检索结果-内蒙古大学图书馆

A landscape analysis of standardisation in the field of artificial intelligence

学校读者我要写书评

暂无评论

Journal of ICT Standardization

Journal of ICT Standardization 2020年第2期8卷 151-184页

作者： Ziegler, Wolfgang Fraunhofer Institute for Algorithms and Scientific Computing SCAI Sankt Augustin Germany

While projects, developments and applications addressing and using artificial intelligence (AI) are rather multifaceted and their number is constantly increasing, the standardisation activities in the field of artificial intelligence are limited, their number is significantly lower and does not increase at the same pace. The European funded project *** aims at supporting European experts' presence in and contributions to international standardisation activities in ICT. The focus of the project is on the 5 priority domains identified by the European Commission (Cloud computing, IoT, Big Data, Cyber Security, 5G) and on Artificial Intelligence while being open for other relevant topics defined in the annual European Rolling Plan for ICT Standardisation. The project has two main outcomes: (i) increased contribution of European experts in international standardisation through support by providing grants for planned contributions of successful applications of experts, and (ii) an online observatory of published standards and ongoing standardisation activities in the areas mentioned before. This observatory (called Standards Watch) is accessible through the project's web site and open for contributions and comments from registered users. As part of the effort for the Standards Watch the projects has prepared a comprehensive analysis of the international standardisation landscape in the AI field, that comprises a description of the ICT standards and ongoing work at international level in the field of AI across the standardisation organisations already active in the field. In this article we will present results of our work where we have analysed the work of the 5 international and European Standards Development Organisations (SDOs) IEEE,1 ISO/IEC,2 ITU-T,3 ETSI4 and CEN-CENELEC5 developing standards in the field of AI. The first 4 bodies have already been active several years in AI standardisation at the time of writing this article. CEN-CENELEC has launched a focu

关键词： Watches

Graph Visualization for Blockchain Data

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Dietl, Marcell Gemünd, Andre Oeltz, Daniel Thiele, Felix M. Werner, Christian Fraunhofer Institute for Algorithms and Scientific Computing SCAI Schloss Birlinghoven Sankt Augustin53757 Germany frontmark GmbH Taunusstraße 63 Wiesbaden65183 Germany

In this report, we introduce a novel approach to visualize extremely large graphs efficiently. Our method combines two force-directed algorithms, Kamada-Kawai and ForceAtlas2, to handle different graph components based on their node count. Additionally, we suggest utilizing the Fast Multipole method to enhance the speed of ForceAtlas2. Although initially designed for analyzing bitcoin transaction graphs, for which we present results here, this algorithm can also be applied to other crypto currency transaction graphs or graphs from diverse domains. Copyright © 2024, The Authors. All rights reserved.

关键词： Directed graphs

Parameterized Neural Networks for Finance

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Oeltz, Daniel Hamaekers, Jan Pilz, Kay F. Fraunhofer Institute for Algorithms and Scientific Computing SCAI Schloss Birlinghoven Sankt Augustin53757 Germany Kinetic Mind GmbH Germany

We discuss and analyze a neural network architecture, that enables learning a model class for a set of different data samples rather than just learning a single model for a specific data sample. In this sense, it may help to reduce the overfitting problem, since, after learning the model class over a larger data sample consisting of such different data sets, just a few parameters need to be adjusted for modeling a new, specific problem. After analyzing the method theoretically and by regression examples for different one-dimensional problems, we finally apply the approach to one of the standard problems asset managers and banks are facing: the calibration of spread curves. The presented results clearly show the potential that lies within this method. Furthermore, this application is of particular interest to financial practitioners, since nearly all asset managers and banks which are having solutions in place may need to adapt or even change their current methodologies when ESG ratings additionally affect the bond spreads. Copyright © 2023, The Authors. All rights reserved.

关键词： Network architecture

QR Factorization of Block Low-Rank Matrices on Multi-instance GPU 23rd

学校读者我要写书评

暂无评论

QR Factorization of Block Low-Rank Matrices on Multi-insta...

23rd International Conference on Parallel and Distributed computing, Applications, and Technologies, PDCAT 2022

作者： Ohshima, Satoshi Ida, Akihiro Yokota, Rio Yamazaki, Ichitaro Information Technology Center Nagoya University Aichi Japan Research Institute for Value-Added-Information Generation Japan Agency for Marine-Earth Science and Technology Kanagawa Japan Global Scientific Information and Computing Center Tokyo Institute of Technology Tokyo Japan Scalable Algorithms Department Sandia National Laboratories New Mexico United States

ISBN: (纸本)9783031299261

The QR factorization, which is a fundamental operation in linear algebra, is used extensively in scientific simulations. The acceleration and memory reduction of it are important research targets. QR factorization using block low-rank matrices (BLR-QR) has previously been proposed to address this issue. In this study, we consider its implementation on a GPU. Current CPUs and GPUs have numerous computational cores and the performance consists of the total performance of them. Therefore, the degree of parallelism of the target calculation is important for obtaining high performance. By contrast, many applications, including BLR-QR, do not have sufficient parallelism. Batched computation has attracted attention for achieving high performance in such calculations. However, the use of it requires major code rewriting and is extremely laborious. Thus, we propose the use of the multi-instance GPU (MIG) feature of current GPUs. Using MIG, we succeeded in obtaining a 53.3% time reduction over the CPU and 77.6% over the GPU without MIG. From the above result, we succeeded in demonstrating rapid implementation of BLR-QR on MIG and usefulness of MIG. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Graphics processing unit

Sizing optimization of hybrid hydrogen energy storage systems: A metamodel-based approach

学校读者我要写书评

暂无评论

International Journal of Hydrogen Energy 2025年

作者： Bareev-Rudy, Michael Schedler, Steffen Clees, Tanja Grantham-Allee 20 Sankt Augustin53757 Germany Fraunhofer Institute for Algorithms and Scientific Computing SCAI Schloss Birlinghoven Sankt Augustin53757 Germany

Hybrid energy storage systems (HESS), consisting of a battery, hydrogen storage, electrolyzer and fuel cell, have received increasing attention from the scientific community in recent years as they can help increase the use of renewable energy. In this paper, a novel metamodel-based sizing optimization workflow is developed. The workflow is demonstrated on residential building scenarios with real solar power data. Sobol sequences are utilized to vary the component size in simulation, while radial basis functions are employed to approximate simulation results, which are then used for the optimization. The utilization of waste heat from Power-to-Gas and Gas-to-Power processes is evaluated using thermal equations by extending an existing coupled electrochemical and thermodynamic HESS model built in the multiphysical energy system simulator MEgy. The results show a functional workflow that optimizes sizing for a given scenario and outputs the component's daily energy balance and state of charge. © 2025 The Authors

关键词： Waste heat utilization

Generalized Sparse Grid Interpolation Based on the Fast Discrete Fourier Transform 1

学校读者我要写书评

暂无评论

5th Workshop on Sparse Grids and Applications, SGA 2018

作者： Griebel, Michael Hamaekers, Jan Institute for Numerical Simulation University of Bonn Bonn Germany Fraunhofer Institute for Algorithms and Scientific Computing SCAI Schloss Birlinghoven Sankt Augustin Germany

ISBN: (数字)9783030813628

ISBN: (纸本)9783030813611

In (Griebel and Hamaekers, Fast discrete Fourier transform on generalized sparse grids, Sparse grids and Applications, volume 97 of Lecture Notes in Computational Science and Engineering, pages 75–108, Springer, 2014), an algorithm for trigonometric interpolation involving only so-called standard information of multivariate functions on generalized sparse grids has been suggested and a study on its application for the interpolation of functions in periodic Sobolev spaces of dominating mixed smoothness has been presented. In this complementary paper, we now give a slight modification of the proofs, which yields an extension from the pairing (Hs,Hmixt) to the more general pairing (Hs,Hmixt,r) and which in addition results in an improved estimate for the interpolation error. The improved (constructive) upper bound is in particular consistent with the lower bound for sampling on regular sparse grids with r = 0 and s = 0 given in (Dũng, Acta Mathematica Vietnamica, 43(1):83–110, 2018;Dũng et al., Hyperbolic Cross Approximation, Advanced Courses in Mathematics - CRM Barcelona, Birkhäuser/Springer, 2018). © 2021, Springer Nature Switzerland AG.

关键词： Discrete Fourier transforms

A Framework for Synthetic Power System Dynamics

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Büttner, Anna Plietzsch, Anton Anvari, Mehrnaz Hellmann, Frank Potsdam-Institute for Climate Impact Research Germany Fraunhofer Research Institution for Energy Infrastructures and Geothermal Systems Germany Fraunhofer Institute for Algorithms and Scientific Computing Germany

We present a modular framework for generating synthetic power grids that considers the heterogeneity of real power grid dynamics but remains simple and tractable. This enables the generation of large sets of synthetic grids for a wide range of applications. For the first time, our synthetic model also includes the major drivers of fluctuations on short-time scales and a set of validators that ensure the resulting system dynamics are plausible. The synthetic grids generated are robust and show good synchronization under all evaluated scenarios, as should be expected for realistic power grids. A software package that includes an efficient Julia implementation of the framework is released as a companion to the paper. © 2023, CC BY.

关键词： System theory

On Multilevel Energy-Based Fragmentation Methods

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Barker, James Griebel, Michael Hamaekers, Jan Institute for Numerical Simulation University of Bonn Friedrich-Hirzebruch-Allee 7 Bonn53115 Germany Fraunhofer Institute for Algorithms and Scientific Computing SCAI Schloss Birlinghoven 1 Sankt Augustin53757 Germany

Energy-based fragmentation methods approximate the potential energy of a molecular system as a sum of contribution terms built from the energies of particular subsystems. Some such methods reduce to truncations of the many-body expansion (MBE);others combine subsystem energies in a manner inspired by the principle of inclusion/exclusion (PIE). The combinatorial technique of Möbius inversion of sums over partially ordered sets, which generalizes the PIE, is known to provide a non-recursive expression for the MBE contribution terms, and has also been connected to related cluster expansion methods. We build from these ideas a very general framework for decomposing potential functions into energetic contribution terms associated with elements of particular partially ordered sets (posets) and direct products thereof. Specific choices immediately reproduce not only the MBE, but also a number of other existing decomposition forms, including, e.g., the multilevel ML-BOSSANOVA schema. Furthermore, a different choice of poset product leads to a setup familiar from the combination technique for high-dimensional approximation, which has a known connection to quantum-chemical composite methods. We present the ML-SUPANOVA decomposition form, which allows the further refinement of the terms of an MBE-like expansion of the Born-Oppenheimer potential according to systematic hierarchies of ab initio methods and of basis sets. We outline an adaptive algorithm for the a posteori construction of quasi-optimal truncations of this decomposition. Some initial experiments are reported and *** Codes 35J10, 65D40, 65Z05, 92E10, 06A07 © 2024, CC BY.

关键词： Adaptive algorithms

Fault Detection in Uni-Directional Tape Production Using Image Processing 25th

学校读者我要写书评

暂无评论

Fault Detection in Uni-Directional Tape Production Using Ima...

25th International Conference on Pattern Recognition Workshops, ICPR 2020

作者： Devagekar, Somesh Delforouzi, Ahmad Plöger, Paul G. Department of Computer Science Hochschule Bonn-Rhein-Sieg Bonn Germany Institute for Algorithms and Scientific Computing Fraunhofer SCAI Bonn Germany

ISBN: (纸本)9783030687984

The quality of uni-directional tape in its production process is affected by environmental conditions like temperature and production speed. In this paper, computer vision algorithms on the scanned images are needed to be used in this context to detect and classify tape damages during the manufacturing procedure. We perform a comparative study among famous feature descriptors for fault candidate generation, then propose own features for fault detection. We investigate various machine learning techniques to find best model for the classification problem. The empirical results demonstrate the high performance of the proposed system and show preference of random forest and canny edges for classifier and feature generator respectively. © 2021, Springer Nature Switzerland AG.

关键词： Feature extraction