检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Gao, Chenyu Xu, Kaiwen Kim, Michael E. Zuo, Lianrui Li, Zhiyuan Archer, Derek B. Hohman, Timothy J. Moore, Ann Zenobia Ferrucci, Luigi Beason-Held, Lori L. Resnick, Susan M. Davatzikos, Christos Prince, Jerry L. Landman, Bennett A. Department of Electrical and Computer Engineering Vanderbilt University NashvilleTN United States Department of Computer Science Vanderbilt University NashvilleTN United States Vanderbilt Memory and Alzheimer’s Center Vanderbilt University Medical Center NashvilleTN United States Department of Neurology Vanderbilt University Medical Center NashvilleTN United States Translational Gerontology Branch National Institute on Aging National Institutes of Health BaltimoreMD United States Laboratory of Behavioral Neuroscience National Institute on Aging National Institutes of Health BaltimoreMD United States AI2D Center for AI and Data Science University of Pennsylvania Philadelphia United States Department of Electrical and Computer Engineering Johns Hopkins University BaltimoreMD United States

Defacing is often applied to head magnetic resonance image (MRI) datasets prior to public release to address privacy concerns. The alteration of facial and nearby voxels has provoked discussions about the true capability of these techniques to ensure privacy as well as their impact on downstream tasks. With advancements in deep generative models, the extent to which defacing can protect privacy is uncertain. Additionally, while the altered voxels are known to contain valuable anatomical information, their potential to support research beyond the anatomical regions directly affected by defacing remains uncertain. To evaluate these considerations, we develop a refacing pipeline that recovers faces in defaced head MRIs using cascaded diffusion probabilistic models (DPMs). The DPMs are trained on images from 180 subjects and tested on images from 484 unseen subjects, 469 of whom are from a different dataset. To assess whether the altered voxels in defacing contain universally useful information, we also predict computed tomography (CT)-derived skeletal muscle radiodensity from facial voxels in both defaced and original MRIs. The results show that DPMs can generate high-fidelity faces that resemble the original faces from defaced images, with surface distances to the original faces significantly smaller than those of a population average face (p -4). For shin muscle, the correlation is statistically significant (p 0.05) when any defacing method is applied, suggesting that defacing might not only fail to protect privacy but also eliminate valuable information. We advocate two solutions for data sharing that comply with privacy: 1) share skull-stripped images along with measurements of facial and cranial features extracted before skull-stripping for public access, while acknowledging that this approach inherently compromises many research potentials;or 2) share the unaltered images with privacy enforced through policy restrictions. © 2025, CC BY-NC-ND.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Energetic Content based Image Retrieval Scheme using Improved Deep Learning Strategy with Image Analysis Technique

Energetic Content based Image Retrieval Scheme using Improve...

引用

International Conference on Smart Structures and Systems (ICSSS)

作者： S. Karkuzhali P. Malathi A Thenmozhi Velu Aiyyasamy Keerthika A G.S. Uthayakumar Department of General Engineering R.M.K. Engineering College Chennai Tamil Nadu India Department of Data Analytics Saveetha College of Liberal Arts and Sciences SIMATS Department of Electronics and Communication Engineering Kings Engineering College Chennai Tamil Nadu India Department of Electronics and Communication Engineering Meenakshi Sundararajan Engineering College Chennai Tamil Nadu India Department of Computer Science and Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Tamil Nadu India Department of ECE St. Joseph’s Institute of Technology Chennai Tamil Nadu India

One popular approach to retrieving images from huge, unprocessed datasets is content-based image retrieval, or CBIR. The conventional ways of data retrieval, however, are not meeting the needs of consumers. The number of consumer-accessible photographs also keeps growing, and there are an abundance of digital platforms for development and dissemination. Consequently, digital image processing is both ubiquitous and permanent in many fields. Consequently, effective strategies are required for both the speedy access to these massive picture databases and the recovery of comparable photos from this massive number of images based on a specific picture (query). The computation of depiction of features and resemblance is crucial to the efficiency of a CBIR system. We introduce LAIRS, a cutting-edge deep learning method that integrates the extraction of features and aims to do this with classification to facilitate rapid picture retrieval. For a transparent evaluation of the proposed scheme’s efficiency, the suggested logic is cross-validated using Convolutional Neural Networks (CNNs), a classic deep learning paradigm. Several in-depth observational experiments for various CBIR tasks employing an image database have shown encouraging results, teaching us important lessons for making CBIR system more efficient. With the use of CBIR structures, a different collection can find similar pictures to the query image. There is little doubt that Google’s search per photo tool is perhaps the most widely used CBIR approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Vortex Feature Positioning: Bridging Tabular IIoT data and Image-Based Deep Learning

arXiv

引用

arXiv 2023年

作者： Park, Jong-Ik Seong, Sihoon Lee, JunKyu Hong, Cheol-Ho Department of Electrical and Computer Engineering Carnegie Mellon University 5000 Forbes Ave PittsburghPA15213 United States Department of Intelligent Semiconductor Engineering Chung-Ang University 84 Heukseok-ro Dongjak District Seoul06974 Korea Republic of Institute for Analytics and Data Science University of Essex Wivenhoe Park ColchesterCO4 3SQ United Kingdom

Tabular data from IIoT devices are typically analyzed using decision tree-based machine learning techniques, which struggle with high-dimensional and numeric data. To overcome these limitations, techniques converting tabular data into images have been developed, leveraging the strengths of image-based deep learning approaches such as Convolutional Neural Networks. These methods cluster similar features into distinct image areas with fixed sizes, regardless of the number of features, resembling actual photographs. However, this increases the possibility of overfitting, as similar features, when selected carefully in a tabular format, are often discarded to prevent this issue. Additionally, fixed image sizes can lead to wasted pixels with fewer features, resulting in computational inefficiency. We introduce Vortex Feature Positioning (VFP) to address these issues. VFP arranges features based on their correlation, spacing similar ones in a vortex pattern from the image center, with the image size determined by the attribute count. VFP outperforms traditional machine learning methods and existing conversion techniques in tests across seven datasets with varying real-valued attributes. © 2023, CC BY-NC-ND.

关键词： Vortex flow

来源：评论

学校读者我要写书评

暂无评论

Adaptive Estimation of Graphical Models under Total Positivity

arXiv

引用

arXiv 2022年

作者： Ying, Jiaxi de M. Cardoso, José Vinícius Palomar, Daniel P. Department of Mathematics The Hong Kong University of Science and Technology Clear Water Bay Hong Kong HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute Shenzhen China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Clear Water Bay Hong Kong Department of Electronic and Computer Engineering Department of Industrial Engineering and Data Analytics The Hong Kong University of Science and Technology Clear Water Bay Hong Kong

We consider the problem of estimating (diagonally dominant) M-matrices as precision matrices in Gaussian graphical models. These models exhibit intriguing properties, such as the existence of the maximum likelihood estimator with merely two observations for M-matrices [Lauritzen et al., 2019;Slawski & Hein, 2015] and even one observation for diagonally dominant M-matrices [Truell et al., 2021]. We propose an adaptive multiple-stage estimation method that refines the estimate by solving a weighted 1-regularized problem at each stage. Furthermore, we develop a unified framework based on the gradient projection method to solve the regularized problem, incorporating distinct projections to handle the constraints of M-matrices and diagonally dominant M-matrices. A theoretical analysis of the estimation error is provided. Our method outperforms state-of-the-art methods in precision matrix estimation and graph edge identification, as evidenced by synthetic and financial time-series data sets. Copyright © 2022, The Authors. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Study and Trend Prediction of Covid-19 cases in India using Deep Learning Techniques 1

Study and Trend Prediction of Covid-19 cases in India using ...

引用

1st International Conference on Mechatronics and Artificial Intelligence, ICMAI 2021

作者： Shrivastava, V.K. Kumar, Ajay Shrivastava, A. Tiwari, A. Thiru, K. Batra, R. Department of Big Data Analytics Adani Institute of Digital Technology Management Gujrat Gandhinagar382423 India Department of Mechanical Engineering SGT University Haryana Gurugram122505 India Department of Electronics and Tele Communication Engineering IIIT Odisha Bhubaneswar751003 India Department of Information Technology Madhav Institute of Technology and Science Gwalior474005 India United World School of Computational Intelligence Karnavati University Gujrat Gandhinagar383422 India Reenu Batra Department of Computer Science and Engineering SGT University Haryana Gurugram122505 India

The novel coronavirus or officially known as SARS-CoV 2 (Severe Acute Respiratory Syndrome Coronavirus 2) has caused a severe pandemic over the world affecting not only the economy of the countries but also the lifestyle of the people worldwide. As on 31.12.2020, Covid-19 (coronavirus disease) has infecting more than 10266674 people and causing about 148738 deaths in India. It has been seen through various statistics of various countries that the number of Covid-19 cases grows exponentially as the number of test increases then after some period, the rate of new cases decreases. In this research paper, researchers have created deep learning-based model to predict the curve of the new Covid-19 cases vs the total number of tests conducted in India. There is still lockdown in some part of the country while some states have partially relaxed the rules and some states totally lifted the lockdown. Predicting the number of new cases and their trend can help in deciding what is the optimal time to release the lockdown. It will also help in determining when the coronavirus will loosen its grip from India. © Published under licence by IOP Publishing Ltd.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Using a statewide health information exchange to enhance COVID research and surveillance: The impact of information fragmentation

引用

International Journal of Medical Informatics 2025年 203卷 105971页

作者： Allen, Katie S. Park, Seho Price, John Ning, Xia Schleyer, Titus Center for Biomedical Informatics Regenstrief Institute Inc United States Department of Industrial and Data Engineering Hongik University Korea People's Democratic Rep Biomedical Informatics Computer Science and Engineering Translational Data Analytics Institute The Ohio State University United States School of Medicine Indiana University United States

Objective: Use of electronic health data for public health surveillance and research has become almost ubiquitous. However, since many patients routinely receive care from multiple healthcare systems, not all information for a patient may be available in a single system. Thus, using data from only a single healthcare system may unintentionally result in inaccuracies. This study compared the variation in the number of inpatient and emergency department encounters, diagnoses, and laboratory results, as well as COVID prevalence, when data about patients was (1) drawn from a single, major health system;(2) augmented with health information exchange (HIE) data;or (3) retrieved entirely from the HIE. Materials and Methods: This study leveraged a registry of 1,343,703 COVID-positive patients covering the state of Indiana containing data from March 6, 2020 − February 14, 2022. The registry included data from the state-wide health information exchange as well as granular data from an individual health system. data elements included encounters, diagnoses, laboratory testing, and death records. Results: Enhancing the cohort with data from the HIE increased the average number of encounters per person from 20.25 to 37.05, unique diagnoses from 16.06 to 30.83, and laboratory results from 0.32 to 7.06. The absolute difference between the single-system and HIE cohorts was 22.5% for the estimated prevalence of COVID, 4% for the number of all-cause hospitalizations and -9.4% for emergency department visits. Conclusion: Information fragmentation can lead to an incomplete picture, or even errors, in research or clinical settings. This study demonstrates that combining clinical data sources creates variation in results. Understanding the issues presented by information fragmentation, such as bias it may create, is critical to enabling accurate disease surveillance and crisis response planning. © 2025

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Attention Field Size Alters Patterns of Population Receptive Fields in the Early Visual Cortex

引用

Neuroscience Bulletin 2022年第2期38卷 205-208页

作者： Bo Liu Xiaochun Wang Le Wang Qiaojun Qu Wei Zhang Bin Wang Jie Xiang Ting Yan Tianyi Yan Hui Zhang College of Medical Imaging Shanxi Medical UniversityTaiyuan 030001China Department of Radiology First Clinical Medical CollegeShanxi Medical UniversityTaiyuan 030001China College of Information and Computer Taiyuan University of TechnologyTaiyuan 030001China Intelligent Imaging Big Data and Functional Nano-imaging Engineering Research Center of Shanxi Province Shanxi Medical UniversityTaiyuan 030001China Translational Medicine Research Center Shanxi Medical UniversityTaiyuan 030001China School of Life Science Beijing Institute of TechnologyBeijing 100081China Ministry of Industry and Information Technology Key Laboratory of Convergence Medical Engineering System and Healthcare TechnologyBeijing Institute of TechnologyBeijing 100081China

Dear Editor,Visual spatial attention is a cognitive process by which prior information about the relevance of spatial locations is used to improve perceptual performance[1].Visual attention is spread across the attention field(AF),a range within visual *** AF reshapes the distribution of activity throughout the visual pathway,including the early visual cortex(EVC)and all areas along the dorsal and ventral visual cortical pathways[2,3].Importantly,the effect of attention depends not only on the spatial position of the AF but also on its size[4].

关键词： Visual Cortex visual

来源：评论

学校读者我要写书评

暂无评论

UseGeo - A UAV-based multi-sensor dataset for geospatial research

引用

ISPRS Open Journal of Photogrammetry and Remote Sensing 2024年 13卷

作者： Nex, F. Stathopoulou, E.K. Remondino, F. Yang, M.Y. Madhuanand, L. Yogender, Y. Alsadik, B. Weinmann, M. Jutzi, B. Qin, R. ITC Department of Earth Observation Science Faculty ITC University of Twente Enschede Netherlands 3D Optical Metrology (3DOM) Unit Bruno Kessler Foundation (FBK) Trento Italy Visual Computing Group University of Bath Bath United Kingdom Department of Physical Geography Faculty of Geosciences University of Utrecht Utrecht Netherlands Inter-university Department of Regional & Urban Studies and Planning (DIST) Politecnico di Torino Italy Institute of Photogrammetry and Remote Sensing Karlsruhe Institute of Technology Karlsruhe Germany Geospatial Data Analytics Laboratory The Ohio State University Columbus United States Department of Civil Environmental and Geodetic Engineering The Ohio State University Columbus United States Department of Electrical and Computer Engineering The Ohio State University Columbus United States Translational Data Analytics Institute The Ohio State University Columbus United States

3D reconstruction is a long-standing research topic in the photogrammetric and computer vision communities;although a plethora of open-source and commercial solutions for 3D reconstruction have been released in the last few years, several open challenges and limitations still exist. Undoubtedly, deep learning algorithms have demonstrated great potential in several remote sensing tasks, including image-based 3D reconstruction. State-of-the-art monocular and stereo algorithms leverage deep learning techniques and achieve increased performance in depth estimation and 3D reconstruction. However, one of the limitations of such methods is that they highly rely on large training sets that are often tedious to obtain;even when available, they typically refer to indoor, close-range scenarios and low-resolution images. Especially while considering UAV (Unmanned Aerial Vehicle) scenarios, such data are not available and domain adaptation is not a trivial challenge. To fill this gap, the UAV-based multi-sensor dataset for geospatial research (UseGeo - https://***/home) is introduced in this paper. It contains both image and LiDAR data and aims to support relevant research in photogrammetry and computer vision with a useful training set for both stereo and monocular 3D reconstruction algorithms. In this regard, the dataset provides ground truth data for both point clouds and depth maps. In addition, UseGeo can be also a valuable dataset for other tasks such as feature extraction and matching, aerial triangulation, or image and LiDAR co-registration. The paper introduces the UseGeo dataset and validates some state-of-the-art algorithms to assess their usability for both monocular and multi-view 3D reconstruction. © 2024 The Authors

关键词： 3D reconstruction Deep learning LiDAR Monocular depth estimation Multi-view stereo Stereo matching UAV

来源：评论

学校读者我要写书评

暂无评论

Automated LoD-2 model reconstruction from very-high-resolution satellite-derived digital surface model and orthophoto

arXiv

引用

arXiv 2021年

作者： Gui, Shengxi Qin, Rongjun Geospatial Data Analytics Lab Ohio State University Columbus United States Department of Civil Environmental and Geodetic Engineering Ohio State University Columbus United States Department of Electrical and Computer Engineering Ohio State University Columbus United States Translational Data Analytics Institute Ohio State University Columbus United States

Digital surface models (DSM) generated from multi-stereo satellite images are getting higher in quality owing to the improved data resolution and photogrammetric reconstruction algorithms. Very-high-resolution (VHR, with sub-meter level resolution) satellite images effectively act as a unique data source for 3D building modeling, because it provides a much wider data coverage with lower cost than the traditionally used LiDAR and airborne photogrammetry data. Although 3D building modeling from point clouds has been intensively investigated, most of the methods are still ad-hoc to specific types of buildings and require high-quality and high-resolution data sources as input. Therefore, when applied to satellite-based point cloud or DSMs, these developed approaches are not readily applicable and more adaptive and robust methods are needed. As a result, most of the existing work on building modeling from satellite DSM achieves LoD-1 generation. In this paper, we propose a model-driven method that reconstructs LoD-2 building models following a "decomposition-optimization-fitting" paradigm. The proposed method starts building detection results through a deep learning-based detector and vectorizes individual segments into polygons using a "three-step" polygon extraction method, followed by a novel grid-based decomposition method that decomposes the complex and irregularly shaped building polygons to tightly combined elementary building rectangles ready to fit elementary building models. We have optionally introduced OpenStreetMap (OSM) and Graph-Cut (GC) labeling to further refine the orientation of 2D building rectangle. The 3D modeling step takes building-specific parameters such as hip lines, as well as non-rigid and regularized transformations to optimize the flexibility for using a minimal set of elementary models. Finally, roof type of building models s refined and adjacent building models in one building segment are merged into the complex polygonal model. Our propo

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

SynFacePAD 2023: Competition on Face Presentation Attack Detection Based on Privacy-aware Synthetic Training data

arXiv

引用

arXiv 2023年

作者： Fang, Meiling Huber, Marco Fierrez, Julian Ramachandra, Raghavendra Damer, Naser Alkhaddour, Alhasan Kasantcev, Maksim Pryadchenko, Vasiliy Yang, Ziyuan Huangfu, Huijie Chen, Yingyu Zhang, Yi Pan, Yuchen Jiang, Junjun Liu, Xianming Sun, Xianyun Wang, Caiyong Liu, Xingyu Chang, Zhaohua Zhao, Guangzhe Tapia, Juan Gonzalez-Soler, Lazaro Aravena, Carlos Schulz, Daniel Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Department of Computer Science TU Darmstadt Darmstadt Germany Biometrics and Data Pattern Analytics Lab Universidad Autonoma de Madrid Spain Norway ID R&D Inc. New York United States School of Cyber Science and Engineering Sichuan University Chengdu China School of Computer Science and Technology Harbin Institute of Technology Harbin China School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture China Biometrics and Security Research Group Hochschule Darmstadt Darmstadt Germany I+D Vision Center Santiago Chile

This paper presents a summary of the Competition on Face Presentation Attack Detection Based on Privacy-aware Synthetic Training data (SynFacePAD 2023) held at the 2023 International Joint Conference on Biometrics (IJCB 2023). The competition attracted a total of 8 participating teams with valid submissions from academia and industry. The competition aimed to motivate and attract solutions that target detecting face presentation attacks while considering synthetic-based training data motivated by privacy, legal and ethical concerns associated with personal data. To achieve that, the training data used by the participants was limited to synthetic data provided by the organizers. The submitted solutions presented innovations and novel approaches that led to outperforming the considered baseline in the investigated benchmarks. © 2023, CC BY-NC-SA.

关键词： Competition

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：