Projects

docQuery - An Intelligent Information System on Travel Medicine (2007- )

docQuery is a project together with mediScon worldwide which aims to develop a collaborative multi-expert system on travel medicine, because it has never been easier than today traveling to different places, experience new cultures and get to know new people. In preparation for a healthy journey it is important to acquire high quality of reliable information about travel medicine prevention.

Currently the World Wide Web offers many websites, discussion forums and services where a traveler can gather information. Usually those websites do not contain all medical information a traveler might need and the editors are mostly unknown. Furthermore the information is spread over hundreds of websites and it is challenging and time-consuming to find appropriate one. Together with mediScon, a team of certified doctors of medicine with a strong background of tourism related medicine, we will implement docQuery to provide travel information based on key data of their journey and travellers (travel period, destination, age(s) of traveller(s), activities, etc.).
Software agents will be used following all kinds of tasks like creating an appropriate question structure avoiding redundant questions or extracting information given in the knowledge bases and creating responses. docQuery will be supervised by experts, although it will integrate the experiences of travellers using the given advices to improve the quality and identify new issues early and providing information about it.

Victory - Audio-Visual Content Search and Retrieval in a Distributed P2P Repository (2007- )

We are subcontractor in Victory that is a EC co-funded research project. It will develop an innovative, distributed search engine, introducing MultiPedia search and retrieval capabilities to a standard (PC-based) and a mobile P2P network. A MultiPedia object is defined as a 3D object along with its accompanied information i.e. 2D views, text, audio, video.

empolis GmbH (2006- )

Cooperation with empolis on research topics like distributed learning systems, knowledge-lines, development of an open source framework for advanced query processing, and healthcare applications.

ChipsandMore GmbH (2006- )

ChipsandMore is a global distributor of franchised and non-franchised electronic components, with a growing customer base of over 8000 OEMs, CEMs, Distributors and Traders throughout our worldwide network. With offering all kind of active, passive and emec electronic components, customer-specific procurement solutions, just-in-time-services, state-of-the-art software development and a growing inventory, they evolved into a global distributor. Since the beginning in 1997, their sales growth is matched only by their commitment to talented team members that extend the most value to their customers. With their defined commitment to excellence and the opening of a branch structure back in January 2000, ChipsandMore established strategic global partnerships and grew into an innovative partner for the entire electronics industry. ChipsandMore brings together logistics and software solutions of the twenty first century backed by a team of skilled sales & engineering professionals committed to one goal.

Currently, ChipsandMore - in collaboration with IIS - develops an intelligent sales support solution to become even more beneficial for their customers.

T-Vos GbR (2005- )

In German only:


Die Firma T-VOS GbR mit Firmensitz in Hannover ist ein deutschlandweit operierendes Dienstleistungsunternehmen, welches für Versicherungen die Schadenshergangs- sowie die Reparatur- bzw. Wiederbeschaffungskostenermittlung übernimmt. Dies erfolgt vorerst im Bereich Elektro-Elektronik. In den kommenden Jahren plant die Geschäftsführung eine Erweiterung der Tätigkeitsfelder, so zum Beispiel KFZ- und Baugutachten. Hierfür ist - in Zusammenarbeit mit IIS - eine Erweiterung der bestehenden Software mit intelligenten Technologien wie Erfahrungsmanagement und Multiagentensystemen zur Unterstützung bei der Ursachendiagnose, Plausibilität des Schadenshergangs und der Preisfindung für Wiederbeschaffungs- und  Reparaturkosten notwendig. Weiterhin sollen intelligente Mechanismen bei der Einsatzplanung der Techniker implementiert werden.

RISE (2003-2004)

The goal of RISE was to provide a comprehensive solution for the reuse of products, methods, models, and experiences in software engineering.
The starting point for this development was how defects are dealt with in software development. This results in a process for practicable software engineering that is particularly tailored to SMEs.
Beyond that, such a process can be the starting point for further software engineering activities. This defect management is seamlessly integrated into the respective SME's feature- and configuration management.

indiGo (2001-2003)

The goal of the indiGo project was the development of an integrated solution for process-oriented knowledge management in a software engineering environment. indiGo supports both the evaluation and improvement of process models and the introduction of processes into an organization.

IPQ (2001-2003)

The IP-based system-level modeling and simulation design methodology represents a breakthrough in current design methodology, which has a strong impact on competitiveness. The main goal of this project is to address the qualification and reuse of intellectual property (IP) in current system design in networking, high-speed links, multimedia, and automotive domains by using system-level modeling and verification techniques. This will include design reuse with qualified and parametric IP cores and a seamless design flow integrating existing and emerging tools. It will enable the improvement of developed tools and possible future commercialization.

ToolIP (2001 - 2003)

TOOLIP's (Tools and Methods for IP) main goal is to address the complexity of current system design in networking, high-speed links, multimedia and automotive domains by using system-level modeling and verification techniques, applying design reuse with qualified and parametric IP cores, and providing a seamless design flow integrating existing and emerging tools. The industrial partners and their applications will be the driving forces of TOOLIP. The close cooperation of IP users, IP providers, designers and research institutes constitutes one of the major potentials of the consortium. TOOLIP will be crucial to the positioning of European industry, since the IP-based system-level modeling and simulation design methodology represents a breakthrough in current design methodology, which would lead to a strong impact on competitiveness and standardization. Furthermore, TOOLIP will enable the improvement of developed tools and possible future commercialization. By establishing a team with the required know-how, TOOLIP will also present new business opportunities, which would facilitate the creation of spin-off companies.

MILOS (1998 - 2000)

The MILOS Project (Minimally Invasive Long-term Organisational Support) is a joint project of the Artificial Intelligence Group at the University of Kaiserslautern and the Software Process Support Group at the University of Calgary. Software engineering processes are highly creative and therefore prone to frequent changes through both, the planning phase and process enactment. Software projects often extend over a long period of time making it impossible to plan the project in detail before process execution starts. Information necessary to complete the plan may not be available at the planning stage but is gathered as part of the process itself. Due to the long project duration, and to the fact that experience with a particular kind of software project is often gained only while executing this project, project plans often turn out to be inadequate. Further, products of the software process are seldom correct "at first try". Usually, several rework circles have to be done, with changes made to products, which in turn necessitate more changes to keep products consistent with each other. In large, distributed software projects, these changes can easily lead to problems: some concerned people may not be informed of the change in time to adjust their own products before a deadline, or perhaps are not notified of the change at all.

WiMo: Knowledge engineering for case-based reasoning (1995-1996)

The WiMo project was carried out at the University of Kaiserslautern in tight collaboration with tecInno GmbH. The goal of this project was to improve case-based reasoning methods for classification tasks, developed at the University of Kaiserslautern, particularly in the INRECA project, for their practical industrial use. The project contributed to the development of methods and tools for modelling the required knowledge of an application area, the development of tools for case acquisition, the development of a CBR server Web server, the development of an enhanced consultation system. Within this project, the prototype of the of the CBR -Works tool was developed and an evaluation copy was distributed to more than 400 people world-wide via the internet. Since May 1996, tecInno GmbH (now: empolis GmbH) is successfully marketing a commercial version of CBR-Works.

INRECA: Induction and Reasoning from Cases (1991-1996)

The ESPRIT project INRECA offers tools and methods for developing, validating, and maintaining decision support systems. Inreca's basic technologies are inductive and case-based reasoning. Induction extracts decision knowledge from case databases. It brings to light patterns among cases and helps monitoring trends over time. Case-based reasoning relates the engineer's current problem to past experiences. Inreca fully integrates both techniques within one environment and uses the respective advantages of both technologies. Inreca offers hypermedia interfaces and graphic browsers. Its object-oriented representation language CASUEL allows the definition of complex case structures and relations. The descriptive model editor is used to interactively define classes, objects, attributes, and relations. The case manager uses this information to build automatically a questionnaire for collecting cases. The questionnaire can be customized and hypermedia entities - such as sound, drawings, pictures, and videos - may be integrated.

VEGA (1993 - 1996)

The VEGA (Validation and Exploration by Global Analysis) research project aims to provide a structured framework for the VALIDATION and EXPLORATION of knowledge bases (KBs) by global analysis. This knowledge EVOLUTION framework will be offered to developers and users of KBs. While much knowledge is acquired and represented in KBs, often its interconnections remain unexplored (lack of discovery support) and its content is not validated (lack of quality control). Expert systems accessing such KBs suffer from the resulting brittleness. Knowledge engineers shall thus interact with the VEGA system for evolving (i.e., exploring and validating) KBs represented in a highly portable (declarative) language. Solution Approach: Provide a language for both problem solving and KB evolution, representing knowledge at a high level of abstraction, and translators from existing KBs to that language. Supply techniques for KB exploration and validation, combining global-analysis and knowledge-transformation methods with scalable, symbolic machine-learning mechanisms. Develop a methodology for exploring hypotheses formulated in the KB language and feeding back interesting, validated patterns into the KB.

Moltke: Workbench for Technical Diagnosis (1986-1996)

In German only:


Zielsetzung des Moltke-Projektes ist die wissens­basierte Entscheidungs­unter­stützung für die Diagnose technischer Systeme. Hierzu wurde eine Familie von Systemen implementiert und an mehreren realen Anwendungen evaluiert. Die jeweiligen Systeme basieren auf verschiedenen Grund­architekturen, die jeweils unter­schiedliche Schwerpunkte setzen hinsichtlich der Verarbeitung der in technischen Domänen vorhandenen Wissens­arten wie Wissen über die Funktion und das Verhalten einer Maschine, abstraktes Diagnosewissen der jeweiligen Experten sowie Fall­wissen.
Verwendete Methoden sind im einzelnen qualitatives, fallbasiertes, induktives und assoziatives Schließen sowie Techniken aus den Bereichen erklärungs­basiertes Lernen, Neuronale Netze und Hypermedia. Forschungs­schwer­punkte sind dabei fallbasierte Entscheidungs­unter­stützung, Hypermedia sowie integrierte Problemlöse- und Lern­architekturen.