检索结果-内蒙古大学图书馆

4th International Conference on Electronics and Sustainable Communication Systems, ICESC 2023

作者： Ahmad, Peerzada Hamid Rai, Munishwar Haryana Mullana133203 India

ISBN: (纸本)9798350300093

Big data management refers to the processes and technologies used to collect, store, organize, and analyses large and complex data sets. This includes data ingestion, storage, and processing to data governance, security, and visualization. The main components of big data management are data warehousing, data governance, data processing, data visualization, data security, cloud storage, and data lakes. Big data management comprises three main components: data framework, storage, and optimization. This study presents many frameworks, data storage, and big data analysis optimization strategies. The approaches, difficulties, and future directions of the big data analysis and optimization research were summarized. © 2023 ieee.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

ieee LDAV 2024 Preface

Proceedings - 2024 IEEE 14th Symposium on Large Data Analysi...

引用

Proceedings - 2024 ieee 14th symposium on large data analysis and visualization, LDAV 2024 2024年 vii页

作者： Beyer, Johanna Frey, Steffen Reina, Guido Rizzi, Silvio Weber, Gunther H. Dutta, Soumya Marsaglia, Nicole Bremer, Peer-Timo Moreland, Kenneth Potter, Kristi Tierny, Julien Wang, Chaoli Yu, Hongfeng Harvard University United States University of Groningen Netherlands University of Stuttgart Germany Argonne National Laboratory United States Lawrence Berkeley National Laboratory United States Kanpur India Lawrence Livermore National Laboratory United States Oak Ridge National Laboratory United States National Renewable Energy Laboratory United States CNRS - Sorbonne Université France University of Notre Dame United States University of Nebraska-Lincoln United States

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of large Language Model Architectures on Frontier 38

Comparative Study of Large Language Model Architectures on F...

引用

International Parallel and Distributed Processing symposium (IPDPS)

作者： Yin, Junqi Bose, Avishek Cong, Guojing Lyngaas, Isaac Anthony, Quentin Oak Ridge Natl Lab Oak Ridge TN 37830 USA

ISBN: (纸本)9798350387117;9798350387124

large language models (LLMs) have garnered significant attention in both the AI community and beyond. Among these, the Generative Pre-trained Transformer (GPT) has emerged as the dominant architecture, spawning numerous variants. However, these variants have undergone pre-training under diverse conditions, including variations in input data, data preprocessing, and training methodologies, resulting in a lack of controlled comparative studies. Here we meticulously examine two prominent open-sourced GPT architectures, GPT-NeoX and LLaMA, leveraging the computational power of Frontier, the world's first Exascale supercomputer. Employing the same materials science text corpus and a comprehensive end-to-end pipeline, we conduct a comparative analysis of their training and downstream performance. Our efforts culminate in achieving state-of-the-art performance on a challenging materials science benchmark. Furthermore, we investigate the computation and energy efficiency, and propose a computationally efficient method for architecture design. To our knowledge, these pre-trained models represent the largest available for materials science. Our findings provide practical guidance for building LLMs on HPC platforms.

关键词： AI foundation model GPT architecture HPC

来源：评论

学校读者我要写书评

暂无评论

Revisiting Viewing Graph Solvability: An Effective Approach Based on Cycle Consistency

引用

ieee TRANSACTIONS ON PATTERN analysis AND MACHINE INTELLIGENCE 2025年第5期47卷 3271-3284页

作者： Arrigoni, Federica Fusiello, Andrea Rizzi, Romeo Ricci, Elisa Pajdla, Tomas Politecn Milan Dipartimento Elettron Informaz & Bioingn DEIB I-20133 Milan Italy Univ Udine Polytech Dept Engn & Architecture DPIA I-33100 Udine Italy Univ Verona Dept Comp Sci I-37129 Verona Italy Univ Trento Dept Informat Engn & Comp Sci DISI I-38122 Trento Italy Fdn Bruno Kessler FBK Deep Visual Learning Grp I-38121 Trento Italy Czech Tech Univ Czech Inst Informat Robot & Cybernet CIIRC Prague 16000 Czech Republic

In the structure from motion, the viewing graph is a graph where the vertices correspond to cameras (or images) and the edges represent the fundamental matrices. We provide a new formulation and an algorithm for determining whether a viewing graph is solvable, i.e., uniquely determines a set of projective cameras. The known theoretical conditions either do not fully characterize the solvability of all viewing graphs, or are extremely difficult to compute because they involve solving a system of polynomial equations with a large number of unknowns. The main result of this paper is a method to reduce the number of unknowns by exploiting cycle consistency. We advance the understanding of solvability by (i) finishing the classification of all minimal graphs up to 9 nodes, (ii) extending the practical verification of solvability to minimal graphs with up to 90 nodes, (iii) finally answering an open research question by showing that finite solvability is not equivalent to solvability, and (iv) formally drawing the connection with the calibrated case (i.e., parallel rigidity). Finally, we present an experiment on real data that shows that unsolvable graphs may appear in practice.

关键词： Cameras Rigidity Three-dimensional displays Image reconstruction visualization Image edge detection Topology Solvability viewing graph structure from motion fundamental matrix uncalibrated camera

来源：评论

学校读者我要写书评

暂无评论

A COMPARATIVE analysis OF CNN AND TRANSFORMER MODELS FOR THE DETECTION OF FIRE-BURNED AREAS IN CALIFORNIA USING LANDSAT 8 SATELLITE IMAGES

A COMPARATIVE ANALYSIS OF CNN AND TRANSFORMER MODELS FOR THE...

引用

ieee International Geoscience and Remote Sensing symposium (IGARSS)

作者： Seo, Youngmin Lee, Yangwon Pukyong Natl Univ Dept Spatial Informat Engn Div Earth Environm Syst Sci Busan South Korea

ISBN: (纸本)9798350360332;9798350360325

large scale wildfires, intensified by climate change, cause severe threats to human life, property, and ecosystems, with potential for secondary damages. Accurate detection and calculation wildfire areas is important, necessitating efficient monitoring through satellite imagery and deep learning. However, the application of deep learning models has been limited, lacking comprehensive quantitative performance evaluation reports. This study focuses on a comparative analysis of performance improvement through model and data design. Utilizing U-Net, HRNet and Swin transformer, we created a model to predict burned area in California, USA. To improve detection performance, transfer learning was applied, and spectral indices like NDVI and NBR, considering vegetation fertility and ground moisture, were used as input images. This deep learning methodology, if further developed, is expected to serve as a foundation for swift wildfire identification and recovery plan establishment.

关键词： Wildfire burned area Deep learning Landsat

来源：评论

学校读者我要写书评

暂无评论

Identifying Locally Turbulent Vortices within Instabilities

Identifying Locally Turbulent Vortices within Instabilities

引用

ieee symposium on large data analysis and visualization (LDAV)

作者： Fabien Vivodtzev Florent Nauleau Jean-Philippe Braeunig Julien Tierny CEA CESTA CNRS Sorbonne Université LIP6.

ISBN: (数字)9798331516925

ISBN: (纸本)9798331516932

This work presents an approach for the automatic detection of locally turbulent vortices within turbulent 2D flows such as instabilites. First, given a time step of the flow, methods from Topological data analysis (TDA) are leveraged to extract the geometry of the vortices. Specifically, the enstrophy of the flow is simplified by topological persistence, and the vortices are extracted by collecting the basins of the simplified enstrophy 's Morse complex. Next, the local kinetic energy power spectrum is computed for each vortex. We introduce a set of indicators based on the kinetic energy power spectrum to estimate the correlation between the vortex's behavior and that of an idealized turbulent vortex. Our preliminary experiments show the relevance of these indicators for distinguishing vortices which are turbulent from those which have not yet reached a turbulent state and thus known as laminar.

关键词： Geometry data analysis Correlation data visualization Kinetic energy data mining Optimization

来源：评论

学校读者我要写书评

暂无评论

A MACHINE-LEARNING APPROACH FOR GENERATING SYNTHETIC PRISMA HYPERSPECTRAL IMAGES FROM MULTISPECTRAL data

A MACHINE-LEARNING APPROACH FOR GENERATING SYNTHETIC PRISMA ...

引用

ieee International Geoscience and Remote Sensing symposium (IGARSS)

作者： Monaco, Manilo Licciardi, Giorgio A. Battagliere, Maria L. Guarini, Rocchina Cimino, Mario G. C. A. Candela, Laura Italian Space Agcy ASI Via Politecn SNC I-00133 Rome Italy Univ Pisa Dept Informat Engn Lgo L Lazzarino 1 I-56122 Pisa Italy

ISBN: (纸本)9798350360332;9798350360325

The scarcity of a sufficiently large and representative hyperspectral image dataset is a substantial obstacle to the effective development of algorithms for remote sensing applications. Hyperspectral images can provide rich spectral information for various tasks, such as land cover classification, vegetation monitoring, and environmental assessment. However, the limited availability of diverse and well-annotated hyperspectral datasets hinders the development and optimization of these models in this domain. For this purpose, the generation of synthetic hyperspectral images has emerged as a pivotal area of research. This paper aims to introduce a preliminary analysis of various AI-based methodologies specifically crafted to generate synthetic PRISMA hyperspectral images derived from Sentinel-2 data. By exploring innovative approaches, this study aims to develop novel techniques for creating synthetic datasets, providing valuable insights into the potential of synthetic hyperspectral imagery for algorithm training and evaluation in the absence of extensive realworld hyperspectral datasets.

关键词： Hyperspectral imagery PRISMA Artificial Intelligence synthetic images

来源：评论

学校读者我要写书评

暂无评论

Mind the Gap: Attainable data Movement and Operational Intensity Bounds for Tensor Algorithms 51

Mind the Gap: Attainable Data Movement and Operational Inten...

引用

ACM/ieee 51st Annual International symposium on Computer Architecture (ISCA)

作者： Huang, Qijing Tsai, Po-An Emer, Joel S. Parashar, Angshuman NVIDIA Santa Clara CA 95051 USA MIT CSAIL Cambridge MA USA

ISBN: (纸本)9798350326598;9798350326581

The architectural design-space exploration (or DSE) process-whether manual or automated-benefits greatly from knowing the limits of the metrics of interest in advance. data movement is rapidly emerging as a critical metric for DSE due to its increasing impact on both performance and energy efficiency. Unfortunately, the commonly used algorithmic minimum (or "compulsory misses") limit for data movement is extremely loose, limiting its utility in design-space search. In this paper, we present Orojenesis, an approach to compute data movement limits (or bounds) for tensor algorithms. Unlike algorithmic-minimum bounds, Orojenesis comprehends reuse and the ability of a buffer (such as a cache or scratchpad) to exploit reuse to reduce data movement. Orojenesis provides a bound that no dataflow or mapping can possibly exceed under varying on-chip buffer capacity constraints, including mappings that fuse a sequence of tensor operations to exploit producer-consumer reuse. Orojenesis produces a plot that shows the relationship between a buffer's size and the lower data movement limit to/from the next level in a memory hierarchy. This plot, dubbed a ski-slope diagram, allows designers to gain critical insights into the behavior of a workload as a function of storage capacity. This analysis can inform early high-level design decisions before embarking on thorough design space searches. We use Orojenesis to analyze a set of valuable tensor algorithms including batched and grouped matrix multiplications, convolutions, and sequences of operations in large Language Models (LLMs). Our analysis reveals a range of architectural insights, including the fact that attainable data movement can be orders-of-magnitude higher than algorithmic minimum, that there exists a sweet spot between SRAM and compute resource provisioning for optimal throughput, and that up to 5.6x data movement reduction can be achieved with fusion with a buffer capacity of 320MB for the GPT-3-6.7b LLM.

关键词： Static random access storage

来源：评论

学校读者我要写书评

暂无评论

Identifying Representation Bias in large Language Models Used in Financial Sentiment analysis

Identifying Representation Bias in Large Language Models Use...

引用

2025 ieee symposium on Computational Intelligence for Financial Engineering and Economics, CiFer 2025

作者： Sabuncuoglu, Alpay Maple, Carsten The Alan Turing Insitute United Kingdom University of Warwick The Alan Turing Institute United Kingdom

ISBN: (纸本)9798331508319

Financial sentiment analysis is the task of evaluating and quantifying the emotions and opinions expressed in financial news, reports, or social media to help investors and institutions make informed decisions. Financial institutions have been actively exploring the use of large language models (LLMs) to analyse market sentiment signals for a more nuanced understanding of a broader context. However, issues such as the scale of training data, model complexity, and the potential for human oversight can introduce or even amplify bias in these systems. Representation bias is a common challenge for LLMs as training data fail to properly represent the target groups, hence causes harmful bias in general-purpose use. Therefore, replacing current solutions with LLMs in financial organisations requires a robust evaluation methodology to ensure fairness. This paper investigates a three-level bias evaluation approach that specifically focuses on representation bias and presents a baseline evaluation of the FinBERT model. Step 1 uses a synthetic dataset that explicitly reveals sources of bias, structured as probability- and embedding-based evaluation recipes. Step 2 evaluates the model against data released by another country (e.g. Indian News dataset) to assess its performance in relation to more implicit biases. Step 3 examines individual problematic samples using token-based interpretability methods (e.g. integrated gradients). This paper presents the application of this structured bias evaluation process and its results on the FinBERT model. The evaluation code and dataset are available on GitHub (https://***/asabuncuoglu13/faid-test-financial-sentiment-analysis). © 2025 ieee.

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

Enhancing Air Quality Long Short Term Memory Networks for Predictive analysis: Insights and visualization-driven analysis

Enhancing Air Quality Long Short Term Memory Networks for Pr...

引用

2024 International Conference on Communication, Computer Sciences and Engineering, IC3SE 2024

作者： Sharma, Parul Katiyar, Kuldip Chandigarh University Department Of Mathematics Mohali India

ISBN: (纸本)9798350366846

An important danger to both the environment and human health is air pollution, necessitating the need for reliable prediction models. This study introduces a novel approach to enhancing air quality prediction using LSTM (Long Short-Term Memory) networks, distinguished for their capacity to extract temporal correlations from sequential data. By employing a large dataset encompassing air quality measurements from various Chinese cities between March 2013 and February 2017, our LSTM-based model demonstrates proficient forecasting of future air quality levels. Furthermore, our research utilizes visualization-driven analysis techniques to deepen understanding of the intricate interplay among air pollution levels, weather conditions, and overall air quality. Interactive visualizations facilitate comprehension and data interpretation, enabling a comprehensive grasp of the dynamics of air pollution. In our experiments, the LSTM-based technique surpasses established methods, showcasing its potential to support decision-making processes for policymakers and environmental stakeholders. By increasing the predictability of air quality and providing insights into pollution dynamics, our research contributes to the formulation of effective strategies for managing air pollution and safeguarding public health. © 2024 ieee.

关键词： Long short-term memory

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：