@article{SteiningerAbelZiegleretal.2023, author = {Steininger, Michael and Abel, Daniel and Ziegler, Katrin and Krause, Anna and Paeth, Heiko and Hotho, Andreas}, title = {ConvMOS: climate model output statistics with deep learning}, series = {Data Mining and Knowledge Discovery}, volume = {37}, journal = {Data Mining and Knowledge Discovery}, number = {1}, issn = {1384-5810}, doi = {10.1007/s10618-022-00877-6}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-324213}, pages = {136-166}, year = {2023}, abstract = {Climate models are the tool of choice for scientists researching climate change. Like all models they suffer from errors, particularly systematic and location-specific representation errors. One way to reduce these errors is model output statistics (MOS) where the model output is fitted to observational data with machine learning. In this work, we assess the use of convolutional Deep Learning climate MOS approaches and present the ConvMOS architecture which is specifically designed based on the observation that there are systematic and location-specific errors in the precipitation estimates of climate models. We apply ConvMOS models to the simulated precipitation of the regional climate model REMO, showing that a combination of per-location model parameters for reducing location-specific errors and global model parameters for reducing systematic errors is indeed beneficial for MOS performance. We find that ConvMOS models can reduce errors considerably and perform significantly better than three commonly used MOS approaches and plain ResNet and U-Net models in most cases. Our results show that non-linear MOS models underestimate the number of extreme precipitation events, which we alleviate by training models specialized towards extreme precipitation events with the imbalanced regression method DenseLoss. While we consider climate MOS, we argue that aspects of ConvMOS may also be beneficial in other domains with geospatial data, such as air pollution modeling or weather forecasts.}, subject = {Klima}, language = {en} } @article{KempfKrugPuppe2023, author = {Kempf, Sebastian and Krug, Markus and Puppe, Frank}, title = {KIETA: Key-insight extraction from scientific tables}, series = {Applied Intelligence}, volume = {53}, journal = {Applied Intelligence}, number = {8}, issn = {0924-669X}, doi = {10.1007/s10489-022-03957-8}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-324180}, pages = {9513-9530}, year = {2023}, abstract = {An important but very time consuming part of the research process is literature review. An already large and nevertheless growing ground set of publications as well as a steadily increasing publication rate continue to worsen the situation. Consequently, automating this task as far as possible is desirable. Experimental results of systems are key-insights of high importance during literature review and usually represented in form of tables. Our pipeline KIETA exploits these tables to contribute to the endeavor of automation by extracting them and their contained knowledge from scientific publications. The pipeline is split into multiple steps to guarantee modularity as well as analyzability, and agnosticim regarding the specific scientific domain up until the knowledge extraction step, which is based upon an ontology. Additionally, a dataset of corresponding articles has been manually annotated with information regarding table and knowledge extraction. Experiments show promising results that signal the possibility of an automated system, while also indicating limits of extracting knowledge from tables without any context.}, language = {en} } @article{MaiwaldBruschkeSchneideretal.2023, author = {Maiwald, Ferdinand and Bruschke, Jonas and Schneider, Danilo and Wacker, Markus and Niebling, Florian}, title = {Giving historical photographs a new perspective: introducing camera orientation parameters as new metadata in a large-scale 4D application}, series = {Remote Sensing}, volume = {15}, journal = {Remote Sensing}, number = {7}, issn = {2072-4292}, doi = {10.3390/rs15071879}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-311103}, year = {2023}, abstract = {The ongoing digitization of historical photographs in archives allows investigating the quality, quantity, and distribution of these images. However, the exact interior and exterior camera orientations of these photographs are usually lost during the digitization process. The proposed method uses content-based image retrieval (CBIR) to filter exterior images of single buildings in combination with metadata information. The retrieved photographs are automatically processed in an adapted structure-from-motion (SfM) pipeline to determine the camera parameters. In an interactive georeferencing process, the calculated camera positions are transferred into a global coordinate system. As all image and camera data are efficiently stored in the proposed 4D database, they can be conveniently accessed afterward to georeference newly digitized images by using photogrammetric triangulation and spatial resection. The results show that the CBIR and the subsequent SfM are robust methods for various kinds of buildings and different quantity of data. The absolute accuracy of the camera positions after georeferencing lies in the range of a few meters likely introduced by the inaccurate LOD2 models used for transformation. The proposed photogrammetric method, the database structure, and the 4D visualization interface enable adding historical urban photographs and 3D models from other locations.}, language = {en} } @article{FischerHarteltPuppe2023, author = {Fischer, Norbert and Hartelt, Alexander and Puppe, Frank}, title = {Line-level layout recognition of historical documents with background knowledge}, series = {Algorithms}, volume = {16}, journal = {Algorithms}, number = {3}, issn = {1999-4893}, doi = {10.3390/a16030136}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-310938}, year = {2023}, abstract = {Digitization and transcription of historic documents offer new research opportunities for humanists and are the topics of many edition projects. However, manual work is still required for the main phases of layout recognition and the subsequent optical character recognition (OCR) of early printed documents. This paper describes and evaluates how deep learning approaches recognize text lines and can be extended to layout recognition using background knowledge. The evaluation was performed on five corpora of early prints from the 15th and 16th Centuries, representing a variety of layout features. While the main text with standard layouts could be recognized in the correct reading order with a precision and recall of up to 99.9\%, also complex layouts were recognized at a rate as high as 90\% by using background knowledge, the full potential of which was revealed if many pages of the same source were transcribed.}, language = {en} } @article{KirikkayisGallikWinteretal.2023, author = {Kirikkayis, Yusuf and Gallik, Florian and Winter, Michael and Reichert, Manfred}, title = {BPMNE4IoT: a framework for modeling, executing and monitoring IoT-driven processes}, series = {Future Internet}, volume = {15}, journal = {Future Internet}, number = {3}, issn = {1999-5903}, doi = {10.3390/fi15030090}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-304097}, year = {2023}, abstract = {The Internet of Things (IoT) enables a variety of smart applications, including smart home, smart manufacturing, and smart city. By enhancing Business Process Management Systems with IoT capabilities, the execution and monitoring of business processes can be significantly improved. Providing a holistic support for modeling, executing and monitoring IoT-driven processes, however, constitutes a challenge. Existing process modeling and process execution languages, such as BPMN 2.0, are unable to fully meet the IoT characteristics (e.g., asynchronicity and parallelism) of IoT-driven processes. In this article, we present BPMNE4IoT—A holistic framework for modeling, executing and monitoring IoT-driven processes. We introduce various artifacts and events based on the BPMN 2.0 metamodel that allow realizing the desired IoT awareness of business processes. The framework is evaluated along two real-world scenarios from two different domains. Moreover, we present a user study for comparing BPMNE4IoT and BPMN 2.0. In particular, this study has confirmed that the BPMNE4IoT framework facilitates the support of IoT-driven processes.}, 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{GreubelAndresHennecke2023, author = {Greubel, Andr{\´e} and Andres, Daniela and Hennecke, Martin}, title = {Analyzing reporting on ransomware incidents: a case study}, series = {Social Sciences}, volume = {12}, journal = {Social Sciences}, number = {5}, issn = {2076-0760}, doi = {10.3390/socsci12050265}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-313746}, year = {2023}, abstract = {Knowledge about ransomware is important for protecting sensitive data and for participating in public debates about suitable regulation regarding its security. However, as of now, this topic has received little to no attention in most school curricula. As such, it is desirable to analyze what citizens can learn about this topic outside of formal education, e.g., from news articles. This analysis is both relevant to analyzing the public discourse about ransomware, as well as to identify what aspects of this topic should be included in the limited time available for this topic in formal education. Thus, this paper was motivated both by educational and media research. The central goal is to explore how the media reports on this topic and, additionally, to identify potential misconceptions that could stem from this reporting. To do so, we conducted an exploratory case study into the reporting of 109 media articles regarding a high-impact ransomware event: the shutdown of the Colonial Pipeline (located in the east of the USA). We analyzed how the articles introduced central terminology, what details were provided, what details were not, and what (mis-)conceptions readers might receive from them. Our results show that an introduction of the terminology and technical concepts of security is insufficient for a complete understanding of the incident. Most importantly, the articles may lead to four misconceptions about ransomware that are likely to lead to misleading conclusions about the responsibility for the incident and possible political and technical options to prevent such attacks in the future.}, language = {en} } @article{HossfeldHeegaardKellerer2023, author = {Hossfeld, Tobias and Heegaard, Poul E. and Kellerer, Wolfgang}, title = {Comparing the scalability of communication networks and systems}, series = {IEEE Access}, volume = {11}, journal = {IEEE Access}, doi = {10.1109/ACCESS.2023.3314201}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-349403}, pages = {101474-101497}, year = {2023}, abstract = {Scalability is often mentioned in literature, but a stringent definition is missing. In particular, there is no general scalability assessment which clearly indicates whether a system scales or not or whether a system scales better than another. The key contribution of this article is the definition of a scalability index (SI) which quantifies if a system scales in comparison to another system, a hypothetical system, e.g., linear system, or the theoretically optimal system. The suggested SI generalizes different metrics from literature, which are specialized cases of our SI. The primary target of our scalability framework is, however, benchmarking of two systems, which does not require any reference system. The SI is demonstrated and evaluated for different use cases, that are (1) the performance of an IoT load balancer depending on the system load, (2) the availability of a communication system depending on the size and structure of the network, (3) scalability comparison of different location selection mechanisms in fog computing with respect to delays and energy consumption; (4) comparison of time-sensitive networking (TSN) mechanisms in terms of efficiency and utilization. Finally, we discuss how to use and how not to use the SI and give recommendations and guidelines in practice. To the best of our knowledge, this is the first work which provides a general SI for the comparison and benchmarking of systems, which is the primary target of our scalability analysis.}, language = {en} } @article{MuellerLeppichGeissetal.2023, author = {M{\"u}ller, Konstantin and Leppich, Robert and Geiß, Christian and Borst, Vanessa and Pelizari, Patrick Aravena and Kounev, Samuel and Taubenb{\"o}ck, Hannes}, title = {Deep neural network regression for normalized digital surface model generation with Sentinel-2 imagery}, series = {IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing}, volume = {16}, journal = {IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing}, issn = {1939-1404}, doi = {10.1109/JSTARS.2023.3297710}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-349424}, pages = {8508-8519}, year = {2023}, abstract = {In recent history, normalized digital surface models (nDSMs) have been constantly gaining importance as a means to solve large-scale geographic problems. High-resolution surface models are precious, as they can provide detailed information for a specific area. However, measurements with a high resolution are time consuming and costly. Only a few approaches exist to create high-resolution nDSMs for extensive areas. This article explores approaches to extract high-resolution nDSMs from low-resolution Sentinel-2 data, allowing us to derive large-scale models. We thereby utilize the advantages of Sentinel 2 being open access, having global coverage, and providing steady updates through a high repetition rate. Several deep learning models are trained to overcome the gap in producing high-resolution surface maps from low-resolution input data. With U-Net as a base architecture, we extend the capabilities of our model by integrating tailored multiscale encoders with differently sized kernels in the convolution as well as conformed self-attention inside the skip connection gates. Using pixelwise regression, our U-Net base models can achieve a mean height error of approximately 2 m. Moreover, through our enhancements to the model architecture, we reduce the model error by more than 7\%.}, language = {en} } @article{LimanMayFetteetal.2023, author = {Liman, Leon and May, Bernd and Fette, Georg and Krebs, Jonathan and Puppe, Frank}, title = {Using a clinical data warehouse to calculate and present key metrics for the radiology department: implementation and performance evaluation}, series = {JMIR Medical Informatics}, volume = {11}, journal = {JMIR Medical Informatics}, issn = {2291-9694}, doi = {10.2196/41808}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-349411}, year = {2023}, abstract = {Background: Due to the importance of radiologic examinations, such as X-rays or computed tomography scans, for many clinical diagnoses, the optimal use of the radiology department is 1 of the primary goals of many hospitals. Objective: This study aims to calculate the key metrics of this use by creating a radiology data warehouse solution, where data from radiology information systems (RISs) can be imported and then queried using a query language as well as a graphical user interface (GUI). Methods: Using a simple configuration file, the developed system allowed for the processing of radiology data exported from any kind of RIS into a Microsoft Excel, comma-separated value (CSV), or JavaScript Object Notation (JSON) file. These data were then imported into a clinical data warehouse. Additional values based on the radiology data were calculated during this import process by implementing 1 of several provided interfaces. Afterward, the query language and GUI of the data warehouse were used to configure and calculate reports on these data. For the most common types of requested reports, a web interface was created to view their numbers as graphics. Results: The tool was successfully tested with the data of 4 different German hospitals from 2018 to 2021, with a total of 1,436,111 examinations. The user feedback was good, since all their queries could be answered if the available data were sufficient. The initial processing of the radiology data for using them with the clinical data warehouse took (depending on the amount of data provided by each hospital) between 7 minutes and 1 hour 11 minutes. Calculating 3 reports of different complexities on the data of each hospital was possible in 1-3 seconds for reports with up to 200 individual calculations and in up to 1.5 minutes for reports with up to 8200 individual calculations. Conclusions: A system was developed with the main advantage of being generic concerning the export of different RISs as well as concerning the configuration of queries for various reports. The queries could be configured easily using the GUI of the data warehouse, and their results could be exported into the standard formats Excel and CSV for further processing.}, language = {en} } @article{SeufertPoigneeSeufertetal.2023, author = {Seufert, Anika and Poign{\´e}e, Fabian and Seufert, Michael and Hoßfeld, Tobias}, title = {Share and multiply: modeling communication and generated traffic in private WhatsApp groups}, series = {IEEE Access}, volume = {11}, journal = {IEEE Access}, doi = {10.1109/ACCESS.2023.3254913}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-349430}, pages = {25401-25414}, year = {2023}, abstract = {Group-based communication is a highly popular communication paradigm, which is especially prominent in mobile instant messaging (MIM) applications, such as WhatsApp. Chat groups in MIM applications facilitate the sharing of various types of messages (e.g., text, voice, image, video) among a large number of participants. As each message has to be transmitted to every other member of the group, which multiplies the traffic, this has a massive impact on the underlying communication networks. However, most chat groups are private and network operators cannot obtain deep insights into MIM communication via network measurements due to end-to-end encryption. Thus, the generation of traffic is not well understood, given that it depends on sizes of communication groups, speed of communication, and exchanged message types. In this work, we provide a huge data set of 5,956 private WhatsApp chat histories, which contains over 76 million messages from more than 117,000 users. We describe and model the properties of chat groups and users, and the communication within these chat groups, which gives unprecedented insights into private MIM communication. In addition, we conduct exemplary measurements for the most popular message types, which empower the provided models to estimate the traffic over time in a chat group.}, language = {en} } @article{LeschKoenigKounevetal.2022, author = {Lesch, Veronika and K{\"o}nig, Maximilian and Kounev, Samuel and Stein, Anthony and Krupitzer, Christian}, title = {Tackling the rich vehicle routing problem with nature-inspired algorithms}, series = {Applied Intelligence}, volume = {52}, journal = {Applied Intelligence}, issn = {1573-7497}, doi = {10.1007/s10489-021-03035-5}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-268942}, pages = {9476-9500}, year = {2022}, abstract = {In the last decades, the classical Vehicle Routing Problem (VRP), i.e., assigning a set of orders to vehicles and planning their routes has been intensively researched. As only the assignment of order to vehicles and their routes is already an NP-complete problem, the application of these algorithms in practice often fails to take into account the constraints and restrictions that apply in real-world applications, the so called rich VRP (rVRP) and are limited to single aspects. In this work, we incorporate the main relevant real-world constraints and requirements. We propose a two-stage strategy and a Timeline algorithm for time windows and pause times, and apply a Genetic Algorithm (GA) and Ant Colony Optimization (ACO) individually to the problem to find optimal solutions. Our evaluation of eight different problem instances against four state-of-the-art algorithms shows that our approach handles all given constraints in a reasonable time.}, language = {en} } @article{ReinhardHelmerichBorasetal.2022, author = {Reinhard, Sebastian and Helmerich, Dominic A. and Boras, Dominik and Sauer, Markus and Kollmannsberger, Philip}, title = {ReCSAI: recursive compressed sensing artificial intelligence for confocal lifetime localization microscopy}, series = {BMC Bioinformatics}, volume = {23}, journal = {BMC Bioinformatics}, number = {1}, doi = {10.1186/s12859-022-05071-5}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-299768}, year = {2022}, abstract = {Background Localization-based super-resolution microscopy resolves macromolecular structures down to a few nanometers by computationally reconstructing fluorescent emitter coordinates from diffraction-limited spots. The most commonly used algorithms are based on fitting parametric models of the point spread function (PSF) to a measured photon distribution. These algorithms make assumptions about the symmetry of the PSF and thus, do not work well with irregular, non-linear PSFs that occur for example in confocal lifetime imaging, where a laser is scanned across the sample. An alternative method for reconstructing sparse emitter sets from noisy, diffraction-limited images is compressed sensing, but due to its high computational cost it has not yet been widely adopted. Deep neural network fitters have recently emerged as a new competitive method for localization microscopy. They can learn to fit arbitrary PSFs, but require extensive simulated training data and do not generalize well. A method to efficiently fit the irregular PSFs from confocal lifetime localization microscopy combining the advantages of deep learning and compressed sensing would greatly improve the acquisition speed and throughput of this method. Results Here we introduce ReCSAI, a compressed sensing neural network to reconstruct localizations for confocal dSTORM, together with a simulation tool to generate training data. We implemented and compared different artificial network architectures, aiming to combine the advantages of compressed sensing and deep learning. We found that a U-Net with a recursive structure inspired by iterative compressed sensing showed the best results on realistic simulated datasets with noise, as well as on real experimentally measured confocal lifetime scanning data. Adding a trainable wavelet denoising layer as prior step further improved the reconstruction quality. Conclusions Our deep learning approach can reach a similar reconstruction accuracy for confocal dSTORM as frame binning with traditional fitting without requiring the acquisition of multiple frames. In addition, our work offers generic insights on the reconstruction of sparse measurements from noisy experimental data by combining compressed sensing and deep learning. We provide the trained networks, the code for network training and inference as well as the simulation tool as python code and Jupyter notebooks for easy reproducibility.}, language = {en} } @article{BencurovaShityakovSchaacketal.2022, author = {Bencurova, Elena and Shityakov, Sergey and Schaack, Dominik and Kaltdorf, Martin and Sarukhanyan, Edita and Hilgarth, Alexander and Rath, Christin and Montenegro, Sergio and Roth, G{\"u}nter and Lopez, Daniel and Dandekar, Thomas}, title = {Nanocellulose composites as smart devices with chassis, light-directed DNA Storage, engineered electronic properties, and chip integration}, series = {Frontiers in Bioengineering and Biotechnology}, volume = {10}, journal = {Frontiers in Bioengineering and Biotechnology}, issn = {2296-4185}, doi = {10.3389/fbioe.2022.869111}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-283033}, year = {2022}, abstract = {The rapid development of green and sustainable materials opens up new possibilities in the field of applied research. Such materials include nanocellulose composites that can integrate many components into composites and provide a good chassis for smart devices. In our study, we evaluate four approaches for turning a nanocellulose composite into an information storage or processing device: 1) nanocellulose can be a suitable carrier material and protect information stored in DNA. 2) Nucleotide-processing enzymes (polymerase and exonuclease) can be controlled by light after fusing them with light-gating domains; nucleotide substrate specificity can be changed by mutation or pH change (read-in and read-out of the information). 3) Semiconductors and electronic capabilities can be achieved: we show that nanocellulose is rendered electronic by iodine treatment replacing silicon including microstructures. Nanocellulose semiconductor properties are measured, and the resulting potential including single-electron transistors (SET) and their properties are modeled. Electric current can also be transported by DNA through G-quadruplex DNA molecules; these as well as classical silicon semiconductors can easily be integrated into the nanocellulose composite. 4) To elaborate upon miniaturization and integration for a smart nanocellulose chip device, we demonstrate pH-sensitive dyes in nanocellulose, nanopore creation, and kinase micropatterning on bacterial membranes as well as digital PCR micro-wells. Future application potential includes nano-3D printing and fast molecular processors (e.g., SETs) integrated with DNA storage and conventional electronics. This would also lead to environment-friendly nanocellulose chips for information processing as well as smart nanocellulose composites for biomedical applications and nano-factories.}, language = {en} } @article{KrenzerMakowskiHekaloetal.2022, author = {Krenzer, Adrian and Makowski, Kevin and Hekalo, Amar and Fitting, Daniel and Troya, Joel and Zoller, Wolfram G. and Hann, Alexander and Puppe, Frank}, title = {Fast machine learning annotation in the medical domain: a semi-automated video annotation tool for gastroenterologists}, series = {BioMedical Engineering OnLine}, volume = {21}, journal = {BioMedical Engineering OnLine}, number = {1}, doi = {10.1186/s12938-022-01001-x}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-300231}, year = {2022}, abstract = {Background Machine learning, especially deep learning, is becoming more and more relevant in research and development in the medical domain. For all the supervised deep learning applications, data is the most critical factor in securing successful implementation and sustaining the progress of the machine learning model. Especially gastroenterological data, which often involves endoscopic videos, are cumbersome to annotate. Domain experts are needed to interpret and annotate the videos. To support those domain experts, we generated a framework. With this framework, instead of annotating every frame in the video sequence, experts are just performing key annotations at the beginning and the end of sequences with pathologies, e.g., visible polyps. Subsequently, non-expert annotators supported by machine learning add the missing annotations for the frames in-between. Methods In our framework, an expert reviews the video and annotates a few video frames to verify the object's annotations for the non-expert. In a second step, a non-expert has visual confirmation of the given object and can annotate all following and preceding frames with AI assistance. After the expert has finished, relevant frames will be selected and passed on to an AI model. This information allows the AI model to detect and mark the desired object on all following and preceding frames with an annotation. Therefore, the non-expert can adjust and modify the AI predictions and export the results, which can then be used to train the AI model. Results Using this framework, we were able to reduce workload of domain experts on average by a factor of 20 on our data. This is primarily due to the structure of the framework, which is designed to minimize the workload of the domain expert. Pairing this framework with a state-of-the-art semi-automated AI model enhances the annotation speed further. Through a prospective study with 10 participants, we show that semi-automated annotation using our tool doubles the annotation speed of non-expert annotators compared to a well-known state-of-the-art annotation tool. Conclusion In summary, we introduce a framework for fast expert annotation for gastroenterologists, which reduces the workload of the domain expert considerably while maintaining a very high annotation quality. The framework incorporates a semi-automated annotation system utilizing trained object detection models. The software and framework are open-source.}, language = {en} } @article{KlemzRote2022, author = {Klemz, Boris and Rote, G{\"u}nter}, title = {Linear-Time Algorithms for Maximum-Weight Induced Matchings and Minimum Chain Covers in Convex Bipartite Graphs}, series = {Algorithmica}, volume = {84}, journal = {Algorithmica}, number = {4}, issn = {1432-0541}, doi = {10.1007/s00453-021-00904-w}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-267876}, pages = {1064-1080}, year = {2022}, abstract = {A bipartite graph G=(U,V,E) is convex if the vertices in V can be linearly ordered such that for each vertex u∈U, the neighbors of u are consecutive in the ordering of V. An induced matching H of G is a matching for which no edge of E connects endpoints of two different edges of H. We show that in a convex bipartite graph with n vertices and m weighted edges, an induced matching of maximum total weight can be computed in O(n+m) time. An unweighted convex bipartite graph has a representation of size O(n) that records for each vertex u∈U the first and last neighbor in the ordering of V. Given such a compact representation, we compute an induced matching of maximum cardinality in O(n) time. In convex bipartite graphs, maximum-cardinality induced matchings are dual to minimum chain covers. A chain cover is a covering of the edge set by chain subgraphs, that is, subgraphs that do not contain induced matchings of more than one edge. Given a compact representation, we compute a representation of a minimum chain cover in O(n) time. If no compact representation is given, the cover can be computed in O(n+m) time. All of our algorithms achieve optimal linear running time for the respective problem and model, and they improve and generalize the previous results in several ways: The best algorithms for the unweighted problem versions had a running time of O(n\(^{2}\)) (Brandst{\"a}dt et al. in Theor. Comput. Sci. 381(1-3):260-265, 2007. https://doi.org/10.1016/j.tcs.2007.04.006). The weighted case has not been considered before.}, language = {en} } @article{GlemarecLugrinBosseretal.2022, author = {Gl{\´e}marec, Yann and Lugrin, Jean-Luc and Bosser, Anne-Gwenn and Buche, C{\´e}dric and Latoschik, Marc Erich}, title = {Controlling the stage: a high-level control system for virtual audiences in Virtual Reality}, series = {Frontiers in Virtual Reality}, volume = {3}, journal = {Frontiers in Virtual Reality}, issn = {2673-4192}, doi = {10.3389/frvir.2022.876433}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-284601}, year = {2022}, abstract = {This article presents a novel method for controlling a virtual audience system (VAS) in Virtual Reality (VR) application, called STAGE, which has been originally designed for supervised public speaking training in university seminars dedicated to the preparation and delivery of scientific talks. We are interested in creating pedagogical narratives: narratives encompass affective phenomenon and rather than organizing events changing the course of a training scenario, pedagogical plans using our system focus on organizing the affects it arouses for the trainees. Efficiently controlling a virtual audience towards a specific training objective while evaluating the speaker's performance presents a challenge for a seminar instructor: the high level of cognitive and physical demands required to be able to control the virtual audience, whilst evaluating speaker's performance, adjusting and allowing it to quickly react to the user's behaviors and interactions. It is indeed a critical limitation of a number of existing systems that they rely on a Wizard of Oz approach, where the tutor drives the audience in reaction to the user's performance. We address this problem by integrating with a VAS a high-level control component for tutors, which allows using predefined audience behavior rules, defining custom ones, as well as intervening during run-time for finer control of the unfolding of the pedagogical plan. At its core, this component offers a tool to program, select, modify and monitor interactive training narratives using a high-level representation. The STAGE offers the following features: i) a high-level API to program pedagogical narratives focusing on a specific public speaking situation and training objectives, ii) an interactive visualization interface iii) computation and visualization of user metrics, iv) a semi-autonomous virtual audience composed of virtual spectators with automatic reactions to the speaker and surrounding spectators while following the pedagogical plan V) and the possibility for the instructor to embody a virtual spectator to ask questions or guide the speaker from within the Virtual Environment. We present here the design, and implementation of the tutoring system and its integration in STAGE, and discuss its reception by end-users.}, language = {en} } @article{HeinLatoschikWienrich2022, author = {Hein, Rebecca M. and Latoschik, Marc Erich and Wienrich, Carolin}, title = {Inter- and transcultural learning in cocial virtual reality: a proposal for an inter- and transcultural virtual object database to be used in the implementation, reflection, and evaluation of virtual encounters}, series = {Multimodal Technologies and Interaction}, volume = {6}, journal = {Multimodal Technologies and Interaction}, number = {7}, issn = {2414-4088}, doi = {10.3390/mti6070050}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-278974}, year = {2022}, abstract = {Visual stimuli are frequently used to improve memory, language learning or perception, and understanding of metacognitive processes. However, in virtual reality (VR), there are few systematically and empirically derived databases. This paper proposes the first collection of virtual objects based on empirical evaluation for inter-and transcultural encounters between English- and German-speaking learners. We used explicit and implicit measurement methods to identify cultural associations and the degree of stereotypical perception for each virtual stimuli (n = 293) through two online studies, including native German and English-speaking participants. The analysis resulted in a final well-describable database of 128 objects (called InteractionSuitcase). In future applications, the objects can be used as a great interaction or conversation asset and behavioral measurement tool in social VR applications, especially in the field of foreign language education. For example, encounters can use the objects to describe their culture, or teachers can intuitively assess stereotyped attitudes of the encounters.}, language = {en} } @article{LohMehlingHossfeld2022, author = {Loh, Frank and Mehling, Noah and Hoßfeld, Tobias}, title = {Towards LoRaWAN without data loss: studying the performance of different channel access approaches}, series = {Sensors}, volume = {22}, journal = {Sensors}, number = {2}, issn = {1424-8220}, doi = {10.3390/s22020691}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-302418}, year = {2022}, abstract = {The Long Range Wide Area Network (LoRaWAN) is one of the fastest growing Internet of Things (IoT) access protocols. It operates in the license free 868 MHz band and gives everyone the possibility to create their own small sensor networks. The drawback of this technology is often unscheduled or random channel access, which leads to message collisions and potential data loss. For that reason, recent literature studies alternative approaches for LoRaWAN channel access. In this work, state-of-the-art random channel access is compared with alternative approaches from the literature by means of collision probability. Furthermore, a time scheduled channel access methodology is presented to completely avoid collisions in LoRaWAN. For this approach, an exhaustive simulation study was conducted and the performance was evaluated with random access cross-traffic. In a general theoretical analysis the limits of the time scheduled approach are discussed to comply with duty cycle regulations in LoRaWAN.}, language = {en} } @article{SteinhaeusserOberdoerfervonMammenetal.2022, author = {Steinhaeusser, Sophia C. and Oberd{\"o}rfer, Sebastian and von Mammen, Sebastian and Latoschik, Marc Erich and Lugrin, Birgit}, title = {Joyful adventures and frightening places - designing emotion-inducing virtual environments}, series = {Frontiers in Virtual Reality}, volume = {3}, journal = {Frontiers in Virtual Reality}, issn = {2673-4192}, doi = {10.3389/frvir.2022.919163}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-284831}, year = {2022}, abstract = {Virtual environments (VEs) can evoke and support emotions, as experienced when playing emotionally arousing games. We theoretically approach the design of fear and joy evoking VEs based on a literature review of empirical studies on virtual and real environments as well as video games' reviews and content analyses. We define the design space and identify central design elements that evoke specific positive and negative emotions. Based on that, we derive and present guidelines for emotion-inducing VE design with respect to design themes, colors and textures, and lighting configurations. To validate our guidelines in two user studies, we 1) expose participants to 360° videos of VEs designed following the individual guidelines and 2) immerse them in a neutral, positive and negative emotion-inducing VEs combining all respective guidelines in Virtual Reality. The results support our theoretically derived guidelines by revealing significant differences in terms of fear and joy induction.}, language = {en} }