@article{ZimmererFischbachLatoschik2018, author = {Zimmerer, Chris and Fischbach, Martin and Latoschik, Marc Erich}, title = {Semantic Fusion for Natural Multimodal Interfaces using Concurrent Augmented Transition Networks}, series = {Multimodal Technologies and Interaction}, volume = {2}, journal = {Multimodal Technologies and Interaction}, number = {4}, issn = {2414-4088}, doi = {10.3390/mti2040081}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-197573}, year = {2018}, abstract = {Semantic fusion is a central requirement of many multimodal interfaces. Procedural methods like finite-state transducers and augmented transition networks have proven to be beneficial to implement semantic fusion. They are compliant with rapid development cycles that are common for the development of user interfaces, in contrast to machine-learning approaches that require time-costly training and optimization. We identify seven fundamental requirements for the implementation of semantic fusion: Action derivation, continuous feedback, context-sensitivity, temporal relation support, access to the interaction context, as well as the support of chronologically unsorted and probabilistic input. A subsequent analysis reveals, however, that there is currently no solution for fulfilling the latter two requirements. As the main contribution of this article, we thus present the Concurrent Cursor concept to compensate these shortcomings. In addition, we showcase a reference implementation, the Concurrent Augmented Transition Network (cATN), that validates the concept's feasibility in a series of proof of concept demonstrations as well as through a comparative benchmark. The cATN fulfills all identified requirements and fills the lack amongst previous solutions. It supports the rapid prototyping of multimodal interfaces by means of five concrete traits: Its declarative nature, the recursiveness of the underlying transition network, the network abstraction constructs of its description language, the utilized semantic queries, and an abstraction layer for lexical information. Our reference implementation was and is used in various student projects, theses, as well as master-level courses. It is openly available and showcases that non-experts can effectively implement multimodal interfaces, even for non-trivial applications in mixed and virtual reality.}, language = {en} } @article{WolffRutter2012, author = {Wolff, Alexander and Rutter, Iganz}, title = {Augmenting the Connectivity of Planar and Geometric Graphs}, series = {Journal of Graph Algorithms and Applications}, journal = {Journal of Graph Algorithms and Applications}, doi = {10.7155/jgaa.00275}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-97587}, year = {2012}, abstract = {In this paper we study connectivity augmentation problems. Given a connected graph G with some desirable property, we want to make G 2-vertex connected (or 2-edge connected) by adding edges such that the resulting graph keeps the property. The aim is to add as few edges as possible. The property that we consider is planarity, both in an abstract graph-theoretic and in a geometric setting, where vertices correspond to points in the plane and edges to straight-line segments. We show that it is NP-hard to � nd a minimum-cardinality augmentation that makes a planar graph 2-edge connected. For making a planar graph 2-vertex connected this was known. We further show that both problems are hard in the geometric setting, even when restricted to trees. The problems remain hard for higher degrees of connectivity. On the other hand we give polynomial-time algorithms for the special case of convex geometric graphs. We also study the following related problem. Given a planar (plane geometric) graph G, two vertices s and t of G, and an integer c, how many edges have to be added to G such that G is still planar (plane geometric) and contains c edge- (or vertex-) disjoint s{t paths? For the planar case we give a linear-time algorithm for c = 2. For the plane geometric case we give optimal worst-case bounds for c = 2; for c = 3 we characterize the cases that have a solution.}, language = {en} } @article{WienrichLatoschik2021, author = {Wienrich, Carolin and Latoschik, Marc Erich}, title = {eXtended Artificial Intelligence: New Prospects of Human-AI Interaction Research}, series = {Frontiers in Virtual Reality}, volume = {2}, journal = {Frontiers in Virtual Reality}, doi = {10.3389/frvir.2021.686783}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-260296}, year = {2021}, abstract = {Artificial Intelligence (AI) covers a broad spectrum of computational problems and use cases. Many of those implicate profound and sometimes intricate questions of how humans interact or should interact with AIs. Moreover, many users or future users do have abstract ideas of what AI is, significantly depending on the specific embodiment of AI applications. Human-centered-design approaches would suggest evaluating the impact of different embodiments on human perception of and interaction with AI. An approach that is difficult to realize due to the sheer complexity of application fields and embodiments in reality. However, here XR opens new possibilities to research human-AI interactions. The article's contribution is twofold: First, it provides a theoretical treatment and model of human-AI interaction based on an XR-AI continuum as a framework for and a perspective of different approaches of XR-AI combinations. It motivates XR-AI combinations as a method to learn about the effects of prospective human-AI interfaces and shows why the combination of XR and AI fruitfully contributes to a valid and systematic investigation of human-AI interactions and interfaces. Second, the article provides two exemplary experiments investigating the aforementioned approach for two distinct AI-systems. The first experiment reveals an interesting gender effect in human-robot interaction, while the second experiment reveals an Eliza effect of a recommender system. Here the article introduces two paradigmatic implementations of the proposed XR testbed for human-AI interactions and interfaces and shows how a valid and systematic investigation can be conducted. In sum, the article opens new perspectives on how XR benefits human-centered AI design and development.}, language = {en} } @article{WienrichKommaVogtetal.2021, author = {Wienrich, Carolin and Komma, Philipp and Vogt, Stephanie and Latoschik, Marc E.}, title = {Spatial Presence in Mixed Realities - Considerations About the Concept, Measures, Design, and Experiments}, series = {Frontiers in Virtual Reality}, volume = {2}, journal = {Frontiers in Virtual Reality}, doi = {10.3389/frvir.2021.694315}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-260328}, year = {2021}, abstract = {Plenty of theories, models, measures, and investigations target the understanding of virtual presence, i.e., the sense of presence in immersive Virtual Reality (VR). Other varieties of the so-called eXtended Realities (XR), e.g., Augmented and Mixed Reality (AR and MR) incorporate immersive features to a lesser degree and continuously combine spatial cues from the real physical space and the simulated virtual space. This blurred separation questions the applicability of the accumulated knowledge about the similarities of virtual presence and presence occurring in other varieties of XR, and corresponding outcomes. The present work bridges this gap by analyzing the construct of presence in mixed realities (MR). To achieve this, the following presents (1) a short review of definitions, dimensions, and measurements of presence in VR, and (2) the state of the art views on MR. Additionally, we (3) derived a working definition of MR, extending the Milgram continuum. This definition is based on entities reaching from real to virtual manifestations at one time point. Entities possess different degrees of referential power, determining the selection of the frame of reference. Furthermore, we (4) identified three research desiderata, including research questions about the frame of reference, the corresponding dimension of transportation, and the dimension of realism in MR. Mainly the relationship between the main aspects of virtual presence of immersive VR, i.e., the place-illusion, and the plausibility-illusion, and of the referential power of MR entities are discussed regarding the concept, measures, and design of presence in MR. Finally, (5) we suggested an experimental setup to reveal the research heuristic behind experiments investigating presence in MR. The present work contributes to the theories and the meaning of and approaches to simulate and measure presence in MR. We hypothesize that research about essential underlying factors determining user experience (UX) in MR simulations and experiences is still in its infancy and hopes this article provides an encouraging starting point to tackle related questions.}, language = {en} } @article{WienrichCarolusMarkusetal.2023, author = {Wienrich, Carolin and Carolus, Astrid and Markus, Andr{\´e} and Augustin, Yannik and Pfister, Jan and Hotho, Andreas}, title = {Long-term effects of perceived friendship with intelligent voice assistants on usage behavior, user experience, and social perceptions}, series = {Computers}, volume = {12}, journal = {Computers}, number = {4}, issn = {2073-431X}, doi = {10.3390/computers12040077}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-313552}, year = {2023}, abstract = {Social patterns and roles can develop when users talk to intelligent voice assistants (IVAs) daily. The current study investigates whether users assign different roles to devices and how this affects their usage behavior, user experience, and social perceptions. Since social roles take time to establish, we equipped 106 participants with Alexa or Google assistants and some smart home devices and observed their interactions for nine months. We analyzed diverse subjective (questionnaire) and objective data (interaction data). By combining social science and data science analyses, we identified two distinct clusters—users who assigned a friendship role to IVAs over time and users who did not. Interestingly, these clusters exhibited significant differences in their usage behavior, user experience, and social perceptions of the devices. For example, participants who assigned a role to IVAs attributed more friendship to them used them more frequently, reported more enjoyment during interactions, and perceived more empathy for IVAs. In addition, these users had distinct personal requirements, for example, they reported more loneliness. This study provides valuable insights into the role-specific effects and consequences of voice assistants. Recent developments in conversational language models such as ChatGPT suggest that the findings of this study could make an important contribution to the design of dialogic human-AI interactions.}, language = {en} } @article{WickHarteltPuppe2019, author = {Wick, Christoph and Hartelt, Alexander and Puppe, Frank}, title = {Staff, symbol and melody detection of Medieval manuscripts written in square notation using deep Fully Convolutional Networks}, series = {Applied Sciences}, volume = {9}, journal = {Applied Sciences}, number = {13}, issn = {2076-3417}, doi = {10.3390/app9132646}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-197248}, year = {2019}, abstract = {Even today, the automatic digitisation of scanned documents in general, but especially the automatic optical music recognition (OMR) of historical manuscripts, still remains an enormous challenge, since both handwritten musical symbols and text have to be identified. This paper focuses on the Medieval so-called square notation developed in the 11th-12th century, which is already composed of staff lines, staves, clefs, accidentals, and neumes that are roughly spoken connected single notes. The aim is to develop an algorithm that captures both the neumes, and in particular its melody, which can be used to reconstruct the original writing. Our pipeline is similar to the standard OMR approach and comprises a novel staff line and symbol detection algorithm based on deep Fully Convolutional Networks (FCN), which perform pixel-based predictions for either staff lines or symbols and their respective types. Then, the staff line detection combines the extracted lines to staves and yields an F\(_1\) -score of over 99\% for both detecting lines and complete staves. For the music symbol detection, we choose a novel approach that skips the step to identify neumes and instead directly predicts note components (NCs) and their respective affiliation to a neume. Furthermore, the algorithm detects clefs and accidentals. Our algorithm predicts the symbol sequence of a staff with a diplomatic symbol accuracy rate (dSAR) of about 87\%, which includes symbol type and location. If only the NCs without their respective connection to a neume, all clefs and accidentals are of interest, the algorithm reaches an harmonic symbol accuracy rate (hSAR) of approximately 90\%. In general, the algorithm recognises a symbol in the manuscript with an F\(_1\) -score of over 96\%.}, language = {en} } @article{WamserSeufertHalletal.2021, author = {Wamser, Florian and Seufert, Anika and Hall, Andrew and Wunderer, Stefan and Hoßfeld, Tobias}, title = {Valid statements by the crowd: statistical measures for precision in crowdsourced mobile measurements}, series = {Network}, volume = {1}, journal = {Network}, number = {2}, issn = {2673-8732}, doi = {10.3390/network1020013}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-284154}, pages = {215 -- 232}, year = {2021}, abstract = {Crowdsourced network measurements (CNMs) are becoming increasingly popular as they assess the performance of a mobile network from the end user's perspective on a large scale. Here, network measurements are performed directly on the end-users' devices, thus taking advantage of the real-world conditions end-users encounter. However, this type of uncontrolled measurement raises questions about its validity and reliability. The problem lies in the nature of this type of data collection. In CNMs, mobile network subscribers are involved to a large extent in the measurement process, and collect data themselves for the operator. The collection of data on user devices in arbitrary locations and at uncontrolled times requires means to ensure validity and reliability. To address this issue, our paper defines concepts and guidelines for analyzing the precision of CNMs; specifically, the number of measurements required to make valid statements. In addition to the formal definition of the aspect, we illustrate the problem and use an extensive sample data set to show possible assessment approaches. This data set consists of more than 20.4 million crowdsourced mobile measurements from across France, measured by a commercial data provider.}, language = {en} } @article{UnruhLandeckOberdoerferetal.2021, author = {Unruh, Fabian and Landeck, Maximilian and Oberd{\"o}rfer, Sebastian and Lugrin, Jean-Luc and Latoschik, Marc Erich}, title = {The Influence of Avatar Embodiment on Time Perception - Towards VR for Time-Based Therapy}, series = {Frontiers in Virtual Reality}, volume = {2}, journal = {Frontiers in Virtual Reality}, doi = {10.3389/frvir.2021.658509}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-259076}, pages = {658509}, year = {2021}, abstract = {Psycho-pathological conditions, such as depression or schizophrenia, are often accompanied by a distorted perception of time. People suffering from this conditions often report that the passage of time slows down considerably and that they are "stuck in time." Virtual Reality (VR) could potentially help to diagnose and maybe treat such mental conditions. However, the conditions in which a VR simulation could correctly diagnose a time perception deviation are still unknown. In this paper, we present an experiment investigating the difference in time experience with and without a virtual body in VR, also known as avatar. The process of substituting a person's body with a virtual body is called avatar embodiment. Numerous studies demonstrated interesting perceptual, emotional, behavioral, and psychological effects caused by avatar embodiment. However, the relations between time perception and avatar embodiment are still unclear. Whether or not the presence or absence of an avatar is already influencing time perception is still open to question. Therefore, we conducted a between-subjects design with and without avatar embodiment as well as a real condition (avatar vs. no-avatar vs. real). A group of 105 healthy subjects had to wait for seven and a half minutes in a room without any distractors (e.g., no window, magazine, people, decoration) or time indicators (e.g., clocks, sunlight). The virtual environment replicates the real physical environment. Participants were unaware that they will be asked to estimate their waiting time duration as well as describing their experience of the passage of time at a later stage. Our main finding shows that the presence of an avatar is leading to a significantly faster perceived passage of time. It seems to be promising to integrate avatar embodiment in future VR time-based therapy applications as they potentially could modulate a user's perception of the passage of time. We also found no significant difference in time perception between the real and the VR conditions (avatar, no-avatar), but further research is needed to better understand this outcome.}, language = {en} } @article{TsouliasJoerissenNuechter2022, author = {Tsoulias, Nikos and J{\"o}rissen, Sven and N{\"u}chter, Andreas}, title = {An approach for monitoring temperature on fruit surface by means of thermal point cloud}, series = {MethodsX}, volume = {9}, journal = {MethodsX}, issn = {2215-0161}, doi = {10.1016/j.mex.2022.101712}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-300270}, year = {2022}, abstract = {Heat and excessive solar radiation can produce abiotic stresses during apple maturation, resulting fruit quality. Therefore, the monitoring of temperature on fruit surface (FST) over the growing period can allow to identify thresholds, above of which several physiological disorders such as sunburn may occur in apple. The current approaches neglect spatial variation of FST and have reduced repeatability, resulting in unreliable predictions. In this study, LiDAR laser scanning and thermal imaging were employed to detect the temperature on fruit surface by means of 3D point cloud. A process for calibrating the two sensors based on an active board target and producing a 3D thermal point cloud was suggested. After calibration, the sensor system was utilised to scan the fruit trees, while temperature values assigned in the corresponding 3D point cloud were based on the extrinsic calibration. Whereas a fruit detection algorithm was performed to segment the FST from each apple. • The approach allows the calibration of LiDAR laser scanner with thermal camera in order to produce a 3D thermal point cloud. • The method can be applied in apple trees for segmenting FST in 3D. Whereas the approach can be utilised to predict several physiological disorders including sunburn on fruit surface.}, language = {en} } @article{ToepferCorovicFetteetal.2015, author = {Toepfer, Martin and Corovic, Hamo and Fette, Georg and Kl{\"u}gl, Peter and St{\"o}rk, Stefan and Puppe, Frank}, title = {Fine-grained information extraction from German transthoracic echocardiography reports}, series = {BMC Medical Informatics and Decision Making}, volume = {15}, journal = {BMC Medical Informatics and Decision Making}, number = {91}, doi = {doi:10.1186/s12911-015-0215-x}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-125509}, year = {2015}, abstract = {Background Information extraction techniques that get structured representations out of unstructured data make a large amount of clinically relevant information about patients accessible for semantic applications. These methods typically rely on standardized terminologies that guide this process. Many languages and clinical domains, however, lack appropriate resources and tools, as well as evaluations of their applications, especially if detailed conceptualizations of the domain are required. For instance, German transthoracic echocardiography reports have not been targeted sufficiently before, despite of their importance for clinical trials. This work therefore aimed at development and evaluation of an information extraction component with a fine-grained terminology that enables to recognize almost all relevant information stated in German transthoracic echocardiography reports at the University Hospital of W{\"u}rzburg. Methods A domain expert validated and iteratively refined an automatically inferred base terminology. The terminology was used by an ontology-driven information extraction system that outputs attribute value pairs. The final component has been mapped to the central elements of a standardized terminology, and it has been evaluated according to documents with different layouts. Results The final system achieved state-of-the-art precision (micro average.996) and recall (micro average.961) on 100 test documents that represent more than 90 \% of all reports. In particular, principal aspects as defined in a standardized external terminology were recognized with f 1=.989 (micro average) and f 1=.963 (macro average). As a result of keyword matching and restraint concept extraction, the system obtained high precision also on unstructured or exceptionally short documents, and documents with uncommon layout. Conclusions The developed terminology and the proposed information extraction system allow to extract fine-grained information from German semi-structured transthoracic echocardiography reports with very high precision and high recall on the majority of documents at the University Hospital of W{\"u}rzburg. Extracted results populate a clinical data warehouse which supports clinical research.}, language = {en} }