检索结果-内蒙古大学图书馆

Leveraging Large Language Models and Agent-Based Systems for scientific data analysis: Validation Study

JMIR MENTAL HEALTH 2025年 12卷 e68135页

作者： Peasley, Dale Kuplicki, Rayus Sen, Sandip Paulus, Martin Laureate Inst Brain Res Civ Ctr 400 Tulsa OK 74136 USA Univ Tulsa Tandy Sch Comp Sci Tulsa OK USA

Background: Large language models have shown promise in transforming how complex scientific data are analyzed and communicated, yet their application to scientific domains remains challenged by issues of factual accuracy and domain-specific precision. The Laureate Institute for Brain Research-Tulsa University (LIBR-TU) Research Agent (LITURAt) leverages a sophisticated agent-based architecture to mitigate these limitations, using external data retrieval and analysis tools to ensure reliable, context-aware outputs that make scientific information accessible to both experts and nonexperts. Objective: The objective of this study was to develop and evaluate LITURAt to enable efficient analysis and contextualization of complex scientific datasets for diverse user expertise levels. Methods: An agent-based system based on large language models was designed to analyze and contextualize complex scientific datasets using a "plan-and-solve" framework. The system dynamically retrieves local data and relevant PubMed literature, performs statistical analyses, and generates comprehensive, context-aware summaries to answer user queries with high accuracy and consistency. Results: Our experiments demonstrated that LITURAt achieved an internal consistency rate of 94.8% and an external consistency rate of 91.9% across repeated and rephrased queries. Additionally, GPT-4 evaluations rated 80.3% (171/213) of the system's answers as accurate and comprehensive, with 23.5% (50/213) receiving the highest rating of 5 for completeness and precision. Conclusions: These findings highlight the potential of LITURAt to significantly enhance the accessibility and accuracy of scientific data analysis, achieving high consistency and strong performance in complex query resolution. Despite existing limitations, such as model stability for highly variable queries, LITURAt demonstrates promise as a robust tool for democratizing data-driven insights across diverse scientific domains.

关键词： LLM agent-based systems scientific data analysis data contextualization AI-driven research tools large language model scientific data analysis contextualization AI artificial intelligence research tool

来源：评论

学校读者我要写书评

暂无评论

ODDS: Optimizing data-Locality Access for scientific data analysis

引用

IEEE TRANSACTIONS ON CLOUD COMPUTING 2020年第1期8卷 220-231页

作者： Wang, Jun Han, Dezhi Yin, Jiangling Zhou, Xiaobo Jiang, Changjun Univ Cent Florida Orlando FL 32816 USA Shanghai Maritime Univ Shanghai 200135 Peoples R China Apple Inc Orlando FL 32816 USA Univ Colorado Springs Colorado Springs CO 80918 USA Tongji Univ Shanghai 200000 Peoples R China

Whereas traditional scientific applications are computationally intensive, recent applications require more data-intensive analysis and visualization to extract knowledge from the explosive growth of scientific information and simulation data. As the computational power and size of compute clusters continue to increase, the I/O read rates and associated network for these data-intensive applications have been unable to keep pace. These applications suffer from long I/O latency due to the movement of "big data" from the network/parallel file system, which results in a serious performance bottleneck. To address this problem, we proposed a novel approach called "ODDS" to optimize data-locality access in scientific data analysis and visualization. ODDS leverages a distributed file system (DFS) to provide scalable data access for scientific analysis. Through exploiting the information of underlying data distribution in DFS, ODDS employs a novel data-locality scheduler to transform a compute-centric mapping into a data-centric one and enables each computational process to access the needed data from a local or nearby storage node. ODDS is suitable for parallel applications with dynamic process-to-data scheduling and for applications with static process-to-data assignment. To demonstrate the efficacy of our methods, we present and evaluate ODDS in the context of two state-of-the-art, scientific-analysis applications-mpiBLAST and ParaView-along with the Hadoop distributed file system (HDFS) across a wide variety of computing platform settings. In comparison to existing deployments using NFS, PVFS, or Lustre as the underlying storage systems, ODDS can greatly reduce the I/O cost and double overall performance.

关键词： Distributed file system I/O data-intensive scientific data analysis data locality

来源：评论

学校读者我要写书评

暂无评论

Space Payload Test System A flexible SW suite for scientific data analysis in space missions 3

Space Payload Test System A flexible SW suite for scientific...

引用

3rd IEEE International Workshop on Metrology for Aerospace (MetroAeroSpace)

作者： Amoruso, L. Abbattista, C. Cinquepalmi, L. Agrimano, L. Planetek Italia Bari Italy

ISBN: (纸本)9781467382922

SpacePTS is a Payload Test System for on-board sensors (and components in general) designed and developed with a special attention to data analysis and scientific users' needs. It aims to bridge the gap between scientists developing the instruments and ground systems operators having to manage the mission as a whole. It has been built around a SW core able to accomplish to all system issues (from HW links to protocols, standard and databases management), enriched by a suite of plug-in modules able to extend the supported HW and the core functionalities, till to include complex monitoring capabilities. This paper describes how the SW suite has been designed within the experience of a scientific mission (the Solar Wind Analyser instrument suite on-board Solar Orbiter).

关键词： ground support equipment payload data scientific data analysis test systems EGSE CCSDS PUS SCOS2000

来源：评论

学校读者我要写书评

暂无评论

ParSA: High-throughput scientific data analysis framework with distributed file system

引用

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 2015年 51卷 111-119页

作者： Zhang, Tao Sun, XiangZheng Xue, Wei Qiao, Nan Huang, Huang Shu, JiWu Zheng, Weimin Tsinghua Univ Dept Comp Sci & Technol Beijing 100084 Peoples R China Intel Corp Beijing Peoples R China

scientific data analysis and visualization have become the key component for nowadays large scale simulations. Due to the rapidly increasing data volume and awkward I/O pattern among high structured files, known serial methods/tools cannot scale well and usually lead to poor performance over traditional architectures. In this paper, we propose a new framework: ParSA (parallel scientific data analysis) for high-throughput and scalable scientific analysis, with distributed file system. ParSA presents the optimization strategies for grouping and splitting logical units to utilize distributed I/O property of distributed file system, scheduling the distribution of block replicas to reduce network reading, as well as to maximize overlapping the data reading, processing, and transferring during computation. Besides, ParSA provides the similar interfaces as the NetCDF Operator (NCO), which is used in most of climate data diagnostic packages, making it easy to use this framework. We utilize ParSA to accelerate well-known analysis methods for climate models on Hadoop Distributed File System (HDFS). Experimental results demonstrate the high efficiency and scalability of ParSA, getting the maximum 1.3 GB/s throughput on a six nodes Hadoop cluster with five disks per node. Yet, it can only get 392 MB/s throughput on a RAID-6 storage node. (C) 2014 Elsevier B.V. All rights reserved.

关键词： data intensive computing scientific data analysis Distributed file system

来源：评论

学校读者我要写书评

暂无评论

A Feature Extraction Framework for 3D scientific Voxel Object Using SVD and Neural Network

A Feature Extraction Framework for 3D Scientific Voxel Objec...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Feng, Zhichen Gao, Yaqian Ye, Huang Zhang, Jian Chinese Acad Sci Comp Network Informat Ctr Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

ISBN: (纸本)9798350359329;9798350359312

Latest advances in computational methods and high-performance computing have enabled large-scale scientific simulations to become feasible. However, efficiently analyzing the resulting large datasets remains challenging. Typically, 3D voxel data occupies huge storage space which causes serious storage pressure. Performing real-time feature extraction during simulations could mitigate this demand. In this paper, We propose a three-decker structure framework for locating and extracting voxel object features such as pose, class, and size. The framework first utilizes a 3D CNN to localize the object's center and size along each axis, enabling adaptive cropping of the target from the original voxel space. Then the singular value decomposition (SVD) will applied to the extracted object to preliminarily extract and refine its posture. Finally, a neural network will refine the SVD-extracted pose and predict the category and size. Finally, a neural network is utilized to infer residual pose corrections as well as category and size information for the object after preliminary pose alignment via SVD decomposition. Our method achieves accurate feature extraction for voxel objects with complex poses. More importantly, we achieve pose estimation without an initial position. By storing extracted features instead of full data, we significantly reduce storage needs. We validate our approach using the phase field simulations dataset and ModelNet40 dataset. At last, based on the proposed framework we develop an in-situ feature extraction library for running with large-scale scientific computing programs and performing realtime feature extraction on the large amount of computation data it generates. As a concrete running example, we selected the microstructure evolution program governed by the phasefield method for a common run and achieved high-accuracy feature extraction.

关键词： scientific data analysis 3D voxel data realtime feature extraction 3D pose estimation

来源：评论

学校读者我要写书评

暂无评论

Empowering beginners in bioinformatics with ChatGPT

引用

Quantitative Biology 2023年第2期11卷 105-108页

作者： Evelyn Shue Li Liu Bingxin Li Zifeng Feng Xin Li Gangqing Hu Department of Microbiology Immunology&Cell BiologyWest Virginia UniversityMorgantownWV 26506USA College of Health Solutions Arizona State UniversityPhoenixAZ 85004USA Biodesign Institute Arizona State UniversityTempeAZ 85281USA Finance Department John Chambers College of Business and EconomicsWest Virginia UniversityMorgantownWV26506USA Department of Economics and Finance The University of Texas at EI PasoEI PasoTX 79902USA Lane Department of Computer Science and Electrical Engineering West Virginia UniversityMorgantownWV 26506USA

The impressive conversational and programming abilities of ChatGPT make it an attractive tool for facilitating the education of bioinformatics data analysis for *** this study,we proposed an iterative model to fine-tune instructions for guiding a chatbot in generating code for bioinformatics data analysis *** demonstrated the feasibility of the model by applying it to various bioinformatics ***,we discussed practical considerations and limitations regarding the use of the model in chatbot-aided bioinformatics education.

关键词： bioinformatics education scientific data analysis ChatGPT

来源：评论

学校读者我要写书评

暂无评论

Towards HPC and Big data Analytics Convergence: Design and Experimental Evaluation of a HPDA Framework for eScience at Scale

引用

IEEE ACCESS 2021年 9卷 73307-73326页

作者： Elia, Donatello Fiore, Sandro Aloisio, Giovanni Euro Mediterranean Ctr Climate Change CMCC Fdn I-73100 Lecce Italy Univ Salento Dept Engn Innovat I-73100 Lecce Italy Univ Trento Dept Informat Engn & Comp Sci I-38123 Trento Italy

Over the last two decades, scientific discovery has increasingly been driven by the large availability of data from a multitude of sources, including high-resolution simulations, observations and instruments, as well as an enormous network of sensors and edge components. In such a dynamic and growing landscape where data continue to expand, advances in Science have become intertwined with the capacity of analysis tools to effectively handle and extract valuable information from this ocean of data. In view of the exascale era of supercomputers that is rapidly approaching, it is of the utmost importance to design novel solutions that can take full advantage of the upcoming computing infrastructures. The convergence of High Performance Computing (HPC) and data-intensive analytics is key to delivering scalable High Performance data Analytics (HPDA) solutions for scientific and engineering applications. The aim of this paper is threefold: reviewing some of the most relevant challenges towards HPDA at scale, presenting a HPDA-enabled version of the Ophidia framework and validating the scalability of the proposed framework through an experimental performance evaluation carried out in the context of the Centre of Excellence in Simulation of Weather and Climate in Europe (ESiWACE). The experimental results show that the proposed solution is capable of scaling over several thousand cores and hundreds of cluster nodes. The proposed work is a contribution in support of scientific large-scale applications along the wider convergence path of HPC and Big data followed by the scientific research community.

关键词： Big data data analysis Convergence data models Europe Ecosystems Software Extreme-scale data challenges HPC and big data convergence high performance data analytics (HPDA) performance evaluation scientific data analysis

来源：评论

学校读者我要写书评

暂无评论

The information of attribute uncertainties: what convolutional neural networks can learn about errors in input data

引用

MACHINE LEARNING-SCIENCE AND TECHNOLOGY 2023年第4期4卷 045019页

作者： Rodrigues, Natalia V. N. Abramo, L. Raul Hirata, Nina S. T. Univ Sao Paulo Inst Fis R Do Matao 1371 BR-05508090 Sao Paulo SP Brazil Univ Sao Paulo Inst Matemat & Estat R Do Matao 1010 BR-05508090 Sao Paulo SP Brazil

Errors in measurements are key to weighting the value of data, but are often neglected in machine learning (ML). We show how convolutional neural networks (CNNs) are able to learn about the context and patterns of signal and noise, leading to improvements in the performance of classification methods. We construct a model whereby two classes of objects follow an underlying Gaussian distribution, and where the features (the input data) have varying, but known, levels of noise-in other words, each data point has a different error bar. This model mimics the nature of scientific data sets, such as those from astrophysical surveys, where noise arises as a realization of random processes with known underlying distributions. The classification of these objects can then be performed using standard statistical techniques (e.g. least squares minimization), as well as ML techniques. This allows us to take advantage of a maximum likelihood approach to object classification, and to measure the amount by which the ML methods are incorporating the information in the input data uncertainties. We show that, when each data point is subject to different levels of noise (i.e. noises with different distribution functions, which is typically the case in scientific data sets), that information can be learned by the CNNs, raising the ML performance to at least the same level of the least squares method-and sometimes even surpassing it. Furthermore, we show that, with varying noise levels, the confidence of the ML classifiers serves as a proxy for the underlying cumulative distribution function, but only if the information about specific input data uncertainties is provided to the CNNs.

关键词： machine learning methods statistical techniques scientific data analysis

来源：评论

学校读者我要写书评

暂无评论

Integrating data and analysis technologies within leading environmental research infrastructures: Challenges and approaches

引用

ECOLOGICAL INFORMATICS 2021年 61卷

作者： Huber, Robert D'Onofrio, Claudio Devaraju, Anusuriya Klump, Jens Loescher, Henry W. Kindermann, Stephan Guru, Siddeswara Grant, Mark Morris, Beryl Wyborn, Lesley Evans, Ben Goldfarb, Doron Genazzio, Melissa A. Ren, Xiaoli Magagna, Barbara Thiemann, Hannes Stocker, Markus Univ Bremen MARUM Ctr Marine Environm Sci Leobener Str 8POB 330440 D-28359 Bremen Germany Lund Univ Dept Phys Geog & Ecosyst Sci ICOS Carbon Portal Solvegatan12 SE-22362 Lund Sweden Univ Queensland TERN Australia Brisbane Qld Australia SIRO 26 Dick Perry Ave Kensington WA Australia Natl Ecol Observ Network NEON Battelle Boulder CO USA DKRZ Deutsch Klimarechenzentrum GmbH Hamburg Germany Australian Natl Univ Natl Computat Infrastruct NCI Canberra ACT Australia Environm Agcy Austria Spittelauer Lande 5 A-1090 Vienna Austria Chinese Acad Sci Inst Geog Sci & Nat Resources Res Key Lab Ecosyst Network Observat & Modeling Beijing 100101 Peoples R China TIB Leibniz Informat Ctr Sci & Technol Hannover Germany

When researchers analyze data, it typically requires significant effort in data preparation to make the data analysis ready. This often involves cleaning, pre-processing, harmonizing, or integrating data from one or multiple sources and placing them into a computational environment in a form suitable for analysis. Research infrastructures and their data repositories host data and make them available to researchers, but rarely offer a computational environment for data analysis. Published data are often persistently identified, but such identifiers resolve onto landing pages that must be (manually) navigated to identify how data are accessed. This navigation is typically challenging or impossible for machines. This paper surveys existing approaches for improving environmental data access to facilitate more rapid data analyses in computational environments, and thus contribute to a more seamless integration of data and analysis. By analysing current state-of-the-art approaches and solutions being implemented by world?leading environmental research infrastructures, we highlight the existing practices to interface data repositories with computational environments and the challenges moving forward. We found that while the level of standardization has improved during recent years, it still is challenging for machines to discover and access data based on persistent identifiers. This is problematic in regard to the emerging requirements for FAIR (Findable, Accessible, Interoperable, and Reusable) data, in general, and problematic for seamless integration of data and analysis, in particular. There are a number of promising approaches that would improve the state-of-the-art. A key approach presented here involves software libraries that streamline reading data and metadata into computational environments. We describe this approach in detail for two research infrastructures. We argue that the development and maintenance of specialized libraries for each RI and a range of progr

关键词： scientific data analysis Research infrastructures data service providers data analysis environments

来源：评论

学校读者我要写书评

暂无评论

Towards High Performance data Analytics for Climate Change 34th

Towards High Performance Data Analytics for Climate Change

引用

34th International Conference on High Performance Computing (ISC High Performance)

作者： Fiore, Sandro Elia, Donatello Palazzo, Cosimo Antonio, Fabrizio D'Anca, Alessandro Foster, Ian Aloisio, Giovanni Euro Mediterranean Ctr Climate Change Fdn Lecce Italy Univ Salento Lecce Italy Univ Chicago Chicago IL 60637 USA Argonne Natl Lab Chicago IL USA

ISBN: (纸本)9783030343569;9783030343552

The continuous increase in the data produced by simulations, experiments and edge components in the last few years has forced a shift in the scientific research process, leading to the definition of a fourth paradigm in Science, concerning data-intensive computing. This data deluge, in fact, introduces various challenges related to big data volumes, formats heterogeneity and the speed in the data production and gathering that must be handled to effectively support scientific discovery. To this end, High Performance Computing (HPC) and data analytics are both considered as fundamental and complementary aspects of the scientific process and together contribute to a new paradigm encompassing the efforts from the two fields called High Performance data Analytics (HPDA). In this context, the Ophidia project provides a HPDA framework which joins the HPC paradigm with scientific data analytics. This contribution presents some aspects regarding the Ophidia HPDA framework, such as the multidimensional storage model, its distributed and hierarchical implementation along with a benchmark of a parallel in-memory time series reduction operator.

关键词： HPDA Climate change scientific data analysis Storage model Multidimensional data

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：