Seiteninhalt Hauptmenü Portalmenu Seitenmenü Schriftgröße ändern Breadcrump Index Suche
ISBI
Seite drucken

Schriftgröße ändern

Seiteninhalt

Projects


 
The following eclectic list shows the variety and diversity of the research projects at the Departments of Informatics. Information to further projects is available on request at the individual offices. 

 
HINT
Available1.6.2013 - 31.5.2016
Sponsored byFFG Forschungsförderungsgesellschaft
Cooperation(s)University Oxford, Siemens Corporate Research, Infineon Technologies Austria
ContactDI Dr. Gerhard Friedrich (Projektleitung)
E-Mail
Phone+43 (0)463 2700 3705
Fax+43 (0)463 2700 99 3705
DescriptionHINT verfügt über ein Projektvolumen von rund 1,13 Mio Euro und zielt darauf ab, die Stärken menschlicher Problemlösungsstrategien für die Künstliche Intelligenz stärker nutzbar zu machen. Der Hintergrund ist jener, dass viele Methoden der Künstlichen Intelligenz trotz immer verbesserter Algorithmen und schnellerer Computerhardware bei komplexen Aufgabenstellungen versagen. Das Problem, welches auch voraussichtlich mit zukünftigen Computersystemen bestehen bleiben wird, ist die enorme Größe des Suchraumes, welcher zur Lösungsfindung durchforstet werden muss. Interessanterweise kommen Menschen mit solch riesigen oder sogar unendlichen Suchräumen sehr viel besser klar, da der Suchraum aufgrund von Intuition  reduziert und erforscht wird. Solch intuitive Lösungsstrategien - in der Fachsprache Heuristiken genannt - sind mittlerweile auch in der Künstlichen Intelligenz mit großem Erfolg im Einsatz. Jedoch ist die Definition und der Einbau von Heuristiken typischerweise nur mit erheblichem menschlichem Aufwand  möglich, da effektive Heuristiken bisher fast immer durch Experten gefunden und definiert werden. Das automatische Finden und Adaptieren von Heuristiken für neue Probleme ist bis jetzt in nur einem sehr eingeschränkten Maße möglich. Genau das hat sich Prof. Friedrich mit seinem Projektteam nun zum herausfordernden Ziel gesetzt, nämlich Methoden zu entwerfen, welche es ermöglichen, Heuristiken automatisch für neue Probleme zu generieren und für ähnliche Probleme zu adaptieren. Praktische Anwendungen gibt es für solche Methoden viele. So sind z.B. die Konfiguration von komplexen Systemen bei Siemens wie auch die Berechnung von optimierten Produktionsabläufen bei Infineon wichtige industrielle Anwendungsfälle.
Further Information

Anfang


O-STAR
Available1.1.2012 -31.12.2014
Sponsored byInterreg (EU)
Cooperation(s)Universität Bozen, EURAC Projektdata, Tourismusverband Bad Kleinkirchheim, TVB Latsch/Martelltal Amt der Südtiroler Landesregierung
Contactassoc. Univ.-Prof. DI Mag. Dr. Markus Zanker
E-Mail
Phone+43 (0)463 2700 3705
Fax+43 (0)463 2700 99 3705
DescriptionNowadays, internet users are confronted with an oversupply of information and thus, often overstrained with the process of decision making. Recommender systems can contribute considerably to simplifying decision making e.g. in the area of free time activities. At the same time, underdeveloped areas can be better positioned in this market segment.

The goal of this project is to develop a prototype, connecting the know-how of the different partner institutions (EURAC, University of Klagenfurt, Free University of Bolzano and 9.6 Office for Spatial and Statistical Data of the Autonomous Province of Bolzano – South Tyrol) about recommender systems, geographical databases and isochrones. This way, spatial aspects and geographical information are both taken into consideration and the end user receives personalized route recommendations, which he or she can look up with the help of a digital map.

However, detailed information requires detailed data. Therefore, a major part of this project is the data collection as well as to create a unified data infrastructure (geo information). The developed prototype will finally be implemented in the two pilot regions (Viva Latsch Ltd., Bad Kleinkirchheimer Tourism Marketing Ltd.). Especially structural weak regions will profit from this approach, since they will be supported with increasing the attractiveness of their location. Thus, they can withstand the pressure of global competition.

Further Information

Anfang


Reconcile
Available1.6.2010 - 30.5.2013
Sponsored byFFG Forschungsförderungsgesellschaft
Cooperation(s)Siemens Corporate Research, Infineon Technologies Austria
ContactO. Univ.-Prof. DI Dr. Gerhard Friedrich
E-Mail
Phone+43 (0)463 2700 3705
Fax+43 (0)463 2700 99 3705
DescriptionThe success of Semantic Systems has led to large instantiations of ontologies which serve as a description of various systems and state of affairs. E.g. such instantiations (also called configurations) specify the structure and properties of Web sites, business processes or technical systems and may comprise more than one million entities. In this context, ontologies describe the allowed configurations and their costs. However, ontologies are not stable but change over time. In this case, the configurations have to be changed in order to reflect the alterations of the ontology. This change is represented by a modification of the ontology instantiation. The generation of this modified instantiation is a complex optimization process for various reasons. In particular, this reconciliation process (called instance reconciliation) must decide which legacy instances can be reused and which new instances must be generated such that the overall set of instances obey the constraints of the new ontology. In addition, the costs of changing a configuration must be minimized. Consequently, a major aim of RECONCILE is to develop a reconciliation language on top of a logical description language that allows the expression of change-knowledge and change-costs. Because of the size of the problems and our practical experiences regarding the expressivity of required language constructs, we expect as a major challenge for RECONCILE the development of feasible problem solving methods. Practical experiences in similar domains (like constraint-based configuration) show the high utility of heuristic search as well as problem decomposition techniques. Consequently, we will explore the application of these techniques for the reconciliation of instances with changed ontologies. Moreover, we will support the users with debugging and repair methods for formulating change-knowledge. All methods are evaluated by proof-of-concept prototypes and examples of real world applications.
Further Information

Anfang


C2DSAS
DescriptionCommand and Control Decision Support and Advisory Services

The C2DSAS project aims at developing innovative, software-based methods in the area of operational decision support, resource optimization, and in particular re-scheduling for complex decision-making processes in crisis and disruption management situations. In the focus of the project are complex decision-making situations that typically arise when damages of natural disasters or terrorist threats and attacks should be minimized by an optimal co-ordination of available civil and military forces and resources.
In the area of basic research, new methods should be developed that build upon recent results in knowledge-based planning, schedule repair, and intelligent explanations. With respect to economical aspects and the transfer of research results into industrial practice, the project includes a detailed evaluation of technical feasibility of a medium-term implementation of these new concepts within an existing information system of the governmental partners. The psychological and sociological implications of the existence of such an extended IT-support for decision makers, who have to take decisions in crisis situations are addressed in an accompanying study.

Further Information

Anfang


COHAVE
DescriptionKnowledge-based recommender applications provide valuable support for online customers in the identification products and services on e-Commerce platforms. State-of-the-art recommender technologies provide a couple of mechanisms for improving the accessibility of product assortments for customers, e.g. in situations where no solution can be found for a given set of customer requirements, the recommender application calculates a set of repair actions (minimal changes to the given customer requirements) which can guarantee the identification of solutions. Further examples for such mechanisms are explanations (why does a certain recommendation fit to the wishes and needs of a customer) or product comparisons (what are the major advantages of a certain product compared to other products in the result set), etc. However, none of the existing recommender approaches exploit an underlying holistic view on the recommender process, i.e. take into account properties of the online customer such as domain knowledge, trust, available time, receptivity, etc. These and other aspects of an online sales dialogs are investigated within COHAVE in order to derive an integrated view on recommender processes. In this context, we analyze existing theories about customer behavior in online sales situations - especially, we focus on the areas of social psychology and cognitive psychology. The goals of COHAVE are the following: - Development of a dialog component which accompanies the online user in a sales dialog by taking into account psychological theories of consumer buying behavior (e.g. minimize time efforts, increasing the interest related to the product domain, etc.). - Implementation of a knowledge acquisition component which allows the explicit definition of strategies how recommenders should behave in certain online buying contexts. - Evaluation of the implemented environment within the context of user studies.
Further Information
Further Information

Anfang


Collaborative Microdrones "cDrones"
DescriptionMikrodronen sind kleine unbemannte Luftfahrzeuge (Quadrocopter), die durch ihre ausgeklügelte Steuerungselektronik eine hohe Flugstabilität besitzen. Ihre Steuerung ist auch für Laien bereits nach einer kurzen Einführung möglich. Die Mikrodronen werden mit Sensoren, wie z.B. Kamera, Mikrophon oder ähnlichem ausgestattet, und können dadurch Daten von dem überflogenen Bereich in Echtzeit an eine Bodenstation liefern. Daten aus der Vogelperspektive sind besonders bei Katastrophenereignissen für die Einsatzkräfte sehr interessant – muss doch rasch ein "Überblick" aus meist unvollständigen und teilweise widersprüchlichen Informationen gewonnen werden. Dieses Projekt verfolgt das Ziel, unterschiedliche Sensordaten mit Hilfe von kooperierenden und vernetzten Mikrodronen zu erfassen, zu analysieren und zu interpretieren sowie diese abstrahierten Daten in geeigneter Form den Einsatzkräften zur Verfügung zu stellen. Dazu formieren sich einige Mikrodronen selbstorganisierend zu einem Schwarm, überfliegen das Einsatzgebiet und übermitteln die erfassten Sensordaten zur Bodenstation. Die Daten der einzelnen Mikrodronen werden fusioniert und zu einem „Gesamtbild“ zusammengefasst. Als Analyse ist geplant, aus den Bilddaten ein dreidimensionales Modell des überflogenen Gebiets zu generieren bzw. interessante Objekte, wie Fahrzeuge oder Personen, autonom zu detektieren. Die Koordination mehrerer Mikrodronen ist bislang nur unzureichend erforscht. Es ist geplant, in folgenden Bereichen den Stand der Technik substantiell zu erweitern: (1) Flugformation: Wie bilden mehrere Mikrodronen selbstorganisatorisch eine Flugformation? Wie wechseln sie von einer Formation zur nächsten? Wie geht man mit dem Ausfall von Dronen um? (2) Missionsplanung und -steuerung: Wie plant und steuert man einen Einsatz mit Mikrodronen? Wie reagiert man auf unvorhergesehene Ereignisse in der Umgebung? (3) Sensordateninterpretation: Wie nutzt man trotz beschränkter Ressourcen auf den Dronen bestmöglich die Fähigkeit zur Sensorfusion und -interpretation?

Further Information
Further Information

Anfang


Customer-oriented Systematically Managed Service Offerings (COSMOS)
DescriptionDas Ziel des Projektes COSMOS ist es, Methoden, Werkzeuge und Theorien zu entwickeln, die Firmen dabei helfen, komplexe Produkt- und Dienstleistungsportfolios effektiv zu managen.
Further Information

Anfang


Interactive Selling Lab (ISL)
DescriptionThe Interactive Selling Lab project aims at advancing the state-of-the-art of recommendation technology. Its focus lies on hybridizing collaborative and learning-based techniques with knowledge-based and conversational recommendation approaches. Within the scope of the project practical B2C applications especially in the e-tourism domain should be fielded and the practical use of the developed concepts evaluated. The project is partly financed by the FFG within the Austrian network of e-tourism and its node ECCA in Innsbruck. Furthermore, private companies such as ConfigWorks, TIScover, Österreichisches Verkehrsbüro/Eurotours, city of Innsbruck and A1 mobilkom provide additional funds and/or act as external stakeholders.
Further Information
Further Information

Anfang


MAPREC
DescriptionMap-based recommendation services for e-tourism applications

Webbasierte geographische Informationssysteme (GIS) sind für die breite Masse der Internetnutzer zu einer selbstverständlichen Informationsquelle und einem liebgewonnenen Hilfsmittel geworden. Allerdings treten im Zusammenhang mit Webbasierten GIS auch Problemstellungen wie Überforderung und Informationsüberflutung der Nutzer auf. Speziell auf Tourismusportalen kommen mittlerweile immer mehr GIS zum Einsatz, um zehntausende von geographisch verorteten Objekten wie touristische Betriebe, öffentliche Einrichtungen und generelle Points of Interest (POIs) vor dem Hintergrund von digitalem Kartenmaterial anzuzeigen. Sie dienen dazu, die primär nicht greifbaren touristischen Leistungen plastisch darzustellen und helfen dem potentiellen Gast sich zu orientieren und sich ein Bild von der Situation vor Ort zu machen. Jedoch liegt die Konzeption und der Aufbau dieser GIS weit hinter den potentiellen Möglichkeiten. Zielsetzung des Projektes ist es daher Methoden des Information Retrieval und aus dem Feld der Empfehlungssysteme auf geographisch verortete Objekte anzuwenden und so seinen Nutzern einen personalisierten und interaktiven Zugang zu touristischen Leistungen im Kontext eines GIS zu ermöglichen. Auf Basis einer bedarfsgerechten Identifikation von geeigneten touristischen Leistungen sollen den Nutzern die sie interessierenden Informationen in adaptiver Weise präsentiert und 'verkauft' werden und so kommerzielle Ziele, wie eine Steigerung von 'lookers-to-bookers' Raten auf e-Tourismus Plattformen erreicht werden.

Further Information

Anfang


Mine2Innovate
DescriptionAustrian E-Tourism: Integrating Customers into New Service Developments The integration of customers into the development process of new products and services is crucial for companies regardless of the industry in which they operate. The Austrian tourism industry is ranked internationally among the top 10 (with respect to arrival and revenue statistics for international tourists) [1] and constitutes an important part of the Austrian economy. The advent of the Internet and new media applications has transformed the value creation processes of the tourism industry to an extent unseen in other industry sectors. Electronic information mediators, such as CRSs/GDSs (computer reservation systems/global distribution systems), as well as the information and booking portals of DMOs (destination management organisations) are becoming an increasingly dominant source of information and opinions for tourists. Even the sales act itself is commonly carried out on the Web. Presumably the Web accounts for more than 5% of the whole European travel market and the amount of sales that result from the opinions that it helps to form is even higher. This situation is the motivating factor for our research into the online-behaviour of tourism platform users with the hope of furthering the development and innovation of services. Due to the interdisciplinary nature of this economically relevant research topic, we propose a project team consisting of researchers from the fields of innovation and technology management as well as from business informatics and business intelligence. We will disseminate project results to the academic audience by targeting publications in renowned international journals and conferences such as Journal of Product Innovation Management, R&D Management or Information Technology and Tourism. Furthermore, we will foster knowledge transfer into the industry by organizing a feedback workshop for companies.
Further Information

Anfang


V-KNOW: Collaborative debugging and refinement of constraint-based knowledge bases
DescriptionKnowledge-based, intelligent systems have made their way into practice: Model-based systems are generating diagnostics for automobiles, configurator applications help us assembling complex products from simpler components, recommender systems generate product proposals that match our needs and requirements, just to name a few. Being the cornerstone for success for many of these applications, the knowledge acquisition problem has been addressed in the past in different dimensions, the main focus lying on knowledge representation and conceptualization issues as well as on process models for capturing and formalizing a domain expert's knowledge.
Historically, one main assumption of these approaches was that there shall exist one single point of knowledge formalization and in consequence one (user-oriented) conceptualization and a central knowledge acquisition tool. In most cases in real world, however, the domain knowledge is in the heads of different stakeholders, typical examples being cross-department or cross-organization business rules or new types of applications, in which large user communities are sharing knowledge in an open-innovation, web-based environment.
Only recently, with the emergence and spread of Web 2.0 and Semantic Web technologies, the opportunities and also the problems of collaborative knowledge acquisition have again become a topic of interest. With regard to the types of knowledge to be acquired, the main focus of these recent developments, however, is on acquiring 'structural' knowledge, i.e., on terms, concepts, and relationships among them. The proposed V-KNOW project shall build upon these new developments, but it however aims at going a step further and target at the collaborative acquisition and refinement of domain-constraints and business rules as they represent the most crucial, frequently updated, and thus costly part in many knowledge-based applications. The main questions answered in the project among others comprise the following: How can we automatically detect and resolve conflicts if knowledge acquisition is distributed between different knowledge contributors? How can we assist the knowledge contributors to acquire knowledge by asking them the “right” questions, i.e. minimizing the interaction needed? How can we generate “good” proposals for changing the knowledge base from different, possibly only partially-defined knowledge chunks, i.e. find plausible (in the eyes of the contributors) changes of the knowledge base?
The results of the proposed research project are methods and algorithms for answering these questions and an evaluation by implementing and testing a prototypical implementation.
Further Information
Further Information

Anfang


WS-Diamond
DescriptionSelf-healing software is one of the challenges for IST research. The aim of this project is a step in this direction, developing a framework for self-healing Web Services. The project will produce: - a framework for self-healing service execution (of conversationally complex Web Services), where monitoring, detection and diagnosis of anomalous situations (due to functional or non-functional errors, e.g., Quality of Service) is carried on and repair/reconfiguration is performed (thus guaranteeing reliability and availability of Web Services); - a methodology for service design that guarantees effective and efficient diagnosability/repairability during execution; - demonstration of these results on real applications. The research is risk-bearing. It builds upon results in different areas such as model-based diagnosis, semantic Web Services, cooperative information systems, and Web Service composition. It goes beyond a number of current projects in the area of Service Oriented Computing and Semantic Web Services, which do not consider the monitoring, diagnosing and repairing of Web Services. The research is timely because the progress in model-based diagnosis and the emergency of Web Services standards occurred in the last decade has reached sufficient foundational advances to make the proposed research feasible. The research is important because new computing technology has a tremendous potential for the creation of complex services to support e-commerce and human activities (e.g., healthcare, communities of workers), creating networks of co-operating eservices. These networks are open and may accommodate dynamically the addition and removal of new services and the disappearance of other ones. Such networks are however hindered by the inherent complexity and difficulty in controlling such complex systems, and require abilities for on-line monitoring, diagnosis, and repair in order to function fully and reliably.
Further Information

Anfang


XPLAIN-IT (Intelligent Explanations in Financial Decision Making)
Description
Further Information

Anfang


AllRight
DescriptionAccurate and complete information and knowledge about goods and services is a necessary precondition for many B2B and B2C software applications. For example knowledge-based advisory and configuration systems help customers to find the right products (services) for their needs and simplify the interaction between users and computer systems. Knowledge acquisition is the key for knowledge-based systems, this process is still too costly and too error-prone for many application domains. This is particularly the case where the application area is highly dynamic (e.g. electronic goods and tourism) and therefore the maintenance costs are prohibitive for deploying successful applications. Many applications suffer from incomplete, outdated, and wrong data causing a high frustration among users. The goal of the proposed project is to exploit the information available on the Web such that knowledge acquisition could be highly automated. Since the efficient acquisition of semantic information is the key for implementing the vision of a Semantic Web and for implementing the vision of intelligent software systems, our project will provide a major contribution for the successful realization of these visions.
Further Information

Anfang


Anbindung eines objektorientierten Konfigurators an eine relationale Datenbank zur Erzeugung grafischer Benutzeroberflächen
Description
Further Information

Anfang


CAWICOMS
Description
Further Information

Anfang


CDM@Airports
Description
Further Information

Anfang


Evaluation des ILOG Konfigurators
Description
Further Information

Anfang


KMPortal
Description
Further Information

Anfang


Koba4MS
Description
Further Information

Anfang


Konzeptstudie zur Realisierung eines Konfigurations- und Projektierungssystems für SIMIS-W
Description
Further Information

Anfang


Modellierung, Planung und Bewertung von Geschäftsprozesstransformationen im Bereich der kundenindividuellen Massenfertigung, ÖNB
Description
Further Information

Anfang


My Gallus
Description
Further Information

Anfang


Software Cluster Südtirol-Kärnten (SCS)
DescriptionIn this joint project with the University of Bolzano, the goal is to develop methods and tools for the successful implementation of integrated „Knowledge Management“ in IT-companies. In particular, these methods should be able to reduce the typically high costs of knowledge acquisition, -maintenance, -and delivery in the domain and on the other hand support a continuous improvement of the development process.
Further Information

Anfang


Tectrans
Description
Further Information

Anfang


Virtuelle Produktberatung für Bankenprodukte
Description
Further Information

Anfang


 
 
© 2009 Alpen-Adria-Universität Klagenfurt | Publication details | Contact | Disclaimer
Responsibility for content: TEWI - Web Administrator
Requests to: TEWI - Web Editor

Sprachauswahl