检索结果-内蒙古大学图书馆

Active learning in computational pathology with noise detection empowered by loss-based prior and feature analysis

Biomedical Signal Processing and Control 2025年 108卷

作者： Huang, Yujian Li, Jinyang An, Hui Luo, Tong Ji, Zheyi Song, Yi Liu, Huijun U, Kaicheng Zhang, Sophia Meixuan Zhao, Junhan Ge, Yongxin School of Big Data and Software Engineering Chongqing University Chongqing401331 China College of Computer Science Chongqing University Chongqing401331 China Neurosurgery Department Chongqing University Three Gorges Hospital Chongqing404100 China Harvard College Harvard University Cambridge02138 United States College of Agriculture and Life Sciences Cornell University Ithaca14850 United States Department of Computational Oncology Memorial Sloan Kettering Cancer Center New York City10065 United States Tri-Institutional Computational Biology & Medicine Weill Cornell Medicine New York City10065 United States Department of Biomedical Informatics Harvard Medical School Boston02115 United States Department of Biostatistics Harvard T.H.Chan School of Public Health Boston02115 United States

AI-based histopathological image analysis has significantly advanced the field of computer-aided diagnosis. While labeled data can enhance model performance, manual annotation by pathologists is labor-intensive and time-consuming, with variability and reliance on coarse slide-level annotations often introducing noise. To address these challenges, we propose introduces BPAL (Beta Mixture Model and Penalized Regression for Active Learning), a novel active learning framework for histopathological whole-slide image analysis. BPAL aims to reduce expert annotation costs and mitigate the impact of noisy samples during training by autonomously managing highly informative samples in each active learning iteration. Our approach integrates two noise detection modules into active learning frameworks. By incorporating Penalized Regression (PR) with parallel computation capabilities into our framework, we enhance the efficiency of noisy sample detection. Leveraging a Beta Mixture Model (BMM) with prior loss knowledge further augments this process by enabling a comprehensive analysis from various angles within the merged feature and label spaces. This approach maximizes the utilization of information extracted from pathological image samples, ensuring a robust and thorough assessment of data quality. We propose a heuristic sampling strategy based on these enhancements. High-information samples identified by the module are categorized into three types: typical samples with high confidence levels that can receive pseudo labels for training, difficult samples requiring expert re-annotation due to complex features, and mislabeled noisy samples. The iterative addition of training sets retains high-information samples while mitigating the impact of noisy samples. Comparative evaluations demonstrate the superior performance of our approach on breast cancer and prostate cancer classification tasks. © 2025 Elsevier Ltd

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

Using data Analytics to Forecast Violent Crime

Using Data Analytics to Forecast Violent Crime

引用

International Conference on computational science and computational Intelligence (CSCI)

作者： Herious Cotton Tor A. Kwembe Computational Data Enabled Science and Engineering Jackson State University Jackson MS USA Department of Mathematics and Statistical Sciences Jackson State University Jackson MS USA

ISBN: (纸本)9781665458429

In this paper, we used data analytics to analyze criminal data. Prophet model, LSTM recurrent neural network model, a linear regression model, and traditional neural network model were used to predict homicide and rape in the Southeastern Cities of Memphis Tennessee, Jackson Mississippi, and New Orleans Louisiana. LSTM recurrent neural network model and traditional neural network model have smaller RMSE. Thus, LSTM recurrent neural network model and traditional neural network model performed better than the prophet and linear regression models. These promising outcomes will be significant to scholars, policymakers, and law enforcement officers.

关键词： Recurrent neural networks data analysis Law enforcement Scientific computing Urban areas Linear regression data visualization

来源：评论

学校读者我要写书评

暂无评论

Hierarchical bucket tree: An efficient account structure for blockchain-based system

Hierarchical bucket tree: An efficient account structure for...

引用

作者： Chen, Weili Zheng, Zibin Ma, Mingjie He, Pinjia Zhou, Yuren Bian, Jing School of Data and Computer Science National Engineering Research Center of Digital Life Sun Yat-sen University Guangzhou510006 China Department of Computer Science ETH Zurich Switzerland School of Data and Computer Science Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Computational Science Guangzhou China

Systems built on top of blockchain are often inefficient. One reason for the inefficiency is that these systems include too many hash operations. To address this problem, we conduct an empirical study on the transaction history of a real-world blockchain-based system (i.e., Ethereum), which contains 300,821 accounts and 14,240,095 transactions. We found that the account usage frequency is highly heterogeneous. Based on this finding, this paper presents hierarchy bucket tree (HBT), an efficient account structure with user transaction behaviour information embedded, to reduce the number of hash operations and thus enhance the efficiency of blockchain-based systems. Extensive experiments have been conducted and the experimental results show that HBT reduces hash operations by nearly 80% compared with the existing account structure. Copyright © 2020 Inderscience Enterprises Ltd.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Towards a Quantum Algorithm for the Incompressible Nonlinear Navier-Stokes Equations

Towards a Quantum Algorithm for the Incompressible Nonlinear...

引用

Quantum Computing and engineering (QCE), IEEE International Conference on

作者： Muralikrishnan Gopalakrishnan Meena Yu Zhang Weiwen Jiang Youzuo Lin Stefanie Günther Xinfeng Gao National Center for Computational Sciences Oak Ridge National Laboratory Oak Ridge TN USA Theoretical Division Los Alamos National Laboratory Los Alamos NM USA Department of Electrical and Computer Engineering George Mason University Fairfax VA USA School of Data Science and Society University of North Carolina at Chapel Hill Chapel Hill NC USA Center for Applied Scientific Computing Lawrence Livermore National Laboratory Livermore CA USA Department of Mechanical and Aerospace Engineering University of Virginia Charlottesville VA USA

ISBN: (数字)9798331541378

ISBN: (纸本)9798331541385

In this work, we present novel concepts for quantum algorithms to solve transient, nonlinear partial differential equations (PDEs). The challenge lies in how to effectively represent, encode, process, and evolve the nonlinear system of PDEs on quantum computers. We will discuss the new techniques using the incompressible Navier-Stokes equations as an example, because it represents the fundamental nonlinear feature and yet removes certain complexity in physics, allowing us to focus on the design of quantum algorithms. Previous attempts solving nonlinear PDEs in quantum computation have often involved storing multiple copies of solutions or employing linearizations. Neither is practical due to exponential scaling with evolution time or insufficient solution accuracy. We propose a new framework based on matrix product states (MPSs) and matrix product operators (MPOs), in addition to the Krylov subspace methods. For example, the solution variables of the Navier-Stokes equations are represented by MPSs, and the linear and nonlinear terms are processed by MPOs. The time evolution of the operators is attained by a fast-forwarding algorithm using Krylov subspace methods. Furthermore, we discuss various techniques for efficient encoding of MPSs, measurement reduction for MPOs, and use of tensor operations to treat multi-variate, multi-physics characteristics of Navier-Stokes.

关键词： Computers Quantum algorithm Tensors Fluids Partial differential equations Encoding Transient analysis Nonlinear systems Physics Navier-Stokes equations

来源：评论

学校读者我要写书评

暂无评论

LINSCAN - A Linearity Based Clustering Algorithm

arXiv

引用

arXiv 2024年

作者： Dennehy, Andrew Zou, Xiaoyu Semnani, Shabnam J. Fialko, Yuri Cloninger, Alexander Committee on Computational and Applied Mathematics University of Chicago ChicagoIL United States Institute of Geophysics and Planetary Physics Scripps Institution of Oceanography University of California La Jolla San DiegoCA92093 United States Department of Structural Engineering University of California La Jolla San DiegoCA92093 United States Department of Mathematics Halcioglu Data Science Institute University of California La Jolla San DiegoCA92093 United States

DBSCAN and OPTICS are powerful algorithms for identifying clusters of points in domains where few assumptions can be made about the structure of the data. In this paper, we leverage these strengths and introduce a new algorithm, LINSCAN, designed to seek lineated clusters that are difficult to find and isolate with existing methods. In particular, by embedding points as normal distributions approximating their local neighborhoods and leveraging a distance function derived from the Kullback Leibler Divergence, LINSCAN can detect and distinguish lineated clusters that are spatially close but have orthogonal covariances. We demonstrate how LINSCAN can be applied to seismic data to identify active faults, including intersecting faults, and determine their orientation. Finally, we discuss the properties a generalization of DBSCAN and OPTICS must have in order to retain the stability benefits of these algorithms. © 2024, CC BY.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

A Two-Stage Approach for Segmenting Spatial Point Patterns Applied to Multiplex Imaging

arXiv

引用

arXiv 2024年

作者： Sheng, Alvin Reich, Brian J. Staicu, Ana-Maria Krishnan, Santhoshi N. Rao, Arvind Frankel, Timothy L. Division of Biostatistics and Health Data Science University of Minnesota MinneapolisMN United States Department of Statistics North Carolina State University RaleighNC United States Department of Computational Medicine and Bioinformatics University of Michigan Ann ArborMI United States Department of Electrical and Computer Engineering Rice University HoustonTX United States Department of Biostatistics University of Michigan Ann ArborMI United States Department of Radiation Oncology University of Michigan Ann ArborMI United States Department of Biomedical Engineering University of Michigan Ann ArborMI United States Department of Surgery University of Michigan Ann ArborMI United States

Recent advances in multiplex imaging have enabled researchers to locate different types of cells within a tissue sample. This is especially relevant for tumor immunology, as clinical regimes corresponding to different stages of disease or responses to treatment may manifest as different spatial arrangements of tumor and immune cells. Spatial point pattern modeling can be used to partition multiplex tissue images according to these regimes. To this end, we propose a two-stage approach: first, local intensities and pair correlation functions are estimated from the spatial point pattern of cells within each image, and the pair correlation functions are reduced in dimension via spectral decomposition of the covariance function. Second, the estimates are clustered in a Bayesian hierarchical model with spatially-dependent cluster labels. The clusters correspond to regimes of interest that are present across subjects;the cluster labels segment the spatial point patterns according to those regimes. Through Markov Chain Monte Carlo sampling, we jointly estimate and quantify uncertainty in the cluster assignment and spatial characteristics of each cluster. Simulations demonstrate the performance of the method, and it is applied to a set of multiplex immunofluorescence images of diseased pancreatic tissue. Copyright © 2024, The Authors. All rights reserved.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

A Design of Nested Photonic Crystal Fiber for OAM Mode Propagation 3rd

A Design of Nested Photonic Crystal Fiber for OAM Mode Pro...

引用

3rd International Conference on Intelligent Computing Techniques for Smart Energy Systems, ICTSES 2023

作者： Punia, Sushma Saharia, Ankur Ismail, Yaseera Petruccione, Francesco Bourdine, Anton V. Demidov, Vladimir V. Morozov, Oleg G. Yin, Juan Singh, Ghanshyam Tiwari, Manish Optoelectronics and Photonics Research Lab Department of Electronics and Communication Engineering Manipal University Jaipur Jaipur303007 India Department of Physics Stellenbosch University Stellenbosch7600 South Africa School of Data Science and Computational Thinking Stellenbosch University Stellenbosch7602 South Africa Stellenbosch South Africa Department of Communication Lines Povolzhskiy State University of Telecommunications and Informatics 23 Lev Tolstoy Street Samara Oblast443010 Russia JSC Scientific Production Association State Optical Institute Named after Vavilov S.I. 36/1 Babushkin Street St. Petersburg192171 Russia Department of Photonics and Communication Links Saint Petersburg State University of Telecommunications Named after M.A. Bonch-Bruevich 22 Bolshevikov Avenue St. Petersburg193232 Russia Department of Radiophotonics and Microwave Technologies Kazan National Research State University named after A.N. Tupolev-KAI 10 Karl Marx Street Kazan420111 Russia Division of Quantum Physics and Quantum Information University of Science and Technology of China 99 Xiupu Road Pudong District Shanghai200093 China Department of ECE Malaviya National Institute of Technology Jaipur Jaipur302017 India

ISBN: (纸本)9789819784639

This work is intended to present a nested Photonic Crystal Fiber (PCF) for OAM mode propagation. The proposed PCF comprises of a dense flint SF6 and a very light flint LLF1. The finite-element method (FEM) is used for the modal analysis to obtain propagating HE/EH modes. The proposed fiber has shown flat dispersion during the propagation of multiple orbital angular momentum (OAM) modes. Furthermore, the designed PCF’s nonlinearity (gamma) and confinement loss (CL) are calculated to prove the practical feasibility of the design. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Photonic crystal fibers

来源：评论

学校读者我要写书评

暂无评论

Trapping-influenced photoluminescence intensity decay in semiconductor nanoplatelets 6

Trapping-influenced photoluminescence intensity decay in sem...

引用

6th International Conference on Metamaterials and Nanophotonics, METANANO 2021

作者： Kurilovich, A.A. Mantsevich, V.N. Stevenson, K.J. Chechkin, A.V. Palyulin, V.V. Center for Energy Science and Technology Skolkovo Institute of Science and Technology Moscow121205 Russia Chair of Semiconductors and Cryoelectronics and Quantum Technology Center Physics department Lomonosov Moscow State University Moscow119991 Russia Institute for Physics and Astronomy University of Potsdam Potsdam-GolmD-14476 Germany Akhiezer Institute for Theoretical Physics National Science Center Kharkov Institute of Physics and Technology" Kharkov61108 Ukraine Center for Computational and Data-intensive Science and Engineering Skolkovo Institute of Science and Technology Moscow121205 Russia

We present a diffusion-based simulation model for explanation of long time power-law decay of photoluminescence (PL) emission intensity in semiconductor nanoplatelets. In our model the shape of emission curves is an outcome of interplay of recombination, diffusion and trapping of excitons. At short times the excitons diffuse freely following the normal diffusion behaviour. The emission decay is purely exponential and is defined by recombination. At long times the transition into the subdiffusive motion happens and the emission occurs due to the release of excitons from surface traps. A power-law tail for intensity is a consequence of the release. The crossover from onelimit to another is controlled by diffusion properties. The approach reproduces the properties of experimental curves measured for different nanoplatelet systems. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Excitons

来源：评论

学校读者我要写书评

暂无评论

Generative AI Enables Medical Image Segmentation in Ultra Low-data Regimes

arXiv

引用

arXiv 2024年

作者： Zhang, Li Jindal, Basu Alaa, Ahmed Weinreb, Robert Wilson, David Segal, Eran Zou, James Xie, Pengtao Department of Electrical and Computer Engineering University of California La Jolla San DiegoCA United States Bakar Computational Health Sciences Institute University of California San Francisco San FranciscoCA United States Department of Electrical Engineering and Computer Sciences University of California Berkeley BerkeleyCA United States Hamilton Glaucoma Center Shiley Eye Institute Viterbi Family Department of Ophthalmology University of California La Jolla San DiegoCA United States Division of Pulmonary Allergy and Critical Care Medicine Department of Medicine University of Pittsburgh PittsburghPA United States Department of Computer Science and Applied Mathematics Weizmann Institute of Science Rehovot Israel Department of Molecular Cell Biology Weizmann Institute of Science Rehovot Israel Department of Biomedical Data Science Stanford University School of Medicine StanfordCA United States Department of Computer Science Stanford University StanfordCA United States Department of Medicine University of California La Jolla San DiegoCA United States

Semantic segmentation of medical images is pivotal in applications like disease diagnosis and treatment planning. While deep learning has excelled in automating this task, a major hurdle is the need for numerous annotated segmentation masks, which are resource-intensive to produce due to the required expertise and time. This scenario often leads to ultra low-data regimes, where annotated images are extremely limited, posing significant challenges for the generalization of conventional deep learning methods on test images. To address this, we introduce a generative deep learning framework, which uniquely generates high-quality paired segmentation masks and medical images, serving as auxiliary data for training robust models in data-scarce environments. Unlike traditional generative models that treat data generation and segmentation model training as separate processes, our method employs multi-level optimization for end-to-end data generation. This approach allows segmentation performance to directly influence the data generation process, ensuring that the generated data is specifically tailored to enhance the performance of the segmentation model. Our method demonstrated strong generalization performance across 9 diverse medical image segmentation tasks and on 16 datasets, in ultra-low data regimes, spanning various diseases, organs, and imaging modalities. When applied to various segmentation models, it achieved performance improvements of 10-20% (absolute), in both same-domain and out-of-domain scenarios. Notably, it requires 8 to 20 times less training data than existing methods to achieve comparable results. This advancement significantly improves the feasibility and cost-effectiveness of applying deep learning in medical imaging, particularly in scenarios with limited data availability. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Foundations of symbolic languages for model interpretability 21

Foundations of symbolic languages for model interpretability

引用

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Marcelo Arenas Daniel Baez Pablo Barceló Jorge Pérez Bernardo Subercaseaux Department of Computer Science PUC-Chile and Millennium Institute for Foundational Research on Data Chile Department of Computer Science Universidad de Chile Institute for Mathematical and Computational Engineering PUC-Chile and Millennium Institute for Foundational Research on Data Chile Department of Computer Science Universidad de Chile and Millennium Institute for Foundational Research on Data Chile Millennium Institute for Foundational Research on Data Chile and Carnegie Mellon University

ISBN: (纸本)9781713845393

Several queries and scores have been proposed to explain individual predictions made by ML models. Examples include queries based on "anchors", which are parts of an instance that are sufficient to justify its classification, and "feature-perturbation" scores such as SHAP. Given the need for flexible, reliable, and easy-to-apply interpretability methods for ML models, we foresee the need for developing declarative languages to naturally specify different explainability queries. We do this in a principled way by rooting such a language in a logic called FOIL, that allows for expressing many simple but important explainability queries, and might serve as a core for more expressive interpretability languages. We study the computational complexity of FOIL queries over classes of ML models often deemed to be easily interpretable: decision trees and more general decision diagrams. Since the number of possible inputs for an ML model is exponential in its dimension, tractability of the FOIL evaluation problem is delicate, but can be achieved by either restricting the structure of the models, or the fragment of FOIL being evaluated. We also present a prototype implementation of FOIL wrapped in a high-level declarative language, and perform experiments showing that such a language can be used in practice.

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：