Research projects

Term: 01/01/2024 - 31/12/2024
Funding source: Siemens AG
Project leader: Richard Lenz

This research project investigates the use of unsupervised change point analysis (CPA) methods for knowledge discovery in large-scale industrial time series datasets. Change point analysis offers a promising tool to mine large time series datasets by identifying abrupt and unexpected changes in time series data without requiring supervision. Relating the detected events between multiple signals offers valuable insight into the behavior of complex, dynamical systems enabling to mine events of interest often hidden in the vast amount of data produced by the systems. We apply the methods to sensor data from combined cycle power plants with thousands of simultaneous data streams.

→ More information

Term: since 16/05/2023
Project leader: Klaus Meyer-Wegener

To test and evaluate a heterogeneous stream-processing system consisting of an FPGA-based systemon-chip and a host, we develop a benchmark called SKYSHARK. It uses real-world data from air-traffic control that is publicly available. These data are enhanced for the purpose of the benchmark without changing their characteristics. They are further enriched with aircraft and airport data. We define 14 queries with respect to the particular requirements of our system. They should be useful for other…

→ More information

Term: 01/01/2023 - 01/01/2026
Funding source: Siemens AG
Project leader: Richard Lenz

We will create a generic data quality framework which can be deployed into an evolutionary data lake environment which makes data quality quantifiable and can direct efforts for data quality improvement.

→ More information

Term: 01/04/2022 - 31/03/2025
Funding source: Siemens AG
Project leader: Richard Lenz

This research project aims to develop different efficient methods that enable knowledge mining in large time series datasets to uncover relationships and descriptive patterns within the dataset. A key focus is the identification of relationships, which are uncovered using the technique of changepoint correlation that we are actively developing within the project. As the project aims to support or even automate a manual process, visualization, and demonstration of the techniques in question also play a major role in the development.

→ More information

Term: 01/08/2021 - 31/07/2024
Funding source: Deutsche Forschungsgemeinschaft (DFG)
Project leader: Klaus Meyer-Wegener

Analysing petabytes of data in an affordable amount of time and energy requires massively parallel processing of data at their source. Active research is therefore directed towards emerging hardware architectures to reduce the volume of data close to their source and towards sound query analysis and optimisation techniques to exploit such novel architectures. The goal of the ReProVide project is to investigate FPGA-based solutions for smart storage and near-data processing together with novel query-optimisation…

→ More information

Term: 02/01/2020 - 19/09/2022
Project leader: Klaus Meyer-Wegener

The compression of data has played a decisive role in data management for a long time. Compressed data can be permanently stored in a more space-saving manner and sent over the network more efficiently. However, the ever-increasing volumes of data mean that the importance of good compression methods is growing all the time.

Within the scope of project Anania (Architecture of Non-Multiple Autoencoders for Non-Lossy Information Agglomeration), we are investigating to what extent classical…

→ More information

Term: since 01/06/2019
Project leader: Richard Lenz

Der Zweck des Semantic Web ist es, den weltweiten Zugang zum Wissen der Menschheit in maschinenverarbeitbarer Form zu ermöglichen. Ein großes Hindernis dabei ist, dass Wissen oft entweder inkohärent repräsentiert oder gar nicht externalisiert und nur in den Köpfen von Menschen vorhanden ist. Der Aufbau eines Wissensgraphen und die manuelle Erstellung und Fortschreibung einer Ontologie durch einen Domänenexperten ist eine mühsame Arbeit, die einen großen initialen Aufwand erfordert, bis das Erg…

→ More information

Term: 01/04/2019 - 30/09/2025
Project leader: Viktor Leis

→ More information

Term: 01/08/2018 - 30/09/2021
Project leader: Richard Lenz

Within the project SIML (Schema Inference and Machine Learning), methods of topological data analysis and unsupervised learning are combined, applied and further developed in order to derive a conceptual schema from unstructured, multivariant data.

→ More information

Term: 28/08/2017 - 01/03/2023
Funding source: DFG / Schwerpunktprogramm (SPP)
Project leader: Stefan Wildermann, Jürgen Teich, Klaus Meyer-Wegener

This project is funded by the German Research Foundation (DFG) within the Priority Program SPP 2037 "Scalable Data Management for Future Hardware".

The goal of this project is to provide novel hardware and optimisation techniques for scalable, high-performance processing of Big Data. We particularly target huge datasets with flexible schemas (row-oriented, column-oriented, document-oriented, irregular, and/or non-indexed) as well as data streams as found in click-stream analysis, enterprise sources like e-mails, software logs and discussion-forum archives, as well as produced by sensors in the Internet of Things (IoT) and in Industrie 4.0. In this realm, the project investigates the potential of hardware-reconfigurable, FPGA-based Systems-on-Chip (SoCs) for near-data processing where computations are pushed towards such heterogeneous data sources. Based on FPGA technology and in particular thier dynamic reconfiguration, we propose a generic architecture called ReProVide for low-cost processing of database queries.

→ More information

Term: 01/01/2017 - 31/12/2020
Funding source: Sonstige EU-Programme (z. B. RFCS, DG Health, IMI, Artemis), Bayerische Staatsministerien
Project leader: Klaus Meyer-Wegener

Within the framework of the EFRE-E|ASY-Opt subproject, the potential of data mining methods in the area of manufacturing is being investigated. Especially the training of Deep-Learning models is a computationally intensive task, which may take hours or several days. The training time can be shortened considerably by using an already trained model, as long as the goal and source task are closely related. This connection is not yet fully understood.

The aim of this research project is to implement a system called REAPER (Reusable Neural Network Pattern Repository) to support data scientists in storing and reusing already trained deep learning models.

→ More information

Term: 01/04/2015 - 31/12/2018
Project leader: Klaus Meyer-Wegener

"You should know your queries!" is the long version of the project title.  It means that you should not just want tho have a database, but you should also think about the evaluations (which are written down as queries) that you actually would like to do with that database.  The creation of a database is quite an effort, regarding not only the deployment of the software on a computer, but even more the capture of all the data to fill it.  This effort should be spent with a goal in mind.  The project will therefore collect queries, which can then even be used to automatically design a database.  This saves resources on one hand, but on the other also supports the privacy goal of data minimization.

→ More information

Term: 01/01/2015 - 30/09/2018
Project leader: Richard Lenz

Fallmanagementsysteme unterstützen Interaktionen zwischen kooperierenden Benutzern typischerweise, indem gemeinsam zu verwendende Dokumente in einem gemeinsamen Repositorium vorgehalten werden. Im vorliegenden Projekt wird untersucht, ob und wie diese Interaktionen durch Klassifikation als Sprechakte besser unterstützt werden können. Die Sprechakt-Theorie beschreibt die pragmatischen Aspekte kommunikativen Handelns. Dabei werden Äußerungen je nach der pragmatischen Intention des Sprechers in v…

→ More information

Term: 01/09/2014 - 31/12/2018
Project leader: Klaus Meyer-Wegener

The world of data-management systems has become a bit confusing during the last years.  Next to the well-established relational database systems, so-called NoSQL systems have been developed, which pretend to cope with much larger data volumes.  At the same time, they can only offer limited functionality with respect to efficient data access and can only give reduced consistency guarantees.  That raises the question when to stick to a relational database and when to move to a NoSQL system.  This project collects the criteria that allow to make such a decision on a well-founded basis.

→ More information

Term: 01/11/2013 - 31/08/2024
Project leader: Richard Lenz

Mehr und mehr Unternehmen sammeln möglichst alle anfallenden Daten in sogenannten "Data Lakes". Obwohl die Daten damit prinzipiell für beliebige Analysen zur Verfügung stehen, bleibt es dennoch unerlässlich für die Analyse, ein Verständnis für die Bedeutung und die Verknüpfungsoptionen der Daten zu entwickeln. Analysten, die diese Arbeit bereits geleistet haben, formulieren Anfragen, in denen solches Wissen implizit enthalten ist. Wenn dieses Wissen jedoch nicht mit anderen geteilt wird, bleiben…

→ More information

Term: 01/08/2012 - 31/12/2018
Funding source: DFG / Forschungsgruppe (FOR)
Project leader: Klaus Meyer-Wegener

Animal observation can be improved significantly with the help of modern technology.  Especially in the case of bats this has been quite difficult in the past, because they are active only at night, and they must not carry a transmitter heavier than 10% of their own body weight.  The progress of micro electronics has made it possible to build complete computers that fulfill these requirements.  They do not just send beacons, but data.  The ground station receives these data and evaluates them.  That begins with the position of the bat, continues with meetings with other bats (of particular interest: mother and child), and ends with body temperature, pulse, and other biosensors.  The data are collected and evaluated as a whole.  Unfortunately, they are rather imprecise and also flawed.  So it is a substantial issue to clean them first.  The far-end goal of the project is to capture only data actually needed for the evaluations given, thus saving energy and allowing to observer the bats even longer.

→ More information

Term: 01/11/2011 - 31/12/2013
Funding source: BMFTR / Spitzencluster
Project leader: Richard Lenz

Die Integration von Medizinprodukten in die realen Abläufe und Arbeitsprozesse einer Produktivumgebung ist sowohl für Hersteller wie auch Betreiber eine schwierige, zeit- und kostenintensive Aufgabe. Trotz Standardisierung von DICOM und HL7 bereitet die Integration von Softwarekomponenten und Medizinprodukten in ein Krankenhausinformationssystem wegen fehlender geeigneter Validierungsumgebungen immer noch einen erheblichen Aufwand. Gegenstand des Projekts ist die Erstellung einer generischen…

→ More information

Term: 15/01/2009 - 15/02/2012
Funding source: Industrie
Project leader: Richard Lenz

Der Einsatz IT-gestützter Prozesse im Kraftwerksbau in den Bereichen Engineering, Procurement and Construction (EPC) nimmt immer mehr zu, wodurch derQualität der Daten in den IMS (Information Management Systems) immer mehr Bedeutung zukommt. Unter IMS werden in diesem Zusammenhang im Wesentlichen die Software-Produkte Vantage Plant Engineering (VPE), Vantage Plant Design (VPD)und Vantage Project Resource Management (VPRM) sowie die angrenzenden Tools(z.B. MOM, PIS, DM, etc.) verstanden.…

→ More information

Term: 01/10/2008 - 30/09/2017
Project leader: Klaus Meyer-Wegener

DSAM is a middleware for managing global data-stream queries. These queries are distributed to heterogeneous platforms including self-contained data-stream management systems and sensor networks. The project's main goal is to automatically distribute and deploy a platform-independent model, i.e. a global query, to heterogeneous and distributed stream-processing components. Queries are defined in a declarative abstract query language. They are partitioned according to cost models and topological constraints. DSAM then generates queries in the target systems' query language, each implementing a partial query. For sensor networks, we additionally adopt source-code generation. Further challenges are monitoring, efficient metadata management and decentralized query management, especially in the context of wireless sensor networks.

→ More information