检索结果-内蒙古大学图书馆

Rationalism in the face of GPT hypes: Benchmarking the output of large language models against human expert-curated biomedical knowledge graphs

引用

ARTIFICIAL INTELLIGENCE IN THE LIFE SCIENCES 2024年 5卷

作者： Babaiha, Negin Sadat Rao, Sathvik Guru Klein, Juergen Schultz, Bruce Jacobs, Marc Hofmann-Apitius, Martin Fraunhofer Inst Algorithms & Sci Comp SCAI Dept Bioinformat D-53757 St Augustin Germany Univ Bonn Bonn Aachen Int Ctr Informat Technol B It D-53115 Bonn Germany

Biomedical knowledge graphs (KGs) hold valuable information regarding biomedical entities such as genes, diseases, biological processes, and drugs. KGs have been successfully employed in challenging biomedical areas such as the identification of pathophysiology mechanisms or drug repurposing. The creation of high-quality KGs typically requires labor-intensive multi-database integration or substantial human expert curation, both of which take time and contribute to the workload of data processing and annotation. Therefore, the use of automatic systems for KG building and maintenance is a prerequisite for the wide uptake and utilization of KGs. Technologies supporting the automated generation and updating of KGs typically make use of Natural Language Processing (NLP), which is optimized for extracting implicit triples described in relevant biomedical text sources. At the core of this challenge is how to improve the accuracy and coverage of the information extraction module by utilizing different models and tools. The emergence of pre-trained large language models (LLMs), such as ChatGPT which has grown in popularity dramatically, has revolutionized the field of NLP, making them a potential candidate to be used in text-based graph creation as well. So far, no previous work has investigated the power of LLMs on the generation of cause-and-effect networks and KGs encoded in Biological Expression Language (BEL). In this paper, we present initial studies towards one-shot BEL relation extraction using two different versions of the Generative Pre-trained Transformer (GPT) models and evaluate its performance by comparing the extracted results to a highly accurate, manually curated BEL KG curated by domain experts.

关键词： Large language models (LLMs) Natural language processing (NLP) Biomedical text mining Biomedical knowledge graphs Biological expression language (BEL)

来源：评论

学校读者我要写书评

暂无评论

Method for automated detection of outliers in crash simulations

引用

INTERNATIONAL JOURNAL OF CRASHWORTHINESS 2023年第1期28卷 96-107页

作者： Kracker, David Dhanasekaran, Revan Kumar Schumacher, Axel Garcke, Jochen Dr Ing HcF Porsche AG Body Engn CAE Vehicle Safety Weissach Germany Univ Wuppertal Fac Mech Engn & Safety Engn Chair Optimizat Mech Struct Wuppertal Germany Fraunhofer Ctr Machine Learning St Augustin Germany Fraunhofer Inst Algorithms & Sci Comp SCAI St Augustin Germany Univ Bonn Inst Numer Simulat Bonn Germany

Stricter legal requirements in crash safety lead to more complex development processes in computer-aided engineering and result in an increasing number of simulations. Both, the construction of the simulation models as well as their evaluation are costly and time-consuming. Therefore, an automated workflow is required that significantly facilitates the analysis of the results by the engineer and increases the quality of the evaluation. In this study an automated evaluation process is proposed that detects anomalous crash behaviour in a bundle of crash simulations. The individual states from the simulation are analysed separately from each other and an outlier score is calculated using a kth-nearest-neighbour approach. Subsequently, these results are averaged into one score for each simulation. With the help of different statistical methods, a threshold value is calculated, from which a simulation can be identified as an outlier. The evaluation is carried out on 5 datasets. On average, the precision and recall of the presented method are 1.0 and 0.91, respectively.

关键词： Crash simulation analysis outlier detection machine learning process automation

来源：评论

学校读者我要写书评

暂无评论

Benchmarking table recognition performance on biomedical literature on neurological disorders

引用

BIOINFORMATICS 2022年第6期38卷 1624-1630页

作者： Adams, Tim Namysl, Marcin Kodamullil, Alpha Tom Behnke, Sven Jacobs, Marc Fraunhofer Inst Algorithms & Sci Comp D-53757 St Augustin Germany Fraunhofer Inst Intelligent Anal & Informat Syst D-53757 St Augustin Germany Univ Bonn Comp Sci Inst 6 Autonomous Intelligent Syst D-53115 Bonn Germany

Motivation Table recognition systems are widely used to extract and structure quantitative information from the vast amount of documents that are increasingly available from different open sources. While many systems already perform well on tables with a simple layout, tables in the biomedical domain are often much more complex. Benchmark and training data for such tables are however very limited. Results To address this issue, we present a novel, highly curated benchmark dataset based on a hand-curated literature corpus on neurological disorders, which can be used to tune and evaluate table extraction applications for this challenging domain. We evaluate several state-of-the-art table extraction systems based on our proposed benchmark and discuss challenges that emerged during the benchmark creation as well as factors that can impact the performance of recognition methods. For the evaluation procedure, we propose a new metric as well as several improvements that result in a better performance evaluation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Methodology for Integrating Hierarchical VMAP-Data Structures into an Ontology Using Semantically Represented Analyses

引用

INFORMATION 2024年第1期15卷

作者： Spelten, Philipp Meyer, Morten-Christian Wagner, Anna Wolf, Klaus Reith, Dirk Fraunhofer Inst Algorithms & Sci Comp SCAI D-53757 St Augustin Germany PROSTEP AG Dolivostr 11 D-64293 Darmstadt Germany Bonn Rhein Sieg Univ Appl Sci Inst Technol Resource & Energy Efficient Engn TREE Grantham Allee 20 D-53757 Bonn Germany

Integrating physical simulation data into data ecosystems challenges the compatibility and interoperability of data management tools. Semantic web technologies and relational databases mostly use other data types, such as measurement or manufacturing design data. Standardizing simulation data storage and harmonizing the data structures with other domains is still a challenge, as current standards such as the ISO standard STEP (ISO 10303 "Standard for the Exchange of Product model data") fail to bridge the gap between design and simulation data. This challenge requires new methods, such as ontologies, to rethink simulation results integration. This research describes a new software architecture and application methodology based on the industrial standard "Virtual Material Modelling in Manufacturing" (VMAP). The architecture integrates large quantities of structured simulation data and their analyses into a semantic data structure. It is capable of providing data permeability from the global digital twin level to the detailed numerical values of data entries and even new key indicators in a three-step approach: It represents a file as an instance in a knowledge graph, queries the file's metadata, and finds a semantically represented process that enables new metadata to be created and instantiated.

关键词： ontology simulation process data management CAE metadata structures semantic technologies

来源：评论

学校读者我要写书评

暂无评论

Analysis of Tensor Approximation Schemes for Continuous Functions

引用

FOUNDATIONS OF COMPUTATIONAL MATHEMATICS 2023年第1期23卷 219-240页

作者： Griebel, Michael Harbrecht, Helmut Univ Bonn Inst Numer Simulat Friedrich Hirzebruch Allee 7 D-53115 Bonn Germany Fraunhofer Inst Algorithms & Sci Comp SCAI D-53754 Schloss Birlinghoven Sankt Augustin Germany Univ Basel Dept Math & Informat Spiegelgasse 1 CH-4051 Basel Switzerland

In this article, we analyze tensor approximation schemes for continuous functions. We assume that the function to be approximated lies in an isotropic Sobolev space and discuss the cost when approximating this function in the continuous analogue of the Tucker tensor format or of the tensor train format. We especially show that the cost of both approximations are dimension-robust when the Sobolev space under consideration provides appropriate dimension weights.

关键词： Tensor format Approximation error Rank complexity Sobolev space with dimension weights

来源：评论

学校读者我要写书评

暂无评论

Unraveling the heterogeneity in Alzheimer's disease progression across multiple cohorts and the implications for data-driven disease modeling

引用

ALZHEIMERS & DEMENTIA 2022年第2期18卷 251-261页

作者： Birkenbihl, Colin Salimi, Yasamin Frohlich, Holger Fraunhofer Inst Algorithms & Sci Comp SCAI Dept Bioinformat St Augustin Germany Rhein Friedrich Wilhelm Univ Bonn Bonn Aachen Int Ctr IT Bonn Germany

Introduction Given study-specific inclusion and exclusion criteria, Alzheimer's disease (AD) cohort studies effectively sample from different statistical distributions. This heterogeneity can propagate into cohort-specific signals and subsequently bias data-driven investigations of disease progression patterns. Methods We built multi-state models for six independent AD cohort datasets to statistically compare disease progression patterns across them. Additionally, we propose a novel method for clustering cohorts with regard to their progression signals. Results We identified significant differences in progression patterns across cohorts. Models trained on cohort data learned cohort-specific effects that bias their estimations. We demonstrated how six cohorts relate to each other regarding their disease progression. Discussion Heterogeneity in cohort datasets impedes the reproducibility of data-driven results and validation of progression models generated on single cohorts. To ensure robust scientific insights, it is advisable to externally validate results in independent cohort datasets. The proposed clustering assesses the comparability of cohorts in an unbiased, data-driven manner.

关键词： Alzheimer's disease cohort study data mining data-driven disease modeling machine learning sampling bias statistical learning translational research

来源：评论

学校读者我要写书评

暂无评论

Efficient Quality Diversity Optimization of 3D Buildings through 2D Pre-Optimization

引用

EVOLUTIONARY COMPUTATION 2023年第3期31卷 287-307页

作者： Hagg, Alexander Kliemank, Martin L. Asteroth, Alexander Wilde, Dominik Bedrunka, Mario C. Foysi, Holger Reith, Dirk Bonn Rhein Sieg Univ Appl Sci Inst Technol Resource & Energy Efficient Engn TREE D-53757 St Augustin Germany Univ Siegen Dept Mech Engn D-57076 Siegen Germany Fraunhofer Inst for Algorithms & Sci Comp SCAI D-53754 St Augustin Germany

Quality diversity algorithms can be used to efficiently create a diverse set of solutions to inform engineers' intuition. But quality diversity is not efficient in very expensive problems, needing hundreds of thousands of evaluations. Even with the assistance of surrogate models, quality diversity needs hundreds or even thousands of evaluations, which can make its use infeasible. In this study, we try to tackle this problem by using a pre-optimization strategy on a lower-dimensional optimization problem and then map the solutions to a higher-dimensional case. For a use case to design buildings that minimize wind nuisance, we show that we can predict flow features around 3D buildings from 2D flow features around building footprints. For a diverse set of building designs, by sampling the space of 2D footprints with a quality diversity algorithm, a predictive model can be trained that is more accurate than when trained on a set of footprints that were selected with a space-filling algorithm like the Sobol sequence. Simulating only 16 buildings in 3D, a set of 1,024 building designs with low predicted wind nuisance is created. We show that we can produce better machine learning models by producing training data with quality diversity instead of using common sampling techniques. The method can bootstrap generative design in a computationally expensive 3D domain and allow engineers to sweep the design space, understanding wind nuisance in early design phases.

关键词： Multisolution optimization quality diversity efficiency pre-optimization wind nuisance Bayesian optimization lattice Boltzmann method design process

来源：评论

学校读者我要写书评

暂无评论

Attention Mechanism-Based Light-Field View Synthesis

引用

IEEE ACCESS 2022年 10卷 7895-7913页

作者： Gul, M. Shahzeb Khan Mukati, M. Umair Batz, Michel Forchhammer, Soren Keinert, Joachim Fraunhofer Inst Integrated Circuits IIS Computat Imaging & Algorithms Grp Moving Picture Technol D-91058 Erlangen Germany Tech Univ Denmark DTU Foton DK-2800 Lyngby Denmark

The angular information of light lost in conventional images but preserved and stored in light-fields plays an instrumental role in many applications such as depth estimation, 3D reconstruction and post-capture refocusing. However, the limited angular resolution of light-field images due to the consumer hardware limitations is a major drawback in its widespread adoption. In this article, we present a novel deep learning-based light-field view synthesis method from a sparse set of input views. Our proposed method, an end-to-end trainable network, utilizes convolutional block attention modules to enhance the built-in depth image-based rendering. The proposed convolutional block attention module consists of two attention modules sequentially applied in the channel and spatial dimensions to focus the network on critical features. The proposed network architecture is a combination of three sub-networks, one for stereo feature extraction, another for disparity estimation, and the last for attention-based refinement. We present two schemes for the refinement network that perform equally well but differ in the number of parameters by 1.2% and execution time by 44%. Quantitative and qualitative results on four challenging real-world datasets show the superiority of the proposed method. Our proposed method shows considerable PSNR gains, around 1 dB compared to the state of the art and around 0.5 dB over our previous method LFVS-AM. In addition, ablation studies demonstrate the effectiveness of each module of the proposed method. Finally, the parallax edge precision-recall curve shows that our method better preserves parallax details.

关键词： Feature extraction Spatial resolution Cameras Image reconstruction Estimation Three-dimensional displays Lenses Light-field view synthesis attention module deep learning neural networks separable convolution

来源：评论

学校读者我要写书评

暂无评论

On the expressivity of embedding quantum kernels

引用

MACHINE LEARNING-SCIENCE AND TECHNOLOGY 2024年第2期5卷 025003-025003页

作者： Gil-Fuster, Elies Eisert, Jens Dunjko, Vedran Free Univ Berlin Dahlem Ctr Complex Quantum Syst D-14195 Berlin Germany Fraunhofer Heinrich Hertz Inst Berlin Germany Helmholtz Zentrum Berlin Mat & Energie D-14109 Berlin Germany Leiden Univ aQaL Appl Quantum Algorithms Leiden Netherlands Leiden Univ LIACS NL-2333 CA Leiden Netherlands

One of the most natural connections between quantum and classical machine learning has been established in the context of kernel methods. Kernel methods rely on kernels, which are inner products of feature vectors living in large feature spaces. Quantum kernels are typically evaluated by explicitly constructing quantum feature states and then taking their inner product, here called embedding quantum kernels. Since classical kernels are usually evaluated without using the feature vectors explicitly, we wonder how expressive embedding quantum kernels are. In this work, we raise the fundamental question: can all quantum kernels be expressed as the inner product of quantum feature states? Our first result is positive: Invoking computational universality, we find that for any kernel function there always exists a corresponding quantum feature map and an embedding quantum kernel. The more operational reading of the question is concerned with efficient constructions, however. In a second part, we formalize the question of universality of efficient embedding quantum kernels. For shift-invariant kernels, we use the technique of random Fourier features to show that they are universal within the broad class of all kernels which allow a variant of efficient Fourier sampling. We then extend this result to a new class of so-called composition kernels, which we show also contains projected quantum kernels introduced in recent works. After proving the universality of embedding quantum kernels for both shift-invariant and composition kernels, we identify the directions towards new, more exotic, and unexplored quantum kernel families, for which it still remains open whether they correspond to efficient embedding quantum kernels.

关键词： quantum machine learning quantum kernels kernel methods supervised learning quantum learning theory

来源：评论

学校读者我要写书评

暂无评论

Signal Processing Architecture for a Trustworthy 77-GHz MIMO Radar

IEEE TRANSACTIONS ON RADAR SYSTEMS

引用

IEEE TRANSACTIONS ON RADAR SYSTEMS 2024年 2卷 1112-1122页

作者： Kishore Arumugam, Ram Froehly, Andre Wallrath, Patrick Herschel, Reinhold Pohl, Nils Fraunhofer Inst High Frequency Phys & Radar Tech Dept Signal Proc & Algorithms D-53343 Wachtberg Germany Ruhr Univ Bochum Inst Integrated Syst D-44801 Bochum Germany Wavesense Dresden GmbH D-01069 Dresden Germany Ruhr Univ Bochum Inst Integrated Syst D-44801 Bochum Germany

Radar systems are used in safety-critical applications in vehicles, so it is necessary to ensure their functioning is reliable and trustworthy. System-on-chip (SoC) radars, which are commonly used now-a-days, are inherently vulnerable to data manipulation and attacks to gain intellectual property (IP) of the system. This article outlines the vulnerabilities of the SoC radars and proposes a distributed signal processing to improve the resilience of the system. The trustworthiness of the system is improved by partitioning the signal processing into smaller modules. We propose to implement these modules on separate processors such that it is made up of multiple application-specific integrated circuits (ASICs). Furthermore, a sparse antenna topology is proposed to limit the information stored in these modules. Therefore, it is difficult to execute a successful attack or gain any knowledge of the targets or system design based on the compromised data in one ASIC. This article introduces the generic structure for partitioning the signal processing steps involved in target detection and the sparse array topology used by the 77-GHz radar. A method for estimating the azimuth and elevation angles for the considered sparse array is also introduced.

关键词： Radar Radar signal processing Signal processing Chiplets Trojan horses Automotive engineering Topology Fast Fourier transforms Estimation Arrays Autonomous vehicles compressed sensing direction-of-arrival estimation distributed algorithms matching pursuit algorithms millimetre-wave radar radar detection radar signal processing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：