检索结果-内蒙古大学图书馆

Predicting neurological outcome in comatose patients after cardiac arrest with multiscale deep neural networks

Resuscitation 2021年第0期169卷 86-94页

作者： Zheng, Wei-Long Amorim, Edilberto Jing, Jin Ge, Wendong Hong, Shenda Wu, Ona Ghassemi, Mohammad Lee, Jong Woo Sivaraju, Adithya Pang, Trudy Herman, Susan T. Gaspard, Nicolas Ruijter, Barry J. Sun, Jimeng Tjepkema-Cloostermans, Marleen C. Hofmeijer, Jeannette van Putten, Michel J.A.M. Westover, M. Brandon Department of Neurology Massachusetts General Hospital Harvard Medical School Boston MA United States Department of Neurology University of California San Francisco San Francisco CA United States Department of Computer Science University of Illinois at Urbana Champaign Champaign IL United States Department of Radiology Massachusetts General Hospital Harvard Medical School Boston MA United States Department of Computer Science and Engineering Michigan State University East Lansing MI United States Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge MA United States Department of Neurology Brigham and Women's Hospital Boston MA United States Department of Neurology Yale School of Medicine New Haven CT United States Department of Neurology Beth Israel Deaconess Medical Center Boston MA United States Barrow Neurological Institute Phoenix AZ United States Department of Neurology Université Libre de Bruxelles Brussels Belgium Department of Clinical Neurophysiology University of Twente Enschede Netherlands Departments of Neurology and Clinical Neurophysiology Medisch Spectrum Twente Enschede Netherlands Department of Neurology Rijnstate Hospital Arnhem Netherlands

Objective: Electroencephalography (EEG) is an important tool for neurological outcome prediction after cardiac arrest. However, the complexity of continuous EEG data limits timely and accurate interpretation by clinicians. We develop a deep neural network (DNN) model to leverage complex EEG trends for early and accurate assessment of cardiac arrest coma recovery likelihood. Methods: We developed a multiscale DNN combining convolutional neural networks (CNN) and recurrent neural networks (long short-term memory [LSTM]) using EEG and demographic information (age, gender, shockable rhythm) from a multicenter cohort of 1,038 cardiac arrest patients. The CNN learns EEG feature representations while the multiscale LSTM captures short-term and long-term EEG dynamics on multiple time scales. Poor outcome is defined as a Cerebral Performance Category (CPC) score of 3-5 and good outcome as CPC score 1-2 at 3-6 months after cardiac arrest. Performance is evaluated using area under the receiver operating characteristic curve (AUC) and calibration error. Results: Model performance increased with EEG duration, with AUC increasing from 0.83 (95% Confidence Interval [CI] 0.79-0.87 at 12h to 0.91 (95%CI 0.88-0.93) at 66h. Sensitivity of good and poor outcome prediction was 77% and 75% at a specificity of 90%, respectively. Sensitivity of poor outcome was 50% at a specificity of 99%. Predicted probability was well matched to the observation frequency of poor outcomes, with a calibration error of 0.11 [0.09-0.14]. Conclusions: These results demonstrate that incorporating EEG evolution over time improves the accuracy of neurologic outcome prediction for patients with coma after cardiac arrest. © 2021 Elsevier B.V.

关键词： Cardiac arrest Deep learning EEG Machine learning Neurological outcome

来源：评论

学校读者我要写书评

暂无评论

Learning how to dynamically route autonomous vehicles on shared roads

arXiv

引用

arXiv 2019年

作者： Lazar, Daniel A. Bıyık, Erdem Sadigh, Dorsa Pedarsani, Ramtin Department of Electrical and Computer Engineering UC Santa Barbara Department of Electrical Engineering Stanford University Departments of Computer Science and Electrical Engineering Stanford University

Road congestion induces significant costs across the world, and road network disturbances, such as traffic accidents, can cause highly congested traffic patterns. If a planner had control over the routing of all vehicles in the network, they could easily reverse this effect. In a more realistic scenario, we consider a planner that controls autonomous cars, which are a fraction of all present cars. We study a dynamic routing game, in which the route choices of autonomous cars can be controlled and the human drivers react selfishly and dynamically. As the problem is prohibitively large, we use deep reinforcement learning to learn a policy for controlling the autonomous vehicles. This policy indirectly influences human drivers to route themselves in such a way that minimizes congestion on the network. To gauge the effectiveness of our learned policies, we establish theoretical results characterizing equilibria and empirically compare the learned policy results with best possible equilibria. We prove properties of equilibria on parallel roads and provide a polynomial-time optimization for computing the most efficient equilibrium. Moreover, we show that in the absence of these policies, high demand and network perturbations would result in large congestion, whereas using the policy greatly decreases the travel times by minimizing the congestion. To the best of our knowledge, this is the first work that employs deep reinforcement learning to reduce congestion by indirectly influencing humans’ routing decisions in mixed-autonomy traffic. Copyright © 2019, The Authors. All rights reserved.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

From 2015 to 2023: How Machine Learning Aids Natural Product Analysis

arXiv

引用

arXiv 2024年

作者： Shi, Suwen Huang, Ziwei Gu, Xingxin Lin, Xu Zhong, Chaoying Hang, Junjie Lin, Jianli Zhong, Claire Chenwen Zhang, Lin Li, Yu Huang, Junjie Department of Chemistry Boston University BostonMA02215 United States Department of Physics Boston University BostonMA02215 United States College of Professional Studies Northeastern University BostonMA02215 United States Department of Thoracic Surgery The First Affiliated Hospital School of Medicine Zhejiang University Zhejiang Hangzhou China Department of Electrical Engineering and Automation Guangdong Ocean University Guangdong China Cancer Hospital & Shenzhen Hospital Chinese Academy of Medical Sciences Peking Union Medical College Guangdong China Peking-Tsinghua Center for Life Sciences Academy for Advanced Interdisciplinary Studies Peking University Beijing China The Jockey Club School of Public Health and Primary Care Faculty of Medicine The Chinese University of Hong Kong Hong Kong Suzhou Industrial Park Monash Research Institute of Science and Technology Suzhou China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong

In recent years, conventional chemistry techniques have faced significant challenges due to their inherent limitations, struggling to cope with the increasing complexity and volume of data generated in contemporary research endeavors. Computational methodologies represent robust tools in the field of chemistry, offering the capacity to harness potent machine-learning models to yield insightful analytical outcomes. This review delves into the spectrum of computational strategies available for natural product analysis and constructs a research framework for investigating both qualitative and quantitative chemistry problems. Our objective is to present a novel perspective on the symbiosis of machine learning and chemistry, with the potential to catalyze a transformation in the field of natural product analysis. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning collision-free space detection from stereo images: Homography matrix brings better data augmentation

arXiv

引用

arXiv 2020年

作者： Fan, Rui Wang, Hengli Cai, Peide Wu, Jin Bocus, Mohammud Junaid Qiao, Lei Liu, Ming Department of Computer Science and Engineering Department of Ophthalmology University of California San Diego San DiegoCA92093 United States Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Department of Electrical and Electronic Engineering University of Bristol BS8 1UB United Kingdom State Key Laboratory of Ocean Engineering School of Naval Architecture Ocean and Civil Engineering Shanghai Jiao Tong University Shanghai200240 China

Collision-free space detection is a critical component of autonomous vehicle perception. The state-of-the-art algorithms are typically based on supervised deep learning. Their performance is dependent on the quality and amount of labeled training data. It remains an open challenge to train deep convolutional neural networks (DCNNs) using only a small quantity of training samples. Therefore, in this paper, we mainly explore an effective training data augmentation approach that can be employed to improve the overall DCNN performance, when additional images captured from different views are available. Due to the fact that the pixels in collision-free space (generally regarded as a planar surface) between two images, captured from different views, can be associated using a homography matrix, the target image can be transformed into the reference view. This provides a simple but effective way to generate training data from additional multi-view images. Extensive experimental results, conducted with six state-of-the-art semantic segmentation DCNNs on three datasets, validate the effectiveness of the proposed method for enhancing collision-free space detection performance. When validated on the KITTI road benchmark, our approach provides the best results, compared with other state-of-the-art stereo vision-based collision-free space detection approaches. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Improved List-Decodability of Reed-Solomon Codes via Tree Packings

arXiv

引用

arXiv 2020年

作者： Guo, Zeyu Li, Ray Shangguan, Chong Tamo, Itzhak Wootters, Mary Department of Computer Science UT Austin United States Department of Computer Science Stanford University United States Research Center for Mathematics and Interdisciplinary Sciences Shandong University Qingdao266237 China Frontiers Science Center for Nonlinear Expectations Ministry of Education Qingdao266237 China Department of Electrical Engineering - Systems Tel Aviv University Departments of Computer Science and Electrical Engineering Stanford University United States

This paper shows that there exist Reed–Solomon (RS) codes, over exponentially large finite fields in the code length, that are combinatorially list-decodable well beyond the Johnson radius, in fact almost achieving the list-decoding capacity. In particular, we show that for any Ε ∈ (0, 1] there exist RS codes with rate Ω(log(1Ε/Ε)+1 ) that are list-decodable from radius of 1 − Ε. We generalize this result to list-recovery, showing that there exist (1 − Ε, , O(/Ε))-list-recoverable RS codes with rate Ω (formula presented) . Along the way we use our techniques to give a new proof of a result of Blackburn on optimal linear perfect hash matrices, and strengthen it to obtain a construction of strongly perfect hash matrices. To derive the results in this paper we show a surprising connection of the above problems to graph theory, and in particular to the tree packing theorem of Nash-Williams and Tutte. We also state a new conjecture that generalizes the tree-packing theorem to hypergraphs, and show that if this conjecture holds, then there would exist RS codes that are optimally (non-asymptotically) list-decodable. Copyright © 2020, The Authors. All rights reserved.

关键词： Reed-Solomon codes

来源：评论

学校读者我要写书评

暂无评论

Universal linguistic inductive biases via meta-learning

arXiv

引用

arXiv 2020年

作者： McCoy, R. Thomas Grant, Erin Smolensky, Paul Griffiths, Thomas L. Linzen, Tal Department of Cognitive Science Johns Hopkins University Department of Electrical Engineering & Computer Sciences University of California Berkeley United States Microsoft Research AI RedmondWA United States Departments of Psychology and Computer Science Princeton University

How do learners acquire languages from the limited data available to them? This process must involve some inductive biases—factors that affect how a learner generalizes—but it is unclear which inductive biases can explain observed patterns in language acquisition. To facilitate computational modeling aimed at addressing this question, we introduce a framework for giving particular linguistic inductive biases to a neural network model;such a model can then be used to empirically explore the effects of those inductive biases. This framework disentangles universal inductive biases, which are encoded in the initial values of a neural network’s parameters, from non-universal factors, which the neural network must learn from data in a given language. The initial state that encodes the inductive biases is found with meta-learning, a technique through which a model discovers how to acquire new languages more easily via exposure to many possible languages. By controlling the properties of the languages that are used during meta-learning, we can control the inductive biases that meta-learning imparts. We demonstrate this framework with a case study based on syllable structure. First, we specify the inductive biases that we intend to give our model, and then we translate those inductive biases into a space of languages from which a model can meta-learn. Finally, using existing analysis techniques, we verify that our approach has imparted the linguistic inductive biases that it was intended to impart. Copyright © 2020, The Authors. All rights reserved.

关键词： Scattering parameters

来源：评论

学校读者我要写书评

暂无评论

Nematoelasticity of hybrid molecular-colloidal liquid crystals

引用

Physical Review E 2021年第1期104卷 014703-014703页

作者： B. Senyuk H. Mundoor I. I. Smalyukh H. H. Wensink Department of Physics University of Colorado Boulder Colorado 80309 USA Department of Electrical Computer and Energy Engineering Materials Science and Engineering Program and Soft Materials Research Center University of Colorado Boulder Colorado 80309 USA Chemical Physics Program Departments of Chemistry and Physics University of Colorado Boulder Colorado 80309 USA Renewable and Sustainable Energy Institute National Renewable Energy Laboratory and University of Colorado Boulder Colorado 80309 USA Laboratoire de Physique des Solides Université Paris-Saclay & CNRS UMR 8502 91405 Orsay France

Colloidal rods immersed in a thermotropic liquid-crystalline solvent are at the basis of so-called hybrid liquid crystals, which are characterized by tunable nematic fluidity with symmetries ranging from conventional uniaxial nematic or antinematic to orthorhombic [Mundoor et al., science 360, 768 (2018)]. We provide a theoretical analysis of the elastic moduli of such systems by considering interactions between the individual rods with the embedding solvent through surface-anchoring forces, as well as steric and electrostatic interactions between the rods themselves. For uniaxial systems, the presence of colloidal rods generates a marked increase of the splay elasticity, which we found to be in quantitative agreement with experimental measurements. For orthorhombic hybrid liquid crystals, we provide estimates of all 12 elastic moduli and show that only a small subset of those elastic constants play a relevant role in describing the nematoelastic properties. The complexity and possibilities related to identifying the elastic moduli in experiments are briefly discussed.

关键词： Biaxial liquid crystals Liquid crystals

来源：评论

学校读者我要写书评

暂无评论

Standard quantum annealing outperforms adiabatic reverse annealing with decoherence

引用

Physical Review A 2022年第3期105卷 032431-032431页

作者： Gianluca Passarelli Ka-Wa Yip Daniel A. Lidar Procolo Lucignano CNR-SPIN c/o Complesso di Monte Sant'Angelo via Cinthia Napoli 80126 Italy Center for Quantum Information Science and Technology University of Southern California Los Angeles California 90089 USA Department of Physics and Astronomy University of Southern California Los Angeles California 90089 USA Departments of Electrical and Computer Engineering Chemistry and Physics University of Southern California Los Angeles California 90089 USA Dipartimento di Fisica “E. Pancini” Università di Napoli Federico II Complesso di Monte Sant'Angelo via Cinthia Napoli 80126 Italy

We study adiabatic reverse annealing (ARA) in an open system. In the closed system (unitary) setting, this annealing protocol allows avoidance of first-order quantum phase transitions of selected models, resulting in an exponential speedup compared with standard quantum annealing, provided that the initial state of the algorithm is close in Hamming distance to the target one. Here, we show that decoherence can significantly modify this conclusion: by resorting to the adiabatic master equation approach, we simulate the dynamics of the ferromagnetic p-spin model with p=3 under independent and collective dephasing. For both models of decoherence, we show that the performance of open system ARA is far less sensitive to the choice of the initial state than its unitary counterpart, and, most significantly, that open system ARA by and large loses its time to solution advantage compared to standard quantum annealing. These results suggest that as a stand-alone strategy ARA is unlikely to experimentally outperform standard “forward” quantum annealing, and that error mitigation strategies will likely be required in order to realize the benefits of ARA in realistic, noisy settings.

关键词： Adiabatic quantum optimization Open quantum systems Quantum computation Quantum protocols

来源：评论

学校读者我要写书评

暂无评论

High-Resolution Three-Dimensional Hybrid MRI + Low Dose CT Vocal Tract Modeling: A Cadaveric Pilot Study

引用

Journal of Voice 2022年

作者： MEYER, David RUSHO, Rushdi Zahid ALAM, Wahidul CHRISTENSEN, Gary E. HOWARD, David M. ATHA, Jarron HOFFMAN, Eric A. STORY, Brad TITZE, Ingo R. LINGALA, Sajan Goud Janette Ogg Voice Research Center Shenandoah University Winchester Virginia United States Roy J Carver Department of Biomedical Engineering University of Iowa Iowa City Iowa United States Department of Electrical and Computer Engineering University of Iowa Iowa City Iowa United States Department of Electronic Engineering Royal Holloway University of London LDN United Kingdom Departments of Radiology Medicine and Roy J Carver Department of Biomedical Engineering University of Iowa Iowa City Iowa United States College of Science University of Arizona Tucson AZ United States Utah Center for Vocology The University of Utah Salt Lake City UT United States

Objectives: MRI based vocal tract models have many applications in voice research and education. These models do not adequately capture bony structures (e.g. teeth, mandible), and spatial resolution is often relatively low in order to minimize scanning time. Most MRI sequences achieve 3D vocal tract coverage at gross resolutions of 2 mm³ within a scan time of <20 seconds. Computed tomography (CT) is well suited for vocal tract imaging, but is infrequently used due to the risk of ionizing radiation. In this cadaveric study, a single, extremely low-dose CT scan of the bony structures is blended with accelerated high-resolution (1 mm³) MRI scans of the soft tissues, creating a high-resolution hybrid CT-MRI vocal tract model. Methods: Minimum CT dosages were determined and a custom 16-channel airway receiver coil for accelerated high (1 mm³) resolution MRI was evaluated. A rigid body landmark based partial volume registration scheme was then applied to the images, creating a hybrid CT-MRI model that was segmented in Slicer. Results: Ultra-low dose CT produced images with sufficient quality to clearly visualize the bone, and exposed the cadaver to 0.06 mSv. This is comparable to atmospheric exposures during a round trip transatlantic flight. The custom 16-channel vocal tract coil produced acceptable image quality at 1 mm³ resolution when reconstructed from ∼6 fold undersampled data. High (1 mm³) resolution MR imaging of short (<10 seconds) sustained sounds was achieved. The feasibility of hybrid CT-MRI vocal tract modeling was successfully demonstrated using the rigid body landmark based partial volume registration scheme. Segmentations of CT and hybrid CT-MRI images provided more detailed 3D representations of the vocal tract than 2 mm³ MRI based segmentations. Conclusions: The method described in this study indicates that high-resolution CT and MR image sets can be combined so that structures such as tee

关键词： Airway Computed Tomography(CT) Magnetic Resonance Imaging(MRI) Modeling Segmentation Vocal tract

来源：评论

学校读者我要写书评

暂无评论

Hybrid Oscillator-Qubit Quantum Processors: Simulating Fermions, Bosons, and Gauge Fields

arXiv

引用

arXiv 2024年

作者： Crane, Eleanor Smith, Kevin C. Tomesh, Teague Eickbusch, Alec Martyn, John M. Kühn, Stefan Funcke, Lena DeMarco, Michael Austin Chuang, Isaac L. Wiebe, Nathan Schuckert, Alexander Girvin, Steven M. Department of Physics Co-Design Center for Quantum Advantage Massachusetts Institute of Technology CambridgeMA02139 United States Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA02139 United States Joint Quantum Institute Joint Center for Quantum Information and Computer Science University of Maryland NIST College ParkMD20742 United States Brookhaven National Laboratory UptonNY11973 United States Yale Quantum Institute PO Box 208 334 17 Hillhouse Ave New HavenCT06520-8263 United States Departments of Applied Physics and Physics Yale University New HavenCT06511 United States Department of Computer Science Princeton University PrincetonNJ08544 United States Infleqtion ChicagoIL60604 United States Center for Theoretical Physics Massachusetts Institute of Technology CambridgeMA02139 United States The NSF AI Institute for Artificial Intelligence and Fundamental Interactions CQTA Deutsches Elektronen-Synchrotron DESY Platanenallee 6 Zeuthen15738 Germany University of Bonn Nussallee 14-16 Bonn53115 Germany Department of Computer Science University of Toronto Canada Pacific Northwest National Laboratory RichlandWA United States Canadian Institute for Advanced Studies Toronto Canada

We develop a hybrid oscillator-qubit processor framework for quantum simulation of strongly correlated fermions and bosons that avoids the boson-to-qubit mapping overhead encountered in qubit hardware. This framework gives exact decompositions of particle interactions such as density-density terms and gauge-invariant hopping, as well as approximate methods based on the Baker-Campbell Hausdorff formulas including the magnetic field term for the U(1) quantum link model in (2 + 1)D. We use this framework to show how to simulate dynamics using Trotterisation, perform ancilla-free partial error detection using Gauss's law, measure non-local observables, estimate ground state energies using a oscillator-qubit variational quantum eigensolver as well as quantum signal processing, and we numerically study the influence of hardware errors in circuit QED experiments. To show the advantages over all-qubit hardware, we perform an end-to-end comparison of the gate complexity for the gauge-invariant hopping term and find an improvement of the asymptotic scaling with the boson number cutoff S from O(log(S)2) to O(1) in our framework as well as, for bosonic matter, a constant factor improvement of better than 104. We also find an improvement from O(log(S)) to O(1) for the U(1) magnetic field term. While our work focusses on an implementation in superconducting hardware, our framework can also be used in trapped ion, and neutral atom hardware. This work establishes digital quantum simulation with hybrid oscillator-qubit hardware as a viable and advantageous method for the study of qubit-boson models in materials science, chemistry, and high-energy physics. Copyright © 2024, The Authors. All rights reserved.

关键词： Ground state

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：