检索结果-内蒙古大学图书馆

On the Trade-Off between Fidelity, Utility and Privacy of Synthetic Patient Data

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Adams, Tim Birkenbihl, Colin Otte, Karen Ng, Hwei Geok Rieling, Jonas Adrian Näher, Anatol-Fiete Sax, Ulrich Prasser, Fabian Fröhlich, Holger Fraunhofer Institute for Algorithms and Scientific Computing Schloss Birlinghoven Sankt Augustin Germany Berlin Germany Department of Medical Informatics University Medical Center Goettingen Goettingen Germany Digital Global Public Health Hasso Plattner Institute for Digital Engineering University of Potsdam Potsdam Germany Method Development Research Infrastructure and Information Technology Robert Koch Institute Berlin Germany Bonn-Aachen International Center for IT Rheinische Friedrich-Wilhelms-Universität Bonn Bonn Germany Department of Neurology Massachusetts General Hospital Harvard Medical School Boston United States

The advancement of medical research and healthcare is increasingly dependent on the analysis of patient-level data, but privacy concerns and legal constraints often hinder data sharing. Synthetic data mimicking real patient data offers a widely discussed potential solution. According to the literature, synthetic data may, however, not fully guarantee patient privacy and can vary greatly in terms of fidelity and utility. In this study, we aim to systematically investigate the trade-off between privacy, fidelity and utility of synthetic patient data. We assess synthetic data fidelity in terms of statistical similarity to real data, and utility via the performance of machine learning models trained on synthetic and tested on real data. Regarding data privacy we focus on membership inference via shadow model attacks as well as singling out and attribute inference risks. In this regard, we also consider differential privacy (DP) as a possible mechanism to probabilistically guarantee a certain level of data privacy, and we compare against classical anonymization techniques. We evaluate the fidelity, utility and privacy of synthetic data generated by five different models for three distinctive patient-level datasets. Our results show that our implementations of DP have a strongly detrimental effect on the fidelity of synthetic data, specifically its correlation structure, and therefore emphasize the need to improve techniques that effectively balance privacy, fidelity and utility in synthetic patient data generation. © 2024, The Authors. All rights reserved.

关键词：

Knowledge Detection and Discovery using Semantic Graph Embeddings on Large Knowledge Graphs generated on Text Mining Results

学校读者我要写书评

暂无评论

Knowledge Detection and Discovery using Semantic Graph Embed...

Federated Conference on Computer Science and Information Systems (FedCSIS)

作者： Jens Dörpinghaus Marc Jacobs German Center for Neurodegenerative Diseases (DZNE) Bonn Germany Fraunhofer Institute for Algorithms and Scientific Computing Schloss Birlinghoven Sankt Augustin Germany

ISBN: (数字)9788395541674

ISBN: (纸本)9781728141473

Knowledge graphs play a central role in big data integration, especially for connecting data from different domains. Bringing unstructured texts, e.g. from scientific literature, into a structured, comparable format is one of the key assets. Here, we use knowledge graphs in the biomedical domain working together with text mining based document data for knowledge extraction and retrieval from text and natural language structures. For example cause and effect models, can potentially facilitate clinical decision making or help to drive research towards precision medicine. However, the power of knowledge graphs critically depends on context information. Here we provide a novel semantic approach towards a context enriched biomedical knowledge graph utilizing data integration with linked data applied to language technologies and text mining. This graph concept can be used for graph embedding applied in different approaches, e.g with focus on topic detection, document clustering and knowledge discovery. We discuss algorithmic approaches to tackle these challenges and show results for several applications like search query finding and knowledge discovery. The presented remarkable approaches lead to valuable results on large knowledge graphs.

关键词：

optimization of Retrieval algorithms on Large Scale Knowledge Graphs

学校读者我要写书评

暂无评论

optimization of Retrieval Algorithms on Large Scale Knowledg...

Federated Conference on Computer Science and Information Systems (FedCSIS)

作者： Jens Dörpinghaus Andreas Stefan German Center for Neurodegenerative Diseases (DZNE) Bonn Germany Fraunhofer Institute for Algorithms and Scientific Computing Schloss Birlinghoven Sankt Augustin Germany

ISBN: (数字)9788395541674

ISBN: (纸本)9781728141473

Knowledge graphs have been shown to play an important role in recent knowledge mining and discovery, for example in the field of life sciences or bioinformatics. Although a lot of research has been done on the field of query optimization, query transformation and of course in storing and retrieving large scale knowledge graphs the field of algorithmic optimization is still a major challenge and a vital factor in using graph databases. Few researchers have addressed the problem of optimizing algorithms on large scale labeled property graphs. Here, we present two optimization approaches and compare them with a naive approach of directly querying the graph database. The aim of our work is to determine limiting factors of graph databases like Neo4j and we describe a novel solution to tackle these challenges. For this, we suggest a classification schema to differ between the complexity of a problem on a graph database. We evaluate our optimization approaches on a test system containing a knowledge graph derived biomedical publication data enriched with text mining data. This dense graph has more than 71M nodes and 850M relationships. The results are very encouraging and- depending on the problem-we were able to show a speedup of a factor between 44 and 3839.

关键词：

Deep neural networks and PIDE discretizations

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Bohn, Bastian Griebel, Michael Kannan, Dinesh Fraunhofer Center for Machine Learning Schloss Birlinghoven Sankt Augustin53754 Germany Fraunhofer Institute for Algorithms and Scientific Computing SCAI Schloss Birlinghoven Sankt Augustin53754 Germany Institute for Numerical Simulation University of Bonn Friedrich-Hirzebruch-Allee 7 Bonn53115 Germany

In this paper, we propose neural networks that tackle the problems of stability and field-of-view of a Convolutional Neural Network (CNN). As an alternative to increasing the network's depth or width to improve performance, we propose integral-based spatially nonlocal operators which are related to global weighted Laplacian, fractional Laplacian and inverse fractional Laplacian operators that arise in several problems in the physical sciences. The forward propagation of such networks is inspired by partial integro-differential equations (PIDEs). We test the effectiveness of the proposed neural architectures on benchmark image classification datasets and semantic segmentation tasks in autonomous driving. Moreover, we investigate the extra computational costs of these dense operators and the stability of forward propagation of the proposed neural *** Codes 65D15, 65L07, 68T05, 68W25, 47G20, 47G30 © 2021, CC BY.

关键词： Deep neural networks

Mathematical modeling and visualization of topologically non-trivial solutions in general relativity

学校读者我要写书评

暂无评论

Journal of Physics: Conference Series 2021年第1期1730卷

作者： Igor Nikitin Fraunhofer Institute for Algorithms and Scientific Computing Schloss Birlinghoven 53757 Sankt Augustin Germany

In general relativity, there is a class of solutions that currently do not have observed analogues, but on which the theory is shaped, giving an understanding what is fundamentally possible within its framework. Such solutions include wormholes, tunnels that connect distant regions in spacetime. Although not a single wormhole has yet been discovered, there is a large number of works devoted to their study, thanks to which wormholes as a class of solutions become firmly established in modern science. In this paper, we consider two topologically nontrivial types of solutions related to wormholes. First: wormholes that can open and close. In this relation, we will discuss topological censorship theorems, which under certain conditions prohibit changing topology. We will also discuss known ways to circumvent these theorems. Using analytical and numerical methods, as well as visualization, we will construct an example of an opening and closing wormhole with the dimensions of the central black hole in the Milky Way galaxy. Our construction continues the work by Kardashev, Novikov and Shatskiy, in which a static wormhole with the same parameters was considered. The second type is a modification of Visser's dihedral wormhole solution for a dynamic case.

关键词：

On dark stars, galactic rotation curves and fast radio bursts

学校读者我要写书评

暂无评论

Journal of Physics: Conference Series 2021年第1期1730卷

作者： Igor Nikitin Fraunhofer Institute for Algorithms and Scientific Computing Schloss Birlinghoven 53757 Sankt Augustin Germany

This paper is a continuation of our recent work on Radial Dark Matter stars (RDM-stars), black holes, coupled with radial flows of dark matter. As a galaxy model, it produces flat rotation curves, approximately valid for many galaxies far from the center. In this paper, more detailed modeling is carried out, including the vicinity of the galactic center. Assuming that the distribution of stellar black holes repeats the distribution of luminous matter, we get a perfect match between the model rotation curves and the observed ones. Further, using numerical integration, we examine the gravitational field of an individual RDM-star. The computation shows the event horizon being erased and rapidly increasing mass density arising instead (mass inflation). In this regime, we apply the previously constructed Planck star model, where at high densities a repulsive force occurs (quantum bounce). In our stationary model, the evolution of a Planck star has stopped under the pressure of dark matter flows. This system is considered as a possible source of Fast Radio Bursts (FRBs). In a scenario involving an asteroid falling onto an RDM-star, the model reproduces the correct frequency range of FRBs. Their total energy, coherence and short duration are explained as well.

关键词：

On the effects of biased quantum random numbers on the initialization of artificial neural networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Heese, Raoul Wolter, Moritz Mücke, Sascha Franken, Lukas Piatkowski, Nico Fraunhofer Center for Machine Learning and Fraunhofer Institute for Industrial Mathematics ITWM Germany Fraunhofer Center for Machine Learning and Fraunhofer Institute for Algorithms and Scientific Computing SCAI Germany Artificial Intelligence Group TU Dortmund University Germany Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS Germany

Recent advances in practical quantum computing have led to a variety of cloud-based quantum computing platforms that allow researchers to evaluate their algorithms on noisy intermediate-scale quantum (NISQ) devices. A common property of quantum computers is that they can exhibit instances of true randomness as opposed to pseudo-randomness obtained from classical systems. Investigating the effects of such true quantum randomness in the context of machine learning is appealing, and recent results vaguely suggest that benefits can indeed be achieved from the use of quantum random numbers. To shed some more light on this topic, we empirically study the effects of hardware-biased quantum random numbers on the initialization of artificial neural network weights in numerical experiments. We find no statistically significant difference in comparison with unbiased quantum random numbers as well as biased and unbiased random numbers from a classical pseudo-random number generator. The quantum random numbers for our experiments are obtained from real quantum hardware. Copyright © 2021, The Authors. All rights reserved.

关键词： Random number generation

INTERATOMIC-POTENTIAL-FREE, DATA-DRIVEN MOLECULAR DYNAMICS

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Bulin, J. Hamaekers, J. Ariza, M. Pilar Ortiz, M. Fraunhofer Institute for Algorithms and Scientific Computing Schloss Birlinghoven Sankt Augustin53757 Germany Escuela Técnica Superior de Ingeniería Universidad de Sevilla Sevilla41092 Spain Hausdorff Center for Mathematics Universität Bonn Endenicher Allee 60 Bonn53115 Germany Division of Engineering and Applied Science California Institute of Technology 1200 E. California Blvd. PasadenaCA91125 United States

We present a Data-Driven (DD) paradigm that enables molecular dynamics calculations to be performed directly from sampled force-field data such as obtained, e. g., from ab initio calculations, thereby eschewing the conventional step of modeling the data by empirical interatomic potentials entirely. The data required by the DD solvers consists of local atomic configurations and corresponding atomic forces and is, therefore, fundamental, i. e., it is not beholden to any particular model. The resulting DD solvers, including a fully explicit DD-Verlet algorithm, are provably convergent and exhibit robust convergence with respect to the data in selected test cases. We present an example of application to C60 buckminsterfullerenes that showcases the feasibility, range and scope of the DD molecular dynamics paradigm. Copyright © 2022, The Authors. All rights reserved.

关键词： Molecular dynamics

SYNTHETIC DATA GENERATION FOR A LONGITUDINAL COHORT STUDY - EVALUATION, METHOD EXTENSION AND REPRODUCTION OF PUBLISHED DATA ANALYSIS RESULTS

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Kühnel, Lisa Schneider, Julian Perrar, Ines Adams, Tim Prasser, Fabian Nöthlings, Ute Fröhlich, Holger Fluck, Juliane Knowledge Management Zb Med Information Centre for Life Sciences Cologne50931 Germany Faculty of Technology Bielefeld University Bielefeld33615 Germany Institute of Nutritional and Food Sciences - Nutritional Epidemiology University of Bonn Bonn53115 Germany Department of Bioinformatics Fraunhofer Institute for Algorithms and Scientific Computing Scai Sankt Augustin53757 Germany Medical Informatics Group Berlin Institute of Health Charité - Universitätsmedizin Berlin Berlin10117 Germany Bonn-Aachen International Center for It University of Bonn Friedrich Hirzebruch-Allee 6 Bonn53115 Germany The Agricultural Faculty University of Bonn Bonn53115 Germany

Access to individual-level health data is essential for gaining new insights and advancing science. In particular, modern methods based on artificial intelligence rely on the availability of and access to large datasets. In the health sector, access to individual-level data is often challenging due to privacy concerns. A promising alternative is the generation of fully synthetic data, i.e. data generated through a randomised process that have similar statistical properties as the original data, but do not have a one-to-one correspondence with the original individual-level records. In this study, we use a state-of-the-art synthetic data generation method and perform in-depth quality analyses of the generated data for a specific use case in the field of nutrition. We demonstrate the need for careful analyses of synthetic data that go beyond descriptive statistics and provide valuable insights into how to realise the full potential of synthetic datasets. By extending the methods, but also by thoroughly analysing the effects of sampling from a trained model, we are able to largely reproduce significant real-world analysis results in the chosen use case. © 2023, CC BY.

关键词： Large dataset