the user’s individual requirements and hence to provide an appropriate user support. For such an assistance currently a generalized, pattern-based approach is missing. Reasons for that are on the one hand that the information-seeking behavior is still not completely investigated and understood. On the other hand, it is not obvious how to model the user’s seeking behavior considering various contexts and interaction modalities to anticipate the user’s current information need. Therefore, within the sub project the information-seeking behavior is investigated in more detail and models that characterize the information-seeking dialogues are developed to consider user’s information access tactics, global- and local structures of the dialogue as well as information about the context.
InnoX - Technologies for supporting the explorative rating of the innovation level
Funding: ZIM BMWi Duration: July 2015 - June 2017
The project "InnoX" deals with the development of concepts for the rating of the innovation level as well as the assessment of technological trends. The central component is a support of the user during the estimation of the innovativeness of scientific and technical documents. The estimation will be bound to the context of the company and will be embedded in different application scenarios. An assessment of various trend and innovation factors will be possible. With the help of user feedback, an individualisation of the system takes place, which enhances the explorative rating process. This project is a cooperation project with the EFB and METOP.
Computational Intelligence for Complex Structured Data
Funding: Australian Research Council Duration: 2014 - 2017
This project is to investigate adaptive natural human pointing and gestures to control an interface on a pseudo-3D display. Highly complex data with interconnections between elements is hard to visualize on screens, such data could be networks of academic citations, or named entities in an investigation. Most current tools are operated using point/click/drag metaphors on 2D screens. The physical technology to capture appropriate human behaviours exists already, but not the adaptive learning of the syntax & semantics of individual gestures and actions, nor the multi-gesture information fusion required for 'understanding'. All of this is done naturally by most human beings, using biological neural networks.
- partiMAN the participation manager for collaborative decision making
Funding: BMBF Duration: November 2014 - October 2017
Further information about the project can be found here.
- EU COST Action KEYSTONE: Semantic keyword-based search on structured data sources
Funding: EU Duration: June 2013 - May 2017
The research group participates in the EU COST Action IC1302: Semantic keyword-based search on structured data sources (KEYSTONE). The proposes to join synergies from several disciplines, such as semantic data management, the semantic web, information retrieval, artificial intelligence, machine learning, user interaction, service science, service design, and natural language processing. Andreas Nürnberger is Management Committee member for Germany.
- Characterization and Modelling of Information Seeking Dialogues (as part of SFB transregio 62)
Funding: Deutsche Forschungsgemeinschaft (DFG) Duration: January 2013 - December 2017
This project studies information seeking dialogues with a special focus on exploratory search. In exploratory search, the user is usually not able to clearly specify the information need and iteratively refines it in an information seeking dialogue while using the search system. This project will develop information behaviour models in order to characterize these dialogues. The obtained models consider interaction logs and also the user's emotions and disposition on different time scales and granularities. Further information about the SFB Transregio 62: http://www.sfb-trr-62.de/
- EU COST Action MUMIA: Multilingual and multifaceted interactive information access
Funding: EU Duration: December 2010 - November 2014
The research group participates in the EU COST Action IC1002: Multilingual and multifaceted interactive information access (MUMIA). This action coordinates collaboration between the research disciplines Machine Translation, Information Retrieval and Multifaceted Interactive Information Access, fostering research and technology transfer in these areas. The core focus is on research within the specific context of patent search and other next generation Web applications. Andreas Nürnberger is, together with Norbert Fuhr Management Committee member for Germany. The action will be active until November 2014.
ViERforES - Virtual and Augmented Reality for maximum Safety and Reliability of Embedded Systems
Funding: BMBF Duration: September 2008 - September 2013
ViERforES is the acronym for “Virtual and Extended Reality for the highest Security and Reliability in Embedded Systems.” The researcher team is using virtual and extended-reality techniques to look specifically at embedded systems such as control software and the microprocessors that form the core of many of today’s products. Researchers of the Otto von Guericke University Magdeburg, engineers from the Fraunhofer IFF Institute, experts from the Fraunhofer IESE Institute and the Technical University of Kaiserlautern are involved. Regional companies provide assistance by testing results in real situations. Further information can be found here (in german).
- SENSE - Management solution for intelligent usage of multimedia document sets
Funding: BMBF (FKZ 01IS11025E) Duration: January 2012 - December 2013
Project partners: Fink & Partner Media Services GmbH, Dresden; Point Software & Systems GmbH, Siegen; planConnect, Dresden; Heinz-Nixdorf-Seniorprofessur für Multimediatechnik, TU Dresden; Data & Knowledge Engineering, Otto von Guericke University Magdeburg. Further information can be found here (in german).
Bisociation Networks for Creative Information Discovery (BISON)
Funding: EU (FP7 FET Open Project) Duration: June 2008 - May 2012
BISON is a research project funded by the European Commission under the Seventh Framework Programme. The goal of BISON is to explore the concept of bisociative discovery on the basis of graph-based data mining. While current ICT approaches provide methodologies and tools for association-based search and processing of information, there is currently no comprehensive ICT methodology or tool which facilitates the bisociative exploration for discovery and design tasks. The overall aim of the BISON project is to develop and validate a computational methodology, which facilitates bisociative information discovery in large-scale heterogeneous information environments. Detailed Information about this project can be found at http://www.bisonet.eu.
Adaptive and User Centered Methods for Organisation und Exploration of Digital Music Archives (AUCOMA)
Funding: Deutsche Forschungsgemeinschaft (DFG) Duration: January 2008 - March 2012
Automatic structuring is one means to ease access to large music collections - be it for organisation or exploration. The AUCOMA project (Adaptive User-Centered Organization of Music Archives) aims to find ways to make such a structuring intuitively understandable to a user through automatic adaptation. Further information can be found here: http://www.findke.ovgu.de/findke/en/Research/Topics/Music+Retrieval.html
Computer generated expressive Music Sonification for Musicology
Funding: Land Sachsen-Anhalt Duration: September 2008 - March 2011
A joined research project between the research groups Visual Computing and Data & Knowledge Engineering of the Faculty and the Zentrum für Telemannpflege und -Forschung Magdeburg.
Adaptive user interfaces for search and navigation in document collections
Funding: Deutsche Forschungsgemeinschaft (DFG) as part of the Emmy Noether Programme. Duration: May 2003 - August 2009
During the last years several approaches have been developed that tackle specific problems of the retrieval process, e.g. feature extraction methods for multimedia data, problem specific similarity measures and interactive user interfaces. These methods enable the design of efficient retrieval tools if the user is able to provide an appropriate query. However, in most cases the user needs several steps in order to find the searched objects. The main reasons for this are on the one hand, the problem of users to specify their interests in the form of a well defined query (which is partially caused by inappropriate user interfaces), on the other hand, the problem of extracting relevant features from the (multimedia) objects. Furthermore, user specific interests and search context are usually neglected when objects are retrieved.
To improve today's retrieval tools and thus the overall satisfaction of a user, it is necessary to develop methods that are able to support the user in the search process, e.g. by providing additional information about the search results as well as the data collection itself and also by adapting the retrieval tool to the user's needs and interests.
Nature-inspired Smart Information Systems (NiSIS)
Funding: EU (Coordination Action) Duration: February 2005 - January 2008
Detailed Information about this project can be found at www.nisis.de.
Building Personalised off-line Self-Service Repositories
Funding: British Telecommunications Duration: October 2005 - October 2007
User Adaptive Search Interfaces
Funding: European Network on Intelligent Technologies for Smart Adaptive Systems (EUNITE) Duration: December 2002 - June 2004
This task force has been formed as part for the European Network of Excellence on Intelligent Technologies for Smart Adaptive Systems (EUNITE) to review the state of the art in user adaptive search interfaces and to initiate and intensify research collaboration between different research communities and the industry.
For further details see the project page.