Stephanidis, Constantine (Ed.): Universal Access in Human-Computer Interaction: Part II : Users Diversity. Berlin, Heidelberg, New York: Springer, 2011. (Lecture Notes in Computer Science (LNCS) 6766), pp. 32-41

We report on work towards an architecture that incorporates accessible design methods, guidelines and support tools for building and testing adaptive and accessible user interfaces (UI) for users with mild impairments. We especially address interaction constraints for elderly people, both during application design time and at run time, targeting on hybrid TV platforms. The functional principle of our architecture is twofold: At runtime, it lets users interact with hybrid TV applications through an ensemble of accessible UIs that cover different input and output modalities and are jointly adapted via user profiles and real-time feedback. At design time, it allows developers to re-use UIs and representative user personas in simulating the effect of the UI modalities on different impairments.

Ruyter, Boris de (Ed.) et al.: Ambient Intelligence : AmI 2010. Berlin; Heidelberg; New York: Springer, 2010. (Lecture Notes in Computer Science (LNCS) 6439), pp. 346-348

Approximately half of the elderly people over 55 suffer from some type of typically mild visual, auditory, motor or cognitive impairment. For them interaction, especially with PCs and other complex devices is sometimes challenging, although accessible ICT applications could make much of a difference for their living quality. Basically they have the potential to enable or simplify participation and inclusion in their surrounding private and professional communities. However, the availability of accessible user interfaces being capable to adapt to the specific needs and requirements of users with individual impairments is very limited. Although there are a number of APIs [1, 2, 3, 4] available for various platforms that allow developers to provide accessibility features within their applications, today none of them provides features for the automatic adaptation of multimodal interfaces being capable to automatically fit the individual requirements of users with different kinds of impairments. Moreover, the provision of accessible user interfaces is still expensive and risky for application developers, as they need special experience and effort for user tests. Today many implementations simply neglect the needs of elderly people, thus locking out a large portion of their potential users. The workshop is organized as part of the dissemination activity for the European-funded project GUIDE "Gentle user interfaces for elderly people", which aims to address this situation with a comprehensive approach for the realization of multimodal user interfaces being capable to adapt to the needs of users with different kinds of mild impairments. As application platform, GUIDE will mainly target TVs and Set-Top Boxes, such as the emerging Connected-TV or WebTV platforms, as they have the potential to address the needs of the elderly users with applications such as for home automation, communication or continuing education.

Buntine, Wray (Ed.) et al.: Machine Learning and Knowledge Discovery in Databases : European Conference, ECML PKDD 2009. Proceedings, Part I. Berlin, Heidelberg, New York: Springer, 2009. (Lecture Notes in Computer Science (LNCS) 5781), pp. 517-532

This article contributes a generic model of topic models. To define the problem space, general characteristics for this class of models are derived, which give rise to a representation of topic models as "mixture networks", a domainspecific compact alternative to Bayesian networks. Besides illustrating the interconnection of mixtures in topic models, the benefit of this representation is ist straight-forward mapping to inference equations and algorithms, which is shown with the derivation and implementation of a generic Gibbs sampling algorithm.

Presents parameter estimation methods common with discrete probability distributions, which is of particular interest in text modeling. Starting with maximum likelihood, a posteriori and Bayesian estimation, central concepts like conjugate distributions and Bayesian networks are reviewed. As an application, the model of latent Dirichlet allocation (LDA) is explained in detail with a full derivation of an approximate inference algorithm based on Gibbs sampling, including a discussion of Dirichlet hyperparameter estimation. Finally, analysis methods of LDA models are discussed.

Mertsching, Baerbel (Ed.) et al.: KI 2009: Advances in Artificial Intelligence : 32nd Annual German Conference on AI. Berlin; Heidelberg; New York: Springer, 2009. (Lecture Notes in Artificial Intelligence (LNAI) 5803), pp. 161-168

The article contributes a derivation of variational Bayes for a large class of topic models by generalising from the well-known model of latent Dirichlet allocation. For an abstraction of these models as systems of interconnected mixtures, variational update equations are obtained, leading to inference algorithms for models that so far have used Gibbs sampling exclusively.

Audio Engineering Society (AES): 125th Audio Engineering Society Convention. Convention Papers [CD-ROM]. New York: AES and Mira Publishing Inc., 2008, 14 p.

We present a platform for real-time transmission of immersive audiovisual impressions using model- and data- based audio wave-field analysis/synthesis and panoramic video capturing/projection. The audio subsystem considered in this paper is based on microphone arrays with different element counts and directivities as well as weakly directional loudspeaker arrays. We report on both linear and circular setups that feed different wave-field synthesis systems. In an attempt to extend this, we present first findings for a data-based approach derived using experimental simulations. This data-based wave-field analysis/synthesis (WFAS) approach uses a combination of cylindrical-harmonic decomposition of cardioid array signals and enforces causal plane wave synthesis by angular windowing and a directional delay term. Specifically, our contributions include (1) a high-resolution telepresence environment that is omnidirectional in both the auditory and visual modality, as well as (2) a study of data-based WFAS realistic microphone directivities as a contribution towards for real-time holophonic reproduction.

Audio Engineering Society (AES): 125th Audio Engineering Society Convention. Convention Papers [CD-ROM]. New York: AES and Mira Publishing Inc., 2008, 14 p.

We present a platform for real-time transmission of immersive audiovisual impressions using model- and data- based audio wave-field analysis/synthesis and panoramic video capturing/projection. The audio subsystem considered in this paper is based on microphone arrays with different element counts and directivities as well as weakly directional loudspeaker arrays. We report on both linear and circular setups that feed different wave-field synthesis systems. In an attempt to extend this, we present first findings for a data-based approach derived using experimental simulations. This data-based wave-field analysis/synthesis (WFAS) approach uses a combination of cylindrical-harmonic decomposition of cardioid array signals and enforces causal plane wave synthesis by angular windowing and a directional delay term. Specifically, our contributions include (1) a high-resolution telepresence environment that is omnidirectional in both the auditory and visual modality, as well as (2) a study of data-based WFAS realistic microphone directivities as a contribution towards for real-time holophonic reproduction.

Hochberger, Christian (Ed.) et al.: Informatik 2006. Informatik für Menschen. Band 1 : Beiträge zur 36. Jahrestagung der Gesellschaft für Informatik e.V.. Bonn: Gesellschaft für Informatik, 2006. (GI-Edition - Lecture Notes in Informatics (LNI) P-93), pp. 20-27

Dieser Beitrag stellt laufende Arbeiten an Testkollektionen vor, die für die realistische Simulation semantischer Suche in P2P-Netzwerken verwendet werden können. Er entwickelt eine allgemeine Vorgehensweise für die Erstellung solcher Simulationsdaten. Mithilfe eines probabilistischen Modells wird die semantische Verteilung von Peer-Dokumentenbeständen und Suchanfragen abgedeckt, wobei die verwendeten Dokumente keine Vorklassifizierung benötigen.

Grgic, Mislav (Ed.) et al.: Proceedings ELMAR-2005. Zadar: Croatian Society Electronics in Marine, 2005, pp. 225-228

This article shows an approach to identify speech in a given signal with moderate noise levels. It is based on the segmental structure of speech processes and has two advantages: It is trained exclusively from speech sounds and has a relatively low computational footprint at testing time.

Cunningham, Paul (Ed.) et al.: Innovation and the Knowledge Economy, Part 2 : Issues, Applications, Case Studies. Amsterdam; Berlin: IOS Press, 2005. (Information and Communication Technologies and the Knowledge Economy 2), pp. 1243-1250

In recent years, modern forms of collaboration such as virtual project teams gain importance. But how do individuals identify and select their collaboration partners possessing the required sets of hard and soft skills? While internet-based applications model individuals' resumes or contact networks, to date no applications exist that merge both worlds: human and social capital. This paper presents a software toolkit complementing expertise attributes by a set of historic and swift trust attributes. We then argue that merging these attribute sets will only be an intermediary step towards IS supported smart collaboration networks. We outline a decentralized architecture in which relational recommender systems allow for the prediction of trusted collaboration partnership thus assisting individuals in identifying the most suited collaboration partners from within or outside their personal contact network.

Weisbecker, Anette (Ed.) et al.: Electronic Business : Innovationen, Anwendungen und Technologien. Stuttgart: Fraunhofer IRB Verlag, 2004, pp. 52-59

Innovationen gehören zu den wichtigsten Triebkräften moderner Märkte, und die unmittelbare Voraussetzung für innovative Produkte ist das Wissen ihrer Entwicker. Wissen möglichst schnell finden und in neuen Projekten nutzen zu können, ist ein wichtiger Wettbewerbsvorteil für Unternehmen, aber auch eine Herausforderung sowohl an die personelle als auch an die technische Infrastruktur in der Organisation. Dabei rückt ein Problem auch in modern strukturierten Unternehmensnetzwerken immer wieder in den Vordergrund: das effiziente Zusammenbringen von Wissensangeboten und -nachfrage. Hierbei spielt die Auffindung von Experten- oder Dokumentenwissen genauso eine Rolle wie dessen effiziente (Wieder-)Verwendung in Projekten. Wenn es um längerfristige Zusammenarbeit mit Wissensträgern geht - z.B. in eigens aufgestellten Expertenteams - spielen außer den eigentlichen Expertiseeigenschaften auch die Soft Skills, Kompatibilität und Vertrauenswürdigkeit eine wichtige Rolle. Für die Identifikation und den Zugriff auf Wissen sowohl in einzelnen Unternehmen als auch in Netzwerken von Organisationen werden in diesem Artikel Lösungen vorgestellt, wie sie in Forschungsprojekten und Entwicklungsdienstleistungen für verschiedene Auftraggeber erstellt wurden. Hierbei wird speziell auch auf die technische Infrastruktur eingegangen, welche ab einer bestimmten Anzahl von Organisationseinheiten bzw. Mitarbeitern den Überblick über die Wissensressourcen oft erst ermöglicht.