Mathias Bauer

This paper proposes a method to assess the cognitive state of a human embodied as an avatar inside a 3-dimensional virtual shop. In order to do so we analyze the trajectories of the avatar movements to classify them against the set of predefined prototypes. To perform the classification we use the trajectory comparison algorithm based on the combin...

Decisions are rarely ever made in total isolation. As a consequence a decision support system should not only be able to take into account a user's preferences, but also consider other persons' interests, likes and dislikes. The MIAU system presented in this paper captures a user's preferences in a c omplex, multivariate preference model and mediat...

Limitation of the human memory is a well-known issue that anybody has experienced. This chapter discusses typical components and processes involved in the building and the exploitation of augmented memories. SPECTER, an adaptive, self-learning system supports the user in everyday activities by interpreting sensor information captured in the environ...

Limitation of the human memory is a well-known issue that anybody has experienced. This chapter discusses typical components and processes involved in the building and the exploitation of augmented memories. SPECTER, an adaptive, self-learning system supports the user in everyday activities by interpreting sensor information captured in the environ...

Adaptive information systems typically exploit knowledge about the user's interests, preferences, goals etc. to determine what should be presented to the user and how this presentation should take place. When dealing with mobile users, however, information about their motions—the places visited, the duration of stays, average velocity etc.—can be a...

User support which takes into account the user‘s current context is a key issue of ambient intelligence applications. In this contribution we address the question of how a user may configure and keep control of situated user support. Background of our work is a system, which creates an augmented, personal memory from events perceived in an instrume...

Machine learning (ML) is a complex process that can hardly be carried out by non-expert users. Especially when using adaptive systems that interpret and exploit observations of the user to modify their behavior according to the user's perceived preferences, even naïve users may be confronted with learning systems. This paper presents an approach to...

Keeping a history of the user's interaction with the environment is of use for many reasons. However, collecting, structuring, accessing, and reviewing such potentially large amounts of information is not trivial. In this paper we present our ideas for a memory model for pervasive computing applications addressing these questions. The proposed arch...

Planerkennung bedeutet, aus den beobachteten Aktionen eines Agenten auf dessen Pläne zu schliessen. Das Wissen um diese Pläne - und damit die Intentionen und Ziele des Agenten - bildet beispielsweise die Grundlage fuer eine der aktuellen Situation angemessene Unterstuetzung durch ein intelligentes Hilfesystem. Sind nun mehrere Planhypothesen mit al...

User models (UM)─the explicit representation of all relevant aspects of a user's preferences, beliefs, etc. ─form the basis of virtually all adaptive systems. While early approaches re- lied on explicit interviews to fill in the details of such a UM, more recent systems unobtru- sively observe their users and automatically in- fer the contents of t...

We discuss and illustrate design principles that have emerged in our ongoing work on a context-aware, user- adaptive mobile personal assistant in which an extended episodic memory—the personal journal—plays a central role. The prototype system SPECTER keeps track of its user's actions and affective states, and it collaborates with the user to creat...

Although there still remain a lot of open questions on technical issues in ubiquitous computing, mobile system must not forget to put the user in the center of their interest. Context data must be presented in an intelligible way, all system behavior must support the user according to a model of her preferences and interests and privacy concerns sh...

With the advent of e-commerce, systems supporting the user in finding just the right product in an electronic catalog have gained increasing attention. While collaborative recommender systems (RS) derive their suggestions from other users’ opinions, structure-based systems assess a product according to how well its properties satisfy a user’s prefe...

INTRODUCTION Communicat on bet ween a user and a programming syst m is a crucial aspect of any programming act vit y. Even iftI programmer knows a st" by st" descrip on of how t o solve a problem,it isoft en di#cult t o e presst his descript on in a form txt can be underst od byt" syst m. The reason fort his communication problem [1] ist he gap bet...

The next generation of voice-based user interface technology will enable easy-to-use automation of new and existing communication services, achieving a more natural human-machine interaction. By natural, we mean that the machine understands what people ...

To date, product recommendation systems have mainly been looked at from a single-agent perspective, where only the interests of a single user are taken into account. We extend this scenario and consider the case where multiple users are planning a joint purchase, and therefore many (potentially conflicting) interests have to be considered. In this...

SAP initiated a survey project on agent technology in which the state of the art in the application of agents to industrial application domains is investigated. In this paper we describe our common effort and activities related to this project. The survey results consist of documents which describe relevant projects and products especially with res...

In Programming by Demonstration (pbd) the user tries to extend a system's capabilities by providing examples of how to perform certain tasks. The system then synthesizes a pro-gram that can be re-used to automate the demonstrated task, thus reducing the amount of routine work for the user. One of the most fundamental obstacles to an efficient user-...

In this paper we introduce an adaptive recommender system that supports the user in finding interesting entries in an electronic product catalog. The Analytic Hierarchy Process (AHP) lays the foundation for the user preferences. The user interests are specified in terms of desired properties of the ideal product, ex-pressed in the form of constrain...

Software agents are intended to perform certain tasks on behalf of their users. In many cases, however, the agent's competence is not sufficient to produce the desired outcome. This chapter presents an approach to cooperative problem solving in which an information agent and its user try to support each other in achieving a particular goal. Program...

Information agents are intended to assist their users in locating relevant information in vast collections of documents like the WWW. In many cases, e.g., when trying to integrate pieces of information from previously unrelated sources, it is not sufficient to merely identify documents containing relevant data. Instead, information agents have to i...

One of the most natural ways to acquire procedural knowledge is to watch somebody performing a number of actions and try to abstract this observed action sequence in order to make it applicable to a wider range of situations. This abstraction process can be significantly facilitated if the performing agent gives additional hints e.g. on the reasons...

Software agents are intended to perform certain tasks on behalf of their users. In many cases, however, the agent's competence is not sufficient to produce the desired outcome. This paper presents an approach to cooperative problem solving in which an information agent and its user try to support each other in the achievement of a particular goal....

this article we will refer to the user in the female form, while the agent will be referred to using male forms

Plan libraries are the most important knowledge source of many plan recognition systems. The plan decompositions they contain provide information about how a plan has to be executed to actually achieve its associated goals and be recognized by the system. This paper presents an approach to the automatic acquisition of plan decompositions from sampl...

This paper gives a brief overview on how machine learning techniques can be used to create and maintain both of these knowledge sources. 2 Plan Libraries

Software agents are intended to perform certain tasks on behalf of their users. In many cases, however, the agent's competence is not sufficient to produce the desired outcome. This paper presents an approach to cooperative problem solving in which an information agent and its user try to support each other in the achievement of a particular goal....

Plan libraries are the most important knowledge source of many plan recognition systems. The plan decompositions they contain provide information about how a plan has to be executed to actually achieve its associated goals and be recognized by the system. This paper presents an approach to the automatic acquisition of plan decompositions from sampl...

With the enormous amount of data contained in the WWW, one of the crucial tasks a user has to face is the identification and aggregation of relevant pieces of information to satisfy her current information needs. This paper presents an approach to the system-supported configuration of individualized information services. The programming-by-demonstr...

. While most plan recognition systems make use of a plan library containing the set of available plan hypotheses, little effort has been devoted to the question of how to create such a library. This problem is particularly difficult to deal with when only little domain knowledge is available---a common situation when e.g. developing a help system f...

Software agents are intended to perform certain tasks on behalf of their users. In many cases, however, the agent's competence is not sufficient to produce the desired outcome. This paper presents an approach to cooperative problem solving in which a software agent and its user try to support each other in the achievement of a particular goal. As a...

We introduce a logic-based system which improves the performance of intelligent help systems by supplying them with plan generation and plan recognition components. Both components work in close mutual cooperation. There are two modes of cross-talk between them, one where plan recognition is done on the basis of abstract plans provided by the plann...

While most plan recognition systems make use of a plan library that contains the set of available plan hypotheses, little effort has been devoted to the question of how to create such a library. This problem is particularly difficult to deal with when only little domain knowledge is available-a common situation when e.g. developing a help system fo...

Over the past few years, the amount of electronic information available through the Internet has increased dramatically. Unfortunately, the search tools currently available for retrieving and filtering information in this space are not effective in ...

The computational complexity of reasoning within the Dempster-Shafer theory of evidence is one of the major points of criticism this formalism has to face. To overcome this difficulty various approximation algorithms have been suggested that aim at reducing the number of focal elements in the belief functions involved. This article reviews a number...

Plan recognition is an important task whenever a system has to take into account an agent's actions and goals in order to be able to react adequately. Most plan recognizers work by merely maintaining a set of equally plausible plan hypotheses each of which proved compatible with recent observations without taking into account individual preferences...

. Expert systems are typically expected to be able to justify their decisions to the user. This paper argues that help systems or tutoring systems based on a plan recognizer can equally benefit from an explanation component. To this end a plan recognition system equipped with a user model is presented and the techniques required to generate precise...

The computational complexity of reasoning within the Dempster-Shafer theory of evidence is one of the main points of criticism this formalism has to face. To overcome this difficulty various approximation algorithms have been suggested that aim at reducing the number of focal elements in the belief functions involved. Besides introducing a new algo...

. Intelligent help systems aim at providing optimal help to the users of complex application systems. In this context plan recognition is essential for a cooperative system behaviour in that it allows the prediction of future user actions, the ascertainment of suboptimal action sequences or even serves as a basis for user-adapted tutoring or learni...

Whenever a system has to take into account an agent's actions or utterances in order to produce a certain kind of cooperative (or competitive) behavior, plan recognition becomes an important task. In many cases it is not sufficient to merely maintain a list of plan hypotheses all of which proved compatible with the observations made so far. If a de...

Plan recognition systems need a measure to assess the quality of their hypotheses about a user's goals. Such a measure allows the exclusion of extremely "bad" hypotheses at an early stage or the selection of the "best" one whenever this is required, e.g. when a help system is asked to provide support to the user of an application system. To work pr...

. Plan recognition is an important task whenever a system has to take into account an agent's actions and goals in order to be able to react adequately. Many plan recognizers, however, are only capable of deriving a set of equally plausible plan hypotheses. This is of little use whenever the system actually has to react, e.g., when an intelligent h...

Plan recognition is an important task whenever a system has to take into account an agent's actions and goals in order to be able to react adequately. Most plan recognizers work by merely maintaining a set of equally plausible plan hypotheseseach of which proved compatible with recent observations without taking into account individual preferences...

We introduce a logic-based system which improves the performance of intelligent help systems by supplying them with plan generation and plan recognition components. Both components work in close mutual cooperation. There are two modes of cross-talk between them, one where plan recognition is done on the basis of abstract plans provided by the plann...

Das Ziel intelligenter Hilfesysteme ist es, den Benutzer eines komplexen Anwendungssystems optimal zu unterstützen. Dabei ist Planerkennung eine wesentliche Voraussetzung für kooperatives Verhalten des Systems. Im Rahmen des Projekts PHI (Planbasierte Hilfesysteme) am DFKI wurde ein neuer logikbasierter Ansatz zur inkrementellen Planerkennung in de...

We describe the embedding of the semantic notions and modal operators of a first-order temporal logic based on time intervals in a multivalued setting. Truth values will be realized as functions from time intervals to ordinary truth values like t and f. The main emphasis lies on the realization of the various modal operators contained in the tempor...

The work we present in this paper is settled within the field of intelligent help systems. Intelligent help systems aim at supporting users of application systems by the achievements of qualified experts. In order to provide such qualified support our approach is based on the integration of plan generation and plan recognition components. Plan reco...

In this article a new form of circumscription, called conditioned circumscription is developed, that permits translating arbitrary defaults to circumscription. As a consequence the deduction methods of first-order predicate logic can be applied to default logic. The circumscription policy will be fixed and by showing the equivalence of conditioned...

SAP initiated a survey project on agent technology in which the state of the art in the application of agents to industrial application domains is investigated. In this paper we describe our common effort and activities related to this project. The survey results consist of documents which describe relevant projects and products especially with res...

After some terminological clarification, we distinguish three possi-ble relationships between invisibility and transparency in the type of system dis-cussed in this workshop. We present examples of the third type of relationship taken from the adaptive, context-and affect-aware personal companion SPECTER.