检索结果-内蒙古大学图书馆

ieee International symposium on Biomedical Imaging

作者： Santosh Dudhabhate Nilanjan Chattopadhyay Akash Parekh Nitin Singhal AIRA Matrix Pvt. Ltd. Mumbai India

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Predicting biochemical recurrence (BCR) is crucial for Prostate Cancer (PCa) treatment plan. We present a novel multi-modal approach using deep learning framework that integrates Whole Slide Images (WSI) with associated clinical text to improve BCR prediction. Our model leverages contrastive learning approach where both visual and textual data are used to effectively capture the interplay between histopathology features and textual information by jointly modeling these data sources. Evaluation results indicate that our model building approach is able to effectively integrates spatial insights from WSIs and clinical texts, leading in enhanced BCR prediction performance compared to other existing methodologies and individual modalities. This approach has the potential to advance precision medicine in PCa care.

关键词： visualization Accuracy Biological system modeling Soft sensors Precision medicine Contrastive learning Predictive models data models Prostate cancer Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

iVR-GS: Inverse Volume Rendering for Explorable visualization via Editable 3D Gaussian Splatting

引用

ieee Transactions on visualization and Computer Graphics 2025年第6期31卷 3783-3795页

作者： Kaiyuan Tang Siyuan Yao Chaoli Wang Department of Computer Science and Engineering University of Notre Dame Notre Dame IN USA

In volume visualization, users can interactively explore the three-dimensional data by specifying color and opacity mappings in the transfer function (TF) or adjusting lighting parameters, facilitating meaningful interpretation of the underlying structure. However, rendering large-scale volumes demands powerful GPUs and high-speed memory access for real-time performance. While existing novel view synthesis (NVS) methods offer faster rendering speeds with lower hardware requirements, the visible parts of a reconstructed scene are fixed and constrained by preset TF settings, significantly limiting user exploration. This article introduces inverse volume rendering via Gaussian splatting (iVR-GS), an innovative NVS method that reduces the rendering cost while enabling scene editing for interactive volume exploration. Specifically, we compose multiple iVR-GS models associated with basic TFs covering disjoint visible parts to make the entire volumetric scene visible. Each basic model contains a collection of 3D editable Gaussians, where each Gaussian is a 3D spatial point that supports real-time scene rendering and editing. We demonstrate the superior reconstruction quality and composability of iVR-GS against other NVS solutions (Plenoxels, CCNeRF, and base 3DGS) on various volume datasets. The code is available at https://***/TouKaienn/iVR-GS .

关键词： Rendering (computer graphics) Three-dimensional displays data visualization Image color analysis Training Real-time systems Computational modeling Neural radiance field Costs Solid modeling

来源：评论

学校读者我要写书评

暂无评论

Utilizing large Language Models (LLMs) in data analysis Pipeline for Digital Phenotyping: Description, Prediction, and visualization

Utilizing Large Language Models (LLMs) in Data Analysis Pipe...

引用

ieee International Conference on Big data

作者： Derek Nissen Tianyang Yu Reyva Babtista Yi Shang Department of Computer Science University of Missouri Columbia MO Department of Computer Science Grinnell College Grinnell IA

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Digital phenotyping is the "moment-by-moment quantification of the individual-level human phenotype in situ using data from personal digital devices," according to Onnela and Rauch. Digital phenotyping research has historically contained many entry barriers due to high costs and complexity. However, the growing popularity of personal devices such as mobile phones has enabled researchers to collect participant data with more convenience and lower costs than ever before. This paper presents the Intelligent Phenotype analysis Suite (IPAS), a new AI-powered tool for streamlined phenotype investigation. This tool provides researchers the ability to generate descriptions, predictions, and visualizations of their digital phenotyping data through a simple, novel chat-bot interface. IPAS combines an array of data science techniques with natural language processing capabilities of large language models to accelerate the data analysis process for researchers. IPAS extracts raw Beiwe data, an intuitive data collection platform which only requires participants to install an application on their mobile phone and permit data collection. Furthermore, we evaluate the accuracy of IPAS by using key LLM performance metrics: Precision, Recall, and F1 Score. While testing, IPAS sometimes struggled to generate code. However, in all test prompts, IPAS correctly identified the pre-written function needed to perform the requested task. Altogether, IPAS improves prior methods by enabling researchers of all levels of experience to analyze digital phenotyping data using natural language queries.

关键词： Analytical models Phenotypes Costs large language models Pipelines data visualization Personal digital devices Mobile handsets data models Testing

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study between Regression Algorithms to Visualize and Analyze the Scalability of large-Scale Graphs in Big data 16

A Comparative Study between Regression Algorithms to Visuali...

引用

16th International Conference on Emerging Technologies, ICET 2021

作者： Latif, Naila Arshad, Muhammad Sheraz Javed, Shahzeb Riphah International University College of Computing Faisalabad Pakistan Government College University Department of Computer Science Faisalabad Pakistan

ISBN: (纸本)9781665494373

data visualization is a powerful paradigm to enhance data analysis. Different type of data visualization techniques are widely used to facilitate graph analysis by taking advantage of humanâs strong ability in visual perception. visualization of large-scale graphs suffers from different kind of problems such as lack of scalability, random access pattern, heavy data conflicts, and poor locality. Scalability analysis is an important factor in visualization of big data. Scalability of large-scale graphs results the irregular and unstructured relationships. Therefore, a comparative study is conducted between ridge regression algorithm and linear regression algorithm for scalability analysis. These algorithms are utilized in visualization of large datasets on scatter plot and distribution plot with respect to scalability analysis. For this purpose, two complex and large datasets are selected and their results are compared against mean standard deviations and execution time of the algorithms. The comparative study indicates that ridge regression technique performed better scalability analysis than linear regression technique. © 2021 ieee.

关键词： data visualization

来源：评论

学校读者我要写书评

暂无评论

Research on Fast analysis Model of Power Big data Integrating 3D data visualization Scene

Research on Fast Analysis Model of Power Big Data Integratin...

引用

data Science and Computer Application (ICDSCA), ieee International Conference on

作者： Lin Qingrui Lin Bixing Gao Shuze Yang Jiangping Wu Chaowang State Grid Info-Telecom Great Power Science and Technology Co. Ltd. Fuzhou Fujian China

After determining large-scale power data and spatial scenarios, a new analysis model is constructed for 3D visualization scenarios. In this model, big data mining and 3D visualization technology are organically integrated, information fusion and fuzzy tomographic analysis method are adopted to realize efficient mining of power big data, and 3D rendering algorithm based on attribute reduction is used to improve the real-time performance of power 3D scene rendering. The visual feature reconstruction technology is used to realize the visual reconstruction of the 3D scene of power big data in the distribution network. The experiment shows that the data visualization management method can realize the efficient mining of power big data and real-time rendering of 3D model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PipelineProfiler: A Visual Analytics Tool for the Exploration of AutoML Pipelines

引用

ieee TRANSACTIONS ON visualization AND COMPUTER GRAPHICS 2021年第2期27卷 390-400页

作者： Ono, Jorge Piazentin Castelo, Sonia Lopez, Roque Bertini, Enrico Freire, Juliana Silva, Claudio NYU New York NY 10003 USA

In recent years, a wide variety of automated machine learning (AutoML) methods have been proposed to generate end-to-end ML pipelines. While these techniques facilitate the creation of models, given their black-box nature, the complexity of the underlying algorithms, and the large number of pipelines they derive, they are difficult for developers to debug. It is also challenging for machine learning experts to select an AutoML system that is well suited for a given problem. In this paper, we present the Pipeline Profiler, an interactive visualization tool that allows the exploration and comparison of the solution space of machine learning (ML) pipelines produced by AutoML systems. PipelineProfiler is integrated with Jupyter Notebook and can be combined with common data science tools to enable a rich set of analyses of the ML pipelines, providing users a better understanding of the algorithms that generated them as well as insights into how they can be improved. We demonstrate the utility of our tool through use cases where PipelineProfiler is used to better understand and improve a real-world AutoML system. Furthermore, we validate our approach by presenting a detailed analysis of a think-aloud experiment with six data scientists who develop and evaluate AutoML tools.

关键词： Automatic Machine Learning Pipeline visualization Model Evaluation

来源：评论

学校读者我要写书评

暂无评论

Improving Clustering Explainability and Automated Cluster Naming with Approximate Inverse Model Explanations and large Language Models

Improving Clustering Explainability and Automated Cluster Na...

引用

Trustworthy, Explainable and Responsible Computational Intelligence (CITREx Companion), ieee symposium on

作者： Takafumi Nakanishi Department of Data Science Musashino University Tokyo Japan

ISBN: (数字)9798331519728

ISBN: (纸本)9798331519735

This study presents a method that combines an explainable AI (XAI) technology called approximate inverse model explanation (AIME) with large language models (LLMs) to improve the explainability of clustering results and automatically generate cluster names. AIME identifies the features that are most important in forming each cluster. A language model then uses these important features to automatically generate names for the clusters. Traditionally, clustering has been used to group similar data; however, determining why clusters form and name them has been left to data analysis. This study automates both tasks by explaining cluster formation and generating cluster names, making it a useful tool in fields such as data mining. For example, in marketing, customer data can be clustered to identify segments, and the characteristics and names of these segments can be automatically generated. This method enhances the explainability of unsupervised learning and offers a new application for explainable AI. Although the method has been demonstrated for data mining, it has potential applications in other fields, such as text mining.

关键词： Text mining data analysis Explainable AI large language models Computational modeling Clustering methods Feature extraction Unsupervised learning Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

An Arduino Based Heartbeat Detection Device (ArdMob-ECG) for Real-Time ECG analysis

An Arduino Based Heartbeat Detection Device (ArdMob-ECG) for...

引用

2022 ieee Signal Processing in Medicine and Biology symposium, SPMB 2022

作者： Moller, T. Georgie, Y. Voss, M. Kaltwasser, L. Berlin School of Mind and Brain Humboldt-Universität Berlin Germany Charité University Medicine Department for Psychiatry and Psychotherapy Berlin Germany Humboldt-Universität Denartment of Comnuter Science Berlin Germany St. Hedwig Krankenhaus Berlin Germany

ISBN: (纸本)9781665470292

This technical paper provides a tutorial to build a low-cost (10-100 USD) and easy to assemble ECG device (ArdMob-ECG) that can be easily used for a variety of different scientific studies. The advantage of this device is that it automatically stores the data and has a built-in detection algorithm for heartbeats. Compared to a clinical ECG, this device entails a serial interface that can send triggers via USB directly to a computer and software (e.g. Unity, Matlab) with minimal delay due to its architecture. Its software and hardware is open-source and publicly available. The performance of the device regarding sensitivity and specificity is comparable to a professional clinical ECG and is assessed in this paper. Due to the open-source software, a variety of different research questions and individual alterations can be adapted using this ECG. The code as well as the circuit is publicly available and accessible for everyone to promote a better health system in remote areas, Open Science, and to boost scientific progress and the development of new paradigms that ultimately foster innovation. © 2022 ieee.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Efficient representation and analysis for a large tetrahedral mesh using Apache Spark

Efficient representation and analysis for a large tetrahedra...

引用

Topological data analysis and visualization (TopoInVis)

作者： Yuehui Qian Guoxi Liu Federico Iuricich Leila De Floriani University of Maryland College Park Clemson University

ISBN: (数字)9798331528447

ISBN: (纸本)9798331528454

Tetrahedral meshes are widely used due to their flexibility and adaptability in representing changes of complex geometries and topology. However, most existing data structures struggle to efficiently encode the irregular connectivity of tetrahedral meshes with billions of vertices. We address this problem by proposing a novel framework for efficient and scalable analysis of large tetrahedral meshes using Apache Spark. The proposed framework, called Tetra-Spark, features optimized approaches to locally compute many connectivity relations by first retrieving the Vertex-Tetrahedron (VT) relation. This strategy significantly improves Tetra-Spark’s efficiency in performing morphology computations on large tetrahedral meshes. To prove the effectiveness and scalability of such a framework, we conduct a comprehensive comparison against a vanilla Spark implementation for the analysis of tetrahedral meshes. Our experimental evaluation shows that Tetra-Spark achieves up to a $78 \times$ speedup and reduces memory usage by up to 80% when retrieving connectivity relations with the VT relation available. This optimized design further accelerates subsequent morphology computations, resulting in up to a $47.7 \times$ speedup.

关键词： Geometry Navigation Scalability Memory management Morphology Cluster computing Computational efficiency Topology Partitioning algorithms Sparks

来源：评论

学校读者我要写书评

暂无评论

Single-PZT-Fiber Transducers for 3D Ultrasound Computed Tomography: Characterization and Modeling

Single-PZT-Fiber Transducers for 3D Ultrasound Computed Tomo...

引用

ieee International Ultrasonics symposium (IUS)

作者： Angerer, Martin Zapf, Michael Gebhardt, Sylvia Ruiter, Nicole V. Karlsruhe Inst Technol KIT Inst Data Proc & Elect Eggenstein Leopoldshafe Germany Fraunhofer Inst Ceram Technol & Syst Fraunhofer IKTS Dresden Germany

ISBN: (数字)9781665466578

ISBN: (纸本)9781665466578

In this work we present the characterization and modeling of ultrasound transducer arrays based on single-PZT-fiber transducers. The arrays were designed for a new generation of 3D ultrasound computed tomography (USCT) devices for breast cancer imaging. At the heart of the new arrays is a piezocomposite disk that features pseudo-random positioning of 18 individual transducers. Several hundred arrays were produced using semi-automated production processes and batch processing techniques. The acoustic characteristics of 54 single transducers were measured in an ultrasound testing setup. The transducers exhibit isotropic ultrasound emission, a large bandwidth (134 %), and a wide opening angle (43 degrees). This makes them well-suited for 3D USCT. A finite element model is presented for design analysis and further optimization. Initial differences between measured and modeled characteristics were reduced by adjusting piezoelectric constants, elastic properties of the passive materials and by including realistic damping in the model. As a result, the adjusted model predicts the acoustic performance over a wide range of emission angles and frequencies with good accuracy. Hence, the presented transducer arrays and the corresponding model provide a promising technology for current and future 3D USCT imaging systems.

关键词： ultrasound computed tomography single-fiber transducers finite element analysis ultrasound testing piezoelectric transducers

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：