检索结果-内蒙古大学图书馆

IEEE International Conference on data Mining (ICDM)

作者： Rongjian Zhao Buyue Qian Xianli Zhang Yang Li Rong Wei Yang Liu Yinggang Pan School of Computer Science and Technology Xi'an Jiaotong University Xi'an China National Engineering Lab for Big Data Analytics Xi'an Jiaotong University Xi'an China The First Affiliated Hospital of Xi'an Jiaotong University Xi'an China

ISBN: (数字)9781728183169

ISBN: (纸本)9781728183176

Deep learning has proved to be a powerful tool for medical image analysis in recent years. data imbalance is a common problem in medical images. Dice Loss is widely used in medical image segmentation tasks to address the data imbalance problem. However, it only addresses the imbalance problem between foreground and background yet overlooks another imbalance between easy and hard examples that also severely affects the training process of a learning model. Empirically speaking, an easy example generally contributes less to the overall loss than a hard example. However, in practice, compared with hard examples, a large number of easy examples will be generated from a medical image and will dominate the training model, resulting in sub-optimal training or worse. To tackle this problem, we propose a novel Focal Dice Loss to alleviate the imbalance between hard examples and easy examples. Focal Dice Loss is able to reduce the contribution from easy examples and make the model focus on hard examples through our proposed novel balanced sampling strategy during the training process. Furthermore, to evaluate the effectiveness of our proposed loss functions, we conduct extensive experiments on two real-world medical image datasets with 2D and 3D convolutional neural networks. The experimental results show that our proposed Focal Dice Loss brings a significant improvement in segmentation performance compared to Dice Loss. Moreover, we find that our proposed Focal Dice Loss can effectively alleviate the over-fitting problem.

关键词： Training Image segmentation Three-dimensional displays Two dimensional displays Tools Task analysis Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Tax Classification of Invoice Details Based on Directed Heterogeneous Graph 19

Tax Classification of Invoice Details Based on Directed Hete...

引用

19th Chinese National Conference on Computational Linguistic, CCL 2020

作者： Zhao, Peiyao Zheng, Qinghua Dong, Bo Ruan, Jianfei Luo, Minnan School of Computer Science and Technology Xi'an Jiaotong University China SPKLSTN Lab Xi'an Jiaotong University China National Engineering Lab for Big Data Analytics Xi'an Jiaotong University China School of Continuing Education Xi'an Jiaotong University China

Taxation is the material basis for the survival of the country. In order to accelerate tax modernization and facilitate taxpayers to issue value-added tax invoices in a convenient and standardized manner, the State Administration of Taxation requires taxpayers to select the tax classification corresponding to the invoice details before issuing invoices in the tax control system Thus, improving the accuracy of tax classification has a crucial role in the construction of tax risk indicators and analysis of taxpayer behavior characteristics. This paper proposes a classification model based on the Heterogeneous Directed Graph Attention Network (HDGAT). The model significantly improves the accuracy of the tax classification of invoice details by using the directed information among the invoice details and external information. © 2020 China National Conference on Computational Linguistics Published under Creative Commons Attribution 4.0 International License

关键词： Taxation

来源：评论

学校读者我要写书评

暂无评论

Chemically inspired Erdős-Rényi oriented hypergraphs

arXiv

引用

arXiv 2023年

作者： Garcia-Chung, Angel Bermúdez-Montaña, Marisol Stadler, Peter F. Jost, Jürgen Restrepo, Guillermo Tecnológico de Monterrey Escuela de Ingeniería y Ciencias Estado de México52926 Mexico Max Planck Institute for Mathematics in the Sciences Leipzig Germany Interdisciplinary Center for Bioinformatics Universität Leipzig Leipzig Germany Bioinformatics Group Department of Computer Science Universität Leipzig Leipzig Germany Institute for Theoretical Chemistry University of Vienna Vienna Austria The Santa Fe Institute Santa FeNM United States Facultad de Ciencias Universidad Nacional de Colombia Bogotá Colombia Center for Scalable Data Analytics and Artificial Intelligence Universität Leipzig Leipzig Germany School of Applied Sciences and Engineering EAFIT University Medellín Colombia

High-order structures have been recognised as suitable models for systems going beyond the binary relationships for which graph models are appropriate. Despite their importance and surge in research on these structures, their random cases have been only recently become subjects of interest. One of these high-order structures is the oriented hypergraph, which relates couples of subsets of an arbitrary number of vertices. Here we develop the Erdős-Rényi model for oriented hypergraphs, which corresponds to the random realisation of oriented hyperedges of the complete oriented hypergraph. A particular feature of random oriented hypergraphs is that the ratio between their expected number of oriented hyperedges and their expected degree or size is 3/2 for large number of vertices. We highlight the suitability of oriented hypergraphs for modelling large collections of chemical reactions and the importance of random oriented hypergraphs to analyse the unfolding of chemistry. © 2023, CC BY-SA.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Multivariate Analysis on Performance Gaps of Artificial Intelligence Models in Screening Mammography

arXiv

引用

arXiv 2023年

作者： Zhang, Linglin Brown-Mulry, Beatrice Nalla, Vineela Hwang, InChan Gichoya, Judy Wawira Gastounioti, Aimilia Banerjee, Imon Seyyed-Kalantari, Laleh Woo, MinJae Trivedi, Hari School of Data Science and Analytics Kennesaw State University 3391 Town Point Dr NW KennesawGA30144 United States Department of Information Technology Kennesaw State University 1100 South Marietta Pkwy MariettaGA30060 United States Department of Radiology and Imaging Sciences Emory University 1364 E Clifton Rd NE AtlantaGA30322 United States Computational Imaging Research Center Washington University in St. Louis School of Medicine 4525 Scott Avenue St. LouisMO63110 United States Department of Radiology Mayo Clinic Arizona 13400 E Shea Blvd ScottsdaleAZ85259 United States School of Computing and Augmented Intelligence Arizona State University 699 S Mill Ave TempeAZ85281 United States Department of Electrical Engineering and Computer Science York University 4700 Keele St TorontoONM3J 1P3 Canada

Although deep learning models for abnormality classification can perform well in screening mammography, the demographic, imaging, and clinical characteristics associated with increased risk of model failure remain unclear. This retrospective study uses the Emory BrEast Imaging dataset (EMBED) containing mammograms from 115,931 patients imaged at Emory Healthcare between 2013-2020, with Breast Imaging Reporting and data System (BI-RADS) assessment, region of interest coordinates for abnormalities, imaging features, pathologic outcomes, and patient demographics. Multiple deep learning models were trained to distinguish between abnormal tissue patches and randomly selected normal tissue patches from screening mammograms. We assessed model performance by subgroups defined by age, race, pathologic outcome, tissue density, and imaging characteristics and investigated their associations with false negatives and false positives. We also performed multivariate logistic regression to control for confounding between subgroups. The top-performing model, ResNet152V2, achieved accuracy of 92.6% (95%CI=92.0-93.2%), and area under the receiver operating characteristics curve 0.975 (95%CI=0.972-0.978). Before controlling for confounding, nearly all subgroups showed statistically significant differences in model performance. However, after controlling for confounding, we found lower false negative risk associates with Other race (RR=0.828;p= .050), biopsy-proven benign lesions (RR=0.927;p= .011), and mass (RR=0.921;p= .010) or asymmetry (RR=0.854;p= .040);higher false negative risk associates with architectural distortion (RR=1.037;p Copyright © 2023, The Authors. All rights reserved.

关键词： Mammography

来源：评论

学校读者我要写书评

暂无评论

From ancient times to modern: realizing the power of data visualization in healthcare and medicine

引用

Big data analytics 2020年第1期5卷 1-7页

作者： Elgendi, Mohamed Howard, Newton Hussain, Amir Menon, Carlo Ward, Rabab School of Electrical and Computer Engineering University of British Columbia Vancouver Canada Faculty of Medicine University of British Columbia Vancouver Canada School of Mechatronic Systems Engineering Simon Fraser University Burnaby Canada Nuffield Department of Surgical Sciences University of Oxford Oxford UK Data Science and Cyber Analytics Research Group Edinburgh Napier University Edinburgh UK

data visuals (scientific images) display and express various amounts and types of information, and, as the saying goes,“an image is worth 1,000 words.” Based on a review of two studies, a new estimation of how many words an image is actually worth was calculated in an attempt to quantify the complicated biological process of image perception. The result revealed that an image is actually worth more than 30,000 words. This new value estimation provides insight into the power of images. Given that figures, graphs, and data visualizations are types of images commonly used in research and publications, every produced figure is important and must be carefully considered during the publication process.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Non-stationary Multivariate Time Series Forecasting

Deep Learning for Non-stationary Multivariate Time Series Fo...

引用

IEEE International Conference on Big data

作者： Manal Almuammar Maria Fasli School of Computer Science and Electronic Engineering University of Essex Colchester UK School of Computer Science and Electronic Engineering Institute for Analytics and Data Science University of Essex Colchester UK

ISBN: (数字)9781728108582

ISBN: (纸本)9781728108599

Forecasting time series that are generated in dynamic environments is challenging due to the characteristic of these series: data generated at high speed and/or large amounts of data which contain multiple variables, and have complex seasonality. Forecasting real-time availability of parking spaces can lead to all sorts of benefits including user satisfaction, energy savings and more efficient use of parking spaces. In this paper, we explorer using deep Gated Recurrent Units (GRUs) to forecast multivariate time series in parking lots setting. Predicting the parking availability mainly depends on the multiple seasonal patterns exhibited in the parking lots and by the real-time occupancy data. In particular, we use the heterogeneous data streams that generated from a limited number of existing Internet of Things (IoT) devices which monitor different parking lots, to construct the parking availability data. Then, we employ GRUs on the parking data to provide predictions across a variety of parking lots. Using the proposed approach, we have provided the real-time parking availability information for different time intervals in six parking lots at University of Essex. Although the results indicate the efficiency of applying GRUs to forecast the multivariate time series, these results show that the simple Multilayer Perceptron (MLPs) can perform better than the GRUs models.

关键词： Time series analysis Forecasting Predictive models Logic gates Machine learning data models Sensors

来源：评论

学校读者我要写书评

暂无评论

RETRACTED ARTICLE: Continuous Activity-Aware Stress Detection Using Sensors

引用

Wireless Personal Communications 2021年第1期127卷 17-17页

作者： Karthick, T. Sangeetha, M. Ramprasath, M. Ananthajothi, K. Department of Data Science and Business Analytics School of Computing SRM Institue of Science and Technology Chennai India Department of Computer Science and Engineering Misrimal Navajee Munoth Jain Engineering College Chennai India

来源：评论

学校读者我要写书评

暂无评论

Feature Extraction and Classification from Planetary science datasets enabled by Machine Learning

Feature Extraction and Classification from Planetary Science...

引用

IEEE Conference on Aerospace

作者： Conor A. Nixon Zachary Yahn Ethan Duncan Ian Neidel Alyssa C. Mills Benoît Seignovert Andrew Larsen Kathryn Gansler Charles Liles Catherine C. Walker Douglas M. Trent John Santerre Planetary Systems Laboratory NASA Goddard Space Flight Center Greenbelt MD Computer Science Department University of Virginia Charlottesville VA School of Information University of California Berkeley Berkeley CA Yale University Timothy Dwight College New Haven CT Geosciences Department Baylor University Waco TX Nantes Université Laboratoire De Planétologie Et Géosciences Nantes France Business Intelligence Division Inntopia Stowe VT Department of Geology University of Maryland College Park MD NASA Langley Research Center Center Operations Directorate Virginia Department of Applied Ocean Physics and Engineering Woods Hole Oceanographic Institution Massachusetts OCIO Information Data & Analytics Services SAIC | East-2 NASA Langley Research Center Virginia

In this paper we present two examples of recent investigations that we have undertaken, applying Machine Learning (ML) neural networks (NN) to image datasets from outer planet missions to achieve feature recognition. Our first investigation was to recognize ice blocks (also known as rafts, plates, polygons) in the chaos regions of fractured ice on Europa. We used a transfer learning approach, adding and training new layers to an industry-standard Mask R-CNN (Region-based Convolutional Neural Network) to recognize labeled blocks in a training dataset. Subsequently, the updated model was tested against a new dataset, achieving 68% precision. In a different application, we applied the Mask R-CNN to recognize clouds on Titan, again through updated training followed by testing against new data, with a precision of 95% over 369 images. We evaluate the relative successes of our techniques and suggest how training and recognition could be further improved. The new approaches we have used for planetary datasets can further be applied to similar recognition tasks on other planets, including Earth. For imagery of outer planets in particular, the technique holds the possibility of greatly reducing the volume of returned data, via onboard identification of the most interesting image subsets, or by returning only differential data (images where changes have occurred) greatly enhancing the information content of the final data stream.

关键词： Training Earth Image recognition Transfer learning Streaming media Feature extraction Ice

来源：评论

学校读者我要写书评

暂无评论

Meta Mask Correction for Nuclei Segmentation in Histopathological Image

Meta Mask Correction for Nuclei Segmentation in Histopatholo...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jiangbo Shi Chang Jia Zeyu Gao Tieliang Gong Chunbao Wang Chen Li National Engineering Lab for Big Data Analytics Xi’an Jiao tong University Xi’an Shaanxi China School of Computer Science and Technology Xi’an Jiao tong University Xi’an Shaanxi China Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Tech.R&D Xi’an Jiao tong University Xi’an Shaanxi China the First Affiliated Hospital of Xi’an Jiaotong University Xi’an Shaanxi China

ISBN: (纸本)9781665429825

Nuclei segmentation is a fundamental task in digital pathology analysis and can be automated by deep learning-based methods. However, the development of such an automated method requires a large amount of data with precisely annotated masks which is hard to obtain. Training with weakly labeled data is a popular solution for reducing the workload of annotation. In this paper, we propose a novel meta-learning-based nuclei segmentation method which follows the label correction paradigm to leverage data with noisy masks. Specifically, we design a fully conventional meta-model that can correct noisy masks using a small amount of clean meta-data. Then the corrected masks can be used to supervise the training of the segmentation model. Meanwhile, a bi-level optimization method is adopted to alternately update the parameters of the main segmentation model and the meta-model in an end-to-end way. Extensive experimental results on two nuclear segmentation datasets show that our method achieves the state-of-the-art result. It even achieves comparable performance with the model training on supervised data in some noisy settings.

关键词： Training Learning systems Image segmentation Pathology Annotations Biological system modeling Optimization methods

来源：评论

学校读者我要写书评

暂无评论

ZSTAD: Zero-Shot Temporal Activity Detection

ZSTAD: Zero-Shot Temporal Activity Detection

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Lingling Zhang Xiaojun Chang Jun Liu Minnan Luo Sen Wang Zongyuan Ge Alexander Hauptmann School of Computer Science and Technology Xi'an Jiaotong University Xian China Ministry of Education Key Lab For Intelligent Networks and Network Security Xian China Faculty of Information Technology Monash University Australia National Engineering Lab for Big Data Analytics Xi'an Jiaotong University Xian China School of Information Technology and Electrical Engineering The University of Queensland Australia School of Computer Science Carnegie Mellon University USA

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos. Currently, the most effective methods of temporal activity detection are based on deep learning, and they typically perform very well with large scale annotated videos for training. However, these methods are limited in real applications due to the unavailable videos about certain activity classes and the time-consuming data annotation. To solve this challenging problem, we propose a novel task setting called zero-shot temporal activity detection (ZSTAD), where activities that have never been seen in training can still be detected. We design an end-to-end deep network based on R-C3D as the architecture for this solution. The proposed network is optimized with an innovative loss function that considers the embeddings of activity labels and their super-classes while learning the common semantics of seen and unseen activities. Experiments on both the THUMOS'14 and the Charades datasets show promising performance in terms of detecting unseen activities.

关键词： Semantics Proposals Training Task analysis Feature extraction Microsoft Windows Three-dimensional displays

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：