检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Wang, Rongguang Chaudhari, Pratik Davatzikos, Christos Department of Electrical and Systems Engineering University of Pennsylvania United States Center for AI and Data Science for Integrated Diagnostics University of Pennsylvania United States Center for Biomedical Image Computing and Analytics University of Pennsylvania United States Department of Computer and Information Science University of Pennsylvania United States Department of Radiology Perelman School of Medicine University of Pennsylvania United States

Despite the great promise that machine learning has offered in many fields of medicine, it has also raised concerns about potential biases and poor generalization across genders, age distributions, races and ethnicities, hospitals, and data acquisition equipment and protocols. In the current study, and in the context of three brain diseases, we provide evidence which suggests that when properly trained, machine learning models can generalize well across diverse conditions and do not necessarily suffer from bias. Specifically, by using multi-study magnetic resonance imaging consortia for diagnosing Alzheimer's disease, schizophrenia, and autism spectrum disorder, we find that well-trained models have a high area-under-the-curve (AUC) on subjects across different subgroups pertaining to attributes such as gender, age, racial groups, and different clinical studies and are unbiased under multiple fairness metrics such as demographic parity difference, equalized odds difference, equal opportunity difference etc. We find that models that incorporate multi-source data from demographic, clinical, genetic factors and cognitive scores are also unbiased. These models have better predictive AUC across subgroups than those trained only with imaging features but there are also situations when these additional features do not help. © 2022, CC BY.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

A Metadata-Based Ecosystem to Improve the FAIRness of Research Software

arXiv

引用

arXiv 2023年

作者： Kuckertz, Patrick Göpfert, Jan Karras, Oliver Neuroth, David Schönau, Julian Pueblas, Rodrigo Ferenz, Stephan Engel, Felix Pflugradt, Noah Weinand, Jann M. Nieße, Astrid Auer, Sören Stolten, Detlef Jülich52425 Germany TIB - Leibniz Information Centre for Science and Technology Hanover30167 Germany Department for Computer Science Carl von Ossietzky University of Oldenburg Oldenburg26129 Germany University of Hannover L3S Research Center Hannover30167 Germany RWTH Aachen University Chair for Fuel Cells Faculty of Mechanical Engineering Aachen52062 Germany

The reuse of research software is central to research efficiency and academic exchange. The application of software enables researchers with varied backgrounds to reproduce, validate, and expand upon study findings. Furthermore, the analysis of open source code aids in the comprehension, comparison, and integration of approaches. Often, however, no further use occurs because relevant software cannot be found or is incompatible with existing research processes. This results in repetitive software development, which impedes the advancement of individual researchers and entire research communities. In this article, the DataDesc ecosystem is presented – an approach to describing data models of software interfaces with detailed and machine-actionable metadata. In addition to a specialized metadata schema, an exchange format and support tools for easy collection and the automated publishing of software documentation are introduced. This approach practically increases the FAIRness, i.e., findability, accessibility, interoperability, and so the reusability of research software, as well as effectively promotes its impact on research. © 2023, CC BY.

关键词： computer software reusability

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Risk Prediction Model for Recurrence-free Survival in Patients with Hepatocellular Carcinoma Using Multi-phase CT Image

Deep Learning-based Risk Prediction Model for Recurrence-fre...

引用

IEEE Global Conference on Consumer Electronics (GCCE)

作者： Weibin Wang Fang Wang Yunjun Yang Yinhao Li Jing Liu Xianhua Han Lanfen Lin Ruofeng Tong Hongjie Hu Yen-Wei Chen Graduate School of Information Science and Engineering Ritsumeikan University Kusatsu Japan Department of Radiology Sir Run Run Shaw Hospital Zhejiang University Hangzhou China Department of Radiology The First Affiliated Hospital Wenzhou Medical University Wenzhou China College of Information Science and Engineering Ritsumeikan University Kusatsu Japan Research Center for Healthcare Data Science Zhejiang Lab Hangzhou China College of Computer Science and Technology Zhejiang University Hangzhou China

ISBN: (纸本)9781665492331

Risk prediction for recurrence is a critical task for patients with hepatocellular carcinoma (HCC). Effective prediction can evaluate treatment options and guide personalized medicine. Traditional approaches use clinical data to construct cox-regression models to predict the risk of recurrence. Recently, prognosis analysis based on image information of patient often has better performance compared with traditional approaches. In particular, deep learning has demonstrated its superiority in medical image processing. In this paper, we propose a deep learning-based model to predict the risk of recurrence. We collected 292 patients with HCC from two independent centers, which were divided into a training set, an internal validation set, and an external validation set. Our models were compared with traditional clinical models and better performance was obtained. Our proposed method achieves a C-index performance of 0.627 and 0.630 for the internal validation set and external validation set, respectively.

关键词： Training Deep learning Precision medicine Computed tomography Predictive models Data models Biomedical image processing

来源：评论

学校读者我要写书评

暂无评论

Development of an in-situ calibration device of firn properties for Askaryan neutrino detectors 37

Development of an in-situ calibration device of firn propert...

引用

37th International Cosmic Ray Conference, ICRC 2021

作者： Beise, Jakob Glaser, Christian Anker, Astrid Baldi, Pierre Barwick, Steven W. Beise, Jakob Bernhoff, Hans Besson, Dave Z. Bingefors, Nils Cataldo, Maddalena Chen, Pisin Fernández, Daniel García Gaswint, Geoffrey Glaser, Christian Hallgren, Allan Hallmann, Steffen Hanson, Jordan C. Klein, Spencer R. Kleinfelder, Stuart A. Lahmann, Robert Liu, Jiayi Magnuson, Mitchell McAleer, Stephen Meyers, Zach Nam, Jiwoo Nelles, Anna Novikov, Alexander Paul, Manuel P. Persichilli, Christopher Plaisier, Ilse Pyras, Lilly Rice-Smith, Ryan Tatar, Joulien Wang, Shih-Hao Welling, Christoph Zhao, Leshan Uppsala University Department of Physics and Astronomy Box 516 Uppsala751 20 Sweden Department of Physics and Astronomy University of California IrvineCA92697 United States Department of Information and Computer Science University of California IrvineCA92697 United States Uppsala University Department of Physics and Astronomy UppsalaSE-752 37 Sweden Uppsala University Department of Engineering Sciences Division of Electricity UppsalaSE-752 37 Sweden Department of Physics and Astronomy University of Kansas LawrenceKS66045 United States Moscow115409 Russia ECAP Friedrich-Alexander Universität Erlangen-Nürnberg Erlangen91058 Germany Department of Physics Leung Center for Cosmology and Particle Astrophysics National Taiwan University Taipei10617 Taiwan DESY Zeuthen15738 Germany Whittier College Department of Physics WhittierCA90602 United States Lawrence Berkeley National Laboratory BerkeleyCA94720 United States Department of Electrical Engineering and Computer Science University of California IrvineCA92697 United States Research Cyberinfrastructure Center University of California IrvineCA92697 United States

High energy neutrinos (E >1017 eV) are detected cost-efficiently via the Askaryan effect in ice, where a particle cascade induced by the neutrino interaction produces coherent radio emission that can be picked up by antennas installed below the surface. A good knowledge of the near surface ice (aka firn) properties is required to reconstruct the neutrino properties. In particular, a continuous monitoring of the snow accumulation (which changes the depth of the antennas) and the index-of-refraction profile are crucial for an accurate determination of the neutrino’s direction and energy. We present an in-situ calibration system that extends the radio detector station with a radio emitter to continuously monitor the firn properties by measuring time differences of direct and reflected (off the surface) signals (D’n’R). We optimized the station layout in a simulation study and quantified the achievable precision. We present 14 months of data of the ARIANNA detector on the Ross Ice Shelf, Antarctica, where a prototype of this calibration system was successfully used to monitor the snow accumulation with unprecedented precision of 1 mm. We explore and test several algorithms to extract the D’n’R time difference from noisy data (including deep learning). This constitutes an in-situ test of the neutrino vertex distance reconstruction using the D’n’R technique which is needed to determine the neutrino energy. © Copyright owned by the author(s).

关键词： Ice

来源：评论

学校读者我要写书评

暂无评论

Roadmap for Unconventional Computing with Nanotechnology

arXiv

引用

arXiv 2023年

作者： Finocchio, Giovanni Incorvia, Jean Anne C. Friedman, Joseph S. Yang, Qu Giordano, Anna Grollier, Julie Yang, Hyunsoo Ciubotaru, Florin Chumak, Andrii Naeemi, Azad J. Cotofana, Sorin D. Tomasello, Riccardo Panagopoulos, Christos Carpentieri, Mario Lin, Peng Pan, Gang Joshua Yang, J. Todri-Sanial, Aida Boschetto, Gabriele Makasheva, Kremena Sangwan, Vinod K. Trivedi, Amit Ranjan Hersam, Mark C. Camsari, Kerem Y. McMahon, Peter L. Datta, Supriyo Koiller, Belita Aguilar, Gabriel H. Temporão, Guilherme P. Rodrigues, Davi R. Sunada, Satoshi Everschor-Sitte, Karin Tatsumura, Kosuke Goto, Hayato Puliafito, Vito Åkerman, Johan Takesue, Hiroki Ventra, Massimiliano Di Pershin, Yuriy V. Mukhopadhyay, Saibal Roy, Kaushik Wang, I-Ting Kang, Wang Zhu, Yao Kaushik, Brajesh Kumar Hasler, Jennifer Ganguly, Samiran Ghosh, Avik W. Levy, William Roychowdhury, Vwani Bandyopadhyay, Supriyo Department of Mathematical and Computer Sciences Physical Sciences and Earth Sciences University of Messina Messina98166 Italy Chandra Family Department of Electrical and Computer Engineering University of Texas at Austin AustinTX78712 United States Department of Electrical and Computer Engineering University of Texas at Dallas RichardsonTX75080 United States Department of Electrical and Computer Engineering National University of Singapore Singapore117576 Singapore Department of Engineering University of Messina Messina98166 Italy Laboratoire Albert Fert CNRS Thales Université Paris-Saclay Palaiseau91767 France IMEC Leuven3001 Belgium Faculty of Physics University of Vienna Vienna1090 Austria School of Electrical & Computer Engineering Georgia Institute of Technology AtlantaGA30332 United States Quantum and Computer Engineering Department Delft University of Technology DelftCD 2628 Netherlands Department of Electrical and Information Engineering Politecnico di Bari Bari70125 Italy Division of Physics and Applied Physics School of Physical and Mathematical Sciences Nanyang Technological University Singapore639798 Singapore College of Computer Science and Technology Zhejiang University Hangzhou310013 China Department of Electrical and Computer Engineering University of Southern California Los AngelesCA90089 United States Electrical Engineering Department Eindhoven University of Technology AZ Eindhoven5612 Netherlands Microelectronics Department LIRMM Université de Montpellier Montpellier34095 France Laplace CNRS UT3 INPT University of Toulouse Toulouse31062 France Department of Materials Science and Engineering Northwestern University EvanstonIL60208 United States Department of Electrical and Computer Engineering University of Illinois at Chicago ChicagoIL60607 United States Department of Electrical and Computer Engineering University of California at Santa Barbara Santa BarbaraCA93106 United States School of Applied and

In the "Beyond Moore's Law" era, with increasing edge intelligence, domain-specific computing embracing unconventional approaches will become increasingly prevalent. At the same time, adopting a variety of nanotechnologies will offer benefits in energy cost, computational speed, reduced footprint, cyber resilience, and processing power. The time is ripe for a roadmap for unconventional computing with nanotechnologies to guide future research, and this collection aims to fill that need. The authors provide a comprehensive roadmap for neuromorphic computing using electron spins, memristive devices, two-dimensional nanomaterials, nanomagnets, and various dynamical systems. They also address other paradigms such as Ising machines, Bayesian inference engines, probabilistic computing with p-bits, processing in memory, quantum memories and algorithms, computing with skyrmions and spin waves, and brain-inspired computing for incremental learning and problem-solving in severely resource-constrained environments. These approaches have advantages over traditional Boolean computing based on von Neumann architecture. As the computational requirements for artificial intelligence grow 50 times faster than Moore's Law for electronics, more unconventional approaches to computing and signal processing will appear on the horizon, and this roadmap will help identify future needs and challenges. In a very fertile field, experts in the field aim to present some of the dominant and most promising technologies for unconventional computing that will be around for some time to come. Within a holistic approach, the goal is to provide pathways for solidifying the field and guiding future impactful discoveries. © 2023, CC BY-NC-SA.

关键词： Nanotechnology

来源：评论

学校读者我要写书评

暂无评论

Long Text Classification Based on BERT 5

Long Text Classification Based on BERT

引用

5th IEEE information Technology, networking, Electronic and Automation Control Conference, ITNEC 2021

作者： Weijie, DIng Yunyi, Li Jing, Zhang Xuchen, Shen Big-data and Network Security Research Institute Zhejiang Police College Hangzhou310053 China College of Information Engineering Zhejiang University of Technology Hangzhou310023 China Key Laboratory of Public Security Information Application Based on Big-data Architecture Ministry of Public Security Hangzhou310053 China Zhejiang Police College Department of Investigation Hangzhou310053 China Zhejiang Police College Department of Computer and Information Security Hangzhou310053 China Science and Technology Management Section Hangzhou311203 China

ISBN: (纸本)9781665415989

Existing text classification algorithms generally have limitations in terms of text length and yield poor classification results for long texts. To address this problem, we propose a BERT-based long text classification method. First, we slice the long text and use BERT to encode the sliced clauses to obtain the local semantic information. Second, we use BiLSTM to fuse the local semantic information and adopt the attention mechanism to increase the weight of important clauses in the long text, so as to obtain the global semantic information. Finally, the global semantic information is input to the softmax layer for classification. Experimental results show that the proposed method achieves higher accuracy than commonly used models. © 2021 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

LAVS: A LIGHTWEIGHT AUDIO-VISUAL SALIENCY PREDICTION MODEL

LAVS: A LIGHTWEIGHT AUDIO-VISUAL SALIENCY PREDICTION MODEL

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Zhu, Dandan Zhao, Defang Min, Xiongkuo Han, Tian Zhou, Qiangqiang Yu, Shaobo Chen, Yongqing Zhai, Guangtao Yang, Xiaokang MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China School of Software Engineering Tongji University China Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Department of Computer Science Stevens Institute of Technology United States School of Software Jiangxi Normal University China Information Technology Services East China Normal University China College of Information and Communication Hainan University China

ISBN: (纸本)9781665438643

Audio information is essential for guiding human attention and visual perception, which has been verified by many comprehensive psychological studies. However, the audio modality has been rather neglected in modeling visual attention, most of the current visual attention models heavily depend on visual information. Additionally, current existing high-performing visual attention models rely on deeper convolution neural networks (CNNs), benefiting from their extraordinary feature learning ability but incurring high computational cost. To this end, we propose a novel lightweight audio-visual saliency (LAVS) model to efficiently address the problem of fixation prediction in videos. To the best of our knowledge, our proposed model constitutes the first attempt to exploit a lightweight network and combines the visual and audio cues to perform saliency estimation in videos. Specifically, our proposed model consists of four modules, which are spatial-temporal visual saliency estimation module, audio features extraction module, source sound localization module, and audio-visual saliency fusion module. Extensive experiments across datasets validate the effectiveness and real-time performance of the proposed LAVS model, which outperforms the other state-of-the-art methods. © 2021 IEEE

关键词： Behavioral research

来源：评论

学校读者我要写书评

暂无评论

Thickness Dependence of Unidirectional Magnetoresistance in Co2MnGa Films

Thickness Dependence of Unidirectional Magnetoresistance in ...

引用

Magnetic Conference - Short Papers (INTERMAG Short Papers), IEEE International

作者： Bin Rong Lizhu Ren Hongsheng Zheng Liang Liu Yumeng Yang School of Information Science and Technology ShanghaiTech University Shanghai China Shanghai Engineering Research Center of Energy Efficient and Custom AI IC ShanghaiTech University Shanghai China Department of Electrical and Computer Engineering National University of Singapore Singapore Key Laboratory of Artificial Structures and Quantum Control (Ministry of Education) TD Lee institute School of Physics and Astronomy Shanghai Jiao Tong University Shanghai China Hefei National Laboratory Hefei China Shanghai Research Center for Quantum Sciences Shanghai China

ISBN: (数字)9798350362213

ISBN: (纸本)9798350362220

With intrinsic giant anomalous Hall and Nernst effects, Weyl ferromagnet C02MnGa stands as an ideal candidate for exploring efficient charge-to-spin conversions. In this work, by utilizing the high-quality epitaxial C02MnGa single films, we observed a sizable unidirectional magnetoresistance. Surprisingly, the isotropic crystallographic axis dependence of unidirectional magnetoresistance, together with its linear scaling to the C02MnGa thickness, neither can be explained by the conventional spin current drift-diffusion process. By employing heat equation, we analytically derived the current induced vertical temperature gradient, and unambiguously show the thickness dependence of unidirectional magnetoresistance induced by anomalous Nernst effects. Our work provides direct evidences of thermoelectric voltages in the nonlinear transport that may be extended to other material systems as well.

关键词： Magnetic films Heating systems Temperature dependence Giant magnetoresistance Epitaxial growth

来源：评论

学校读者我要写书评

暂无评论

Room-temperature multiple ligands-tailored SnO_(2) quantum dots endow in situ dual-interface binding for upscaling efficient perovskite photovoltaics with high V_(OC)

引用

Light(science & Applications) 2021年第12期10卷 2467-2481页

作者： Zhiwei Ren Kuan Liu Hanlin Hu Xuyun Guo Yajun Gao Patrick W.K.Fong Qiong Liang Hua Tang Jiaming Huang Hengkai Zhang Minchao Qin Li Cui Hrisheekesh Thachoth Chandran Dong Shen Ming-Fai Lo Annie Ng Charles Surya Minhua Shao Chun-Sing Lee Xinhui Lu Frédéric Laquai Ye Zhu Gang Li Department of Electronic and Information Engineering Research Institute for Smart Energy(RISE)Guangdong-Hong Kong-Macao(GHM)Joint Laboratory for Photonic-Thermal-Electrical Energy Materials and DevicesThe Hong Kong Polytechnic UniversityHung HomKowloonHong KongChina Department of Electrical and Computer Engineering Nazarbayev UniversityNur-SultanKazakhstan The Hong Kong Polytechnic University Shenzhen Research Institute Shenzhen 518057China Hoffmann Institute of Advanced Materials Shenzhen Polytechnic7098 Liuxian BoulevardShenzhen 518055China Department of Applied Physics The Hong Kong Polytechnic UniversityHung HomKowloonHong KongChina Department of Chemical and Biological Engineering The Hong Kong University of Science and TechnologyClear Water BayKowloonHong KongChina King Abdullah University of Science and Technology(KAUST) KAUST Solar Center(KSC)Physical Sciences and Engineering Division(PSE)Material Science and Engineering Program(MSE)Thuwal 23955-6900Kingdom of Saudi Arabia Department of Physics The Chinese University of Hong KongShatin 999077 Hong KongChina Center of Super-Diamond and Advanced Films(COSDAF) Department of ChemistryCity University of Hong KongHong KongChina

The benchmark tin oxide(SnO_(2))electron transporting layers(ETLs)have enabled remarkable progress in planar perovskite solar cell(PSCs).However,the energy loss is still a challenge due to the lack of“hidden interface”*** report a novel ligand-tailored ultrafine SnO_(2) quantum dots(QDs)via a facile rapid room temperature ***,the ligand-tailored SnO_(2) QDs ETL with multi-functional terminal groups in situ refines the buried interfaces with both the perovskite and transparent electrode via enhanced interface binding and perovskite *** novel ETLs induce synergistic effects of physical and chemical interfacial modulation and preferred perovskite crystallization-directing,delivering reduced interface defects,suppressed non-radiative recombination and elongated charge carrier *** conversion efficiency(PCE)of 23.02%(0.04 cm^(2))and 21.6%(0.98 cm^(2),V_(OC) loss:0.336 V)have been achieved for the blade-coated PSCs(1.54 eV E_(g))with our new ETLs,representing a record for SnO_(2) based blade-coated ***,a substantially enhanced PCE(V_(OC))from 20.4%(1.15 V)to 22.8%(1.24 V,90 mV higher V_(OC),0.04 cm^(2) device)in the blade-coated 1.61 eV PSCs system,via replacing the benchmark commercial colloidal SnO_(2) with our new ETLs.

关键词： perovskite interface quantum

来源：评论

学校读者我要写书评

暂无评论

DUBLINE: A DEEP UNFOLDING network FOR B-LINE DETECTION IN LUNG ULTRASOUND IMAGES

arXiv

引用

arXiv 2023年

作者： Yang, Tianqi Anantrasirichai, Nantheera Karakuş, Oktay Allinovi, Marco Koydemir, Hatice Ceylan Achim, Alin Visual Information Lab University of Bristol Bristol United Kingdom School of Computer Science and Informatics Cardiff University Cardiff United Kingdom Nephrology Dialysis and Transplantation Careggi University Hospital Florence Italy Department of Biomedical Engineering Texas A&M University United States Center for Remote Health Technologies and Systems Texas A&M Engineering Experiment Station United States

In the context of lung ultrasound, the detection of B-lines, which are indicative of interstitial lung disease and pulmonary edema, plays a pivotal role in clinical diagnosis. Current methods still rely on visual inspection by experts. Vision-based automatic B-line detection methods have been developed, but their performance has yet to improve in terms of both accuracy and computational speed. This paper presents a novel approach to posing B-line detection as an inverse problem via deep unfolding of the Alternating Direction Method of Multipliers (ADMM). It tackles the challenges of data la-belling and model training in lung ultrasound image analysis by harnessing the capabilities of deep neural networks and model-based methods. Our objective is to substantially enhance diagnostic accuracy while ensuring efficient real-time capabilities. The results show that the proposed method runs more than 90 times faster than the traditional model-based method and achieves an F1 score that is 10.6% higher. © 2023, CC BY.

关键词： Inverse problems

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：