ABIS 2003 – 11. GI-Workshop "Adaptivität und Benutzermodellierung in interaktiven Softwaresystemen"
Karlsruhe, 6.-8. Oktober 2003
Homepage des Workshops
Homepage des Workshops
Auflistung nach:
Auflistung ABIS 2003 – 11. GI-Workshop "Adaptivität und Benutzermodellierung in interaktiven Softwaresystemen" nach Titel
1 - 10 von 18
Treffer pro Seite
Sortieroptionen
- KonferenzbeitragA Smart Shopping Assistant utilising Adaptive Plan Recognition(11. GI-Workshop "Adaptivität und Benutzermodellierung in interaktiven Softwaresystemen", 2003) Schneider, MichaelIn this paper we describe an adaptive shopping assistant system utilising plan recognition. Radio Frequency Identification (RFID) sensory is used to observe a shopper’s actions, from which the plan recogniser tries to infer the goals of the user. Using this information, an automated assistant provides help tailored to the shopper’s concrete needs. We discuss why it is crucial to make the plan recognition process itself user adaptive and present ideas how to realise this through modification of existing plan recognition approaches.
- KonferenzbeitragA User Profiling Component with the aid of User Ontologies(11. GI-Workshop "Adaptivität und Benutzermodellierung in interaktiven Softwaresystemen", 2003) Nébel, István Tibor; Smith, Barry; Paschke, RalfWhat follows is a contribution to the field of user modeling for adaptive teaching and learning programs especially in the medical field. The paper outlines existing approaches to the problem of extracting user information in a form that can be exploited by adaptive software. We focus initially on the so-called stereotyping method, which allocates users into classes adaptively, reflecting characteristics such as physical data, social background, and computer experience. The user classifications of the stereotyping method are however ad hoc and unprincipled, and they can be exploited by the adaptive system only after a large number of trials by various kinds of users. We argue that the remedy is to create a database of user ontologies from which ready- made taxonomies can be derived in such a way as to enable associated software to support a variety of different types of users.
- KonferenzbeitragAdapting Spoken and Visual Output for a Pedestrian Navigation System, based on given Situational Statements(11. GI-Workshop "Adaptivität und Benutzermodellierung in interaktiven Softwaresystemen", 2003) Wasinger, Rainer; Oliver, Dominika; Heckmann, Dominik; Braun, Bettina; Brandherm, Boris; Stahl, ChristophAs mobile devices become more and more complex, there is an increasing desire for these devices to adapt to their users. This paper identifies parameters for different input sources (user, device and environment), and the parameters of media output (speech, graphics, sound and text), that may be modified to tailor user presentation in a pedestrian navigation system. We also provide an initial insight into some of the causal relationships between our input and output parameters, with a specific focus on the effects that speech can con- tribute to the presentation of media output.
- KonferenzbeitragAdaptive Coherence Information as an Approach to facilitate the Comprehension of Online Learning Courses(11. GI-Workshop "Adaptivität und Benutzermodellierung in interaktiven Softwaresystemen", 2003) Lippitsch, Stefan; Weber, GerhardKnowledge acquisition with online learning courses is mostly a matter of reading texts on a display. Understanding the text might be more problematic than in a book because of the possible gaps which could be produced by jumps to remote pages. Building an inadequate mental model might be a more probable danger for readers with little or no background knowledge because they do not have sufficient substitutions for lacking actual coherent information. This situation could be prevented by an adaptive feature that supports the user with additional information. We plan to examine the effectiveness and efficiency of an additional adaptive coherence information.
- KonferenzbeitragEin erweiterbares Architekturkonzept zur aktiven Lernermodellierung für das Web-gestutzte Lernen(11. GI-Workshop "Adaptivität und Benutzermodellierung in interaktiven Softwaresystemen", 2003) Langner, Holger; Schmidsberger, Falk; Dilger, WernerDieser Artikel befasst sich mit dem Entwurf eines Konzepts zur Realisierung von Lernerassistenzfunktionen für das Web-gestützte Lernen. Die Offenheit von Web-gestützten Lernumgebungen, die Heterogenität von Lerninhalten und Nutzerprofilen und das Erfordernis der kommunikativen Vernetzung vereinzelter Lerner werden dabei als Anforderungen verstanden, die das Web-based Learning weniger als eine untergeordnete Variante des Lernens mit Intelligenten Tutorsystemen charaktisieren, sondern viel- mehr als ein eigenständiges Anwendungsfeld, das spezifische Anforderungen an Lernerassistenzkonzepte stellt. Im Vordergrund stehen daher Verfahren, die einen benutzerbezogenen Zugang zu vernetzten Informationsbeständen erleichtern sollen. Ausgehend von der These, dass die Skalierbarkeit solcher benutzeradaptiver Funktionen im Hin- blick auf die verfügbaren Nutzungsdaten und den jeweiligen Zweck eine wichtige Voraussetzung für ihren sinnvollen praktischen Einsatz darstellt, schlägt dieser Artikel ein offenes, erweiterbares Architekturkonzept zur flexiblen, Lernszenario-spezifischen Integration von benutzeradaptiven Techniken als Ausgangspunkt für ihre praktische Erprobung vor.
- KonferenzbeitragImplicit Feedback for User-Adaptive Systems by Analyzing the Users’ Speech(11. GI-Workshop "Adaptivität und Benutzermodellierung in interaktiven Softwaresystemen", 2003) Wittig, Frank; Müller, ChristianThis paper describes an approach to recognize the gender and age of a user on the basis of her/his speech. Within a two-level framework, machine learning techniques are applied to learn several appropriate classifiers whose results are combined on the top level to improve the overall classification of the user. As a part of the user model, the information about the user’s age and gender can be an important basis for appropriate adaptation decisions.
- KonferenzbeitragIntroducing ”Situational Statements” as an integrating Data Structure for User Modeling, Context-Awareness and Resource-Adaptive Computing(11. GI-Workshop "Adaptivität und Benutzermodellierung in interaktiven Softwaresystemen", 2003) Heckmann, DominikUbiquitous computing will have a unifying influence on user modeling, context-awareness and resource-adaptivity. The idea of this paper is to suggest a basic, semantically founded, uniform data structure that is simple but still expressive enough to cover all representational needs. An extended triple, which is based on RDF resources is introduced as well as an XML application for so called ”Situational Statements”.
- KonferenzbeitragKontextbezogene Informationsversorgung: Anwenderanforderungen und Granularität der Modellierung(11. GI-Workshop "Adaptivität und Benutzermodellierung in interaktiven Softwaresystemen", 2003) Engelbach, Wolf; Delp, MartinInformationsrecherchen werden von Mitarbeitern in einem konkreten Kontext durchgeführt. Der Beitrag untersucht anhand von fünf Unternehmen, welche Einflussfaktoren diesen Kontext bestimmen und welche Informationsquellen verwendet werden. Exemplarisch werden die Erfassungsmöglichkeiten des Einflussfaktors „Hilfsbereitschaft im Team“ sowie seine Auswirkungen auf die Informationsrecherche diskutiert. Abschließend wird für Recherche, Prozess, Rolle und Begriffe jeweils erörtert, welche Konsequenzen sich aus den Untersuchungsergebnissen für eine geeignete Granularität ihrer Modellierung ableiten lassen. Da in den Unternehmen viele Vorarbeiten nicht vorhanden sind, sollten Systeme zur Unterstützung der Informationsrecherche so aufgebaut sein, dass die Erfassung solcher kontextdefinierender Einflussfaktoren nicht zur Systemeinführung zwingend erforderlich ist, sondern sukzessive erfolgen kann.
- KonferenzbeitragLearning for User Adaptive Systems: Likely Pitfalls and Daring Rescue(11. GI-Workshop "Adaptivität und Benutzermodellierung in interaktiven Softwaresystemen", 2003) Müller, Martin E.Adaptive user interfaces adapt themselves to the user by reasoning about the user and refining their internal model of the user’s needs. In machine learning, artificial systems learn how to perform better through experience. By observing examples from a sample, the learning algorithm tries to in- duce a hypothesis which approximates the target function. It seems obvious, that ma- chine learning exactly offers what is desperately needed in intelligent adaptive behavior. But when trying to adapt by learning, one will sooner or later encounter one or more well–known problems, some of which have been discussed in [Webb et al., 2001]. We propose a framework for describing user modeling problems, identify several reasons for inherent noise and discuss few promising approaches which tackle these problems.
- KonferenzbeitragLISTEN: Contextualized Presentation for Audio-Augmented Environments(11. GI-Workshop "Adaptivität und Benutzermodellierung in interaktiven Softwaresystemen", 2003) Zimmermann, Andreas; Lorenz, AndreasThe paper deals with the awareness of and the adaptation to the context in audio-augmented environments. Taking into account the relationship between aural and visual perceptions, we focus on the issues and the potential of adapting intelligent audio interfaces to augment the visual real environment. The description of the LISTEN project, a system for the creation of immersive audio-augmented environments, is taken as showcase; in particular, our focus is on the modelling and personalization methods affecting the audio design and presentation. The outcomes of the preliminary tests are reported in order to describe the is- sues and complexity of intelligent user model- ling in audio-augmented environments.