检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Camsari, Kerem Y. Torunbalci, Mustafa Mert Borders, William A. Ohno, Hideo Fukami, Shunsuke Department of Electrical and Computer Engineering University of California Santa Barbara Santa BarbaraCA93106 United States Birck Nanotechnology Center Purdue University West LafayetteIN47907 United States Laboratory for Nanoelectronics and Spintronics Research Institute of Electrical Communication Tohoku University Japan Center for Spintronics Research Network Tohoku University Japan Center for Science and Innovation in Spintronics Tohoku University Japan WPI-Advanced Institute for Materials Research Tohoku University Japan

Naturally random devices that exploit ambient thermal noise have recently attracted attention as hardware primitives for accelerating probabilistic computing applications. One such approach is to use a low barrier nanomagnet as the free layer of a magnetic tunnel junction (MTJ) whose magnetic fluctuations are converted to resistance fluctuations in the presence of a stable fixed layer. Here, we propose and theoretically analyze a magnetic tunnel junction with no fixed layers but two free layers that are circularly shaped disk magnets. We use an experimentally benchmarked model that accounts for finite temperature magnetization dynamics, bias-dependent charge and spin-polarized currents as well as the dipolar coupling between the free layers. We obtain analytical results for statistical averages of fluctuations that are in good agreement with the numerical model. We find that the free layers with low diameters fluctuate to randomize the resistance of the MTJ in an approximately bias-independent manner. We show how such MTJs can be used to build a binary stochastic neuron (or a p-bit) in hardware. Unlike earlier stochastic MTJs that need to operate at a specific bias point to produce random fluctuations, the proposed design can be random for a wide range of bias values, independent of spin-transfer-torque pinning. Moreover, in the absence of a carefully optimized stabled fixed layer, the symmetric double-free layer stack can be manufactured using present day Magnetoresistive Random Access Memory (MRAM) technology by minimal changes to the fabrication process. Such devices can be used as hardware accelerators in energy-efficient computing schemes that require a large throughput of tunably random bits. Copyright © 2020, The Authors. All rights reserved.

关键词： MRAM devices

来源：评论

学校读者我要写书评

暂无评论

Least-squares-based System Error Estimation Using ADS-B Measurements and Its Application to Three-dimensional Radar

引用

Journal of computers (Taiwan) 2019年第6期30卷 297-310页

作者： Qin, Gao-De Fan, E. Li, Pengfei Yuan, Chang-Hong School of Artificial Intelligence Shenzhen Polytechnic No. 4089 Shahe West Road Shenzhen518055 China Department of Computer Science and Engineering Shaoxing University No. 508 Huancheng West Road Shaoxing312000 China PLA Army Artillery Air Defense Academy Zhengzhou Campus No. 24 Jianshe East Road Zhengzhou450052 China Network Center Southern Medical University Guangzhou 510515 China No. 1023 Tainan Road Guangzhou510630 China

Abstract. Three-dimensional radar combined with an automatic dependent surveillancebroadcast (ADS-B) device is a typical multisensor data-fusion system. To estimate the system error of three-dimensional radar, a least-squares-based radar system error method (FL-LSr) using ADS-B measurements is proposed in a local rectangular radar coordinate system. In the proposed method, a unified observed model is established first, and the radar measurements and ADS-B measurements are transformed into the unified coordinated system. Then, the outliers in radar measurements are eliminated according to the 3σ rule. The corresponding sampling time of radar measurements is regarded as the reference time, and interpolation from straight-line fitting is used to reconstruct the ADS-B measurements. Additionally, the radar measurements and ADS-B are fitted to two straight-lines, and the angle between these two straight-lines is applied to compensate the azimuth components of radar measurements. Finally, the least squares estimation algorithm is utilized to estimate the system error of the three-dimensional radar. Experimental results with real data illustrate that the proposed method can estimate radar system error effectively and accurately compared with traditional radar system error estimation methods.. © 2019 computer Society of the Republic of China. All rights reserved.

关键词： Radar measurement

来源：评论

学校读者我要写书评

暂无评论

Left ventricle contouring in cardiac images based on deep reinforcement learning

TechRxiv

引用

TechRxiv 2021年

作者： Yin, Sixing Han, Yameng Pan, Judong Wang, Yining Li, Shufang Yu, F. Richard Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing100876 China University of California San Francisco San FranciscoCA94117 United States State Key Laboratory of Complex Severe and Rare Diseases Chinese Academy of Medical Sciences Peking Union Medical College Beijing100730 China The Department of Systems and Computer Engineering Carleton University OttawaONK1S 5B6 Canada

Assessment of the left ventricle segmentation in cardiac magnetic resonance imaging (MRI) is of crucial importance for cardiac disease diagnosis. However, conventional manual segmentation is a tedious task that requires excessive human effort, which makes automated segmentation highly desirable in practice to facilitate the process of clinical diagnosis. In this paper, we propose a novel reinforcement-learning-based framework for left ventricle contouring, which mimics how a cardiologist outlines the left ventricle in a cardiac image. Since such a contour drawing process is simply moving a paintbrush along a specific trajectory, it is thus analogized to a path finding problem. Following the algorithm of proximal policy optimization (PPO), we train a policy network, which makes a stochastic decision on the agent’s movement according to its local observation such that the generated trajectory matches the true contour of the left ventricle as much as possible. Moreover, we design a deep learning model with a customized loss function to generate the agent’s landing spot (or coordinate of its initial position on a cardiac image). The experiment results show that the coordinate of the generated landing spot is sufficiently close to the true contour and the proposed reinforcement-learning-based approach outperforms the existing U-net model even with limited training set. © 2021, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Graphical Counterfactuals: An Overview

arXiv

引用

arXiv 2024年

作者： Kang, Mingyu Chen, Duxin Pu, Ziyuan Gao, Jianxi Yu, Wenwu School of Cyber Science and Engineering Southeast University Nanjing210096 China School of Mathematics Southeast University Nanjing210096 China School of Transportation Southeast University Nanjing210096 China Department of Computer Science Center for Network Science and Technology Rensselaer Polytechnic Institute TroyNY12180 United States Frontiers Science Center for Mobile Information Communication and Security School of Mathematics Southeast University Nanjing210096 China Purple Mountain Laboratories Nanjing211102 China

Counterfactual thinking is a critical yet challenging topic for artificial intelligence to learn knowledge from data and ultimately improve their performances for new scenarios. Many research works, including Potential Outcome Model and Structural Causal Model, have been proposed to realize it. However, their modelings, theoretical foundations and application approaches are usually different. Moreover, there is a lack of graphical approach to infer spatio-temporal counterfactuals, that considers spatial and temporal interactions between multiple units. Thus, in this work, our aim is to investigate a survey to compare and discuss different counterfactual models, theories and approaches, and further build a unified graphical causal frameworks to infer the spatio-temporal counterfactuals. Copyright © 2024, 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

Toward an automatic system for computer-aided assessment in facial palsy

arXiv

引用

arXiv 2019年

作者： Guarin, Diego L. Yunusova, Yana Taati, Babak Dusseldorp, Joseph R. Mohan, Suresh Tavares, Joana van Veen, Martinus M. Fortier, Emily Hadlock, Tessa A. Jowett, Nate KITE Toronto Rehabilitation Institute University Health Network TorontoON Canada Department of Otolaryngology/Head and Neck Surgery Massachusetts Eye and Ear Infirmary Harvard Medical School Boston United States Department of Speech Language Pathology University of Toronto TorontoON Canada Hurvitz Brain Sciences Program Sunnybrook Research Institute ON Canada Department of Computer Science University of Toronto TorontoON Canada Institute of Biomaterials and Biomedical Engineering University of Toronto TorontoON Canada Department of Plastic and Reconstructive Surgery Royal Australasian College of Surgeons University of Sydney Sydney Australia Faculty of Health Sciences Brasilia University Brasilia Brazil

Importance: Quantitative assessment of facial function is challenging, and subjective grading scales such as House-Brackmann, Sunnybrook, and eFACE have well-recognized limitations. Machine learning approaches to facial landmark localization carry great clinical potential as they enable high-throughput automated quantification of relevant facial metrics from photographs and videos. However, the translation from research settings to clinical application still requires important improvements. Objective: To develop a novel machine learning algorithm for fast and accurate localization of facial landmarks in photographs of facial palsy patients and utilize this technology as part of an automated computer-aided diagnosis system. Design, Setting, and Participants: Portrait photographs of eight expressions obtained from 200 facial palsy patients and 10 healthy participants were manually annotated, by localizing 68 facial landmarks in each photograph, by three trained clinicians using a custom graphical user interface. A novel machine learning model for automated facial landmark localization was trained using this disease-specific database. Algorithm accuracy was compared to manual markings and the output of a model trained using a larger database consisting only of healthy subjects. Main Outcomes and measurements: Root mean square error normalized by the inter-ocular distance (NRMSE) of facial landmark localization between prediction of machine learning algorithm and manually localized landmarks. Results: Publicly available algorithms for facial landmark localization provide poor localization accuracy when applied to photographs of patients compared to healthy controls (NRMSE, 8.56 ± 2.16 vs. 7.09 ± 2.34, p Copyright © 2019, The Authors. All rights reserved.

关键词： Photography

来源：评论

学校读者我要写书评

暂无评论

Secure topology for electronic medical record transmissions

引用

Journal of Applied Sciences 2006年第6期6卷 954-958页

作者： Alanazi, Hamdan O. Mat Kiah, M.L. Zaidan, A.A. Zaidan, B.B. Alam, Gazi Mahabubul Faculty of Computer Science and Information Technology University Malaysia 50603 Kuala Lumpur Malaysia Faculty of Engineering Multimedia University Jalan Multimedia 63100 Cyberjaya Selangor Malaysia Network and Commuunication Secutiry Reasearch Group ICT and Computational Science Research Cluster University of Malaya 50603 Kuala Lumpur Malaysia Department of Educational Management Planning and Policy Faculty of Education University of Malaya 50606 Kuala Lumpur Malaysia Faculty of Applied Medical Science King Saud University P.O. Box 2454 Riyadh 11451 Saudi Arabia

In this study, handshake protocol for patient, medical center and doctor, medical center is proposed for electronic medical record transmission to improve the confidentiality of data transmission and non-repudiation of sending and receiving medical records. The proposed topology depends on symmetric and asymmetric cryptography to achieve high level of secrecy for electronic medical records. The new topology has been described on multi-users (i.e., Doctors and Patient). The new topology has been implemented using Ntru crypto-system and AES encryption method. The proposed solution has been tested to have high level of confidentiality up to the legal age of the medical records. © 2010 Asian network for Scientific Information.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

YOLO-TP: A process detection model of tunnel real scene based on gradient information interaction

YOLO-TP: A process detection model of tunnel real scene base...

引用

computer, Big Data and Artificial Intelligence (ICCBD+AI), International Conference on

作者： Jiaying Fan Shuping Pan Xinbo Jiang Shengtao Zhang Hongliang Liu Chuan Wang Jianghua Li Chenglin Ke Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Technological Innovation Department Shandong Hi-Speed Group Co Ltd JiNan China School of Qilu Transportation Shandong University JiNan China China Railway 14th Bureau Group First Engineering Development Co. Ltd RiZhao China

ISBN: (数字)9798331533991

ISBN: (纸本)9798331534004

Target detection technology is an effective method to detect tunnel operation safety. Although the field has made some progress in detection models, the lack of datasets and detection models has hindered its development. We produce and propose Tunnel Processes data (TP), a challenging dataset of high-precision real-world tunnel process target detection that reduces the limitations of research in this field. TP has a high resolution: 1920×1080, 1734images,9 categories. TP is the first tunnel process data set under construction to date, and its fidelity exceeds that of other tunnel process datasets in the field of target detection. In addition, we also propose a YOLO-TP benchmark model to make up for the lack of a high-precision tunnel process image target detection baseline model. Experiments on TP datasets demonstrate their validity, and experiments on the dataset presented in this paper demonstrate the validity of the benchmark model.

关键词： Accuracy Image resolution Computational modeling Object detection Benchmark testing Big Data Feature extraction Data models Safety Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to "Lateralization of resting state networks and relationship to age and gender" [NeuroImage 104 (2015) 310-325]

引用

NeuroImage 2018年 167卷 504页

作者： O Agcaoglu R Miller A R Mayer K Hugdahl V D Calhoun Mind Research Network Albuquerque NM USA University of New Mexico Department of Electrical and Computer Engineering Albuquerque NM USA. Electronic address: oagcaoglu@***. Mind Research Network Albuquerque NM USA. University of New Mexico Health Science Center USA. University of Bergen Department of Biological and Medical Psychology Norway. University of New Mexico Department of Electrical and Computer Engineering Albuquerque NM USA.

来源：评论

学校读者我要写书评

暂无评论

Small worlds and clustering in spatial networks

arXiv

引用

arXiv 2019年

作者： Boguña, Marián Krioukov, Dmitri Almagro, Pedro Serrano, M. Ángeles Departament de Física de la Matèria Condensada Universitat de Barcelona Martí i Franquès 1 BarcelonaE-08028 Spain Universitat de Barcelona Barcelona Spain Network Science Institute Northeastern University 177 Huntington avenue BostonMA022115 United States Department of Physics Department of Mathematics Department of Electrical & Computer Engineering Northeastern University 110 Forsyth Street 111 Dana Research Center BostonMA02115 United States Passeig Lluís Companys 23 BarcelonaE-08010 Spain

networks with underlying metric spaces attract increasing research attention in network science, statistical physics, applied mathematics, computer science, sociology, and other fields. This attention is further amplified by the current surge of activity in graph embedding. In the vast realm of spatial network models, only a few reproduce even the most basic properties of real-world networks. Here, we focus on three such properties—sparsity, small worldness, and clustering—and identify the general subclass of spatial homogeneous and heterogeneous network models that are sparse small worlds and that have nonzero clustering in the thermodynamic limit. We rely on the maximum entropy approach where network links correspond to noninteracting fermions whose energy dependence on spatial distances determines network small worldness and clustering. Copyright © 2019, The Authors. All rights reserved.

关键词： Heterogeneous networks

来源：评论

学校读者我要写书评

暂无评论

Progression to AML Is Predictable and Distinct from Age Related Clonal Hematopoiesis

引用

BLOOD 2017年 130卷 471-471页

作者： Abelson, Sagi Ng, Stanley W. K. Wiessbrod, Omer Zuzarte, Philip Heisler, Lawrence Sundaravadanam, Yogi Wang, Ting Ting Pugh, Trevor J. Soave, David Brennan, Paul Johansson, Mattias Awadalla, Phillip Bratman, Scott V. Wang, Jean Minden, Mark D. Dick, John E. Shlush, Liran I. Princess Margaret Cancer Centre University Health Network Toronto Canada Institute of Biomaterials and Biomedical Engineering University of Toronto Toronto Canada Department of Computer Science and Applied Mathematics Weizmann Institute of Science Israel Rehovot Israel Ontario Institute for Cancer Research Toronto Canada University of Toronto Princess Margaret Cancer Centre Toronto Canada Department of Medical Biophysics University of Toronto Toronto Canada International Agency for Research on Cancer (WHO-IARC) Lyon France Department of Radiation Oncology University of Toronto Toronto Canada Department of Medicine University of Toronto Toronto Canada Division of Medical Oncology and Hematology UHN Toronto Canada Princess Margaret Cancer Centre Division of Medical Oncology and Hematology University Health Network University of Toronto Toronto Canada Department of Molecular Genetics University of Toronto Toronto Canada

471

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：