检索结果-内蒙古大学图书馆

Proceedings - 2023 ieee 13th symposium on large data analysis and visualization, LDAV 2023 2023年 VI页

作者： Bremer, Peer-Timo Potter, Kristi Frey, Steffen Rizzi, Silvio Weber, Gunther Dutta, Soumya Lukasczyk, Jonas Marsiglia, Nicole Lawrence Livermore National Laboratory United States National Renewable Energy Laboratory United States University of Groningen Netherlands Argonne National Laboratory United States Lawrence Berkeley National Laboratory United States India Technical University Kaiserslautern Germany

来源：评论

学校读者我要写书评

暂无评论

DELVING INTO THE EXPLAINABILITY OF PROTOTYPE-BASED CNN FOR BIOLOGICAL CELL analysis 31

DELVING INTO THE EXPLAINABILITY OF PROTOTYPE-BASED CNN FOR B...

引用

2024 International Conference on Image Processing

作者： Blanchard, Martin Delezay, Olivier Ducottet, Christophe Muselet, Damien Univ Jean Monnet St Etienne CNRS Inst Optique Grad Sch Lab Hubert CurienUMR 5516 St Etienne France Univ Jean Monnet Lab Sainboise INSERM UMR 1059 St Etienne France

ISBN: (纸本)9798350349405;9798350349399

Deep learning for automated cell imaging analysis has become a tool of choice to process large amounts of data. But many of these methods lack explainability, slowing down their deployment for tasks such as diagnosis. We present a prototype-based framework to analyze structural changes which addresses the specific challenges of explainability in the context of cell imaging. Our method relies on classification between two distinct cell populations in a weakly supervised context where no label for individual cells is available. Our model extracts typical features from each population, representing intra-cellular structure, and provides an explanation on its classification decision by creating visualization of the local textures corresponding to the structures of interest. We show a real application where it effectively highlights a change in the organization of the actin content of the cells.

关键词： Visual Feature Learning Biocellular Imaging Explainable AI Deep Neural Networks

来源：评论

学校读者我要写书评

暂无评论

Cartolabe: A Web-Based Scalable visualization of large Document Collections

引用

ieee COMPUTER GRAPHICS AND APPLICATIONS 2021年第2期41卷 76-87页

作者： Caillou, Philippe Renault, Jonas Fekete, Jean-Daniel Letournel, Anne-Catherine Sebag, Michele Univ Paris Saclay CNRS INRIA LRI F-91190 Gif Sur Yvette France

We describe Cartolabe, a web-based multiscale system for visualizing and exploring large textual corpora based on topics, introducing a novel mechanism for the progressive visualization of filtering queries. Initially designed to represent and navigate through scientific publications in different disciplines, Cartolabe has evolved to become a generic framework and accommodate various corpora, ranging from Wikipedia (4.5M entries) to the French National Debate (4.3M entries). Cartolabe is made of two modules: The first relies on natural language processing methods, converting a corpus and its entities (documents, authors, and concepts) into high-dimensional vectors, computing their projection on the two-dimensional plane, and extracting meaningful labels for regions of the plane. The second module is a web-based visualization, displaying tiles computed from the multidimensional projection of the corpus using the Umap projection method. This visualization module aims at enabling users with no expertise in visualization and data analysis to get an overview of their corpus, and to interact with it: exploring, querying, filtering, panning, and zooming on regions of semantic interest. Three use cases are discussed to illustrate Cartolabe's versatility and ability to bring large-scale textual corpus visualization and exploration to a wide audience.

关键词： data visualization Two dimensional displays Organizations Task analysis Pipelines visualization Navigation

来源：评论

学校读者我要写书评

暂无评论

analysis of the Efficiency of Using Computers with an Array-parallel Architecture for Processing Spectral data of Astronomical Objects

Analysis of the Efficiency of Using Computers with an Array-...

引用

2024 ieee East-West Design and Test symposium, EWDTS 2024

作者： Barkovska, Olesia Nikolaienko, Dmytro Rusnak, Patrik Tkachov, Vitalii Havrashenko, Anton Kharkiv National University of Radio Electronics Department of Electronic Computers Kharkiv Ukraine University of Zilina Department of Informatics Zilina Slovakia

ISBN: (纸本)9798331515768

The work is devoted to the methods of parallel processing of spectral data of astronomical objects, which is an important aspect in many scientific fields, in particular in astronomy when studying physical processes and chemical composition of space objects. The relevance and practical significance of the work is caused by the increase in the amount of spectral data obtained from modern radio telescopes, which requires new approaches to their processing. The use of GPU-based massively parallel computers provides fast and efficient processing of large data sets, which is critical for modern astronomical research. This paper proposes an improved model for processing spectral data of astronomical objects using parallel computing on GPUs. The aim of this paper is to analyse the efficiency of using computers with an array-parallel architecture for processing spectral data of astronomical objects. To achieve this goal, the following methods were analysed and used: morphological operations, methods of preliminary data normalisation, methods of load balancing during parallel processing of input data, methods of massively parallel computing, methods of creating windows and graphic elements. The study results showed that with large amounts of data, the GPU is more efficient than the CPU, providing more than 1.6 times the speedup. For example, when the initial dataset size specified in the experiment was increased, the processing time on the GPU (0.091471 seconds) was significantly less than on the CPU (0.126231 seconds). Further research will focus on improving the algorithms for parallel processing of spectral data, expanding the functionality of the tools used, and adapting the model for new applications in astronomy. © 2024 ieee.

关键词： NASA

来源：评论

学校读者我要写书评

暂无评论

A SYSTEMATIC SPATIO-TEMPORAL analysis OF RELEVANT METEOROLOGICAL VARIABLES FOR SOLAR IRRADIANCE FORECASTING

A SYSTEMATIC SPATIO-TEMPORAL ANALYSIS OF RELEVANT METEOROLOG...

引用

ieee International Geoscience and Remote Sensing symposium (IGARSS)

作者： Jain, Mayank Jain, Navya Sinha, Nityaa Dev, Soumyabrata ADAPT SFI Res Ctr Dublin Ireland Univ Coll Dublin Sch Comp Sci Dublin Ireland Univ Delhi Ram Lal Anand Coll Delhi India Indira Gandhi Delhi Tech Univ Women Delhi India

ISBN: (纸本)9798350320107

Over the past few years, photovoltaic systems are replacing traditional sources of energy. These photovoltaic systems are powered by solar energy, which depends on the amount of incident solar irradiance. However, solar irradiance has a large amount of variability due to various spatio-temporal factors including region, cloud cover, humidity, and rainfall. In this paper1, we identify the most relevant spatio-temporal features for estimating solar irradiance. Such an accurate identification of weather variables is useful for developing accurate data-driven solar irradiance estimation models. This leads to an improved forecasting performance, thus creating a stable photovoltaic system. We base our analysis on the dataset of three countries, Ireland, Singapore and India. We identify the cloud type as the most relevant weather variables in all regions. The other relevant features holding differential importance across regions include time, relative humidity, solar zenith angle, and pressure.

关键词： solar irradiance renewable energy remote sensing satellite data

来源：评论

学校读者我要写书评

暂无评论

XTQA: Span-Level Explanations for Textbook Question Answering

引用

ieee TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024年第11期35卷 16493-16503页

作者： Ma, Jie Chai, Qi Liu, Jun Yin, Qingyu Wang, Pinghui Zheng, Qinghua Xi An Jiao Tong Univ Minist Educ Sch Cyber Sci & Engn Shaanxi Prov Key Lab Big Data Knowledge Engn Xian 710049 Shaanxi Peoples R China Xi An Jiao Tong Univ Sch Comp Sci & Technol Shaanxi Prov Key Lab Big Data Knowledge Engn Xian 710049 Shaanxi Peoples R China Amazon Palo Alto CA 94301 USA

Textbook question answering (TQA) is the task of correctly answering diagram or nondiagram (ND) questions given large multimodal contexts consisting of abundant essays and diagrams. In real-world scenarios, an explainable TQA system plays a key role in deepening humans' understanding of learned knowledge. However, there is no work to investigate how to provide explanations currently. To address this issue, we devise a novel architecture toward span-level eXplanations for TQA (XTQA). In this article, spans are the combinations of sentences within a paragraph. The key idea is to consider the entire textual context of a lesson as candidate evidence and then use our proposed coarse-to-fine grained explanation extracting (EE) algorithm to narrow down the evidence scope and extract the span-level explanations with varying lengths for answering different questions. The EE algorithm can also be integrated into other TQA methods to make them explainable and improve the TQA performance. Experimental results show that XTQA obtains the best overall explanation result [mean intersection over union (mIoU)] of 52.38% on the first 300 questions of CK12-QA test splits, demonstrating the explainability of our method (ND: 150 and diagram: 150). The results also show that XTQA achieves the best TQA performance of 36.46% and 36.95% on the aforementioned splits. We have released our code in https://***/dr-majie/opentqa.

关键词： Task analysis Question answering (information retrieval) Cognition visualization Knowledge engineering Indexes Feature extraction Explanation extracting (EE) question answering

来源：评论

学校读者我要写书评

暂无评论

Annotation of International Chinese Classroom Components Based on large Language Model 13

Annotation of International Chinese Classroom Components Bas...

引用

13th International Conference on Educational and Information Technology, ICEIT 2024

作者： Chen, Siting Cao, Ni Wang, Ziyu Li, Jimei School of Information Science Beijing Language and Culture University Beijing China

ISBN: (纸本)9798350372663

The paper aims to explore the differences in the field of smart education by comparing and analyzing the annotation results of international Chinese classroom data. Applying Professor Yanqun Zheng's International Chinese Language Teaching Components Model, further annotation work was carried out based on the research of its structure and process. First, we carefully annotated the data from the international Chinese education classroom of Beijing Language and Culture University. Then we explored the differences in the application of large Language Models (LLMs) in the field of education through the results of manual annotation. The experimental results show that the Annotation of SparkDesk is more consistent with the results annotated by people. It may contribute to the development of LLMs in educational classroom data annotation and analysis, as well as their application in the field of education. © 2024 ieee.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Research on the Construction of Damage Effect dataset and data analysis Based on Wargame Replay Big data 7

Research on the Construction of Damage Effect Dataset and Da...

引用

7th International Conference on Artificial Intelligence and Big data (ICAIBD)

作者： Shi, Yang Officers Coll PAP Chengdu Sichuan Peoples R China

ISBN: (纸本)9798350385113;9798350385106

In recent years, wargame has become an important competition in China. The data research of the MiaoSuan Wargame platform provide powerful data computing support for effective decision-making to commanders, who will face a large number of rapidly updated battlefield situation data per second. In this paper, three kinds of damage effect datasets of direct aiming attack, indirect aiming attack and guided aiming attack have been constructed based on the wargame replay big data and the matching map data, and visual data analysis has been carried out. The correlation between the damage effect and each parameter have been analyzed. Preparing for the model of future machine learning algorithm training, which can provide damage effect prediction analysis for commanders decision-making to improve damage effect and attack efficiency.

关键词： wargame replay damage effect dataset visual data analysis

来源：评论

学校读者我要写书评

暂无评论

AMST: Accelerating large-Scale Graph Minimum Spanning Tree Computation on FPGA 38

AMST: Accelerating Large-Scale Graph Minimum Spanning Tree C...

引用

International Parallel and Distributed Processing symposium (IPDPS)

作者： Fan, Haishuang Meng, Rui Sun, Qichu Wu, Jingya Lu, Wenyan Li, Xiaowei Yan, Guihai Chinese Acad Sci Inst Comp Technol State Key Lab Processors Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China YUSUR Technol Co Ltd Beijing Peoples R China

ISBN: (纸本)9798350387117;9798350387124

The minimum spanning tree (MST) plays an important role in variant fields, such as chip design and network analysis. With the rapid expansion of vertices in real-life graphs, the bottleneck problem of MST algorithms in large-scale graphs grows more prominent. While there have been many FPGA-based accelerators for large-scale graph algorithms such as Graph Random Walk, and various algorithms to accelerate MST on CPUs and GPUs, effectively implementing MST algorithms for large-scale graphs on FPGAs remains quite challenging. This is due to several reasons: (1) The neighbor vertices in the graph require extensive random memory access and the memory access characteristics vary across different stages and iterations. (2) There are a large number of useless computations due to the existence of internal edges within a component (intra-edge). (3) Parallel MST algorithm suffers from significant communication overhead due to the minimum edge data update conflicts and memory read-write conflicts. This paper proposes AMST to accelerate large-scale graph MST computation on FPGA. First, AMST employs a customized hash-based high-degree vertex cache (HDC) to improve memory access efficiency. Second, AMST adopts a graph pruning strategy that skips intra-edge and sorts edges by weight to eliminate useless computation and memory access. Finally, AMST utilizes a sorting networking module and a multi-port HDC to improve parallel efficiency. The experimental results demonstrate that AMST achieves an average performance speedup of 17.52x over CPU and 1.89x over GPU, as well as 74.96x over CPU and 10.45x over GPU on energy efficiency.

关键词： Graph Accelerator Minimum Spanning Tree FPGA

来源：评论

学校读者我要写书评

暂无评论

Detection of Inconsistencies in Privacy Practices of Browser Extensions 44

Detection of Inconsistencies in Privacy Practices of Browser...

引用

44th ieee symposium on Security and Privacy (SP)

作者： Bui, Duc Tang, Brian Shin, Kang G. Univ Michigan Ann Arbor MI 48109 USA

ISBN: (纸本)9781665493369

All major web browsers support extensions to provide additional functionalities and enhance users' browsing experience while the extensions can access and collect users' data during their web browsing. Although the web extensions inform users of their data practices via multiple forms of notices, prior work has overlooked the critical gap between the actual data practices and the published privacy notices of browser extensions. To fill this gap, we propose ExtPrivA that automatically detects the inconsistencies between browser extensions' data collection and their privacy disclosures. From the privacy policies and Dashboard disclosures, ExtPrivA extracts privacy statements to have a clear interpretation of the privacy practices of an extension. It emulates user interactions to trigger the extension's functionalities and analyzes the initiators of network requests to accurately extract the users' data transferred by the extension from the browser to external servers. Our end-to-end evaluation has shown ExtPrivA to detect inconsistencies between the privacy disclosures and data-collection behavior with an 85% precision. In a large-scale study of 47.2k extensions on the Chrome Web Store, we found 820 extensions with 1,290 flows that are inconsistent with their privacy statements. Even worse, we have found 525 pairs of contradictory privacy statements in the Dashboard disclosures and privacy policies of 360 extensions. These discrepancies between the privacy disclosures and the actual data-collection behavior are deemed as serious violations of the Store's policies. Our findings highlight the critical issues in the privacy disclosures of browser extensions that potentially mislead, and even pose high privacy risks to, end-users.

关键词： browser-extension consistency-analysis privacy-disclosure privacy-policy

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：