检索结果-内蒙古大学图书馆

Lecture Notes in Electrical Engineering 2020年 603卷 v-vi页

作者： Alfred, Rayner Haviluddin, Haviluddin Lim, Yuto On, Chin Kim Knowledge Technology Research Unit Faculty of Computing and Informatics Universiti Malaysia Sabah Kota KinabaluSabah Malaysia Department of Computer Science Universitas Mulawarman Samarinda Indonesia School of Information Science Security and Networks Area Japan Advanced Institute of Science and Technology Nomi Ishikawa Japan Center of Data and Information Management Universiti Malaysia Sabah Kota KinabaluSabah Malaysia

来源：评论

学校读者我要写书评

暂无评论

Biomedical image analysis competitions: The state of current participation practice

arXiv

引用

arXiv 2022年

作者： Eisenmann, Matthias Reinke, Annika Weru, Vivienn Tizabi, Minu Dietlinde Isensee, Fabian Adler, Tim J. Godau, Patrick Cheplygina, Veronika Kozubek, Michal Maier-Hein, Klaus Jäger, Paul F. Kopp-Schneider, Annette Maier-Hein, Lena Ali, Sharib Gupta, Anubha Kybic, Jan Noble, Alison de Solórzano, Carlos Ortiz Pachade, Samiksha Petitjean, Caroline Sage, Daniel Wei, Donglai Wilden, Elizabeth Alapatt, Deepak Andrearczyk, Vincent Baid, Ujjwal Bakas, Spyridon Balu, Niranjan Bano, Sophia Bawa, Vivek Singh Bernal, Jorge Bodenstedt, Sebastian Casella, Alessandro Choi, Jinwook Commowick, Olivier Daum, Marie Depeursinge, Adrien Dorent, Reuben Egger, Jan Eichhorn, Hannah Engelhardt, Sandy Ganz, Melanie Girard, Gabriel Hansen, Lasse Heinrich, Mattias Heller, Nicholas Hering, Alessa Huaulmé, Arnaud Kim, Hyunjeong Li, Hongwei Bran Landman, Bennett Li, Jianning Ma, Jun Martel, Anne Martín-Isla, Carlos Menze, Bjoern Nwoye, Chinedu Innocent Oreiller, Valentin Padoy, Nicolas Pati, Sarthak Payette, Kelly Sudre, Carole van Wijnen, Kimberlin Vardazaryan, Armine Vercauteren, Tom Wagner, Martin Wang, Chuanbo Yap, Moi Hoon Yu, Zeyun Yuan, Chun Zenk, Maximilian Zia, Aneeq Zimmerer, David Bao, Rina Choi, Chanyeol Cohen, Andrew Dzyubachyk, Oleh Galdran, Adrian Gan, Tianyuan Guo, Tianqi Gupta, Pradyumna Haithami, Mahmood Ho, Edward Jang, Ikbeom Li, Zhili Luo, Zhengbo Lux, Filip Makrogiannis, Sokratis Müller, Dominik Oh, Young-Tack Pang, Subeen Pape, Constantin Polat, Gorkem Reed, Charlotte Rosalie Ryu, Kanghyun Scherr, Tim Thambawita, Vajira Wang, Haoyu Wang, Xinliang Xu, Kele Yeh, Hung Yeo, Doyeob Yuan, Yixuan Zeng, Yan Zhao, Xin Abbing, Julian Adam, Jannes Adluru, Nagesh Agethen, Niklas Ahmed, Salman Al Khalil, Yasmina Alenyà, Mireia Alhoniemi, Esa An, Chengyang Arega, Tewodros Weldebirhan Avisdris, Netanell Aydogan, Dogu Baran Bai, Yingbin Calisto, Maria Baldeon Basaran, Berke Doga Beetz, Marcel Bian, Hao Blansit, Kevin Bloch, Louise Bohnsack, Robert Bosticardo, Sara Breen, Jack Brudfors, Mikael Brüngel, Raphael Cabezas, Mariano Cacciola, Alb Heidelberg Division of Intelligent Medical Systems Germany Heidelberg HI Helmholtz Imaging Germany Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany Heidelberg Division of Biostatistics Germany Heidelberg Division of Medical Image Computing Germany Heidelberg HI Applied Vision Lab Germany IT University of Copenhagen Copenhagen Denmark Centre for Biomedical Image Analysis Masaryk University Brno Czech Republic Heidelberg Interactive Machine Learning Group Germany Faculty of Mathematics and Computer Science and Medical Faculty Heidelberg University Heidelberg Germany NCT Heidelberg DKFZ University Hospital Heidelberg Germany School of Computing University of Leeds Leeds United Kingdom SBILab Department of ECE IIIT-Delhi India Faculty of Electrical Engineering Czech Technical University Prague Czech Republic Institute of Biomedical Engineering University of Oxford United Kingdom Center for Applied Medical Research Pamplona Spain Shri Guru Gobind Singhji Institute of Engineering and Technology Maharashtra Nanded India Université de Rouen Normandie France Lausanne Switzerland School of Engineering and Applied Science Harvard University United States ICube University of Strasbourg CNRS France Institute of Informatics School of Management HES-SO Valais-Wallis University of Applied Sciences and Arts Western Switzerland Techno-Pôle 3 Sierre3960 Switzerland Department of Nuclear Medicine and Molecular Imaging Lausanne University Hospital Rue du Bugnon 46 LausanneCH-1011 Switzerland University of Pennsylvania PhiladelphiaPA United States Department of Radiology University of Washington United States Wellcome EPSRC Centre for Interventional and Surgical Sciences University College London London United Kingdom Visual Artificial Intelligence Lab Oxford Brookes University Oxford United Kingdom Universitat Autònoma de Barcelona & Computer Vision Center Spain Dresden Fetscherstraße 74 PF 64 Dresden01307 Germany

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps. © 2022, CC BY.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Spatially-resolved spectro-photometric SED Modeling of NGC 253’s Central Molecular Zone I. Studying the star formation in extragalactic giant molecular clouds

arXiv

引用

arXiv 2025年

作者： Humire, Pedro K. Dey, Subhrata Ronconi, Tommaso Sasse, Victor H. Fernandes, Roberto Cid Martín, Sergio Donevski, Darko Malek, Katarzyna Fernández-Ontiveros, Juan A. Song, Yiqing Hamed, Mahmoud Mangum, Jeffrey G. Henkel, Christian Rivilla, Víctor M. Colzi, Laura Harada, N. Demarco, Ricardo Goyal, Arti Meier, David S. Panda, Swayamtrupta Krabbe, Ângela C. Yan, Yaoting Lopes, Amanda R. Sakamoto, K. Muller, S. Tanaka, K. Yoshimura, Y. Nakanishi, K. Kanaan, Antonio Ribeiro, Tiago Schoenell, William de Oliveira, Claudia Mendes Departamento de Astronomia Instituto de Astronomia Geofísica e Ciências Atmosféricas da USP Cidade Universitária SP São Paulo05508-090 Brazil Astronomical Observatory The Jagiellonian University Orla 171 Kraków30-244 Poland National Center for Nuclear Research ul. Pasteura 7 Warsaw02-093 Poland Via Bonomea 265 TriesteIT-34136 Italy Via Beirut 2 TriesteIT-34151 Italy Via Gobetti 93/3 BolognaI-40127 Italy ICSC – Centro Nazionale di Ricerca in High Performance Computing Big Data e Quantum Computing Via Magnanelli 2 Bologna Italy Universidade Federal de Santa Catarina Campus Universitário Reitor João David Ferreira Lima SC Florianópolis88040-900 Brazil European Southern Observatory Alonso de Córdova 3107 Vitacura Santiago763-0355 Chile Joint ALMA Observatory Alonso de Córdova 3107 Vitacura Santiago763-0355 Chile Plaza San Juan 1 TeruelE–44001 Spain CSIC-INTA Carretera de Ajalvir km 4 Torrejón de Ardoz Madrid28850 Spain National Radio Astronomy Observatory 520 Edgemont Road CharlottesvilleVA22903-2475 United States Max-Planck-Institut für Radioastronomie Auf-dem-Hügel 69 Bonn53121 Germany Xinjiang Astronomical Observatory Chinese Academy of Sciences Urumqi830011 China National Astronomical Observatory of Japan 2-21-1 Osawa Mitaka Tokyo181-8588 Japan Institute of Astronomy and Astrophysics Academia Sinica 11F of AS/NTU Astronomy-Mathematics Building No.1 Sec. 4 Roosevelt Rd Taipei106319 Taiwan 2-21-1 Osawa Mitaka Tokyo181-1855 Japan Institute of Astrophysics Facultad de Ciencias Exactas Universidad Andrés Bello Sede Concepción Talcahuano Chile New Mexico Institute of Mining and Technology 801 Leroy Place SocorroNM87801 United States International Gemini Observatory NSF NOIRLab Casilla 603 La Serena Chile Instituto de Astrofísica de La Plata CONICET-UNLP Paseo del Bosque s/n B1900FWA Argentina Department of Space Earth and Environment Chalmers University of Technology Onsala Space Observatory OnsalaSE-4

Context. Studying the interstellar medium in nearby starbursts is essential for gaining insights into the physical mechanisms driving these extreme objects, thought to be analogs of young, primeval, star-forming galaxies. This task is now feasible due to deep spectro-photometric data enabled by rapid advancements in ground- and space-based facilities. To fully leverage this wealth of information, extracting insights from the spectral line properties, and the spectral energy distribution (SED) is imperative. Aims. This study aims to produce and analyze the physical properties of the first spatially-resolved multi-wavelength SED of an extragalactic source that covers six decades in frequency (from near-ultraviolet to centimeter wavelengths) at an angular resolution of 3′′ which corresponds to linear scale of ∼51 pc at the distance of NGC 253. We focus on the central molecular zone (CMZ) of this starburst galaxy, which contains giant molecular clouds (GMCs) responsible for half of the galaxy’s star formation. Methods. We retrieve archival data from optical to centimeter wavelengths, covering six decades of spectral range. We compute SEDs to fit the observations using the GalaPy code and confronting results with the CIGALE code for validation. We also employ starlight library to analyze the stellar optical spectra of the GMCs. Results. Our results reveal significant differences between central and external GMCs in terms of stellar and dust masses, star formation rates (SFRs), and bolometric luminosities, to provide a few. We have obtained tight relations between monochromatic stellar tracers and star-forming conditions obtained from panchromatic emission. We find that the best SFR tracers are radio continuum bands at 33 GHz, radio recombination lines (RRLs), and the total infrared (IR) luminosity range (LIR;8–1000µm) as well as the IR emission at 60µm. The emission line diagnostics based on the BPT and WHAN diagrams suggest that the nuclear region of NGC 253 exhibits sh

关键词： Optical emission spectroscopy

来源：评论

学校读者我要写书评

暂无评论

The Wide-field Spectroscopic Telescope (WST) science White Paper

arXiv

引用

arXiv 2024年

作者： Mainieri, Vincenzo Anderson, Richard I. Brinchmann, Jarle Cimatti, Andrea Ellis, Richard Hill, Vanessa Kneib, Jean-Paul McLeod, Anna Opitom, Cyrielle Roth, Martin M. Sáez, Paula Sánchez Smiljanic, Rodolfo Tolstoy, Eline Bacon, Roland Randich, Sofia Pasquini, Luca Barsanti, Stefania Bryant, Julia Bryson, Ian Casali, Mark Colless, Matthew Couch, Warrick Danielski, Camilla Dierickx, Philippe Driver, Simon Fontana, Adriano Garilli, Bianca de Jong, Roelof S. Lee, David Lehnert, Matt Magrini, Laura Montet, Ben Sanchez-Janssen, Ruben Pandey-Pommier, Mamta Sargent, Mark Schipani, Pietro Steinmetz, Matthias Travouillon, Tony Tresse, Laurence Vernet, Joël Yeche, Christophe Ziegler, Bodo Audard, Marc Arévalo, Patricia Bayo Aran, Amelia M. Bisero, Sofia Bisogni, Susanna Blondin, Stéphane Bonito, Rosaria Branchesi, Marica Catelan, Márcio D'Ammando, Filippo Dainotti, Maria G. De Cia, Annalisa Dhawan, Suhail Dupletsa, Ulyana Hazra, Nandini Ilić, Dragana Ivanov, Valentin D. Izzo, Luca Kovačević, Andjelka B. Kuncarayakti, Hanindyo Kwon, Yuna La Forgia, Fiorangela Lazzarin, Monica Lira, Paulina Loffredo, Eleonora Maguire, Kate Majidi, Fatemeh Z. Marconi, Marcella McGee, Sean Migliorini, Alessandra Minniti, Dante Nicholl, Matt Onori, Francesca Pala, Anna F. Panda, Swayamtrupta Pawlak, Michal Pessi, Priscila J. Popović, Luka Č. Smith, Graham P. Vergani, Susanna D. Vietri, Giustina Ye, Quanzhi Zafar, Tayyaba Matsuno, Tadafumi Kordopatis, Georges Annibali, Francesca Bayo, Amelia Bellazzini, Michele Beltran, Maria Teresa Berni, Leda Bianchi, Simone Biazzo, Katia Bland-Hawthorn, Joss Boffin, Henri M.J. Bono, Giuseppe Bowman, Dominic Braga, Vittorio F. Bragaglia, Angela Brucalassi, Anna Busà, Innocenza Casali, Giada Casasola, Viviana Castro, Norberto Cavallo, Lorenzo Chiappini, Cristina Colzi, Laura Damiani, Francesco da Silva, Ronaldo D'Orazi, Valentina Escorza, Ana Fabrizio, Michele Fiorentino, Giuliana Fontani, Francesco François, Patrick Galindo-Guil, Francisco J. Galli, Daniele Garcia-Rojas, Jorge Guarcello, Mario Giuseppe Helmi, Am European Southern Observatory Karl-Schwarzschild-Strasse 2 Garching bei München85748 Germany Switzerland Instituto de Astrofísica e Ciências do Espaço Universidade do Porto Portugal Dipartimento di Fisica e Astronomia "Augusto Righi" Alma Mater Studiorum Università di Bologna Italy Department of Physics and Astronomy University College London United Kingdom Observatoire de la Côte d'Azur Université Côte d'Azur CNRS Laboratoire Lagrange France Centre for Extragalactic Astronomy Department of Physics Durham University United Kingdom Institute for Computational Cosmology Department of Physics University of Durham United Kingdom Institute for Astronomy University of Edinburgh United Kingdom Germany Nicolaus Copernicus Astronomical Center Polish Academy of Sciences Poland Kapteyn Astronomical Institute University of Groningen Netherlands France INAF - Osservatorio Astrofisico di Arcetri Italy Stockholm University Sweden INAF - Osservatorio di Astrofisica e Scienza dello Spazio di Bologna Italy Universidad de Valparaíso Chile University of Geneva Switzerland Research School of Astronomy and Astrophysics Australian National University CanberraACT2611 Australia Australia Instituto de Astrofísica de Canarias Spain Universidad de La Laguna Spain SISSA - Scuola Internazionale Superiore di Studi Avanzati Italy University of Florence Italy INAF - Osservatorio Astronomico di Roma Italy GEPI Observatoire de Paris Universite PSL CNRS France INAF Istituto di Astrofisica Spaziale e Fisica cosmica Milano Italy Sydney Institute for Astronomy School of Physics The University of Sydney Australia Aix Marseille Univ CNRS CNES LAM France INAF - Osservatorio Astronomico di Palermo Italy University of Rome Tor Vergata Italy Newcastle University United Kingdom Italy UK Astronomy Technology Ctr. Royal Observatory Edinburgh United Kingdom INAF OACT Italy Dipartimento di Fisica Università degli Studi di Torino Italy Istituto Nazionale di Fisica Nucleare INFN Sezione di

The WST is proposed as a new facility dedicated to the efficient delivery of spectroscopic surveys and this white paper summarises the initial concept as well as the corresponding science cases. It will provide an end-to-end service from the preparation of surveys to the delivery of high-quality calibrated science data product. Uniquely, it will have the ability to simultaneously deliver fibre-fed multi-object spectroscopy over a large field of view (MOS) and integral field imaging spectroscopy of a central field of 3 × 3 arcmin2 (IFS). WST will fill a crucial gap in the astronomical landscape and will allow full exploitation of major current and upcoming ground and space-based facilities. WST will address outstanding scientific questions in the areas of cosmology;galaxy assembly, evolution, and enrichment, including our own Milky Way;origin of stars and planets;time domain and multi-messenger astrophysics. WST features a 12 meter aperture telescope that covers the UV to the H band and operates in seeing limited conditions. Its field of view (FoV) of 3.1 deg2 will be the largest of any telescope equipped with a MOS. In particular, its FoV is 2.5 times larger than PFS@Subaru and a remarkable 22 times larger than MOONS@VLT. In addition, the WST has a substantial aperture, twice as large (100 square metres) as its 8 meter class competitors. A central circular area with a diameter of 13 arcmin is available for simultaneous IFS observations. Within this area, the IFS with a FoV of 3 × 3 arcmin2 (9 times larger than MUSE@VLT) can be utilised simultaneously with the MOS. In addition, the IFS can be used to mosaic a larger area within the 13 arcmin circle (an area larger than the entire FoV of the ELT) while the MOS positioner can perform multiple configurations. The WST operational model will also implement target of opportunity (ToO) operations at both the telescope and MOS fibre levels to support the time domain science cases. The demand for a facility dedicated to spect

关键词： Telescopes

来源：评论

学校读者我要写书评

暂无评论

Magnetohydrodynamics with Forced Convection in Micropolar Fluid Flows Pass a Magnetic Porous Sphere

引用

Journal of Physics: Conference Series 2019年第1期1153卷

作者： Basuki Widodo Rahayu Oktavia P Nur Asiyah Dieky Adzkiya Department of Mathematics Faculty of Mathematics Computing and Data Science Institut Teknologi Sepuluh Nopember Jl. Raya ITS Sukolilo Surabaya 60111 INDONESIA

The research of fluid flows is growing. The physical research requires a high cost. So, it is needed science studies that can solve the problem. One of them is mathematical modeling. This research considers magnetic field effect in unsteady magnetohydrodynamics of micropolar fluid through a magnetic porous sphere with forced convection. Governing equations are derived from continuity, momentum, angular momentum, and energy equations. The form of these equations are two dimensional partial differential equations. Dimensional equations are transformed to non-dimensional equations and then, it will be converted to similarity equations. The similarity equations are solved numerically using Keller-Box scheme. It could be concluded that velocity curve decreases when magnetic, porosity and micropolar parameters increase. Microrotation curve increases with the increasing of magnetic, porosity, and micropolar parameters.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implementation Euler implicit scheme of unsteady magnetohydrodinamic micropolar fluid pass a sphere affected by mixed convection

引用

Journal of Physics: Conference Series 2019年第1期1153卷

作者： Basuki Widodo Mufatin Fauziyah Dieky Adzkiya Mathematics Departemen Faculty of Mathematics Computing and Science Data Institut Teknologi Sepuluh Nopember Indonesia Jalan Raya ITS Sukolilo Surabaya 60111 INDONESIA

This paper considers the effect of mixed convection and magnetic field sphere in the unsteady magnetohydrodynamic micropolar fluid. For solving this problem, we develop dimensional governing equations from mass conservation law, energy conservation law, and Second Newton Law for momentum and angular momentum. We further convert them into non dimensional equations by using non dimensional variables. These non dimensional equations are further transformed into similarity equations using stream functions. Similarity equations are further solved numerically by implementing numerical method with euler implicit scheme. The result shows that the velocity and temperature will increase when parameter magnetic and mixed convection decrease. The higher magnetic parameter leads to higher microrotation of micropolar fluid particle. Whereas microrotation profile decrease with increasing mixed convection parameter.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An energy-efficient VM consolidation algorithm for cloud data centers 5

An energy-efficient VM consolidation algorithm for cloud dat...

引用

5th International Conference on Information science and Cloud computing, ISCC 2017

作者： Wu, Xiaodong Faculty of Mathematics and Computer Science Quanzhou Normal University Fujian Provincial Key Laboratory of Data Intensive Computing Quanzhou362000 China

Cloud data centers consume vast amounts of electrical energy all over the world. Energy conservation in data centers has become a severe problem. This paper presents an energy-efficient virtual machine (VM) consolidation algorithm for cloud data centers. The proposed policy exploits the average utilization of each VM to estimate the expected utilization of physical hosts. Then, the expected utilization, the actual utilization and the static threshold are combined together to determine whether a host is at the status of overloading or not. Some VM(s) on the overloading hosts are then selected for migration to avoid Service Level Agreements (SLA) violations. The results of the experiment show that the proposed algorithm can effectively reduce energy consumption while guarantee SLAs. © Copyright owned by the author(s).

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

DP03 Melanoma detection in whole-slide images using a convolutional neural network for objective prognostic biomarker generation

引用

British Journal of Dermatology 2024年第SUPPLEMENT_1期191卷 i108–i108页

作者： Clarke, Emily L Magee, Derek Newton-Bishop, Julia Merchant, William Hall, Marlous Insall, Robert Maher, Nigel G Scolyer, Richard A Farnworth, Grace Ali, Anisah Saldanha, Gerald Bamford, Mark Sitcova, Eva Kujal, Petr O’Shea, Sally Treanor, Darren Department of Histopathology Leeds Teaching Hospitals NHS Trust Leeds UK Division of Pathology and Data Analytics University of Leeds Leeds UK School of Computing University of Leeds Leeds UK Leeds Institute for Medical Research University of Leeds Leeds UK Department of Clinical and Population Sciences Leeds Institute of Cardiovascular and Metabolic Medicine University of Leeds Leeds UK Department of Cell and Developmental Biology University College London London UK Melanoma Institute Australia The University of Sydney Sydney Australia Faculty of Medicine and Health The University of Sydney Sydney Australia Tissue Pathology and Diagnostic Oncology Royal Prince Alfred Hospital and NSW Health Pathology Sydney Australia Charles Perkins Centre The University of Sydney Sydney NSW Australia Leicester Cancer Research Centre University of Leicester Leicester UK Department of Histopathology University Hospitals of Leicester NHS Trust Leicester UK Department of Pathology Third Faculty of Medicine Charles University and Teaching Hospital Královské Vinohrady Prague Czechia Dermatology Department South Infirmary Victoria University Hospital Cork Ireland School of Medicine University College Cork Ireland Department of Clinical Pathology and Department of Clinical and Experimental Medicine Linköping University Linköping Sweden Center for Medical Image Science and Visualization (CMIV) Linköping University Linköping Sweden

The current melanoma staging system is predictive of 74% of the variance in survival, with prognostic biomarkers subject to high levels of interobserver and intraobserver variation. Melanoma morphology appears to be of greater significance than in other solid tumours, with Breslow thickness remaining the strongest prognostic indicator. The application of convolutional neural networks (CNNs) to whole-slide images (WSIs) may reveal new insights into tumour morphology and therefore patient prognosis. This work outlines the development and evaluation of a CNN for invasive cutaneous melanoma detection in WSIs, to enable the creation of objective prognostic biomarkers based on the tissue morphology. In total, 1157 WSIs containing cutaneous melanoma from five sources have been used in the initial development and evaluation of a custom-designed two-class tumour segmentation network with a fully convolutional architecture. The CNN detected and located invasive melanoma tissue of no specific type with an average per-pixel sensitivity and specificity of 97.6% and 99.9%, respectively across, the five test sets (three external). There were no statistical differences between tumour dimensions generated by the CNN compared with manual annotation. Similarly, there were no statistically significant differences between CNN-generated tumour dimensions across three scanning platforms. Furthermore, we have identified that this CNN can be used to calculate the ‘digital Breslow thickness’, which is a strong independent prognostic predictor of overall survival and melanoma-specific survival, across three test sets with follow-up data (hazard ratio 1.26, 95% confidence interval 1.19–1.34,P< 0.001). We have also shown that the ‘nodularity index’ determined by the tumour shape, independently of size, is predictive of survival; the rounder the tumour the worse the outcome (hazard ratio 0.71, 95% confidence interval 0.60–0.83,P< 0.001). We have developed and performed initial evaluation of a CN

关键词：

来源：评论

学校读者我要写书评

暂无评论

Two layers of annotation for representing event mentions in news stories 11

Two layers of annotation for representing event mentions in ...

引用

11th Linguistic Annotation Workshop, LAW 2017

作者： Di Buono, Maria Pia Tutek, Martin Šnajder, Jan Glavaš, Goran Bašić, Bojana Dalbelo Milić-Frayling, Nataša TakeLab Faculty of Electrical Engineering and Computing University of Zagreb Croatia Data and Web Science Group University of Mannheim Germany School of Computer Science University of Nottingham United Kingdom

ISBN: (纸本)9781945626395

In this paper, we describe our preliminary study of methods for annotating event mentions as part of our research on highprecision models for event extraction from news. We propose a two-layer annotation scheme, designed to capture the functional and the conceptual aspects of event mentions separately. We hypothesize that the precision can be improved by modeling and extracting the different aspects of news events separately, and then combining the extracted information by leveraging the complementarities of the models. We carry out a preliminary annotation using the proposed scheme and analyze the annotation quality in terms of inter-annotator agreement. © 2017 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predicting news values from headline text and emotions 2

Predicting news values from headline text and emotions

引用

EMNLP 2017 2nd Workshop on Natural Language Processing Meets Journal., NLPmJ 2017

作者： Di Buono, Maria Pia Šnajder, Jan Bašic, Bojana Dalbelo Glavaš, Goran Tutek, Martin Milic-Frayling, Natasa TakeLab Faculty of Electrical Engineering and Computing University of Zagreb Croatia Data and Web Science Group University of Mannheim Germany School of Computer Science University of Nottingham United Kingdom

ISBN: (纸本)9781945626883

We present a preliminary study on predicting news values from headline text and emotions. We perform a multivariate analysis on a dataset manually annotated with news values and emotions, discovering interesting correlations among them. We then train two competitive machine learning models - an SVM and a CNN - to predict news values from headline text and emotions as features. We find that, while both models yield a satisfactory performance, some news values are more difficult to detect than others, while some profit more from including emotion information. © EMNLP *** right reserved.

关键词： Forecasting

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：