检索结果-内蒙古大学图书馆

On the influence of several factors on pathway enrichment analysis

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Mubeen, Sarah Kodamullil, Alpha Tom Hofmann-Apitius, Martin Domingo-Fernández, Daniel Department of Bioinformatics Fraunhofer Institute for Algorithms and Scientific Computing Sankt Augustin53757 Germany University of Bonn Bonn53115 Germany Fraunhofer Center for Machine Learning Germany Enveda Biosciences BoulderCO80301 United States

Pathway enrichment analysis has become a widely used knowledge-based approach for the interpretation of biomedical data. Its popularity has led to an explosion of both enrichment methods and pathway databases. While the elegance of pathway enrichment lies in its simplicity, multiple factors can impact the results of such an analysis which may not be accounted for. Researchers may fail to give influential aspects their due, resorting instead to popular methods and gene set collections, or default settings. Despite ongoing efforts to establish set guidelines, meaningful results are still hampered by a lack of consensus or gold standards around how enrichment analysis should be conducted. Nonetheless, such concerns have prompted a series of benchmark studies specifically focused on evaluating the influence of various factors on pathway enrichment results. In this review, we organize and summarize the findings of these benchmarks to provide a comprehensive overview on the influence of these factors. Our work covers a broad spectrum of factors, spanning from methodological assumptions to those related to prior biological knowledge, such as pathway definitions and database choice. In doing so, we aim to shed light on how these aspects can lead to insignificant, uninteresting, or even contradictory results. Finally, we conclude the review by proposing future benchmarks as well as solutions to overcome some of the challenges which originate from the outlined factors. © 2022, CC BY.

关键词： Database systems

Informed machine learning - A taxonomy and survey of integrating prior knowledge into learning systems

学校读者我要写书评

暂无评论

arXiv 2019年

作者： von Rueden, Laura Mayer, Sebastian Beckh, Katharina Georgiev, Bogdan Giesselbach, Sven Heese, Raoul Kirsch, Birgit Pfrommer, Julius Pick, Annika Ramamurthy, Rajkumar Walczak, Michal Garcke, Jochen Bauckhage, Christian Schuecker, Jannis The Fraunhofer IAIS Institute for Intelligent Analysis and Information Systems Sankt Augustin53757 Germany The Fraunhofer SCAI Institute for Algorithms and Scientific Computing Sankt Augustin53757 Germany The Fraunhofer ITWM Institute for Industrial Mathematics Kaiserslautern67663 Germany The Fraunhofer IOSB Institute for Optronics System Technologies and Image Exploitation Karlsruhe76131 Germany

Despite its great success, machine learning can have its limits when dealing with insufficient training data. A potential solution is the additional integration of prior knowledge into the training process which leads to the notion of informed machine learning. In this paper, we present a structured overview of various approaches in this field. We provide a definition and propose a concept for informed machine learning which illustrates its building blocks and distinguishes it from conventional machine learning. We introduce a taxonomy that serves as a classification framework for informed machine learning approaches. It considers the source of knowledge, its representation, and its integration into the machine learning pipeline. Based on this taxonomy, we survey related research and describe how different knowledge representations such as algebraic equations, logic rules, or simulation results can be used in learning systems. This evaluation of numerous papers on the basis of our taxonomy uncovers key methods in the field of informed machine learning. © 2019, CC BY.

关键词： Surveys

Benchmark gas distribution network for cross-sectoral applications

学校读者我要写书评

暂无评论

Benchmark gas distribution network for cross-sectoral applic...

International Energy and Sustainability Conference (IESC)

作者： Christian Brosig Silvan Fassbender Eberhard Waffenschmidt Sebastian Janocha Bernhard Klaassen Cologne Institute of Renewable Energy (ClRE) Cologne University of Applied Sciences Cologne Germany Rheinische NETZGesellschaft mbH (RNG) Cologne Germany Fraunhofer Institute for Algorithms and Scientific Computing SCAI Sankt Augustin Germany

Cross-sectoral coupling of energy systems could provide the necessary flexibility for future energy systems with a high share of renewable energies. The gas grid implies large storage capacities and thus promises an economically attractive balance for fluctuating energy sources. A benchmark gas distribution network, coupled to the CIGRE benchmark network for electricity is presented within this paper, to universally investigate the impacts on gas grid infrastructure. The network includes interconnected meshed and radial topologies for both low and medium pressure gas networks. They have been synthesized from existing real networks in cooperation with the Rheinische NETZGesellschaft mbH. Applications range from analyzing network impacts of widespread CHP or fuel cell implementation, over comparing the cost-effectiveness of different future pathways between expansion and decommissioning of the gas grid network, to analyzing the impacts of distributed injection of renewable gas. The overall aim is to build a complete network benchmark for an integral cross-sectoral energy system including also heat.

关键词： Steel Benchmark testing Fuel cells Hydrogen Cogeneration Regulators Couplings

Integrating Cloud computing, Bayesian Optimization, and Neural-Additive Modeling for Enhanced CAM Systems in 5-Axis Milling 34

学校读者我要写书评

暂无评论

Integrating Cloud Computing, Bayesian Optimization, and Neur...

34th CIRP Design Conference, CIRP 2024

作者： Rudel, Viktor Vinogradov, Georg Ganser, Philipp Bergs, Thomas Vahl, Christopher Frings, Markus König, Valentina Schambach, Maximilian Dietzel, Stefan Königs, Michael Fraunhofer Institute for Production Technology IPT Steinbachstraße 17 Aachen52074 Germany RWTH Aachen University Campus-Boulevard 30 Aachen52074 Germany Fraunhofer Institute for Algorithms and Scientific Computing SCAI Schloss Birlinghoven 1 Sankt Augustin53757 Germany ModuleWorks GmbH Henricistraße 50 Aachen52072 Germany Merantix Momentum Merantix AI Campus Max-Urich-Straße 3 Berlin13355 Germany EXAPT Systemtechnik GmbH Theaterstraße 12 Aachen52062 Germany

This publication introduces the development and application of an advanced CAD/CAM/CAE system that leverages the computational capabilities of an edge-cloud infrastructure. The developed system consists of containerized technology models for various complex process planning simulation tasks in 5-axis-milling, such as toolpath calculation, cutter-workpiece-engagement, uncut chip geometry or cutting force simulations. Moreover, a Bayesian optimization (BO) algorithm is coupled with the system enabling multi-objective optimizations of the considered machining operations by varying predefined CAM-parameters. The result of the optimization consists of a set of Pareto-efficient solutions. Each solution realizes a different tradeoff between the technological objectives of the process planner. Since mastering the complexity of the design space is a major challenge in today's CAM programming workflow, a Neural-Additive Model (NAM) is coupled with the system improving guided search through the configuration/result space. This reduces the convergence time to an optimal CAM parameter set. The coupling of the cloud computing, multi-objective optimization and artificial intelligence method with a CAM-kernel is demonstrated based on the process design of 5-axis milling operations for a blade-integrated disk (blisk). © 2024 The Authors. Published by Elsevier B.V.

关键词： Milling (machining)

Privacy Risk Assessment for Synthetic Longitudinal Health Data

学校读者我要写书评

暂无评论

Privacy Risk Assessment for Synthetic Longitudinal Health Da...

69th Annual Meeting of the German Association of Medical Informatics, Biometry and Epidemiology, GMDS 2024

作者： Schneider, Julian Walter, Marvin Otte, Karen Meurers, Thierry Perrar, Ines Nöthlings, Ute Adams, Tim Fröhlich, Holger Prasser, Fabian Fluck, Juliane Kühnel, Lisa Knowledge Management ZB MED - Information Centre for Life Sciences Cologne Germany Medical Informatics Group Berlin Institute of Health at Charité - Universitätsmedizin Berlin Berlin Germany Institute of Nutritional and Food Sciences - Nutritional Epidemiology University of Bonn Bonn Germany Department of Bioinformatics Fraunhofer Institute for Algorithms and Scientific Computing SCAI Sankt Augustin Germany The Agricultural Faculty University of Bonn Bonn Germany Faculty of Technology Bielefeld University Bielefeld Germany

ISBN: (纸本)9781643685366

Introduction A modern approach to ensuring privacy when sharing datasets is the use of synthetic data generation methods, which often claim to outperform classic anonymization techniques in the trade-off between data utility and privacy. Recently, it was demonstrated that various deep learning-based approaches are able to generate useful synthesized datasets, often based on domain-specific analyses. However, evaluating the privacy implications of releasing synthetic data remains a challenging problem, especially when the goal is to conform with data protection guidelines. Methods Therefore, the recent privacy risk quantification framework Anonymeter has been built for evaluating multiple possible vulnerabilities, which are specifically based on privacy risks that are considered by the European Data Protection Board, i.e. singling out, linkability, and attribute inference. This framework was applied to a synthetic data generation study from the epidemiological domain, where the synthesization replicates time and age trends previously found in data collected during the DONALD cohort study (1312 participants, 16 time points). The conducted privacy analyses are presented, which place a focus on the vulnerability of outliers. Results The resulting privacy scores are discussed, which vary greatly between the different types of attacks. Conclusion Challenges encountered during their implementation and during the interpretation of their results are highlighted, and it is concluded that privacy risk assessment for synthetic data remains an open problem. © 2024 The Authors.

关键词： Differential privacy

StarWatch 2.0: RFI Filter for SETI Signals

学校读者我要写书评

暂无评论

StarWatch 2.0: RFI Filter for SETI Signals

International Conference on Cyberworlds

作者： Stanislav Klimenko Igor Nikitin Lialia Nikitina Kira Konich Kevin Reinartz Sergey Tyul'Bashev Institute of Computing for Physics and Technology Moscow Institute for Physics and Technology (State University) Protvino Russia Fraunhofer Institute for Algorithms and Scientific Computing Sankt Augustin Germany Bauhaus University Weimar Germany Fiziceskij institut imeni P N Lebedeva RAN Moskva Moskva RU

We extend our system for radio astronomical monitoring by a cross-validation filter, separating near Earth radio frequency interference (RFI) from deep space signals. The filter searches for similar signals in a nearby frequency band, coming from a different spatial direction than the tested signal. The filter passes the signals which do not have such duplicates. We apply this technique to a database of SETI institute (***), containing 1.5 millions of sky observations in a frequency range 0.5-11.2 GHz, where our primary selection identified 28 strong signals possessing extraterrestrial (ET) signature. Crossvalidation allows to filter out 24 of those signals as satellite RFI. We present parameters for the remaining 4 signals and discuss statistical significance of these findings.

关键词： Satellites Satellite broadcasting Telescopes Brain models Antennas Radio astronomy

A Partition of Unity Construction of the Stabilization Function in Nitsche's Method for Variational Problems

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Jiménez Recio, Pablo Schweitzer, Marc Alexander Institut für Numerische Simulation Universität Bonn Friedrich-Hirzebruch-Allee 7 Bonn53115 Germany Fraunhofer Institute for Algorithms and Scientific Computing Schloss Birlinghoven Sankt Augustin53757 Germany

In this paper we develop a partition-of-unity construction of the stabilization function needed in Nitsche’s method, which can be seen as a generalization of the element-wise construction that is widely used in finite element methods. This allows for the use of Nitsche’s method within the Partition of Unity Method with a stabilization function that is not simply a constant over the whole boundary. In addition to that, we introduce a patch-aggregation approach designed to avoid arbitrarily large values of the stabilization function and the associated ill-conditioned systems and deteriorated convergence rates. We present numerical results to validate the proposed methods, covering Dirichlet boundary conditions, interface constraints and higher- order problems. These results clearly show that our approach leads to optimal convergence rates. © 2024, The Authors. All rights reserved.

关键词： Boundary conditions

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

Feature-based prediction of properties of cross-linked epoxy polymers by molecular dynamics and machine learning techniques

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Sindu, B.S. Hamaekers, Jan Special and Multifunctional Structures Laboratory CSIR-Structural Engineering Research Centre Taramani Tamil Nadu Chennai600113 India Fraunhofer Institute for Algorithms and Scientific Computing Schloss Birlinghoven Sankt AugustinD-53757 Germany

Epoxy polymers are used in wide range of applications. The properties and performance of epoxy polymers depend upon various factors like the type of constituents and their proportions used and other process parameters. The conventional way of developing epoxy polymers is usually labor-intensive and may not be fully efficient, which has resulted in epoxy polymers having a limited performance range due to the use of predetermined blend combinations, compositions and development parameters. Hence, in order to experiment with more design parameters, robust and easy computational techniques need to be established. To this end, we developed and analyzed in this study a new machine learning (ML) based approach to predict the mechanical properties of epoxy polymers based on their basic structural features. The results from molecular dynamics (MD) simulations have been used to derive the ML model. The salient feature of our work is that for the development of epoxy polymers based on EPON-862, several new hardeners were explored in addition to the conventionally used ones. The influence of additional parameters like the proportion of curing agent used and the extent of curing on the mechanical properties of epoxy polymers were also investigated. This method can be further extended by providing the epoxy polymer with the desired properties through knowledge of the structural characteristics of its constituents. The findings of our study can thus lead toward development of efficient design methodologies for epoxy polymeric systems. © 2023, CC BY-NC-ND.

关键词： Molecular dynamics