检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Goyal, Manu Marotti, Jonathan D. Workman, Adrienne A. Kuhn, Elaine P. Tooker, Graham M. Ramin, Seth K. Chamberlin, Mary D. diFlorio-Alexander, Roberta M. Hassanpour, Saeed Department of Biomedical Data Science Dartmouth College HanoverNH United States Department of Pathology and Laboratory Medicine Dartmouth Health LebanonNH United States Geisel School of Medicine Dartmouth College HanoverNH United States Department of Radiology Dartmouth Health LebanonNH United States Department of Medicine Dartmouth Health LebanonNH United States Departments of Biomedical Data Science Computer Science and Epidemiology Dartmouth College HanoverNH United States

Breast cancer is the most common malignancy affecting women worldwide and is notable for its morphologic and biologic diversity, with varying risks of recurrence following treatment. The Oncotype DX Breast Recurrence Score test is an important predictive and prognostic genomic assay for estrogen receptor-positive breast cancer that guides therapeutic strategies;however, such tests can be expensive, delay care, and are not widely available. The aim of this study was to develop a multi-model approach integrating the analysis of whole slide images and clinicopathologic data to predict their associated breast cancer recurrence risks and categorize these patients into two risk groups according to the predicted score: low and high risk. The proposed novel methodology uses convolutional neural networks for feature extraction and vision transformers for contextual aggregation, complemented by a logistic regression model that analyzes clinicopathologic data for classification into two risk categories. This method was trained and tested on 993 hematoxylin and eosin-stained whole-slide images of breast cancers with corresponding clinicopathological features that had prior Oncotype DX testing. The model's performance was evaluated using an internal test set of 198 patients from Dartmouth Health and an external test set of 418 patients from the University of Chicago. The multi-model approach achieved an AUC of 0.92 (95% CI: 0.88-0.96) on the internal set and an AUC of 0.85 (95% CI: 0.79-0.90) on the external cohort. These results suggest that with further validation, the proposed methodology could provide an alternative to assist clinicians in personalizing treatment for breast cancer patients and potentially improving their outcomes. © 2024, CC BY.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Optimizing Network Management and Virtualization Using Machine Learning Approach: Network Slice Prediction

Optimizing Network Management and Virtualization Using Machi...

引用

science, Engineering and Business for Sustainable Development Goals (SEB-SDG), International Conference on

作者： Lateef Adesola Akinyemi Olamide Peter Oshinuga Sunday Oladayo Oladejo Stephen Obono Ekwe Mbuyu Sumbwanyanbe Ernest Mnkandla Oluwagbemiga Omotayo Shoewu Departments of Computer Science and Elect. Engineering CSET University of South Africa Johannesburg South Africa Department of Electronic and Computer Engineering Lagos State University Lagos Nigeria School for Data Science and Computational Thinking Stellenbosch University Stellenbosch South Africa Department of Elect. Electronic and Computer Engineering Cape Peninsula University of Technology Cape Town South Africa Department of Electrical Engineering CSET University of South Africa Johannesburg South Africa Department for Computer Science CSET University of South Africa Johannesburg South Africa

ISBN: (数字)9798350358155

ISBN: (纸本)9798350358162

This study demonstrates the utilization of Machine Learning (ML) for network slice prediction, enabling the optimization of resources for diverse network slices. Traditional methods for network slice prediction often lack efficiency and result in inaccuracies. By leveraging ML algorithms such as Naive Bayes and Random Forest, an intelligent framework that automates network slice prediction is developed. This framework enhances network virtualization and management, facilitating resource allocation. The ML algorithms take real-time network conditions and usages, such as packet delay and smart city, as input and output for selecting the most suitable network slice. data analysis is further conducted to reveal the connections between the input parameters and how these parameters influence the selection of the accurate network slice. Network slicing plays a crucial role as it enables the customization of services and facilitates efficient scaling to meet the specific needs of different applications and industries. The accuracy scores of the employed ML algorithms were generally perfect, except for the KNN and SVM classifiers, which achieved an accuracy of 94.30% and 92.16%, respectively, for the prediction of network slices based on incoming network connections and usages.

关键词： Support vector machines Machine learning algorithms Accuracy data analysis Smart cities Network slicing Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

PPI++: Efficient Prediction-Powered Inference

arXiv

引用

arXiv 2023年

作者： Angelopoulos, Anastasios N. Duchi, John C. Zrnic, Tijana Department of Electrical Engineering and Computer Sciences UC Berkeley United States Departments of Statistics and Electrical Engineering Stanford University United States Department of Statistics and Stanford Data Science Stanford University United States

We present PPI++: a computationally lightweight methodology for estimation and inference based on a small labeled dataset and a typically much larger dataset of machine-learning predictions. The methods automatically adapt to the quality of available predictions, yielding easy-to-compute confidence sets—for parameters of any dimensionality—that always improve on classical intervals using only the labeled data. PPI++ builds on prediction-powered inference (PPI), which targets the same problem setting, improving its computational and statistical efficiency. Real and synthetic experiments demonstrate the benefits of the proposed adaptations. Copyright © 2023, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Are Fair Learning To Rank Models Really Fair? An Analysis Using Inferred Gender

Are Fair Learning To Rank Models Really Fair? An Analysis Us...

引用

IEEE MIT Undergraduate Research Technology Conference (URTC)

作者： Alexander Pietrick Alyssa Romportl Shailen Smith Oluseun Olulana Kathleen Cachel Elke Rundensteiner Departments of Computer Science and Data Science Worcester Polytechnic Institute Worcester MA United States Departments of Mathematics and Psychology St. Olaf College Northfield MN United States Department of Mathematics Stony Brook University Stony Brook NY United States Department of Data Science Worcester Polytechnic Institute Worcester MA United States

Fair Learning To Rank (LTR) frameworks require demographic information; however, that information is often unavailable. Inference algorithms may infer the missing demographic information to supply to the fair LTR model. In this study, we analyze the effect of using a trained fair LTR model with uncertain demographic inferences. We show that inferred data results in varying levels of fairness and utility depending on inference accuracy. Specifically, less accurate inferred data adversely affects the rankings’ fairness, while more accurate inferred data creates fairer rankings. Therefore, we recommend that a careful evaluation of demographic inference algorithms before use is critical.

关键词： Analytical models Inference algorithms

来源：评论

学校读者我要写书评

暂无评论

Development of Phylum Chordata Sound Recognition System using Machine Learning and Deep Learning Techniques: A Case Study of Catfish

Development of Phylum Chordata Sound Recognition System usin...

引用

Electrical, computer and Energy Technologies (ICECET), International Conference on

作者： Lateef Adesola Akinyemi Olamide Peter Oshinuga Oluwafikunmi Adegbenga Eshilokun Sunday Oladayo Oladejo Stephen Obono Ekwe Departments of Computer Science and Electrical Engineering CSET University of South Africa Johannesburg South Africa Department of Electronic and Computer Engineering Lagos State University Lagos Nigeria School for Data Science and Computational Thinking Stellenbosch University Stellenbosch South Africa Department of Electrical Electronic and Computer Engineering Cape Peninsula University of Technology Cape Town South Africa

Sound recognition refers to the technology or process of identifying and classifying different sounds or audio signals. This study aims to develop a sound recognition system using machine learning (ML) and deep learning (DL) techniques to classify and identify the gender of catfish based on their speech patterns. The study explores a range of supervised ML and DL algorithms, such as the Artificial Neural Network (ANN), Naïve Bayes (NB), and others, to predict the gender of catfish. The extracted features from the audio signals of the catfish serve as inputs to these algorithms, which produce binary predictions classifying the catfish samples as either male or female. This study further explores data analysis of the audio signals from the male and female catfish. The automated sound recognition system proves to be a more efficient and accurate approach compared to traditional methods, which rely on time-consuming visual observations. Evaluation metrics such as Accuracy, Sensitivity, and more, were employed to gauge the effectiveness of the algorithms in predicting the gender of catfish based on speech patterns. Among the employed algorithms, ANN and NB demonstrate the highest accuracy, achieving a score of 89.47%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Conditional Flow Variational Autoencoder for Controllable Synthesis of Virtual Populations of Anatomy

arXiv

引用

arXiv 2023年

作者： Dou, Haoran Ravikumar, Nishant Frangi, Alejandro F. University of Leeds Leeds United Kingdom Division of Informatics Imaging and Data Science Schools of Computer Science and Health Sciences University of Manchester Manchester United Kingdom Electrical Engineering and Cardiovascular Sciences Departments KU Leuven Leuven Belgium Alan Turing Institute London United Kingdom

The generation of virtual populations (VPs) of anatomy is essential for conducting in silico trials of medical devices. Typically, the generated VP should capture sufficient variability while remaining plausible and should reflect the specific characteristics and demographics of the patients observed in real populations. In several applications, it is desirable to synthesise virtual populations in a controlled manner, where relevant covariates are used to conditionally synthesise virtual populations that fit a specific target population/characteristics. We propose to equip a conditional variational autoencoder (cVAE) with normalising flows to boost the flexibility and complexity of the approximate posterior learnt, leading to enhanced flexibility for controllable synthesis of VPs of anatomical structures. We demonstrate the performance of our conditional flow VAE using a data set of cardiac left ventricles acquired from 2360 patients, with associated demographic information and clinical measurements (used as covariates/conditional information). The results obtained indicate the superiority of the proposed method for conditional synthesis of virtual populations of cardiac left ventricles relative to a cVAE. Conditional synthesis performance was evaluated in terms of generalisation and specificity errors and in terms of the ability to preserve clinically relevant biomarkers in synthesised VPs, that is, the left ventricular blood pool and myocardial volume, relative to the real observed population. © 2023, CC BY.

关键词： Population statistics

来源：评论

学校读者我要写书评

暂无评论

A Dynamic-Static Weighted Network with Diverse-Token Fusion Attention for Rhexis Margin Recognition in Microscopic Surgery

A Dynamic-Static Weighted Network with Diverse-Token Fusion ...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Zhen Li Wen-Qian Yue Gui-Bin Bian Shuai Zhang Wei-Peng Liu Shuo Li School of Electronic and Information Engineering Tongji University Shanghai China Institute of Automation Chinese Academy of Sciences Beijing China School of Health Sciences and Biomedical Engineering Hebei University of Technology Tianjin China School of Artificial Intelligence and Data Science Hebei University of Technology Tianjin China Departments Biomedical Engineering and Computer and Data Science Case Western Reserve University

In microscopic cataract surgery, capsulorhexis is the first, most critical step. However, recognizing the boundary of the rhexis during capsulorhexis is challenging and has rarely been studied due to its intraoperative invisibility, variable shape, and lack of a proprietary labeled dataset, especially in the robot-sssisted surgery. To solve the problems, this paper proposes a creative dynamic boundary recognition solution, which includes a novel segmentation network, DCTNet, and a compensation block. First, the dilated HRNet is designed to constrain the over-compression while maintaining high-resolution representation for better detail preservation. Second, the cascaded transformer block is proposed: The decoupling transformer (DET) is developed to assign dynamic-static weights thus learning the variation pattern for segmented targets decoupling. The coupling transformer(COT) with redistributed embeddings is then developed to fuse diverse-resolution tokens for multi-scale prediction coupling. Moreover, the compensation block compensates for inter-frame movement by key-point registration and recovers a more realistic boundary by a smoothing process. Creatively, we mathematically estimate the uncertainty of framework to eliminate the misidentifications due to aleatoric uncertainty in data. Finally, to evaluate the proposed framework, we establish the first known capsulorhexis dataset, CapSeg. Our proposed DCTNet achieves superior performance to state-of-the-art networks with a lower computational cost, and the feasibility experiment shows its great potential in medical surgical robot.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Nonconvex Factorization and Manifold Formulations are Almost Equivalent in Low-rank Matrix Optimization

arXiv

引用

arXiv 2021年

作者： Luo, Yuetian Li, Xudong Zhang, Anru R. Data Science Institute University of Chicago United States School of Data Science Fudan University China Departments of Biostatistics & Bioinformatics Computer Science Electrical & Computer Engineering Mathematics and Statistical Science Duke University United States

In this paper, we consider the geometric landscape connection of the widely studied manifold and factorization formulations in low-rank positive semidefinite (PSD) and general matrix optimization. We establish a sandwich relation on the spectrum of Riemannian and Euclidean Hessians at first-order stationary points (FOSPs). As a result of that, we obtain an equivalence on the set of FOSPs, second-order stationary points (SOSPs), and strict saddles between the manifold and the factorization formulations. In addition, we show the sandwich relation can be used to transfer more quantitative geometric properties from one formulation to another. Similarities and differences in the landscape connection under the PSD case and the general case are discussed. To the best of our knowledge, this is the first geometric landscape connection between the manifold and the factorization formulations for handling rank constraints, and it provides a geometric explanation for the similar empirical performance of factorization and manifold approaches in low-rank matrix optimization observed in the literature. In the general low-rank matrix optimization, the landscape connection of two factorization formulations (unregularized and regularized ones) is also provided. By applying these geometric landscape connections, in particular, the sandwich relation, we are able to solve unanswered questions in literature and establish stronger results in the applications on geometric analysis of phase retrieval, well-conditioned low-rank matrix optimization, and the role of regularization in factorization arising from machine learning and signal processing. © 2021, CC BY-SA.

关键词： Matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Learning in Diffusion Models for Generating Cerebral Aneurysm Geometries

Few-Shot Learning in Diffusion Models for Generating Cerebra...

引用

IEEE International Symposium on Biomedical Imaging

作者： Yash Deo Fengming Lin Haoran Dou Nina Cheng Nishant Ravikumar Alejandro F Frangi Toni Lassila CISTIB University of Leeds Leeds UK NIHR Leeds Biomedical Research Centre Leeds UK Alan Turing Institute London UK Electrical Engineering and Cardiovascular Sciences Departments Medical Imaging Research Center (MIRC) KU Leuven Leuven Division of Informatics Imaging and Data Science Schools of Computer Science and Health Sciences University of Manchester Manchester UK

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

The study of brain vessel pathologies is critical for the advancement o f neurovascular medicine, yet researchers often face significant hurdles due to the scarcity of imaging data for certain uncommon types of aneurysms. Generative deep learning models have been proposed to address the lack of high-quality labeled medical images - however, the shortage of data also presents a unique challenge in training generative models. To address this issue, our work explores the efficacy of training latent diffusion models (LDMs) with few-shot learning, enabling the generation of detailed vessel segmentations from as few as five images per class. By incorporating set-based vision transformers for class embeddings and leveraging signed distance functions (SDFs) as a novel form of conditioning, our method reduces the need for extensive datasets for training. Comparative studies with established generative models, including variational autoencoders (VAEs) and generative adversarial networks (GANs), highlight the robustness of our approach. Our model not only successfully generates high-quality segmentations of brain vessels with aneurysms but also significantly outperforms the standard generative models.

关键词： Training Image segmentation Biological system modeling Aneurysm Brain modeling Diffusion models Transformers

来源：评论

学校读者我要写书评

暂无评论

Learn to match with no regret: reinforcement learning in Markov matching markets 22

Learn to match with no regret: reinforcement learning in Mar...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Yifei Min Tianhao Wang Ruitu Xu Zhaoran Wang Michael I. Jordan Zhuoran Yang Department of Statistics and Data Science Yale University New Haven CT Departments of Industrial Engineering and Management Sciences Northwestern University Evanston IL Department of Electrical Engineering and Computer Science University of California Berkeley CA

ISBN: (纸本)9781713871088

We study a Markov matching market involving a planner and a set of strategic agents on the two sides of the market. At each step, the agents are presented with a dynamical context, where the contexts determine the utilities. The planner controls the transition of the contexts to maximize the cumulative social welfare, while the agents aim to find a myopic stable matching at each step. Such a setting captures a range of applications including ridesharing platforms. We formalize the problem by proposing a reinforcement learning framework that integrates optimistic value iteration with maximum weight matching. The proposed algorithm addresses the coupled challenges of sequential exploration, matching stability, and function approximation. We prove that the algorithm achieves sublinear regret.

关键词：

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：