Informatik

Permanent URI for this collectionhttps://oa.tib.eu/renate/handle/123456789/4453

Browse

Now showing 1 - 20 of 226

Digitalisierung in den Gesundheitsberufen
([Leverkusen] : Verlag Barbara Budrich, 2024) Weyland, Ulrike; Koschel, Wilhelm; Reiber, Karin; Dorin, Lena; Peters, Miriam; Arndt, Laura; Behr, Dominik; Bergmann, Dana; Buchmann, Ulrike; Ebbighausen, Marc; Engl, Anna-Teresa; Ettl, Katrin; Fathi, Madjid; Fischer, Andreas; Freese, Christiane; Haussmann, Andreas; Hiestand, Stefanie; Hofstetter, Sebastian; Hüttner, Aneli; Jahn, Patrick; Jürgensen, Anke; Kaiser, Sophie; Kaufhold, Marisa; Kismihók, Gábor; Klus, Christina; Kobus, Julia; Köhler, Sonja; Kraft, Bernhard; Makowsky, Katja; Meng, Michael; Michel, Natalie; Nagel, Lisa; Nauerth, Annette; Nerdel, Claudia; Paulicke, Denny; Preißler, Ronja; Rasheed, Hasan A.; Rechl, Friederike; Richter, Katja E.; Richter, Patrick; Schröder, Martina; Schröer, Laura; Schwarz, Karsten; Seltrecht, Astrid; Steindorff, Jenny-Victoria; Stirner, Alexander; Stoevesandt, Dietrich; Völz, Silke; Wagner-Herrbach, Cornelia; Weber, Christian; Wittmann, Eveline; Zepelin, Lyn Anne von; Ziegler, Sven; Zilezinski, Max
Digitale Technologien führen zu veränderten Kommunikations-, Lern- und Arbeitsformen. Für die Gesundheitsberufe ergeben sich durch die Digitalisierung vielfältige Veränderungen und Herausforderungen, die bei positiver Wendung auch als Chance verstanden werden können. Wenn Digitalisierungsprozesse in den Gesundheitsberufen aktiv durch die Berufsgruppen mitgestaltet werden, so können positive Ansätze für die Versorgung hilfs- und pflegebedürftiger Menschen entwickelt werden, aber ebenso für die Professionalisierung der Fachkräfte und des beruflichen Bildungspersonals. Dieser Band dokumentiert die Beiträge zum AG-BFN-Forum „Digitalisierung in den Gesundheitsberufen“, das im Oktober 2021 an der Universität Münster stattfand. Im Fokus stehen aktuelle Entwicklungen in den Bereichen Digitalität in pflege- und gesundheitsberuflichen Handlungsfeldern, Professionalisierung des Bildungspersonals und digital gestützte Lehr-/Lernszenarien in den Gesundheitsberufen.
Redefining nursing skills in AI and robotisation, with a particular focus on conditions requiring long-term care
(Nyíregyháza : University of Debrecen Faculty of Health Department of Gerontology, 2022) Szőllősi, Anna; Kismihók, Gábor; Keszler, Ádám; Karamánné Pakai, Annamária; Lukács, Miklós; Szatmári, Angelika; Ujváriné Siket, Adrienn
Owing to the enormous improvements in health and lifestyle over the last century, the average age has increased. Although longevity is an important achievement of the modern age, it is a challenge for the care of an ageing population. As people in the richest parts of the world live longer, there is a growing shortage of carers for an ageing population. This paper reviews the literature and describes the global challenges of caregiving, future issues in elderly care, the emergence of robotization in the field of nursing care and how this can contribute to improving the quality of care for the older people. It also discusses the experience of using robots in international and domestic elderly care and briefly describes how the use of AI-based technology has contributed to improving the effectiveness of care in the context of the coronavirus epidemic. The paper concludes by presenting a vision and directions for training development for Advance Practice Nurses, Register Nurses and post-secondary nurses, and other health care professionals to improve attitudes, enhance knowledge, and develop services to improve elderly care.
Enhancing Knowledge Graph Extraction and Validation From Scholarly Publications Using Bibliographic Metadata
(Lausanne : Frontiers Media, 2021) Turki, Houcemeddine; Hadj Taieb, Mohamed Ali; Ben Aouicha, Mohamed; Fraumann, Grischa; Hauschke, Christian; Heller, Lambert
[No abstract available]
An Artificial Intelligence-Based Tool for Data Analysis and Prognosis in Cancer Patients: Results from the Clarify Study
(Basel : MDPI, 2022) Torrente, María; Sousa, Pedro A.; Hernández, Roberto; Blanco, Mariola; Calvo, Virginia; Collazo, Ana; Guerreiro, Gracinda R.; Núñez, Beatriz; Pimentao, Joao; Sánchez, Juan Cristóbal; Campos, Manuel; Costabello, Luca; Novacek, Vit; Menasalvas, Ernestina; Vidal, María Esther; Provencio, Mariano
Background: Artificial intelligence (AI) has contributed substantially in recent years to the resolution of different biomedical problems, including cancer. However, AI tools with significant and widespread impact in oncology remain scarce. The goal of this study is to present an AI-based solution tool for cancer patients data analysis that assists clinicians in identifying the clinical factors associated with poor prognosis, relapse and survival, and to develop a prognostic model that stratifies patients by risk. Materials and Methods: We used clinical data from 5275 patients diagnosed with non-small cell lung cancer, breast cancer, and non-Hodgkin lymphoma at Hospital Universitario Puerta de Hierro-Majadahonda. Accessible clinical parameters measured with a wearable device and quality of life questionnaires data were also collected. Results: Using an AI-tool, data from 5275 cancer patients were analyzed, integrating clinical data, questionnaires data, and data collected from wearable devices. Descriptive analyses were performed in order to explore the patients’ characteristics, survival probabilities were calculated, and a prognostic model identified low and high-risk profile patients. Conclusion: Overall, the reconstruction of the population’s risk profile for the cancer-specific predictive model was achieved and proved useful in clinical practice using artificial intelligence. It has potential application in clinical settings to improve risk stratification, early detection, and surveillance management of cancer patients.
Traditional Machine Learning Models and Bidirectional Encoder Representations From Transformer (BERT)-Based Automatic Classification of Tweets About Eating Disorders: Algorithm Development and Validation Study
(Toronto : [Verlag nicht ermittelbar], 2022) Benítez-Andrades, José Alberto; Alija-Pérez, José-Manuel; Vidal, Maria-Esther; Pastor-Vargas, Rafael; García-Ordás, María Teresa
Background: Eating disorders affect an increasing number of people. Social networks provide information that can help. Objective: We aimed to find machine learning models capable of efficiently categorizing tweets about eating disorders domain. Methods: We collected tweets related to eating disorders, for 3 consecutive months. After preprocessing, a subset of 2000 tweets was labeled: (1) messages written by people suffering from eating disorders or not, (2) messages promoting suffering from eating disorders or not, (3) informative messages or not, and (4) scientific or nonscientific messages. Traditional machine learning and deep learning models were used to classify tweets. We evaluated accuracy, F1 score, and computational time for each model. Results: A total of 1,058,957 tweets related to eating disorders were collected. were obtained in the 4 categorizations, with The bidirectional encoder representations from transformer-based models had the best score among the machine learning and deep learning techniques applied to the 4 categorization tasks (F1 scores 71.1%-86.4%). Conclusions: Bidirectional encoder representations from transformer-based models have better performance, although their computational cost is significantly higher than those of traditional techniques, in classifying eating disorder-related tweets.
Food information engineering
(Menlo Park, Calif. : AAAI, 2024) Jiomekong, Azanzi; Oelen, Allard; Auer, Sören; Lorenz, Anna-Lena; Vogt, Lars
Food information engineering relies on statistical and AI techniques (e.g., symbolic, connectionist, and neurosymbolic AI) for collecting, storing, processing, diffusing, and putting food information in a form exploitable by humans and machines. Food information is collected manually and automatically. Once collected, food information is organized using tabular data representation schema, symbolic, connectionist or neurosymbolic AI techniques. Once collected, processed, and stored, food information is diffused to different stakeholders using appropriate formats. Even if neurosymbolic AI has shown promising results in many domains, we found that this approach is rarely used in the domain of food information engineering. This paper aims to serve as a good reference for food information engineering researchers. Unlike existing reviews on the subject, we cover all the aspects of food information engineering and we linked the paper to online resources built using Open Research Knowledge Graph. These resources are composed of templates, comparison tables of research contributions and smart reviews. All these resources are organized in the “Food Information Engineering” observatory and will be continually updated with new research contributions.
Final Report for the Emmy Noether Project : ConcSys: Reliable and Efficient Complex, Concurrent Software Systems
(Hannover : Technische Informationsbibliothek, 2025-06) Pradel, Michael
The ConcSys project aims to develop techniques for testing and analyzing complex software systems, with a focus on increasing the correctness and performance of such systems. The project was running from March 2015 until December 2024. In this period, we made significant progress, both in terms of scientific results and in terms of building up a research group. The scientific results include novel techniques for (i) finding and preventing concurrency bugs, (ii) understanding and analyzing software performance, (iii) automated test generation, (iv) program analysis for WebAssembly, and (v) foundations of dynamic analysis. These results are presented in 83 peer-reviewed publications at top-tier conferences and journals in software engineering and programming languages, e.g., ICSE, OOPSLA, PLDI, and FSE. Beyond these scientific results, the project has enabled the PI, Michael Pradel, to build up his own a research group, to establish himself as an internationally recognized leader in the field, and to secure a permanent professorship at the University of Stuttgart. The project has directly and indirectly contributed to the careers of 12 doctoral students, out of which seven have been partially funded by the project and six have already graduated.
DFG Final Report: "LIVE: Empirical Studies on the Effects of Liveness on Programming"
(Hannover : Technische Informationsbibliothek, 2025-06-13) Hirschfeld, Robert
Liveness in programming tools is the impression of changing a program while it is running. Various tools support liveness, including commercial programming systems, such as MS Excel and Jupyter Notebooks. Tool designers assume that liveness improves the programming experience, but this assumption has insufficient and inconclusive empirical backing. This lack of evidence might lead to the promotion of liveness in unsuitable settings and the neglect of important settings, which would waste design and implementation efforts. In this project, we investigated the effects of live tools on debugging. In two controlled experiments we studied the influence of task complexity and delayed interactions on the effects of live tools. Compared to previous experiments on liveness, the participants in our experiments had considerable experience with live tools. In our first experiment we tested whether the influence of live tools on debugging time differs for simple and complex tasks. We found that live tools significantly shorten the time needed to debug defects. At the same time, we could not confirm our main hypothesis that task complexity moderates this effect. However, our results indicate that task complexity indeed influences the effect, but less than suggested by the pilot. For programming tool researchers and designers, our results show that programmers can benefit from live tools, but that they need to consider task complexity and participants' experience with liveness when preparing studies or building tools. With our second experiment, we aimed to better understand the first experiment's observations. Based on Information Foraging Theory, we assumed that live tools reduce the perceived cost of obtaining dynamic information so that programmers consult it more often when helpful. Therefore, we tested whether programmers use live tools less frequently if access to them is delayed. The experiment did not yield sufficiently enough results for a thorough analysis, but the collected data shows no clear decline in live tool usage. Yet, an ongoing post hoc analysis using edit-run cycles suggests that participants' workflows changed. During the first experiment, we found that it is a great challenge to operationalize the complexity of maintenance tasks in programming tool studies. Thus, we conducted a survey to curate a collection of factors from related studies that can help shape the complexity of such tasks. With this collection, researchers can deliberately decide on the complexity level for their studies' tasks. This project also resulted in a novel concept for teaching debugging through contests and improved setups for related studies on liveness conducted in our group.
Final Report on DFG Project "Automatic Transcription of Conversations"
(Hannover : Technische Informationsbibliothek, 2025) Häb-Umbach, Reinhold; Schlüter, Ralf
Multi-talker conversational speech recognition is concerned with transcribing meetings recorded with distant microphones. The difficulty of the task can be attributed to three factors. First, the recording conditions are challenging: The speech signal captured by microphones from a distance is noisy and reverberated and often contains nonstationary acoustic distortions, which makes it hard to decode. Second, there is a significant percentage of time with overlapped speech, where multiple speakers talk at the same time. Finally, the interaction dynamics of the scenario are challenging because speakers articulate themselves in an intermittent manner with alternating segments of speech inactivity, single-, and multi-talker speech. This project was concerned with developing a transcription system that can operate on arbitrarily long input, correctly handles segments of overlapped as well as non-overlapped speech, and transcribes the speech of different speakers consistently into separate output streams. Such a multi-talker Automatic Speech Recognition (ASR) system typically consists of the following three components: a source separation and enhancement block, a diarization stage, that attributes segments of input speech to speakers, and an ASR stage, whereby different orders of processing have been proposed. Those orders differ in when to do diarization. While existing approaches employed separately trained subsystems for diarization, separation, and recognition, our research hypothesis was that a joint approach, which is optimized under a single training objective, should lead to superior solutions compared to the separate optimization of individual components. Such a coherent formulation, however, would not necessarily mean that the three aforementioned tasks had to be carried out in a single, monolithic (probably neural) integrated system. Indeed, the research carried out showed that it is beneficial to have separate subsystems, however, with a tight coupling between them. Examples of such systems we developed are • TS-SEP, which carries out diarization and separation/enhancement, with a tight coupling in-between. • Mixture encoder, which leverages explicit speech separation, but also forwards the not yet separated speech to the ASR module to mitigate error propagation from the separator to the recognizer. • Joint diarization and separation, realized by a statistical mixture model, which integrates a mixture model for diarization and one for separation, that share a common hidden state variable. • Transcription-supported diarization, which uses sentence- and word-level boundaries of the ASR module to support speaker turn detection. Furthermore, we developed new approaches to the individual subsystems and shared several tools and data sets with the research community.
DFG Final Report for Automatic Fact Checking for Biomedical Information in Social Media and Scientific Literature (FIBISS), project number 667374
(Hannover : Technische Informationsbibliothek, 2025-04-10) Klinger, Roman; Wührl, Amelie
Research into methods for the automatic verification of facts, i.e., computational models that can distinguish correct information from misinformation or disinformation, is largely focused on the news domain and on the analysis of posts in social media. Among other things, texts are checked for their truthfulness. This can be done by analyzing linguistic features that suggest an intention to deceive or by comparing them with other sources that make comparable statements in terms of content. Most studies focus on politically relevant areas. The biomedical domain is also an area of particular social relevance. In social media, various actors and medical laypersons share reports on treatment methods, successes and failures, such as the (disproven) method of treating viral infections with deworming agents or disinfectants. There are also reports on (disproven) links between treatments and adverse effects, such as the causation of autism by vaccination. However, the biomedical domain, unlike other areas relevant for automated fact checking, benefits from a large resource of reliable scientific articles. The aim of the FIBISS project was therefore to develop and evaluate methods that can extract biomedical claims in social media and compare them with reliable sources. One challenge here is that social media does not typically use technical language, so different vocabularies have to be combined. The approach in FIBISS was therefore to develop generalizing information extraction methods. In the course of the project, large language models also became prominent as a further methodological approach. The project was therefore adapted to optimize general representations of claims in such a way that they are suitable for comparison using automatic fact-checking procedures. As a result, we contribute text corpora that are used to develop and evaluate automated biomedical fact-checking systems. We propose methods that automatically reformulate claims so that they are suitable to be automatically verified. Furthermore, we present approaches that can automatically assess the credibility of claims, even independently of existing evidence.
Final Report of the DFG Project "Drawing Graphs: Geometric Aspects Beyond Planarity" (project number 654838)
(Hannover : Technische Informationsbibliothek, 2025-04) Wolff, Alexander
The aim of our project was to get a better understanding of the mathematical structures that correspond to the different ways of measuring the visual complexity of a drawing of a graph. Examples for such measures are the local crossing number, that is, the maximum number of crossings per edge, the slope number, that is, the number of different slopes in a crossing-free straight-line drawing, the segment number or the line cover number, that is, the number of straight-line segments or straight lines needed to cover a crossing-free straight-line drawing. For a graph, the measures are defined as the minimum over all drawings (of the corresponding type). The center of our studies became the measure segment number, which is known to be NP-hard to compute. In particular, we showed that there is a parameterized algorithm for computing the segment number of a given graph with respect to the several parameters; the natural parameter, the line cover number, and the vertex cover number. The latter proof was the technically most challenging. In a different work, we showed that it is ETR-complete to compute the segment number of a given graph, that is, the segment number of a graph can be expressed in terms of the existential theory of the reals, but its computation is at least as hard as every problem in the complexity class ETR. Moreover, we extended a result concerning the segment number of triconnected cu- bic planar graphs by showing that the segment number of every triconnected 4-regular planar graph with n vertices is at most n + 3, which is tight up to the additive constant. We have proved the first linear universal lower bounds for the segment number of out- erpaths, maximal outerplanar graphs, 2-trees, and planar 3-trees. This shows that the existing algorithms for these graph classes are in fact constant-factor approximation algorithms. For maximal outerpaths, our universal lower bound is best possible.
Multiscale phenomena: Green's functions, the Dirichlet-to-Neumann formulation, subgrid scale models, bubbles and the origins of stabilized methods
(Amsterdam [u.a.] : Elsevier Science, 1995) Hughes, Thomas J. R.
An approach is developed for deriving variational methods capable of representing multiscale phenomena. The ideas are first illustrated on the exterior problem for the Helmholtz equation. This leads to the well-known Dirichlet-to-Neumann formulation. Next, a class of subgrid scale models is developed and the relationships to 'bubble function' methods and stabilized methods are established. It is shown that both the latter methods are approximate subgrid scale models. The identification for stabilized methods leads to an analytical formula for τ, the 'intrinsic time scale', whose origins have been a mystery heretofore. © 1995.
Implementation of an adaptive BDF2 formula and comparison with the MATLAB Ode15s
(Amsterdam [u.a.] : Elsevier, 2014) Celaya, E. Alberdi; Aguirrezabala, J. J. Anza; Chatzipantelidis, P.
After applying the Finite Element Method (FEM) to the diffusion-type and wave-type Partial Differential Equations (PDEs), a first order and a second order Ordinary Differential Equation (ODE) systems are obtained respectively. These ODE systems usually present high stiffness, so numerical methods with good stability properties are required in their resolution. MATLAB offers a set of open source adaptive step functions for solving ODEs. One of these functions is the ode15s recommended to solve stiff problems and which is based on the Backward Differentiation Formulae (BDF). We describe the error estimation and the step size control implemented in this function. The ode15s is a variable order algorithm, and even though it has an adaptive step size implementation, the advancing formula and the local error estimation that uses correspond to the constant step size formula. We have focused on the second order accurate and unconditionally stable BDF (BDF2) and we have implemented a real adaptive step size BDF2 algorithm using the same strategy as the BDF2 implemented in the ode15s, resulting the new algorithm more efficient than the one implemented in MATLAB. © The Authors. Published by Elsevier B.V.
The finite volume-complete flux scheme for advection-diffusion-reaction equations
(New York, NY [u.a.] : Springer Science + Business Media B.V., 2010) ten Thije Boonkkamp, J. H. M.; Anthonissen, M. J. H.
We present a new finite volume scheme for the advection-diffusion-reaction equation. The scheme is second order accurate in the grid size, both for dominant diffusion and dominant advection, and has only a three-point coupling in each spatial direction. Our scheme is based on a new integral representation for the flux of the one-dimensional advection-diffusion-reaction equation, which is derived from the solution of a local boundary value problem for the entire equation, including the source term. The flux therefore consists of two parts, corresponding to the homogeneous and particular solution of the boundary value problem. Applying suitable quadrature rules to the integral representation gives the complete flux scheme. Extensions of the complete flux scheme to two-dimensional and time-dependent problems are derived, containing the cross flux term or the time derivative in the inhomogeneous flux, respectively. The resulting finite volume-complete flux scheme is validated for several test problems. © 2010 The Author(s).
The systems biology format converter
(London : BioMed Central, 2016) Rodriguez, Nicolas; Pettit, Jean-Baptiste; Dalle Pezze, Piero; Li, Lu; Henry, Arnaud; van Iersel, Martijn P.; Jalowicki, Gael; Kutmon, Martina; Natarajan, Kedar N.; Tolnay, David; Stefan, Melanie I.; Evelo, Chris T.; Le Novère, Nicolas
Background: Interoperability between formats is a recurring problem in systems biology research. Many tools have been developed to convert computational models from one format to another. However, they have been developed independently, resulting in redundancy of efforts and lack of synergy. Results: Here we present the System Biology Format Converter (SBFC), which provide a generic framework to potentially convert any format into another. The framework currently includes several converters translating between the following formats: SBML, BioPAX, SBGN-ML, Matlab, Octave, XPP, GPML, Dot, MDL and APM. This software is written in Java and can be used as a standalone executable or web service. Conclusions: The SBFC framework is an evolving software project. Existing converters can be used and improved, and new converters can be easily added, making SBFC useful to both modellers and developers. The source code and documentation of the framework are freely available from the project web site.
The Design of a Python Library for the Automatic Definition and Simulation of Transient Ionization Fronts
(New York, NY : IEEE, 2023) Wong, Timothy; Timoshkin, Igor; MacGregor, Scott; Wilson, Mark; Given, Martin
In recent years, the interest in nonthermal plasma dynamics has grown significantly, within both industry and research. This has been driven by the development of several novel cold plasma technologies across a wide range of different fields, for example, for plasma medicine, chemical processing, pollution control, and surface treatment. The optimization of these technologies relies heavily upon the understanding of gas discharge plasmas: their generation, electrical characteristics, and interaction with their surroundings. Moreover, the manifestation of nonthermal plasmas in the form of streamers is of high relevance and critical importance to high voltage insulation technology, and has further significance to geophysical research concerning atmospheric discharges. The present work describes the development of the StrAFE (Streamers on Adaptive Finite Elements) package, a dedicated Python library built atop the popular open-source FEniCS finite element software, designed with the objective to simplify and to automate the solution of ionization front models. The library features support for mesh adaptivity, distributed memory parallelism, and an intuitive programming interface, while providing an exceptionally high level of user configurability. This article presents the software implementation, describes its features, and presents several code verification studies performed within simple and complex domains. It is concluded that the numerical results gained from this open-source framework are comparable to other well-established software in terms of accuracy. Therefore, it further demonstrates the great potential for open-source software to make significant contributions to technologies involving nonthermal plasmas, ionization fronts, and gas discharges.
Tutorial applications for Verification, Validation and Uncertainty Quantification using VECMA toolkit
(Amsterdam [u.a.] : Elsevier, 2021) Suleimenova, Diana; Arabnejad, Hamid; Edeling, Wouter N.; Coster, David; Luk, Onnie O.; Lakhlili, Jalal; Jancauskas, Vytautas; Kulczewski, Michal; Veen, Lourens; Ye, Dongwei; Zun, Pavel; Krzhizhanovskaya, Valeria; Hoekstra, Alfons; Crommelin, Daan; Coveney, Peter V.; Groen, Derek
The VECMA toolkit enables automated Verification, Validation and Uncertainty Quantification (VVUQ) for complex applications that can be deployed on emerging exascale platforms and provides support for software applications for any domain of interest. The toolkit has four main components including EasyVVUQ for VVUQ workflows, FabSim3 for automation and tool integration, MUSCLE3 for coupling multiscale models and QCG tools to execute application workflows on high performance computing (HPC). A more recent addition to the VECMAtk is EasySurrogate for various types of surrogate methods. In this paper, we present five tutorials from different application domains that apply these VECMAtk components to perform uncertainty quantification analysis, use surrogate models, couple multiscale models and execute sensitivity analysis on HPC. This paper aims to provide hands-on experience for practitioners aiming to test and contrast with their own applications.
CauseKG: A Framework Enhancing Causal Inference With Implicit Knowledge Deduced From Knowledge Graphs
(New York, NY : IEEE, 2024) Huang, Hao; Vidal, Maria-Esther
Causal inference is a critical technique for inferring causal relationships from data and distinguishing causation from correlation. Causal inference frameworks rely on structured data, typically represented in flat tables or relational models. These frameworks estimate causal effects based only on explicit facts, overlooking implicit information in the data, which can lead to inaccurate causal estimates. Knowledge graphs (KGs) inherently capture implicit information through logical rules applied to explicit facts, providing a unique opportunity to leverage implicit knowledge. However, existing frameworks are not applicable to KGs due to their semi-structured nature. CauseKG is a causal inference framework designed to address the intricacies of KGs and seamlessly integrate implicit information using KG-specific entailment techniques, providing a more accurate causal inference process. We empirically evaluate the effectiveness of CauseKG against benchmarks constructed from synthetic and real-world datasets. The results suggest that CauseKG can produce a lower mean absolute error in causal inference compared to state-of-the-art methods. The empirical results demonstrate CauseKG's ability to address causal questions in a variety of domains. This research highlights the importance of extending causal inference techniques to KGs, emphasising the improved accuracy that can be achieved by integrating implicit and explicit information.
Robust Fusion of Time Series and Image Data for Improved Multimodal Clinical Prediction
(New York, NY : IEEE, 2024) Rasekh, Ali; Heidari, Reza; Hosein Haji Mohammad Rezaie, Amir; Sharifi Sedeh, Parsa; Ahmadi, Zahra; Mitra, Prasenjit; Nejdl, Wolfgang
With the increasing availability of diverse data types, particularly images and time series data from medical experiments, there is a growing demand for techniques designed to combine various modalities of data effectively. Our motivation comes from the important areas of predicting mortality and phenotyping where using different modalities of data could significantly improve our ability to predict. To tackle this challenge, we introduce a new method that uses two separate encoders, one for each type of data, allowing the model to understand complex patterns in both visual and time-based information. Apart from the technical challenges, our goal is to make the predictive model more robust in noisy conditions and perform better than current methods. We also deal with imbalanced datasets and use an uncertainty loss function, yielding improved results while simultaneously providing a principled means of modeling uncertainty. Additionally, we include attention mechanisms to fuse different modalities, allowing the model to focus on what's important for each task. We tested our approach using the comprehensive multimodal MIMIC dataset, combining MIMIC-IV and MIMIC-CXR datasets. Our experiments show that our method is effective in improving multimodal deep learning for clinical applications. The code for this work is publicly available at: https://github.com/AliRasekh/TSImageFusion.
Organizing Scientific Knowledge from Engineering Sciences Using the Open Research Knowledge Graph: The Tailored Forming Process Chain Use Case
(Paris : CODATA, 2024) Karras, Oliver; Budde, Laura; Merkel, Paulina; Hermsdorf, Jörg; Stonis, Malte; Overmeyer, Ludger; Behrens, Bernd-Arno; Auer, Sören
Background: Engineering sciences are essential for addressing contemporary technical, environmental, and economic challenges. Despite its data-intensive and interdisciplinary nature, the organization of Findable, Accessible, Interoperable, and Reusable (FAIR) scientific knowledge and data in this research field remains understudied. Engineers need infrastructures with services that support them in organizing FAIR scientific knowledge and data for communication and (re-)use. Aim: We explore the use of the Open Research Knowledge Graph (ORKG) as such an infrastructure by demonstrating how engineers can utilize the ORKG in innovative ways for communication and (re-)use. Method: For a use case from the Collaborative Research Center 1153 “Tailored Forming”, we collect, extract, and analyze scientific knowledge on 10 Tailored Forming Process Chains (TFPCs) from five publications in the ORKG. In particular, we semantically describe the TFPCs, i.a., regarding their steps, manufacturing methods, measurements, and results. The usefulness of the data extraction topics, their organization, and the relevance of the knowledge described is examined by an expert consultation with 21 experts. Results: Based on the described knowledge, we build and publish an ORKG comparison as a detailed overview for communication. Furthermore, we (re-)use the knowledge and answer eight competency questions asked by two domain experts. The validation shows a clear agreement of the 21 experts regarding the examined usefulness and relevance. Conclusions: Our use case shows that the ORKG as a ready-to-use infrastructure with services supports researchers, including engineers, in sustainably organizing FAIR scientific knowledge. The direct use of the ORKG by engineers is feasible, so the ORKG is a promising infrastructure for innovative ways of communicating and (re-)using FAIR scientific knowledge in engineering sciences, thus advancing this research field.

Browse

Recent Submissions