检索结果-内蒙古大学图书馆

10th ieee symposium on large data analysis and visualization (LDAV)

作者： Kress, James Larsen, Matthew Choi, Jong Kim, Mark Wolf, Matthew Podhorszki, Norbert Klasky, Scott Childs, Hank Pugmire, David Oak Ridge Natl Lab Oak Ridge TN 37830 USA Univ Oregon Eugene OR 97403 USA Lawrence Livermore Natl Lab Livermore CA 94550 USA

ISBN: (纸本)9781728184685

This short paper considers time-To-solution for two in situ visualization paradigms: in-line and in-Transit. It is a follow-on work to two previous studies. The first study [10] considered time-To-solution (wall clock time) and total cost (total node seconds incurred) for a single visualization algorithm (isosurfacing). The second study [11] considered only total cost and added a second algorithm (volume rendering). This short paper completes the evaluation, considering time-To-solution for both algorithms. In particular, it extends the first study by adding additional insights from including a second algorithm at larger scale and by doing more extended and formal analysis regarding time-To-solution. Further, it complements the second study as the best in situ configuration to choose can vary when considering time-To-solution over cost. It also makes use of the same data corpus used in the second study, although that data corpus has been refactored with time-To-solution in mind. © 2020 ieee.

关键词： in line in situ in transit visualization

来源：评论

学校读者我要写书评

暂无评论

Integrating Natural Language Processing and large Language Models Into DHIS2 to Improve Health data Utilization

Integrating Natural Language Processing and Large Language M...

引用

Software Engineering in the Global South (SEiGS), ieee/ACM symposium on

作者： Angella Nabasirye Irene Wanyana Ssali Department Services Uganda National Health Labaratory Ministry of Health Kampala Uganda Master of Health Informatics School of Public Health Makerere University Kampala Uganda

ISBN: (数字)9798331514280

ISBN: (纸本)9798331514297

In the evolving landscape of global healthcare, the need for efficient and scalable data analysis has never been more critical. This research explores the integration of large Language Models (LLMs) and Natural Language Processing (NLP) into the District Health Information System 2 (DHIS2), a platform widely used for health data management in Uganda. The objective of this study is to enhance the usability and data analysis capabilities of DHIS2, making it accessible to both technical and non-technical users. By leveraging AI-driven models like LangChain and Ollama, the research developed an automated data analysis system that allows users to interact with DHIS2 using natural language queries in English. This integration simplifies the extraction of meaningful insights from complex datasets, thereby improving decision-making processes. The system was evaluated for usability, performance, and its potential to enhance public health data analysis. Results demonstrate that the AI-augmented DHIS2 platform significantly reduces analysis time, improves data accessibility, and facilitates timely public health interventions. This innovation presents a scalable solution for improving health information systems globally, particularly in resource-constrained environments.

关键词： Technological innovation data analysis large language models Decision making Natural language processing data models Usability Public healthcare Informatics Software engineering

来源：评论

学校读者我要写书评

暂无评论

Adaptive Covers for Mapper Graphs Using Information Criteria

Adaptive Covers for Mapper Graphs Using Information Criteria

引用

9th ieee International Conference on Big data (ieee Bigdata)

作者： Chalapathi, Nithin Zhou, Youjia Wang, Bei Univ Calif Berkeley Berkeley CA 94720 USA Univ Utah Salt Lake City UT USA

ISBN: (纸本)9781665439022

The mapper construction is a widely used tool from topological data analysis in obtaining topological summaries of large, high-dimensional point cloud data. It has enjoyed great success in data science, including cancer research, sports analytics, and visualization. However, developing practical and automatic parameter selection for the mapper construction remains a challenging open problem for both the topological analysis and visualization communities. In this paper, we focus on parameter selection for the 1-dimensional skeleton of the mapper construction, called the mapper graph. Specifically, we explore how information criteria used in the X-means clustering algorithm can inform and generate adaptive covers for mapper graphs. Our approach thus makes novel progress towards automatic parameter selection for the mapper construction using information theory.

关键词： Topological data analysis topology in visualization mapper information theory

来源：评论

学校读者我要写书评

暂无评论

Parameter-Efficient Fine-Tuning Medical Multimodal large Language Models for Medical Visual Grounding

Parameter-Efficient Fine-Tuning Medical Multimodal Large Lan...

引用

ieee International symposium on Biomedical Imaging

作者： Jinlong He Pengfei Li Gang Liu Shenjun Zhong College of Computer Science and Technology Harbin Engineering University China Monash Biomedical Imaging Monash University Australia

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Multimodal large Language Models (MLLMs) inherit the superior text understanding capabilities of LLMs and extend these capabilities to multimodal scenarios. These models achieve excellent results in the general domain of multimodal tasks. However, in the medical domain, the substantial training costs and the requirement for extensive medical data pose challenges to the development of medical MLLMs. Furthermore, due to the free-text form of answers, tasks such as visual grounding that need to produce output in a prescribed form become difficult for MLLMs. So far, there have been no medical MLLMs works in medical visual grounding area. For the medical vision grounding task, which involves identifying locations in medical images based on short text descriptions, we propose Parameter-efficient Fine-tuning medical multi-modal large language models for Medcial Visual Grounding (PFMVG). To validate the performance of the model, we evaluate it on a public benchmark dataset for medical visual grounding, where it achieves competitive results, and significantly outperforming GPT-4v.

关键词： Training visualization Costs Grounding large language models Biological system modeling Focusing Benchmark testing Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Differential Privacy from Locally Adjustable Graph Algorithms: k-Core Decomposition, Low Out-Degree Ordering, and Densest Subgraphs 63

Differential Privacy from Locally Adjustable Graph Algorithm...

引用

63rd Annual ieee symposium on Foundations of Computer Science (FOCS)

作者： Dhulipala, Laxman Liu, Quanquan C. Raskhodnikova, Sofya Shi, Jessica Shun, Julian Yu, Shangdi Univ Maryland Dept Comp Sci College Pk MD 20742 USA Northwestern Univ Dept Comp Sci Evanston IL USA Boston Univ Dept Comp Sci 111 Cummington St Boston MA 02215 USA MIT CSAIL Cambridge MA 02139 USA

ISBN: (纸本)9781665455190

Differentially private algorithms allow large-scale data analytics while preserving user privacy. Designing such algorithms for graph data is gaining importance with the growth of large networks that model various (sensitive) relationships between individuals. While there exists a rich history of important literature in this space, to the best of our knowledge, no results formalize a relationship between certain parallel and distributed graph algorithms and differentially private graph analysis. In this paper, we define locally adjustable graph algorithms and show that algorithms of this type can be transformed into differentially private algorithms. Our formalization is motivated by a set of results that we present in the central and local models of differential privacy for a number of problems, including k-core decomposition, low out-degree ordering, and densest subgraphs. First, we design an epsilon-edge differentially private (DP) algorithm that returns a subset of nodes that induce a subgraph of density at least D */1+eta - O (poly(log n)/epsilon), where D* is the density of the densest subgraph in the input graph (for any constant eta > 0). This algorithm achieves a two-fold improvement on the multiplicative approximation factor of the previously best-known private densest subgraph algorithms while maintaining a near-linear runtime. Then, we present an epsilon-locally edge differentially private (LEDP) algorithm for k-core decompositions. Our LEDP algorithm provides approximates the core numbers (for any constant eta > 0) with (2+eta) multiplicative and O (poly (log n) /epsilon) additive error. This is the first differentially private algorithm that outputs private k-core decomposition statistics. We also modify our algorithm to return a differentially private low out-degree ordering of the nodes, where orienting the edges from nodes earlier in the ordering to nodes later in the ordering results in out-degree at most O (d + poly(log n) /epsilon) (where d is th

关键词： Computer science Differential privacy Runtime data analysis Additives Approximation algorithms data models

来源：评论

学校读者我要写书评

暂无评论

Spectra Dimensional Reduction Coupled with Machine Learning for the Detection of Pepper Yellow Leaf Curl Virus 13

Spectra Dimensional Reduction Coupled with Machine Learning ...

引用

13th International symposium on Image and Signal Processing and analysis, ISPA 2023

作者： Agustika, Dyah Kurniawati Malika, Endah Hidayat, Sri Hendrastuti Purwanto, Agus Iliescu, Doina Daciana Leeson, Mark Stephen School of Engineering The University of Warwick Coventry United Kingdom Universitas Negeri Yogyakarta Dept. of Physics Education Sleman Indonesia IPB University Department of Plant Protection Bogor Indonesia

ISBN: (纸本)9798350315363

Spectra of Fourier Transform Infrared (FTIR) Spectroscopy have wide wavenumber ranges. The resultant large data set contains noise as well as unwanted information. Dimensional reduction techniques are thus needed to process and highlight important spectral information. This study focuses on optimizing the dimension reduction technique to process FTIR spectra to detect Pepper Yellow Leaf Curl Virus (PYLCV) disease infection in chilli plants. In this paper, Principal Component analysis (PCA) and Discrete Wavelet Transform (DWT) were used for the dimension reduction. To find out the best technique, the resulting data reduction is processed with three types of learning machines, namely Support Vector Machine (SVM), Linear Discriminant analysis (LDA), and Random Forest (RF). Here, we split the training data into only 20% and 80% for the testing. From the results of the analysis, it was found that for PCA, the best classification results were dimension reduction with the first five principal components (PCs), which produced the highest score of 79.17% in the LDA and RF techniques. For DWT, level 4 decomposition gives 95.83% accuracy for LDA and RF. The DWT level result was then fed into a feedforward artificial neural network (ANN), which showed that the network could process the input and give the same best accuracy result as LDA and RF. This demonstrates that the best dimensional reduction technique for the classification of PYLCV-infected chilli plants is DWT level 4. © 2023 ieee.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

The Unreasonable Effectiveness of CLIP Features for Image Captioning: An Experimental analysis

The Unreasonable Effectiveness of CLIP Features for Image Ca...

引用

ieee/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Barraco, Manuele Cornia, Marcella Cascianelli, Silvia Baraldi, Lorenzo Cucchiara, Rita Univ Modena & Reggio Emilia Modena Italy

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Generating textual descriptions from visual inputs is a fundamental step towards machine intelligence, as it entails modeling the connections between the visual and textual modalities. For years, image captioning models have relied on pre-trained visual encoders and object detectors, trained on relatively small sets of data. Recently, it has been observed that large-scale multi-modal approaches like CLIP (Contrastive Language-Image Pre-training), trained on a massive amount of image-caption pairs, provide a strong zero-shot capability on various vision tasks. In this paper, we study the advantage brought by CLIP in image captioning, employing it as a visual encoder. Through extensive experiments, we show how CLIP can significantly out-perform widely-used visual encoders and quantify its role under different architectures, variants, and evaluation protocols, ranging from classical captioning performance to zero-shot transfer.

关键词： visualization Computer vision Protocols Conferences Detectors Distance measurement data models

来源：评论

学校读者我要写书评

暂无评论

ViSNeRF: Efficient Multidimensional Neural Radiance Field Representation for visualization Synthesis of Dynamic Volumetric Scenes

ViSNeRF: Efficient Multidimensional Neural Radiance Field Re...

引用

Pacific (formerly Asia-Pacific APVIS) visualization symposium

作者： Siyuan Yao Yunfei Lu Chaoli Wang University of Notre Dame

ISBN: (数字)9798331505813

ISBN: (纸本)9798331505820

Domain scientists often face I/O and storage challenges when keeping raw data from large-scale simulations. Saving visualization images, albeit practical, is limited to preselected viewpoints, transfer functions, and simulation parameters. Recent advances in scientific visualization leverage deep learning techniques for visualization synthesis by offering effective ways to infer unseen visualizations when only image samples are given during training. However, due to the lack of 3D geometry awareness, existing methods typically require many training images and significant learning time to generate novel visualizations faithfully. To address these limitations, we propose ViSNeRF, a novel 3D-aware approach for visualization synthesis using neural radiance fields. Leveraging a multidimensional radiance field representation, ViSNeRF efficiently reconstructs visualizations of dynamic volumetric scenes from a sparse set of labeled image samples with flexible parameter exploration over transfer functions, isovalues, timesteps, or simulation parameters. Through qualitative and quantitative comparative evaluation, we demonstrate ViSNeRF’s superior performance over several representative baseline methods, positioning it as the state-of-the-art solution. The code is available at https://***/JCBreath/ViSNeRF.

关键词： Training Learning systems Geometry visualization Three-dimensional displays Scalability data visualization Transfer functions Neural radiance field Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Evaluating Visual Quality of Autostereoscopic Displays Using an Interactive Perception Network

引用

ieee TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Pan, Zhaoqing Yi, Jiaojiao Peng, Bo Lei, Jianjun Wang, Fu Lee Ling, Nam Kwong, Sam Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China Hong Kong Metropolitan Univ Sch Sci & Technol Hong Kong Peoples R China Santa Clara Univ Dept Comp Sci & Engn Santa Clara CA 95053 USA Lingnan Univ Sch Data Sci Hong Kong Peoples R China

Visual quality assessment of autostereoscopic displays aims to evaluate the stereoscopic visual experience they provide to the viewer, which is crucial for quantifying and optimizing the performance of autostereoscopic displays. In order to automatically evaluate the visual quality of the display, the relationship between the visual quality and the perceptual crosstalk was investigated because the perceptual crosstalk could degrade the visual quality of autostereoscopic displays. However, the visual quality of autostereoscopic displays is comprehensively determined by a series of display parameters such as crosstalk, screen resolution, and screen size, a single display parameter cannot accurately reflect the visual quality. To address this problem, an interactive perception network (IPNet)-based visual quality assessment method is proposed in this article, which models the relationship between the visual quality of the display and the display parameters to accurately evaluate the visual quality of autostereoscopic displays. Since the crosstalk level perceived by the human eye is highly correlated with color differences, a color-informed crosstalk aware module (CCAM) is proposed, which learns features that are highly related to the perceptual crosstalk under the guidance of color difference information. To further analyze the visual impacts of other perceptual fidelity parameters, such as screen resolution, screen size, and viewing angle, a multidomain binocular interaction module (MBIM) is proposed, which models the binocular interaction process in both channel and spatial domains to achieve fine-grained binocular semantic understanding. To train the proposed IPNet for evaluating the visual quality of autostereoscopic displays, a well-annotated large-scale dataset called TJU autostereoscopic display dataset is created, which contains 800 simulated autostereoscopic displays with different display parameters. Extensive experimental results demonstrate that the propose

关键词： visualization Crosstalk Quality assessment Stereo image processing Three-dimensional displays Image color analysis Feature extraction Semantics Training Spatial resolution Autostereoscopic display color-informed crosstalk aware module (CCAM) display parameter multidomain binocular interaction module (MBIM) visual quality assessment

来源：评论

学校读者我要写书评

暂无评论

How Effective are LLMs for data Science Coding? A Controlled Experiment

How Effective are LLMs for Data Science Coding? A Controlled...

引用

International Mining Software Repositories, MSR

作者： Nathalia Nascimento Everton Guimaraes Sai Sanjna Chintakunta Santhosh Anitha Boominathan EASER Eng. Division Pennsylvania State University Great Valley USA

ISBN: (数字)9798331501839

ISBN: (纸本)9798331501846

The adoption of large Language Models (LLMs) for code generation in data science offers substantial potential for enhancing tasks such as data manipulation, statistical analysis, and visualization. However, the effectiveness of these models in the data science domain remains underexplored. This paper presents a controlled experiment that empirically assesses the performance of four leading LLM-based AI assistants-Microsoft Copilot (GPT-4 Turbo), ChatGPT (o1-preview), Claude (3.5 Sonnet), and Perplexity Labs (Llama-3.1-70b-instruct)-on a diverse set of data science coding challenges sourced from the Stratacratch platform. Using the Goal-Question-Metric (GQM) approach, we evaluated each model’s effectiveness across task types (Analytical, Algorithm, visualization) and varying difficulty levels. Our statistical testing confirms that all models achieved success rates significantly above $50 \%$, demonstrating performance beyond chance. ChatGPT and Claude significantly exceeded the $60 \%$ threshold, but no model reached $70 \%$, indicating limitations in achieving higher accuracy. ChatGPT maintained consistent performance across difficulty levels, whereas Claude’s success varied with task complexity. Hypothesis testing indicates that task type does not significantly impact success rate overall. For analytical tasks, efficiency analysis shows no significant differences in execution times, though ChatGPT tended to be slower and less predictable despite high success rates. For visualization tasks, while similarity quality among LLMs is comparable, ChatGPT consistently delivered the most accurate outputs. This study provides a structured, empirical evaluation of LLMs in data science, delivering insights that support informed model selection tailored to specific task demands. Our findings establish a framework for future AI assessments, emphasizing the value of rigorous evaluation beyond basic accuracy measures.

关键词： visualization Accuracy Statistical analysis large language models data visualization data science Chatbots Encoding data models Testing

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：