Fraunhofer-Institut für Angewandte Informationstechnik FIT

Filters
Reset filters

Settings
Now showing 1 - 10 of 1617
  • Publication
    Pushing the frontiers of service research - A taxonomy of proactive services
    ( 2021)
    Rau, D.
    ;
    Röglinger, M.
    ;
    Perlitt, L.-H.
    ;
    Wenninger, A.
    Rapid advancements in digital technologies and data analysis led to a new service type. With their push-rationale, proactive services (PAS) are pushing the frontiers of traditional and even digital or smart services. Such PAS anticipate consumer needs and address them proactively. For instance, a smart fridge replenishes groceries in line with the consumer's preferences, based on anticipated demand, and without the consumer's intervention. In this paper, we contribute to a better understanding of the PAS phenomenon. Therefore, we propose a literature-backed and empirically validated multilayer taxonomy of PAS along the layers consumer, data, and interaction. Further, we compile a list of 45 PAS examples, demonstrate our taxonomy with three illustrative scenarios, and evaluate their understandability and applicability in seven interviews with domain and method experts. Based on gained insights on this rapidly emerging and important phenomenon, we highlight implications f or both researchers and practitioners, and suggest future research directions.
  • Publication
    3CS algorithm for efficient Gaussian process model retrieval
    ( 2021)
    Berns, F.
    ;
    Schmidt, K.
    ;
    Bracht, I.
    ;
    Beecks, C.
    Gaussian Process Models (GPMs) are Bayesian machine learning models that have been widely applied in the domain of pattern recognition due to their ability to infer from unreliable, noisy, or highly idiosyncratic data. Retrieving a complex GPM describing the data's inherent statistical patterns, such as trends, seasonalities, and periodicities, is a key requirement for various pattern recognition tasks. In this paper, we propose a novel approach for efficient large-scale GPM retrieval: the Concatenated Composite Covariance Search (3CS) algorithm. By making use of multiple local kernel searches on dynamically partitioned data, the 3CS algorithm is able to overcome the performance limitations of state-of-the-art GPM retrieval algorithms and to efficiently retrieve GPMs for large-scale data up to three orders of magnitude as fast as state-of-the-art algorithms.
  • Publication
    Freezing Sub-models During Incremental Process Discovery
    ( 2021)
    Schuster, D.
    ;
    Zelst, S.J. van
    ;
    Aalst, W.M.P. van der
    Process discovery aims to learn a process model from observed process behavior. From a user's perspective, most discovery algorithms work like a black box. Besides parameter tuning, there is no interaction between the user and the algorithm. Interactive process discovery allows the user to exploit domain knowledge and to guide the discovery process. Previously, an incremental discovery approach has been introduced where a model, considered to be under ""construction"", gets incrementally extended by user-selected process behavior. This paper introduces a novel approach that additionally allows the user to freeze model parts within the model under construction. Frozen sub-models are not altered by the incremental approach when new behavior is added to the model. The user can thus steer the discovery algorithm. Our experiments show that freezing sub-models can lead to higher quality models.
  • Publication
    Structuring the Jungle of Capabilities Fostering Digital Innovation
    ( 2021)
    Buck, C.
    ;
    Grüneke, T.
    ;
    Stelzl, K.
    Driven by digitalization, the business environment is changing at an increasing pace. To be able to react to this, organizations must gain competitive advantages through Digital Innovation (DI). This special form of innovation requires a reorganization and further development of the resource and capability base of an organization. The existing literature shows a proliferation of definitions and a jungle of individual capabilities with regard to DI. Based on a structured literature review and a qualitative analysis of existing capabilities, the paper presents a DI Capability Model. By structuring layers, areas and associated capabilities, the model provides the first holistic view in the literature. It will serve as a basis for a targeted scientific discourse and a valuable orientation model for the development of a capability composition to foster DI in organizations.
  • Publication
    Innovating with artificial intelligence: Capturing the constructive functional capabilities of deep generative learning
    ( 2021)
    Hofmann, P.
    ;
    Rückel, T.
    ;
    Urbach, N.
    As an emerging species of artificial intelligence, deep generative learning models can generate an unprecedented variety of new outputs. Examples include the creation of music, text-to-image translation, or the imputation of missing data. Similar to other AI models that already evoke significant changes in society and economy, there is a need for structuring the constructive functional capabilities of DGL. To derive and discuss them, we conducted an extensive and structured literature review. Our results reveal a substantial scope of six constructive functional capabilities demonstrating that DGL is not exclusively used to generate unseen outputs. Our paper further guides companies in capturing and evaluating DGL's potential for innovation. Besides, our paper fosters an understanding of DGL and provides a conceptual basis for further research.
  • Publication
    Knowledge-Based Digital Twin for Predicting Interactions in Human-Robot Collaboration
    ( 2021)
    Tuli, T.B.
    ;
    Kohl, L.
    ;
    Chala, S.A.
    ;
    Manns, M.
    ;
    Ansari, F.
    Semantic representation of motions in a human-robot collaborative environment is essential for agile design and development of digital twins (DT) towards ensuring efficient collaboration between humans and robots in hybrid work systems, e.g., in assembly operations. Dividing activities into actions helps to further conceptualize motion models for predicting what a human intends to do in a hybrid work system. However, it is not straightforward to identify human intentions in collaborative operations for robots to understand and collaborate. This paper presents a concept for semantic representation of human actions and intention prediction using a flexible task ontology interface in the semantic data hub stored in a domain knowledge base. This semantic data hub enables the construction of a DT with corresponding reasoning and simulation algorithms. Furthermore, a knowledge-based DT concept is used to analyze and verify the presented use-case of Human-Robot Collaboration i n assembly operations. The preliminary evaluation showed a promising reduction of time for assembly tasks, which identifies the potential to i) improve efficiency reflected by reducing costs and errors and ultimately ii) assist human workers in improving decision making. Thus the contribution of the current work involves a marriage of machine learning, robotics, and ontology engineering into DT to improve human-robot interaction and productivity in a collaborative production environment.
  • Publication
    Discrepancy detection in merkle tree-based hash aggregation
    ( 2021)
    Osterland, T.
    ;
    Lemme, G.
    ;
    Rose, T.
    Hash aggregation is an accepted approach to mitigate the burden of storing substantial amounts of data on a distributed ledger. Merkle trees are used to derive a single hash from data and ensure the integrity of the aggregated individual information. However, to identify a single manipulated datum or a subset of manipulated data, one needs to have access to the entire Merkle tree. This is not a problem if the Merkle tree is stored on the distributed ledger. However, for substantial amounts of hashes, such a tree can become quite large. At some point it is not longer feasible to store the tree on the ledger. Especially, when aggregating large numbers of transactions that occur in a high frequency. In this paper, we discuss four approaches to identify manipulated data in a Merkle tree without the need to persist the entire Merkle tree on the distributed ledger.
  • Publication
    SynZ: Enhanced Synthetic Dataset for Training UI Element Detectors
    ( 2021)
    Pandian Sermuga Pandian, Vinoth
    ;
    Suleri, Sarah
    ;
    Jarke, Matthias
    User Interface (UI) prototyping is an iterative process where designers initially sketch UIs before transforming them into interactive digital designs. Recent research applies Deep Neural Networks (DNNs) to identify the constituent UI elements of these UI sketches and transform these sketches into front-end code. Training such DNN models requires a large-scale dataset of UI sketches, which is time-consuming and expensive to collect. Therefore, we earlier proposed Syn to generate UI sketches synthetically by random allocation of UI element sketches. However, these UI sketches are not statistically similar to real-life UI screens. To bridge this gap, in this paper, we introduce the SynZ dataset, which contains 175,377 synthetically generated UI sketches statistically similar to real-life UI screens. To generate SynZ, we analyzed, enhanced, and extracted annotations from the RICO dataset and used 17,979 hand-drawn UI element sketches from the UISketch dataset. Further, we fine-tuned a UI element detector with SynZ and observed that it doubles the mean Average Precision of UI element detection compared to the Syn dataset.
  • Publication
    Cultural Master Plan Bamiyan (Afghanistan) - A Process Model for the Management of Cultural Landscapes Based on Remote-Sensing Data
    ( 2021)
    Toubekis, G.
    ;
    Jansen, M.
    ;
    Jarke, M.
    The Cultural Landscape and Archaeological Remains of the Bamiyan Valley are inscribed on the UNESCO World Heritage List since 2003. An international safeguarding campaign is active for its preservation, including the remains of the Buddha figures destroyed by the Taliban in 2001. Efforts are underway to set up an effective management system for the historical areas within a wider landscape approach balancing conflicting uses and demands. Based on detailed high-resolution satellite imagery and accompanying ground surveys, a comprehensive inventory of vernacular settlements, traditional water systems, and historic cultural remains was compiled. The Bamiyan Cultural Masterplan has been elaborated as a zoning proposal to support future planning processes in Bamiyan. A GIS System has been set up to manage planning and monitoring activities in the future. The current condition of the archaeological remains of Bamiyan has been documented with different remote sensing and high precision 3D documentation methods. Within cultural heritage management, Virtual Reality technologies are an innovative approach for documentation and presentation of complex architectural objects, especially in landscape settings. The project includes a digital reconstruction of the destroyed Small Buddha (38 m) Figure of Bamiyan integrated into the high-resolution 3D model of the niche and the cliff. The composite model of previous and actual conditions serves as a communication and planning tool for future consolidation for experts and the interested public.