This paper features SEASALT, an intelligent information system architecture that follows the example of collaborating human experts. Modular- ised knowledge is provided in a number of case bases that offer their topic ex- pertise which is used to combine knowledge for individual queries. We describe how collaborative multi-expert systems can be instantiated using CBR technology to cover the experts' roles and agent technology in order to enable their collaboration. We focus on the maintenance of cases in such multi-case- base systems regarding inter-case base dependencies. We evaluate our approach based on the real-life application of travel medicine and show how the requirements of an information system on travel medicine can be fulfilled using our hybrid, agent based CBR system architecture.

Sharing Experience using an Agent-based System Architecture Layout (SEASALT) presents an instantiation of the Collaborating Multi-expert Systems (CoMES) approach. It integrates techniques from software engineering and combines them with artificial intelligence methodologies. The approach offers an application-independent architecture that features knowledge acquisition from a web-community, knowledge modularisation and agent-based knowledge maintenance. The paper introduces a travel medicine as application domain which applies SEASALT and describes each part of the novel architecture for extracting, analysing, sharing and providing community experiences in an individualised way.

This chapter focuses on knowledge management for complex application domains using Collaborative Multi-Expert-Systems. We explain how different knowledge sources can be described and organized in order to be used in collaborative knowledge-based systems. We present the docQuery system and the application domain travel medicine to exemplify the knowledge modularization and how the distributed knowledge sources can be dynamically accessed and finally reassembled. Further on we present a set of properties for the classification of knowledge sources and in which way these properties can be assessed.

SEASALT (Sharing Experience using an Agent-based System Architecture LaYouT) presents an instantiation of the Collaborating Multi-Expert Systems (CoMES) approach [1]. It offers an application-independent architecture that features knowledge acquisition from a web-community, knowledge modularization. and agent-based knowledge maintenance. The paper introduces an application domain which applies SEASALT and describes each part of the novel architecture for extracting, analyzing, sharing and providing community experiences in an individualized way.

edge acquisition step. This paper’s focus 1 lies on the distributed knowledge sources of the SEASALT architecture [Reichle et al., 2009a] and their management and (optimised) querying using a Coordination Agent [Bach et al., 2008]. Within SEASALT knowledge modularisation is realised in the Knowledge Line that is based on the principle of product lines as it is known from software engineering. We apply this to the knowledge in knowledge-based systems, thus splitting rather complex knowledge in smaller, reusable units (knowledge sources). Moreover, the knowledge sources contain different kinds of information as well as there can also be multiple knowledge sources for the same purpose. Therefore each source has to be described in order to be integrated in a retrieval process which uses a various number of knowledge sources. A so called Knowledge Map organises all available knowledge sources that can be accessed by a Coordination Agent that creates individual requests and combines information. The term Knowledge Map originates in Davenport’s and Prusak’s work on Working Knowledge [Davenport and Prusak, 2000] in which they describe a Knowledge Map from the organisational point of view mapping human experts in a large organisation or company. We transfer this concept to an intelligent agent framework that coordinates different knowledge sources. The Coordination Agent navigates through the Map and subsequently queries the individual knowledge sources and thus creating an individual path through the map[ReichleSchmehl, 2008]. There are dependencies between knowledge sources, a dependency exists if one source’s output serves as another’s input and thus enforces a subsequent query. Since the dependencies between knowledge sources can take any form, the Knowledge Map is implemented as a graph where each knowledge source is represented by a node and directed edges denote the dependencies. Retrieval paths are computed based on the information a user gives in an individual query and the properties of the knowledge sources. Our current implementation provides an a-priori computation of the retrieval path using a modified Dijkstra algorithm to determine an optimal route over the graph. Considering knowledge sources, different characteristics, and aspects on which to assess knowledge source properties come to mind. The possible properties can refer to content (e.g. quality or topicality) as well as metainformation (e.g. answer speed or access limits). In detail 1 This is a one-page abstract for the full paper and references

In this paper we present a method for supplementing incomplete cases with information from other cases within a case base. The acquisition of complete and correct cases is a time-consuming task, but nevertheless crucial for the quality and acceptance of a case-based reasoning system. The method introduced in this paper uses association rules to identify relations between attributes and, based on the discovered relations we are able to supplement values in order to complete cases. We argue that using these related attributes when retrieving supplementation candidates will yield better results than simply picking the case with the highest global similarity. The evaluation of the method is carried out using four different publicly available case bases.

This paper focuses on knowledge management for complex application domains using Collaborative Multi-Expert-Systems. We explain how different knowledge sources can be described and organised in order to be used in collaborative knowledge-based systems. We present the docQuery system and the application domain travel medicine to exemplify the knowledge modularisation and how the distributed knowledge sources can be dynamically accessed. Further on we present a set of properties for the classification of knowledge sources and in which way these properties can be assessed.

This paper addresses the realization of modularized knowledge models within a heterogeneous application domain using an existing knowledge management tool. The application domain we deal with is travel medicine, which combines medical aspects with geography, climate, holiday activities and associated traveling conditions. In this paper we present the application's requirements and show how knowledge models can be developed using an industrial strength application. Furthermore we present the challenges of a knowledge model based on multi-case bases whereas each case base represents its own area of expertise. Hence, we introduce our knowledge model for the travel medicine application and exemplify the implementation of typical data types and similarity measures.

A method and apparatus for the transmission of time discrete signals between source and sink systems wherein a first signal x(n) is generated by the source system at a first sampling rate fi and a second time discrete signal y(m) is generated by a sink system at a second sampling rate f0. The method is carried out by cyclically distributing the first time discrete signal to each of L filter groups at the first sampling rate fi. Each of the L filter groups comprises M filter elements which have their inputs connected to a common terminal and have the transfer function Hl,m(zLM, where L and M are integers, l is an integer 0, 1 . . . L-1 corresponding to the filter group in which the filter element is located and m is an integer 0, 1 . . . M-1 corresponding to the location of the filter element in its associated filter group. The first time discrete signal is filtered in each of the filter elements at a processing rate fi/L and the filtered signals stored in the filter elements. Thereafter, the stored outputs of the M filter elements in each of the L filter groups are cyclically sampled at the second sampling rate f0 and coupled to corresponding inputs of a summing element which generates a signal f0 at its output equal to M/L fi.

The work presented in this paper focuses on the composition of retrieval results returned by distributed case bases. We describe how different knowledge sources can be accessed using an abstract description language and in which way we handle the resulting heterogeneous information. The realisation of this query agent is a part of SEASALT, an architecture for intelligent information systems, which follows the example of collaborating human experts and further on provides an architecture that contains all aspects of knowledge utilisation. Within SEASALT knowledge is provided in distributed knowledge sources represented by a number of case based agents. The coordination agent presented in this paper uses those knowledge sources to combine information to compose information into individual answers. We evaluate our approach based on the real-life application of travel medicine and show how the retrieval in distributed case bases can be coordinated and executed.

Case-based reasoning (CBR) is a sub-field of Artificial Intelligence that deals with experience-based problem solving. CBR has its roots in different disciplines such as cognitive science, machine learning, and knowledge-based systems. Today, it is a well established research field of its own, which produced a rich variety of specific methods, as well as applications implementing those methods for particular tasks and domains. This paper gives a compact overview of CBR in general and further discusses recent advancements in selected topics.

We propose SEASALT, an architecture based on the CoMES approach on developing collaborative multi-expert-systems using case-based reasoning and software agents technology. SEASALT is built on a modular structure and will allow implementing intelligent information systems for different kinds of application scenarios based on the architecture we are presenting. Introducing SEASALT furthers knowledge intensive services based on distributed knowledge sources. In our approach we integrate “knowledge work” in a community eliciting new information. Hence, in SEASALT agents act alongside with human beings on a community platform proving and receiving information.

We describe a new research effort for developing knowledge-based systems using a combination of methods from Software Engineering and Artificial Intelligence: software product-lines, experience factory, case-based reasoning, multi-agent-systems, and semantic web technology. We motivate our approach, shortly describe three different application scenarios, and provide our current ideas of how to implement our approach, which we call “collaborative multi-expert-systems” (CoMES).

We propose the implementation of an intelligent information system on free and open source software. This system will consist of a case-based reasoning (CBR) system and several machine learning modules to maintain the knowledge base and train the CBR system thus enhancing its performance. Our knowledge base will include data on free and open source software provided by the Debian project, the FLOSSmole project, and other public free and open source software directories. We plan to enrich these data by learning additional information such as concepts and different similarities. With this knowledge base, we hope to be able to create an information system that will be capable of answering queries based on precise as well as vague criteria and give intelligent recommendations on software based on the preferences of the user.

This article reports the development of a chatbot for the university library in Hildesheim. The System responds to queries in typed natural lanaguage The concept and the implementation with the Artifical Intelligence Markup Language are described. An evaluation hints that such a system may be acceptable for users.

This article deals with several aspects of a marketing-oriented analysis of web log files. It discusses their preprocessing and possible ways to enrich the raw data that can be gained from a web log file in order to facilitate a later use in different analyses. Further, we look at the question which requirements a good web log analysis software needs to meet and offer an overview over current and future analysis practices including their advantages and disadvantages.

Case-based reasoning (CBR) is a sub-field of Artificial Intelligence that deals with experience-based problem solving. CBR has its roots in different disciplines such as cognitive science, machine learning, and knowledge-based systems. Today, it is a well established research field of its own, which produced a rich variety of specific methods, as well as applications implementing those methods for particular tasks and domains. This paper gives a compact overview of CBR in general and further discusses recent advancements in selected topics.