检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Bortsova, Gerda Bos, Daniel Dubost, Florian Vernooij, Meike W. Ikram, M. Kamran van Tulder, Gijs de Bruijne, Marleen Biomedical Imaging Group Rotterdam Department of Radiology and Nuclear Medicine Erasmus MC Rotterdam Netherlands Department of Epidemiology Erasmus MC Rotterdam Netherlands Department of Biomedical Data Science Stanford University United States Department of Radiology and Nuclear Medicine Erasmus MC Rotterdam Netherlands Faculty of Science Radboud University Netherlands Machine Learning Section Department of Computer Science University of Copenhagen Copenhagen Denmark

Purpose To develop and evaluate a fully-automated deep-learning-based method for assessment of intracranial carotid artery calcification (ICAC). Methods This was a secondary analysis of prospectively collected data from the Rotterdam study (2003-2006) to develop and validate a deep-learning-based method for automated ICAC delineation and volume measurement. Two observers manually delineated ICAC in non-contrast CT scans of 2,319 participants (mean age 69 ± 7 years;1154 women [53.2%]) and a deep learning model was trained to segment ICAC and quantify its volume. Model performance was assessed by comparing manual and automated segmentations and volume measurements to those produced by an independent observer (available in 47 scans), comparing the segmentation accuracy in a blinded qualitative visual comparison by an expert observer, and comparing the association with first stroke incidence from the scan date until 2016. All method performance metrics were computed using 10-fold cross-validation. Results The automated delineation of ICAC reached sensitivity of 83.8% and positive predictive value (PPV) of 88%. The intraclass correlation between automatic and manual ICAC volume measures was 0.98 (95% CI: 0.97, 0.98;computed in the entire dataset). Measured between the assessments of independent observers, sensitivity was 73.9%, PPV was 89.5%, and intraclass correlation was 0.91 (95% CI: 0.84, 0.95;computed in the 47-scan subset). In the blinded visual comparisons of 294 regions, automated delineations were judged as more accurate than manual delineations in 131 regions, less accurate in 94 regions, and equally accurate in the rest of the regions (131 of 225;58.2%;P =.01). The association of ICAC volume with incident stroke was similarly strong for both automated (hazard ratio, 1.38 [95% CI: 1.12, 1.75] and manually measured volumes (hazard ratio, 1.48 [95% CI: 1.20, 1.87]). Conclusions The developed model was capable of automated segmentation and volume quantification of

关键词： Biomineralization

来源：评论

学校读者我要写书评

暂无评论

Accurate machine Learned Quantum-Mechanical Force Fields for Biomolecular Simulations

arXiv

引用

arXiv 2022年

作者： Unke, Oliver T. Stöhr, Martin Ganscha, Stefan Unterthiner, Thomas Maennel, Hartmut Kashubin, Sergii Ahlin, Daniel Gastegger, Michael Sandonas, Leonardo Medrano Tkatchenko, Alexandre Müller, Klaus-Robert Google Research Brain Team Machine Learning Group Technische Universität Berlin Berlin10587 Germany Technische Universität Berlin Berlin10623 Germany Department of Physics and Materials Science University of Luxembourg Luxembourg CityL-1511 Luxembourg BASLEARN TU Berlin Berlin10587 Germany BASF Joint Lab for Machine Learning Technische Universität Berlin Berlin10587 Germany Department of Artificial Intelligence Korea University Anam-dong Seongbuk-gu Seoul02841 Korea Republic of Max Planck Institute for Informatics Stuhlsatzenhausweg Saarbrücken66123 Germany BIFOLD Berlin Institute for the Foundations of Learning and Data Berlin Germany

Molecular dynamics (MD) simulations allow atomistic insights into chemical and biological processes. Accurate MD simulations require computationally demanding quantum-mechanical calculations, being practically limited to short timescales and few atoms. For larger systems, efficient, but much less reliable empirical force fields are used. Recently, machine learned force fields (MLFFs) emerged as an alternative means to execute MD simulations, offering similar accuracy as ab initio methods at orders-of-magnitude speedup. Until now, MLFFs mainly capture short-range interactions in small molecules or periodic materials, due to the increased complexity of constructing models and obtaining reliable reference data for large molecules, where long-ranged many-body effects become important. This work proposes a general approach to constructing accurate MLFFs for large-scale molecular simulations (GEMS) by training on "bottom-up" and "top-down" molecular fragments of varying size, from which the relevant physicochemical interactions can be learned. GEMS is applied to study the dynamics of alanine-based peptides and the 46-residue protein crambin in aqueous solution, allowing nanosecond-scale MD simulations of >25k atoms at essentially ab initio quality. Our findings suggest that structural motifs in peptides and proteins are more flexible than previously thought, indicating that simulations at ab initio accuracy might be necessary to understand dynamic biomolecular processes such as protein (mis)folding, drug–protein binding, or allosteric regulation. Copyright © 2022, The Authors. All rights reserved.

关键词： Molecular dynamics

来源：评论

学校读者我要写书评

暂无评论

What is the best data augmentation approach for brain tumor segmentation using 3D U-Net?

arXiv

引用

arXiv 2020年

作者： Cirillo, Marco Domenico Abramian, David Eklund, Anders Division of Medical Informatics Department of Biomedical Engineering Division of Statistics & Machine Learning Department of Computer and Information Science Linköping University Sweden

Training segmentation networks requires large annotated datasets, which in medical imaging can be hard to obtain. Despite this fact, data augmentation has in our opinion not been fully explored for brain tumor segmentation (a possible explanation is that the number of training subjects (369) is rather large in the BraTS 2020 dataset). Here we apply different types of data augmentation (flipping, rotation, scaling, brightness adjustment, elastic deformation) when training a standard 3D U-Net, and demonstrate that augmentation significantly improves performance on the validation set (125 subjects) in many cases. Our conclusion is that brightness augmentation and elastic deformation works best, and that combinations of different augmentation techniques do not provide further improvement compared to only using one augmentation technique. Our code is available at https://***/mdciri/augmentation. © 2020, CC-BY.

关键词： Elastic deformation

来源：评论

学校读者我要写书评

暂无评论

Efficient dataset generation for machine learning halide perovskite alloys

引用

Physical Review Materials 2025年第5期9卷 053802-053802页

作者： Henrietta Homm Jarno Laakso Patrick Rinke Department of Applied Physics Aalto University 00076 Aalto Finland Physics Department Technical University of Munich Garching Germany Atomistic Modelling Center Munich Data Science Institute Technical University of Munich Garching Germany Munich Center for Machine Learning (MCML) Munich Germany

Lead-based perovskite solar cells have reached high efficiencies, but toxicity and lack of stability hinder their wide-scale adoption. These issues have been partially addressed through compositional engineering of perovskite materials, but the vast complexity of the perovskite materials space poses a significant obstacle to exploration. We previously demonstrated how machine learning (ML) can accelerate property predictions for the CsPb(Cl/Br)3 perovskite alloy. However, the substantial computational demand of density functional theory (DFT) calculations required for model training prevents applications to more complex materials. Here, we introduce a data-efficient scheme to facilitate model training, validated initially on CsPb(Cl/Br)3 data and extended to the ternary alloy CsSn(Cl/Br/I)3. Our approach employs clustering to construct a compact yet diverse initial dataset of atomic structures. We then apply a two-stage active learning approach to first improve the reliability of the ML-based structure relaxations and then refine accuracy near equilibrium structures. Tests for CsPb(Cl/Br)3 demonstrate that our scheme reduces the number of required DFT calculations during the different parts of our proposed model training method by up to 20% and 50%. The fitted model for CsSn(Cl/Br/I)3 is robust and highly accurate, evidenced by the convergence of all ML-based structure relaxations in our tests and an average relaxation error of only 0.5 meV/atom.

关键词： Ternary alloys

来源：评论

学校读者我要写书评

暂无评论

Multi-Task learning for Sparsity Pattern Heterogeneity: Statistical and Computational Perspectives

arXiv

引用

arXiv 2022年

作者： Behdin, Kayhan Loewinger, Gabriel Kishida, Kenneth T. Parmigiani, Giovanni Mazumder, Rahul MIT Operations Research Center CambridgeMA United States Machine Learning Team National Institute on Mental Health BethesdaMD United States Department of Physiology and Pharmacology Department of Neurosurgery Wake Forest School of Medicine Winston SalemNC United States Department of Biostatistics Harvard School of Public Health BostonMA United States Department of Data Science Dana Farber Cancer Institute BostonMA United States MIT Sloan Schools of Management CambridgeMA United States

We consider a problem in Multi-Task learning (MTL) where multiple linear models are jointly trained on a collection of datasets ("tasks"). A key novelty of our framework is that it allows the sparsity pattern of regression coefficients and the values of non-zero coefficients to differ across tasks while still leveraging partially shared structure. Our methods encourage models to share information across tasks through separately encouraging 1) coefficient supports, and/or 2) nonzero coefficient values to be similar. This allows models to borrow strength during variable selection even when non-zero coefficient values differ across tasks. We propose a novel mixed-integer programming formulation for our estimator. We develop custom scalable algorithms based on block coordinate descent and combinatorial local search to obtain high-quality (approximate) solutions for our estimator. Additionally, we propose a novel exact optimization algorithm to obtain globally optimal solutions. We investigate the theoretical properties of our estimators. We formally show how our estimators leverage the shared support information across tasks to achieve better variable selection performance. We evaluate the performance of our methods in simulations and two biomedical applications. Our proposed approaches appear to outperform other sparse MTL methods in variable selection and prediction accuracy. We provide the sMTL package on CRAN. Copyright © 2022, The Authors. All rights reserved.

关键词： Linearization

来源：评论

学校读者我要写书评

暂无评论

BUILDING machine learning LIMITED AREA MODELS: KILOMETER-SCALE WEATHER FORECASTING IN REALISTIC SETTINGS

arXiv

引用

arXiv 2025年

作者： Adamov, Simon Oskarsson, Joel Denby, Leif Landelius, Tomas Hintz, Kasper Christiansen, Simon Schicker, Irene Osuna, Carlos Lindsten, Fredrik Fuhrer, Oliver Schemm, Sebastian Federal Office for Meteorology and Climatology MeteoSwiss Institute of Atmospheric and Climate Science Department of Environmental Science ETH Zurich Switzerland Division of Statistics and Machine Learning Department of Computer and Information Science Linköping University Sweden Danish Meteorological Institute Swedish Meteorological and Hydrological Institute Sweden GeoSphere Austria Department of Applied Mathematics and Theoretical Physics University of Cambridge Cambridge United Kingdom

machine learning is revolutionizing global weather forecasting, with models that efficiently produce highly accurate forecasts. Apart from global forecasting there is also a large value in high-resolution regional weather forecasts, focusing on accurate simulations of the atmosphere for a limited area. Initial attempts have been made to use machine learning for such limited area scenarios, but these experiments do not consider realistic forecasting settings and do not investigate the many design choices involved. We present a framework for building kilometer-scale machine learning limited area models with boundary conditions imposed through a flexible boundary forcing method. This enables boundary conditions defined either from reanalysis or operational forecast data. Our approach employs specialized graph constructions with rectangular and triangular meshes, along with multi-step rollout training strategies to improve temporal consistency. We perform systematic evaluation of different design choices, including the boundary width, graph construction and boundary forcing integration. Models are evaluated across both a Danish and a Swiss domain, two regions that exhibit different orographical characteristics. Verification is performed against both gridded analysis data and in-situ observations, including a case study for the storm Ciara in February 2020. Both models achieve skillful predictions across a wide range of variables, with our Swiss model outperforming the numerical weather prediction baseline for key surface variables. With their substantially lower computational cost, our findings demonstrate great potential for machine learning limited area models in the future of regional weather forecasting. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Understanding telecom customer churn with machine learning: From prediction to causal inference 31st

Understanding telecom customer churn with machine learning: ...

引用

31st Benelux Conference on Artificial Intelligence and the 28th Belgian Dutch Conference on machine learning, BNAIC/BENELEARN 2019

作者： Verhelst, Théo Caelen, Olivier Dewitte, Jean-Christophe Lebichot, Bertrand Bontempi, Gianluca Machine Learning Group Computer Science Department Université Libre de Bruxelles Brussels Belgium Data Science Team Orange Belgium

ISBN: (纸本)9783030651534

Telecommunication companies are evolving in a highly competitive market where attracting new customers is much more expensive than retaining existing ones. Though retention campaigns may be used to prevent customer churn, their success depends on the availability of accurate prediction models. Churn prediction is notoriously a difficult problem because of the large amount of data, non-linearity, imbalance and low separability between the classes of churners and non-churners. In this paper, we discuss a real case of churn prediction based on Orange Belgium customer data. In the first part of the paper we focus on the design of an accurate prediction model. The large class imbalance between the two classes is handled with the EasyEnsemble algorithm using a random forest classifier. We assess also the impact of different data preprocessing techniques including feature selection and engineering. Results show that feature selection can be used to reduce computation time and memory requirements, though engineering variables does not necessarily improve performance. In the second part of the paper we explore the application of data-driven causal inference, which aims to infer causal relationships between variables from observational data. We conclude that the bill shock and the wrong tariff plan positioning are putative causes of churn. This is supported by the prior knowledge of experts at Orange Belgium. Finally, we present a novel method to evaluate, in terms of the direction and magnitude, the impact of causally relevant variables on churn, making the assumption of no confounding factors. © 2020, Springer Nature Switzerland AG.

关键词： Big data Causal inference Churn prediction machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep CNN: A machine learning approach for driver drowsiness detection based on eye state

引用

Revue d'Intelligence Artificielle 2019年第6期33卷 461-466页

作者： Reddy Chirra, Venkata Rami Uyyala, Srinivasulu Reddy Kishore Kolli, Venkata Krishna Department of Computer Applications National Institute of Technology Tiruchirappalli620015 India Machine Learning and Data Analytics Lab Department of Computer Applications National Institute of Technology Tiruchirappalli620015 India Department of Computer Science and Engineering VFSTR Guntur522213 India

Driver drowsiness is one of the reasons for large number of road accidents these days. With the advancement in Computer Vision technologies, smart/intelligent cameras are developed to identify drowsiness in drivers, thereby alerting drivers which in turn reduce accidents when they are in fatigue. In this work, a new framework is proposed using deep learning to detect driver drowsiness based on Eye state while driving the vehicle. To detect the face and extract the eye region from the face images, Viola-Jones face detection algorithm is used in this work. Stacked deep convolution neural network is developed to extract features from dynamically identified key frames from camera sequences and used for learning phase. A SoftMax layer in CNN classifier is used to classify the driver as sleep or non-sleep. This system alerts driver with an alarm when the driver is in sleepy mood. The proposed work is evaluated on a collected dataset and shows better accuracy with 96.42% when compared with traditional CNN. The limitation of traditional CNN such as pose accuracy in regression is overcome with the proposed Staked Deep CNN. © 2019 Lavoisier. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Florid – a Nationwide Identification Service for Plants from Photos and Habitat Information

SSRN

引用

SSRN 2024年

作者： Brun, Philipp de Witte, Lucienne Popp, Manuel Richard Zurell, Damaris Karger, Dirk Nikolaus Descombes, Patrice de Lutio, Riccardo Wegner, Jan Dirk Bornand, Christophe Eggenberg, Stefan Olevski, Tasko Zimmermann, Niklaus E. Swiss Federal Research Institute WSL Birmensdorf8903 Switzerland Musée et jardins botaniques cantonaux Lausanne1007 Switzerland Institute of Biochemistry and Biology University of Potsdam Potsdam14469 Germany EcoVision Lab Photogrammetry and Remote Sensing ETH Zurich Zürich8092 Switzerland Department of Mathematical Modeling and Machine Learning University of Zurich Zürich8057 Switzerland InfoFlora Switzerland Bern3013 Switzerland Swiss Data Science Center ETH Zurich Zürich8092 Switzerland University of Basel Switzerland

Citizen science has become key to biodiversity monitoring but critically depends on accurate quality control that is scalable and tailored to the focal region. We developed FlorID, a free-to-use identification service for all native and many non-native plants of Switzerland. FlorID can identify >3000 species, using vision transformers trained on 1.5M photos, and ecological predictions from multilayer perceptrons, trained on 6.7M occurrence observations and 20 high-resolution environmental variables. Embedded in a free-to-use application programming interface, FlorID can be accessed directly, via webservice, and via FlorApp smartphone application. If multiple images and spatiotemporal location are available, FlorID correctly identifies 93% of field observations and has a top-5 accuracy of 99%. Ecological predictions boost identification success especially for native species with distinct distributions. By evaluating information on appearance and fine-grained ecology, FlorID is a blueprint for similar solutions targeting different taxa or regions, and a basis for developments like automated community inventories. © 2024, The Authors. All rights reserved.

关键词： Blueprints

来源：评论

学校读者我要写书评

暂无评论

A three-dimensional dual-domain deep network for high-pitch and sparse helical CT reconstruction

arXiv

引用

arXiv 2022年

作者： Wang, Wei Xia, Xiang-Gen He, Chuanjiang Ren, Zemin Lu, Jian The School of Biomedical Engineering Shenzhen University Shenzhen China The Department of Electrical and Computer Engineering University of Delaware NewarkDE19716 United States The College of Mathematics and Statistics Chongqing University Chongqing China The College of Mathematics and Physics Chongqing University of Science and Technology Chongqing China The Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University Shenzhen China

In this paper, we propose a new GPU implementation of the Katsevich algorithm for helical CT reconstruction. Our implementation divides the sinograms and reconstructs the CT images pitch by pitch. By utilizing the periodic properties of the parameters of the Katsevich algorithm, our method only needs to calculate these parameters once for all the pitches and so has lower GPU-memory burdens and is very suitable for deep learning. By embedding our implementation into the network, we propose an end-to-end deep network for the high pitch helical CT reconstruction with sparse detectors. Since our network utilizes the features extracted from both sinograms and CT images, it can simultaneously reduce the streak artifacts caused by the sparsity of sinograms and preserve fine details in the CT images. Experiments show that our network outperforms the related methods both in subjective and objective evaluations. Copyright © 2022, The Authors. All rights reserved.

关键词： Computerized tomography

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：