检索结果-内蒙古大学图书馆

JACC: Advances 2022年第1期1卷 100003-100003页

作者： Schlesinger, Daphne E. Diamant, Nathaniel Raghu, Aniruddh Reinertsen, Erik Young, Katherine Batra, Puneet Pomerantsev, Eugene Stultz, Collin M. Harvard-MIT Division of Health Sciences and Technology MIT Cambridge MA United States Institute for Medical Engineering and Science MIT Cambridge MA United States Research Laboratory of Electronics Computer Science & Artificial Intelligence Laboratory MIT Cambridge MA United States Broad Institute of MIT and Harvard Cambridge MA United States Department of Electrical Engineering and Computer Science MIT Cambridge MA United States Division of Cardiology Massachusetts General Hospital Boston MA United States

Background: Central hemodynamic parameters are typically measured via pulmonary artery catherization—an invasive procedure that involves some risk to the patient and is not routinely available in all settings. Objectives: This study sought to develop a noninvasive method to identify elevated mean pulmonary capillary wedge pressure (mPCWP). Methods: We leveraged data from 248,955 clinical records at the Massachusetts General Hospital to develop a deep learning model that can infer when the mPCWP >15 mmHg using the 12-lead electrocardiogram (ECG). Of these data, 242,216 records were used to pre-train a model that generates useful ECG representations. The remaining 6,739 records contain encounters with direct measurements of the mPCWP. Eighty percent of these data were used for model development and testing (5,390), and the remaining records comprise a holdout set (1,349) that was used to evaluate the model. We developed an associated unreliability score that identifies when model predictions are likely to be untrustworthy. Results: The model achieves an area under the receiver operating characteristic curve (AUC) of 0.80 ± 0.02 (test set) and 0.79 ± 0.01 (holdout set). Model performance varies as a function of the unreliability, where patients with high unreliability scores correspond to a subgroup where model performance is poor: for example, patients in the holdout set with unreliability scores in the highest decile have a reduced AUC of 0.70 ± 0.06. Conclusions: The mPCWP can be inferred from the ECG, and the reliability of this inference can be measured. When invasive monitoring cannot be expeditiously performed, deep learning models may provide information that can inform clinical care. © 2022 The Authors

关键词： deep learning ECG pulmonary artery occlusion pressure pulmonary artery wedge pressure pulmonary capillary wedge pressure

来源：评论

学校读者我要写书评

暂无评论

LEARNING-AUGMENTED DATA STREAM ALGORITHMS 8

LEARNING-AUGMENTED DATA STREAM ALGORITHMS

引用

8th International Conference on Learning Representations, ICLR 2020

作者： Jiang, Tanqiu Li, Yi Lin, Honghao Ruan, Yisong Woodruff, David P. Department of Electrical and Computer Engineering Lehigh University BethlehemPA18015 United States School of Physical and Mathematical Sciences Nanyang Technological University Singapore637371 Singapore Zhiyuan College Shanghai Jiao Tong University Shanghai200240 China Department of Software Engineering Xiamen University Fujian Xiamen361000 China Computer Science Department Carnegie Mellon University PittsburghPA15213 United States

The data stream model is a fundamental model for processing massive data sets with limited memory and fast processing time. Recently Hsu et al. (2019) incorporated machine learning techniques into the data stream model in order to learn relevant patterns in the input data. Such techniques led to the training of an oracle to predict item frequencies in the streaming model. In this paper we explore the full power of such an oracle, showing that it can be applied to a wide array of problems in data streams, sometimes resulting in the first optimal bounds for such problems, and sometimes bypassing known lower bounds without such an oracle. We apply the oracle to counting distinct elements on the difference of streams, estimating frequency moments, estimating cascaded aggregates, and estimating moments of geometric data streams. For the distinct elements problem, we bypass the known lower bound and obtain a new space-optimal algorithm. For estimating the p-th frequency moment for 0 2 we obtain a quadratic savings in memory, bypassing known lower bounds without an oracle. We empirically validate our results, demonstrating also our improvements in practice. © 2020 8th International Conference on Learning Representations, ICLR 2020. All rights reserved.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Unsupervised learning of deep-learned features from breast cancer images.

arXiv

引用

arXiv 2020年

作者： Lee, Sanghoon Zhao, Yanjun Farley, Colton Choi, Wookjin Shim, Simon Yoo, Wook-Sung Department of Computer Sciences Electrical Engineering Marshall University Huntington WV United States Department of Computer Science Troy University Troy AL United States Department of Engineering Computer Science Virginia State University Petersburg VA United States Department of Biomedical Engineering

Detecting cancer manually in whole slide images requires significant time and effort on the laborious process. Recent advances in whole slide image analysis have stimulated the growth and development of machine learning-based approaches that improve the efficiency and effectiveness in the diagnosis of cancer diseases. In this paper, we propose an unsupervised learning approach for detecting cancer in breast invasive carcinoma (BRCA) whole slide images. The proposed method is fully automated and does not require human involvement during the unsupervised learning procedure. We demonstrate the effectiveness of the proposed approach for cancer detection in BRCA and show how the machine can choose the most appropriate clusters during the unsupervised learning procedure. Moreover, we present a prototype application that enables users to select relevant groups mapping all regions related to the groups in whole slide images. Copyright © 2020, The Authors. All rights reserved.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Melanoma Detection using a Random Forest Algorithm

Melanoma Detection using a Random Forest Algorithm

引用

E-Health and Bioengineering Conference (EHB)

作者： Felicia-Anisoara Damian Simona Moldovanu Luminita Moraru The Modelling & Simulation Laboratory University Dunarea de Jos of Galati UGAL Galati Romania Department of Computer Science and Information Technology Faculty of Automation Computers Electrical Engineering and Electronics University Dunarea de Jos of Galati UGAL Galati Romania Department of Chemistry Physics and Environment Faculty of Sciences and Environment University Dunarea de Jos of Galati UGAL Galati Romania

ISBN: (数字)9781665485579

ISBN: (纸本)9781665485586

In recent years, statistical evidence has identified melanoma as a major cause of skin cancer deaths. In this study, we propose a skin analysis lesions based on colour features (C) and Hu (H) moments to differentiate benign (nevi) and malignant (melanoma) lesions and, a classification based on Random Forest algorithm. Colour features are found as follows. Pre-processing for hair removing using the Dull-razor method; image segmentation based on the optimal colour threshold set on each RGB colour channel (red, green, blue); 23 colour features extraction using the minimum and maximum RGB intensity and Hu moments; Random Forest (RF) algorithm to accurately differentiate benign and malignant skin lesions. This study used three datasets: 7-Point, Med-Node, PH2. RF classifier performance in terms of accuracy was: 94% for the 7-point dataset with H5, H7, H6, H2, C08 selected as relevant features; 98.1% for the Med-Node dataset and H7, H5, H6, H2, H1 ACC the relevant features; and, 96.5% for the PH2 dataset and H5, H6, H7, C03, H1 selected as relevant features, respectively. Shape features based on Hu moments are found to improve the classification performance of the skin lesions compared to the colour features.

关键词： Visualization Image segmentation Image color analysis Shape Melanoma Skin Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Fast Interpretable Greedy-Tree Sums

arXiv

引用

arXiv 2022年

作者： Tan, Yan Shuo Singh, Chandan Nasseri, Keyan Agarwal, Abhineet Duncan, James Ronen, Omer Epland, Matthew Kornblith, Aaron Yu, Bin Department of Statistics and Data Science National University of Singapore Singapore Department of Electrical Engineering and Computer Sciences UC Berkeley United States Microsoft Research United States Department of Statistics UC Berkeley United States Graduate Group in Biostatistics UC Berkeley United States Overjet Department of Emergency Medicine UC San Francisco United States Department of Pediatrics UC San Francisco United States

Modern machine learning has achieved impressive prediction performance, but often sacrifices interpretability, a critical consideration in high-stakes domains such as medicine. In such settings, practitioners often use highly interpretable decision tree models, but these suffer from inductive bias against additive structure. To overcome this bias, we propose Fast Interpretable Greedy-Tree Sums (FIGS), which generalizes the CART algorithm to simultaneously grow a flexible number of trees in summation. By combining logical rules with addition, FIGS is able to adapt to additive structure while remaining highly interpretable. Extensive experiments on real-world datasets show that FIGS achieves state-of-the-art prediction performance. To demonstrate the usefulness of FIGS in high-stakes domains, we adapt FIGS to learn clinical decision instruments (CDIs), which are tools for guiding clinical decision-making. Specifically, we introduce a variant of FIGS known as G-FIGS that accounts for the heterogeneity in medical data. G-FIGS derives CDIs that reflect domain knowledge and enjoy improved specificity (by up to 20% over CART) without sacrificing sensitivity or interpretability. To provide further insight into FIGS, we prove that FIGS learns components of additive models, a property we refer to as disentanglement. Further, we show (under oracle conditions) that unconstrained tree-sum models leverage disentanglement to generalize more efficiently than single decision tree models when fitted to additive regression functions. Finally, to avoid overfitting with an unconstrained number of splits, we develop Bagging-FIGS, an ensemble version of FIGS that borrows the variance reduction techniques of random forests. Bagging-FIGS enjoys competitive performance with random forests and XGBoost on real-world datasets. © 2022, CC BY.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Coherently driven ring quantum cascade lasers

Coherently driven ring quantum cascade lasers

引用

CLEO: science and Innovations, S and I 2022

作者： Kazakov, Dmitry Piccardo, Marco Letsou, Theodore L. Beiser, Maximilian Zhi, Yiyang Columbo, Lorenzo Brambilla, Massimo Schwarz, Benedikt Capasso, Federico Harvard John A. Paulson School of Engineering and Applied Sciences Harvard University CambridgeMA02138 United States Center for Nano Science and Technology Fondazione Istituto Italiano di Tecnologia Milan Italy Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA02138 United States Institute of Solid State Electronics TU Wien Vienna1040 Austria Case Western Reserve University ClevelandOH United States Dipartimento di Elettronica e Telecomunicazioni Politecnico di Torino Torino10129 Italy CNR-Istituto di Fotonica e Nanotecnologie Bari70126 Italy Dipartimento di Fisica Interateneo CNR-IFN Università e Politecnico di Bari Bari70125 Italy

Ring quantum cascade lasers generate self-starting frequency combs and dissipative cavity solitons. We present a reengineered ring resonator with an evanescent wave directional coupler that allows coherent control ove... 详细信息

ISBN: (纸本)9781557528209

关键词： Quantum cascade lasers

来源：评论

学校读者我要写书评

暂无评论

Energy-based out-of-distribution detection 20

Energy-based out-of-distribution detection

引用

Proceedings of the 34th International Conference on Neural Information Processing Systems

作者： Weitang Liu Xiaoyun Wang John D. Owens Yixuan Li Department of Computer Science and Engineering University of California San Diego La Jolla CA Department of Computer Science University of California Davis Davis CA Department of Electrical and Computer Engineering University of California Davis Davis CA Department of Computer Sciences University of Wisconsin-Madison Madison WI

ISBN: (纸本)9781713829546

Determining whether inputs are out-of-distribution (OOD) is an essential building block for safely deploying machine learning models in the open world. However, previous methods relying on the softmax confidence score suffer from overconfident posterior distributions for OOD data. We propose a unified framework for OOD detection that uses an energy score. We show that energy scores better distinguish in- and out-of-distribution samples than the traditional approach using the softmax scores. Unlike softmax confidence scores, energy scores are theoretically aligned with the probability density of the inputs and are less susceptible to the overconfidence issue. Within this framework, energy can be flexibly used as a scoring function for any pre-trained neural classifier as well as a trainable cost function to shape the energy surface explicitly for OOD detection. On a CIFAR-10 pre-trained WideResNet, using the energy score reduces the average FPR (at TPR 95%) by 18.03% compared to the softmax confidence score. With energy-based training, our method outperforms the state-of-the-art on common benchmarks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Effects of Surface Passivation on CdZnTeSe Nuclear Detectors

Effects of Surface Passivation on CdZnTeSe Nuclear Detectors

引用

IEEE Symposium on Nuclear science (NSS/MIC)

作者： Stephen U. Egarievwe Utpal N. Roy Ezekiel O. Agbalagba Amir H. Davis Mordecai B. Israel Parion L. Alexander Ralph B. James Department of Electrical Engineering and Computer Science Nuclear Engineering and Radiological Science Center Alabama A&M University AL USA Department of Nonproliferation and National Security Brookhaven National Laboratory NY USA Science and Technology Savannah River National Laboratory Aiken SC USA Department of Physics Federal University of Petroleum Resources Delta State Nigeria Department of Bioengineering Stanford University CA USA Department of Electrical and Computer Engineering University of South Alabama Mobile AL USA Department of Biological and Environmental Sciences Alabama A&M University AL USA

ISBN: (数字)9781665421133

ISBN: (纸本)9781665421140

Cadmium zinc telluride selenide (CdZnTeSe) has shown great promise in reducing the cost of semiconductor nuclear detectors that can operate at room temperature without cryogenic cooling. This is due to the high yield of detector-grade materials in the CdZnTeSe crystal growth process, which can be attributed to the much smaller numbers of Te inclusions and grain boundary network in CdZnTeSe compared to other CdTe-based semiconductors such as CdZnTe. In the present work, we study the effects of surface passivation on CdZnTe detectors using a mixture of ammonium fluoride and hydrogen peroxide solution (NH 4 F + H 2 O 2 + H 2 O). Detectors fabricated from CdZnTeSe crystals showed very good energy resolutions: 1.1% for the 662-keV gamma peak of 137 Cs by Frisch-grid detectors, and 5.9% for the 59.6-keV gamma peak of 241 Am by planar detectors. Experimental results show that the leakage current is increased immediately after passivation and then decreases as the surfaces stabilizes. The resistivity of the CdZnTeSe is of the order of 10 10 Ω-cm. The surface passivation improved the energy resolution of planar detector by 18% for the 59.6-keV gamma peak of 241 Am.

关键词： Water Grain boundaries Crystal growth Energy resolution Hydrogen Detectors Leakage currents

来源：评论

学校读者我要写书评

暂无评论

Room temperature charge-to-spin conversion from q-2DEG at SrTiO3-based interfaces

arXiv

引用

arXiv 2022年

作者： Shashank, Utkarsh Deka, Angshuman Fukuma, Yasuhiro Ye, Chen Wang, X. Renshaw Gupta, Surbhi Rawat, Rajdeep Singh Medwal, Rohit Asada, Hironori Department of Physics and Information Technology Faculty of Computer Science and System Engineering Kyushu Institute of Technology 680-4 Kawazu Iizuka820-8502 Japan Birck Nanotechnology Center School of Electrical and Computer Engineering Purdue University West LafayetteIN47907 United States Research Center for Neuromorphic AI hardware Kyushu Institute of Technology Kitakyushu808-0196 Japan School of Physical and Mathematical Sciences Nanyang Technological University 637616 Singapore School of Electrical and Electronic Engineering Nanyang Technological University 639798 Singapore Natural Science and Science Education National Institute of Education Nanyang Technological University 637616 Singapore Department of Physics Indian Institute of Technology Kanpur Kanpur208016 India Graduate School of Sciences and Technology for Innovation Yamaguchi University 2-16-1 Tokiwadai Ube755-8611 Japan

Interfacial two-dimensional electron gas (2DEG), especially the SrTiO3-based ones at the unexpected interface of insulators, have emerged to be a promising candidate for efficient charge-spin current interconversion. In this article, to gain insight into the mechanism of the charge-spin current interconversion at the oxide-based 2DEG, we focused on conducting interfaces between insulating SrTiO3 and two types of aluminium-based amorphous insulators, namely SrTiO3/AlN and SrTiO3/Al2O3, and estimated their charge-spin conversion efficiency, θcs. The two types of amorphous insulators were selected to explicitly probe the overlooked contribution of oxygen vacancy to the θcs. We proposed a mechanism to explain results of spin-torque ferromagnetic resonance (ST-FMR) measurements and developed an analysis protocol to reliably estimate the θcs of the oxide based 2DEG. The resultant θcs/t, where t is the thickness of the 2DEG, were estimated to be 0.244 nm-1 and 0.101 nm-1 for the SrTiO3/AlN and SrTiO3/Al2O3, respectively, and they are strikingly comparable to their crystalline counterparts. Furthermore, we also observe a large direct current modulation of resonance linewidth in SrTiO3/AlN samples, confirming its high θcs and attesting an oxygen-vacancy-enabled charge-spin conversion. Our findings emphasize the defects' contribution to the charge-spin interconversion, especially in the oxide-based low dimensional systems, and provide a way to create and enhance charge-spin interconversion via defect engineering. Copyright © 2022, The Authors. All rights reserved.

关键词： Aluminum compounds

来源：评论

学校读者我要写书评

暂无评论

Observation of current-induced switching in non-collinear antiferromagnetic IrMn3 by differential voltage measurements

arXiv

引用

arXiv 2021年

作者： Arpaci, Sevdenur Lopez-Dominguez, Victor Shi, Jiacheng Sánchez-Tejerina, Luis Garesci, Francesca Wang, Chulin Yan, Xueting Sangwan, Vinod K. Grayson, Matthew Hersam, Mark C. Finocchio, Giovanni Amiri, Pedram Khalili Department of Electrical and Computer Engineering Northwestern University EvanstonIL60208 United States Graduate Program in Applied Physics Northwestern University EvanstonIL60208 United States Department of Mathematical and Computer Sciences Physical Sciences and Earth Sciences University of Messina Messina98166 Italy Department of Engineering University of Messina Messina98166 Italy Department of Materials Science and Engineering Northwestern University EvanstonIL60208 United States Department of Chemistry Northwestern University EvanstonIL60208 United States

There is accelerating interest in developing memory devices using antiferromagnetic (AFM) materials, motivated by the possibility for electrically controlling AFM order via spin-orbit torques, and its read-out via magnetoresistive effects. Recent studies have shown, however, that high current densities create non-magnetic contributions to resistive switching signals in AFM/heavy metal (AFM/HM) bilayers, complicating their interpretation. Here we introduce an experimental protocol to unambiguously distinguish current-induced magnetic and nonmagnetic switching signals in AFM/HM structures, and demonstrate it in IrMn3/Pt devices. A six-terminal double-cross device is constructed, with an IrMn3 pillar placed on one cross. The differential voltage is measured between the two crosses with and without IrMn3 after each switching attempt. For a wide range of current densities, reversible switching is observed only when write currents pass through the cross with the IrMn3 pillar, eliminating any possibility of non-magnetic switching artifacts. Micromagnetic simulations support our findings, indicating a complex domain-mediated switching process. © 2021, CC BY.

关键词： Binary alloys

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：