检索结果-内蒙古大学图书馆

2nd Workshop of the DFG's International Research Training Group on visualization of Large and Unstructured data Sets - Applications in Geospatial Planning, Modeling, and Engineering, VLUDS 2007

作者： Rübel, O. Weber, G.H. Huang, M.-Y. Bethel, E.W. Keränen, S.V.E. Fowlkes, C.C. Hendriks, C.L. Luengo DePace, Angela H. Simirenko, L. Eisen, M.B. Biggin, M.D. Hagen, H. Malik, J. Knowles, D.W. Hamann, B. International Research Training Group University of Kaiserslautern Germany Institute for Data Analysis and Visualization University of California Davis United States Computational Research Division Lawrence Berkeley National Laboratory Berkeley United States Genomics Division Lawrence Berkeley National Laboratory Berkeley United States Computer Science Department University of California Irvine United States Computer Science Division University of California Berkeley United States Lawrence Berkeley National Laboratory Life Sciences Division Berkeley United States Department of Molecular and Cellular Biology Center for Integrative Genomics University of California Berkeley United States

ISBN: (纸本)9783885794417

To better understand how developmental regulatory networks are defined in the genome sequence, the Berkeley Drosophila Transcription Network Project (BDNTP ) has developed a suite of methods to describe 3D gene expression data, i.e., the output of the network at cellular resolution for multiple time points. To allow researchers to explore these novel data sets we have developed PointCloudXplore (PCX). In PCX we have linked physical and information visualization views via the concept of brushing (cell selection). For each view dedicated operations for performing selection of cells are available. In PCX, all cell selections are stored in a central management system. Cells selected in one view can in this way be highlighted in any view allowing further cell subset properties to be determined. Complex cell queries can be defined by combining different cell selections using logical operations such as AND, OR, and NOT. Here we are going to provide an overview of PointCloudXplore 2 (PCX2), the latest publicly available version of PCX. PCX2 has shown to be an effective tool for visual exploration of 3D gene expression data. We discuss (i) all views available in PCX2, (ii) different strategies to perform cell selection, (iii) the basic architecture of PCX2., and (iv) illustrate the usefulness of PCX2 using selected examples.

关键词： visualization

来源：评论

学校读者我要写书评

暂无评论

A Deep learning study on osteosarcoma detection from histological images

arXiv

引用

arXiv 2020年

作者： Anisuzzaman, D.M. Barzekar, Hosein Tong, Ling Luo, Jake Yu, Zeyun Big Data Analytics and Visualization Laboratory Department of Computer Science University of Wisconsin-Milwaukee MilwaukeeWI53211 United States Department of Health Informatics and Administration University of Wisconsin-Milwaukee MilwaukeeWI53211 United States Department of Biomedical Engineering University of Wisconsin-Milwaukee MilwaukeeWI53211 United States

In the U.S, 5-10% of new pediatric cases of cancer are primary bone tumors. The most common type of primary malignant bone tumor is osteosarcoma. The intention of the present work is to improve the detection and diagnosis of osteosarcoma using computer-aided detection (CAD) and diagnosis (CADx). Such tools as convolutional neural networks (CNNs) can significantly decrease the surgeon’s workload and make a better prognosis of patient conditions. CNNs need to be trained on a large amount of data in order to achieve a more trustworthy performance. In this study, transfer learning techniques, pre-trained CNNs, are adapted to a public dataset on osteosarcoma histological images to detect necrotic images from non-necrotic and healthy tissues. First, the dataset was preprocessed, and different classifications are applied. Then, Transfer learning models including VGG19 and Inception V3 are used and trained on Whole Slide Images (WSI) with no patches, to improve the accuracy of the outputs. Finally, the models are applied to different classification problems, including binary and multi-class classifiers. Experimental results show that the accuracy of the VGG19 has the highest, 96%, performance amongst all binary classes and multiclass classification. Our fine-tuned model demonstrates state-of-the-art performance on detecting malignancy of Osteosarcoma based on histologic images. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

MultiNet with Transformers: A Model for Cancer Diagnosis Using Images

arXiv

引用

arXiv 2023年

作者： Barzekar, Hosein Patel, Yash Tong, Ling Yu, Zeyun Big Data Analytics and Visualization Laboratory Department of Computer Science University of Wisconsin-Milwaukee MilwaukeeWI53211 United States Department of Health Informatics and Administration University of Wisconsin-Milwaukee MilwaukeeWI53211 United States Department of Biomedical Engineering University of Wisconsin-Milwaukee MilwaukeeWI53211 United States

Cancer is a leading cause of death in many countries. An early diagnosis of cancer based on biomedical imaging ensures effective treatment and a better prognosis. However, biomedical imaging presents challenges to both clinical institutions and researchers. Physiological anomalies are often characterized by slight abnormalities in individual cells or tissues, making them difficult to detect visually. Traditionally, anomalies are diagnosed by radiologists and pathologists with extensive training. This procedure, however, demands the participation of professionals and incurs a substantial cost. The cost makes large-scale biological image classification impractical. In this study, we provide unique deep neural network designs for multiclass classification of medical images, in particular cancer images. We incorporated transformers into a multiclass framework to take advantage of data-gathering capability and perform more accurate classifications. We evaluated models on publicly accessible datasets using various measures to ensure the reliability of the models. Extensive assessment metrics suggest this method can be used for a multitude of classification tasks. © 2023, CC BY.

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Abstract: Exploring Performance data with Boxfish

Abstract: Exploring Performance Data with Boxfish

引用

High Performance Computing, Networking, Storage and Analysis (SCC), SC Companion:

作者： Katherine E. Isaacs Aaditya G. Landge Todd Gamblin Peer-Timo Bremer Valerio Pascucci Bernd Hamann Institute for Data Analysis and Visualization Department of Computer Science University of California Davis CA USA Scientific Computing and Imaging Institute University of Utah Salt Lake UT USA Center for Applied Scientific Computing Lawrence Livermore National Laboratories Livermore CA USA

The growth in size and complexity of scaling applications and the systems on which they run pose challenges in analyzing and improving their overall performance. With metrics coming from thousands or millions of processes, visualization techniques are necessary to make sense of the increasing amount of data. To aid the process of exploration and understanding, we announce the initial release of Boxfish, an extensible tool for manipulating and visualizing data pertaining to application behavior. Combining and visually presenting data and knowledge from multiple domains, such as the application's communication patterns and the hardware's network configuration and routing policies, can yield the insight necessary to discover the underlying causes of observed behavior. Boxfish allows users to query, filter and project data across these domains to create interactive, linked visualizations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An improved N-bit to N-bit reversible Haar-like transform

An improved N-bit to N-bit reversible Haar-like transform

引用

Pacific Conference on Computer Graphics and Applications

作者： J.G. Senecal P. Lindstrom M.A. Duchaineau K.I. Joy Inst. for Sci. Comput. Res. Lawrence Livermore Nat. Lab. CA USA Center for Applied Scientific Computing Lawrence Livemore National Laboratory USA Institute for Data Analysis and Visualization Computer Science Department University of California Davis USA

We introduce the piecewise-linear Haar (PLHaar) transform, a reversible n-bit to n-bit transform that is based on the Haar wavelet transform. PLHaar is continuous, while all current n-bit to n-bit methods are not, and is therefore uniquely usable with both lossy and lossless methods (e.g. image compression). PLHaar has both integer and continuous (i.e. non-discrete) forms. By keeping the coefficients to n bits PLHaar is particularly suited for use in hardware environments where channel width is limited, such as digital video channels and graphics hardware.

关键词： Wavelet transforms Continuous wavelet transforms Hardware Dynamic range Image coding Scientific computing Image reconstruction Laboratories data analysis data visualization

来源：评论

学校读者我要写书评

暂无评论

Advances in Visual Computing 1

引用

丛书名： Lecture Notes in Computer science

1000年

作者： George Bebis Richard Boyle Bahram Parvin Darko Koracin Paolo Remagnino Ara Nefian Gopi Meenakshisundaram Valerio Pascucci Jiri Zara Jose Molineros Holger Theisel Tom Malzbender

ISBN: (数字)9783540486312

ISBN: (纸本)9783540486282

It is with great pleasure that we welcome you all to the proceedings of the 2nd InternationalSymposiumonVisualComputing(ISVC2006)heldinLakeTahoe. Followinga successfulmeeting lastyear,wewitnesseda muchstrongerandmore productive event this year. ISVC o?ers a common umbrella for the four main areas of visual computing including vision, graphics, visualization, and virtual reality. Its goal is to provide a forum for researchers, scientists, engineers and practitionersthroughouttheworldtopresenttheirlatestresearch?ndings,ideas, developments and applications in the broader area of visual computing. This year, the program consisted of 13 oral sessions, one poster session, ten special tracks, and six keynote presentations. The response to the call for - pers was very strong. We received more than twice the papers received last year. Speci?cally, we received over 280 submissions for the main symposium from which we accepted 65 papers for oral presentation (23% acceptance) and 56 papers for poster presentation (20% acceptance). Special track papers were solicited separately through the Organizing and Program Committees of each track. A total of 57 papers were accepted for presentation in the special tracks. All papers were reviewed with an emphasis on potential to contribute to the state of the art in the ?eld. Selection criteria included accuracy and originality of ideas, clarity and signi?cance of results, and presentation quality. The review process was quite rigorous, involving two to three independent blind reviews followed by several days of discussion. During the discussion period we tried to correct anomalies and errors that might have existed in the initial reviews.

关键词： Software Engineering/Programming and Operating Systems Pattern Recognition Image Processing and Computer Vision Artificial Intelligence Computer Graphics Algorithm Analysis and Problem Complexity

来源：评论

学校读者我要写书评

暂无评论

Advances in Visual Computing 1

引用

丛书名： Lecture Notes in Computer science

1000年

作者： George Bebis Richard Boyle Bahram Parvin Darko Koracin Paolo Remagnino Ara Nefian Gopi Meenakshisundaram Valerio Pascucci Jiri Zara Jose Molineros Holger Theisel Tom Malzbender

ISBN: (数字)9783540486275

ISBN: (纸本)9783540486268

关键词： Pattern Recognition Computer Applications Programming Techniques Image Processing and Computer Vision Artificial Intelligence Computer Graphics

来源：评论

学校读者我要写书评

暂无评论

Wound Tissue Segmentation in Diabetic Foot Ulcer Images Using Deep Learning: A Pilot Study

arXiv

引用

arXiv 2024年

作者： Dhar, Mrinal Kanti Wang, Chuanbo Patel, Yash Zhang, Taiyu Niezgoda, Jeffrey Gopalakrishnan, Sandeep Chen, Keke Yu, Zeyun Big Data Analytics and Visualization Lab Department of Computer Science University of Wisconsin-Milwaukee MilwaukeeWI United States Auxillium Health MilwaukeeWI United States Wound Healing and Tissue Repair Analytics Laboratory School of Biomedical Sciences & Health Care Administration University of Wisconsin Milwaukee MilwaukeeWI United States Department of Computer Science Marquette University MilwaukeeWI United States

Identifying individual tissues, so-called tissue segmentation, in diabetic foot ulcer (DFU) images is a challenging task and little work has been published, largely due to the limited availability of a clinical image dataset. To address this gap, we have created a DFUTissue dataset for the research community to evaluate wound tissue segmentation algorithms. The dataset contains 110 images with tissues labeled by wound experts and 600 unlabeled images. Additionally, we conducted a pilot study on segmenting wound characteristics including fibrin, granulation, and callus using deep learning. Due to the limited amount of annotated data, our framework consists of both supervised learning (SL) and semi-supervised learning (SSL) phases. In the SL phase, we propose a hybrid model featuring a Mix Transformer (MiT-b3) in the encoder and a CNN in the decoder, enhanced by the integration of a parallel spatial and channel squeeze- and-excitation (P-scSE) module known for its efficacy in improving boundary accuracy. The SSL phase employs a pseudo-labeling-based approach, iteratively identifying and incorporating valuable unlabeled images to enhance overall segmentation performance. Comparative evaluations with state-of-the-art methods are conducted for both SL and SSL phases. The SL achieves a Dice Similarity Coefficient (DSC) of 84.89%, which has been improved to 87.64% in the SSL phase. Furthermore, the results are benchmarked against two widely used SSL approaches—Generative Adversarial Networks and Cross-Consistency Training. Additionally, our hybrid model outperforms the state-of-the-art methods with a 92.99% DSC in performing binary segmentation of DFU wound areas when tested on the Chronic Wound dataset. Codes and data are available at https://***/uwm-bigdata/DFUTissueSegNet. © 2024, CC BY-NC-SA.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Rotation-Inversion Isomerization of Tertiary Carbamates: Potential Energy Surface Analysis of Multi-Paths Isomerization Using Boltzmann Statistics

引用

CHEMPHYSCHEM 2023年第1期24卷 e202200442-e202200442页

作者： Jameson, Brian Glaser, Rainer Department of Chemistry Missouri University of Science and Technology Rolla Missouri 65401 USA Contribution: Conceptualization (supporting) Data curation (lead) Formal analysis (equal) Visualization (lead) Writing - original draft (equal) Writing - review & editing (supporting) Contribution: Conceptualization (lead) Formal analysis (equal) Funding acquisition (lead) Project administration (lead) Supervision (lead) Writing - original draft (equal) Writing - review & editing (lead)

The front cover artwork is provided by Prof. Rainer Glaser's group at the Missouri University of science and Technology. The image shows one of four potential energy surfaces generated from our rotation-inversion study of tertiary carbamates and highlights two of the eight possible transition state pathways between two ensembles of E- and Z-minima. In the context of synthetic studies of fluorinated carbamates R1O-CO-N(R-2)CH2CF3, we unexpectedly observed two sets of C-13 NMR quartets for the CF3 group and we needed to understand their origin. Read the full text of the Research Article at 10.1002/cphc.2022005442.

关键词： carbamates multipaths equilibria negative hyperconjugation rotation-inversion second-order saddle points

来源：评论

学校读者我要写书评

暂无评论

Individual Animal Identification and Feed Grading Using Computer Vision and Unsupervised Statistical Clustering

SSRN

引用

SSRN 2024年

作者： Pi, Yalong Wooley, Jack Mendes, Egleu D.M. Kaniyamattam, Karun Tedeschi, Luis O. Tao, Jian Duffield, Nick Institute of Data Science Texas A&M University College StationTX United States Department of Animal Science Texas A&M University College StationTX United States School of Performance Visualization and Fine Arts Texas A&M University College StationTX United States Department of Electrical and Computer Engineering Texas A&M University College StationTX United States

Livestock farming is under increasing pressure to improve efficiency and sustainability. Individual feed data are critical to feed cost management and animal disease and nutrition research. This paper proposes a framework (relying only on camera input) that integrates computer vision and unsupervised statistical clustering for individual livestock identification and feed grading. The framework leverages deep learning-based computer vision algorithms, including convolutional neural networks (CNN), to extract meaningful features from digital images captured in livestock farming environments. The proposed framework consists of three main components: animal presence sensing, animal identification (individual ID), and feed grading. Animal presence sensing is achieved through supervised transfer learning, where deep CNNs are trained to classify frames as either containing animals or not with labeled data. Animal identification employs unsupervised clustering algorithms such as k-means and DBSCAN to assign unique IDs to individual animals. This method automatically assigns different IDs to the incoming and outgoing animals without manual labeling. This ID task achieved an Adjusted Rand Index (ARI) up to 0.96 in our experiment, indicating a robust animal ID capability. A feed grading task for 6 classes was performed using pre-trained ResNet models with transfer learning on a manually labeled dataset, which accomplished an overall 91.16% accuracy when tested on unseen new data. This feed grading function can replace the traditional laborious manual examination. The proposed framework holds promise for enhancing the efficiency and sustainability of livestock farming practices by providing cheap and fast individual animal feeding data over long periods. © 2024, The Authors. All rights reserved.

关键词： Computer vision

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：