检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zeng, Jinzhe Zhang, Duo Lu, Denghui Mo, Pinghui Li, Zeyu Chen, Yixiao Rynik, Marián Huang, Li'ang Li, Ziyao Shi, Shaochen Wang, Yingze Ye, Haotian Tuo, Ping Yang, Jiabin Ding, Ye Li, Yifan Tisi, Davide Zeng, Qiyu Bao, Han Xia, Yu Huang, Jiameng Muraoka, Koki Wang, Yibo Chang, Junhan Yuan, Fengbo Bore, Sigbjørn Løland Cai, Chun Lin, Yinnian Wang, Bo Xu, Jiayan Zhu, Jia-Xin Luo, Chenxing Zhang, Yuzhi Goodall, Rhys E.A. Liang, Wenshuo Singh, Anurag Kumar Yao, Sikai Zhang, Jingchao Wentzcovitch, Renata Han, Jiequn Liu, Jie Jia, Weile York, Darrin M. Weinan, E. Car, Roberto Zhang, Linfeng Wang, Han Laboratory for Biomolecular Simulation Research Institute for Quantitative Biomedicine Department of Chemistry and Chemical Biology Rutgers University PiscatawayNJ08854 United States AI for Science Institute Beijing100080 China DP Technology Beijing100080 China Academy for Advanced Interdisciplinary Studies Peking University Beijing100871 China HEDPS CAPT College of Engineering Peking University Beijing100871 China College of Electrical and Information Engineering Hunan University Changsha China Yuanpei College Peking University Beijing100871 China Program in Applied and Computational Mathematics Princeton University PrincetonNJ08540 United States Department of Experimental Physics Comenius University Mlynská Dolina F2 Bratislava842 48 Slovakia Center for Quantum Information Institute for Interdisciplinary Information Sciences Tsinghua University Beijing100084 China Center for Data Science Peking University Beijing100871 China ByteDance Research Zhonghang Plaza No. 43 North 3rd Ring West Road Haidian District Beijing China College of Chemistry and Molecular Engineering Peking University Beijing100871 China Baidu Inc. Beijing China Key Laboratory of Structural Biology of Zhejiang Province School of Life Sciences Westlake University Zhejiang Hangzhou China Westlake AI Therapeutics Lab Westlake Laboratory of Life Sciences and Biomedicine Zhejiang Hangzhou China Department of Chemistry Princeton University PrincetonNJ08544 United States SISSA Scuola Internazionale Superiore di Studi Avanzati Trieste34136 Italy Laboratory of Computational Science and Modeling Institute of Materials École Polytechnique Fédérale de Lausanne Lausanne1015 Switzerland Department of Physics National University of Defense Technology Hunan Changsha410073 China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China School of Electronics Engineerin

DeePMD-kit is a powerful open-source software package that facilitates molecular dynamics simulations using machine learning potentials (MLP) known as Deep Potential (DP) models. This package, which was released in 2017, has been widely used in the fields of physics, chemistry, biology, and material science for studying atomistic systems. The current version of DeePMD-kit offers numerous advanced features such as DeepPot-SE, attention-based and hybrid descriptors, the ability to fit tensile properties, type embedding, model deviation, Deep Potential - Range Correction (DPRc), Deep Potential Long Range (DPLR), GPU support for customized operators, model compression, non-von Neumann molecular dynamics (NVNMD), and improved usability, including documentation, compiled binary packages, graphical user interfaces (GUI), and application programming interfaces (API). This article presents an overview of the current major version of the DeePMD-kit package, highlighting its features and technical details. Additionally, the article benchmarks the accuracy and efficiency of different models and discusses ongoing developments. © 2023, CC BY-NC-ND.

关键词： Molecular dynamics

来源：评论

学校读者我要写书评

暂无评论

Interlayer connectivity reconstruction for multilayer brain networks using phase oscillator models

引用

NEW JOURNAL OF PHYSICS 2021年第6期23卷

作者： Tewarie, Prejaas Prasse, Bastian Meier, Jil Byrne, Aine De Domenico, Manlio Stam, Cornelis J. Brookes, Matthew J. Hillebrand, Arjan Daffertshofer, Andreas Coombes, Stephen Van Mieghem, Piet Sir Peter Mansfield Imaging Centre School of Physics and Astronomy University of Nottingham Nottingham United Kingdom Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft The Netherlands Charité – Universitätsmedizin Berlin Corporate Member of Freie Universität Berlin Humboldt-Universität zu Berlin and Berlin Institute of Health Department of Neurology Brain Simulation Section Berlin Germany School of Mathematics and Statistics University College Dublin Dublin Ireland Fondazione Bruno Kessler Povo (TN) Italy Amsterdam UMC Vrije Universiteit Amsterdam Department of Clinical Neurophysiology and MEG Center Amsterdam Neuroscience Amsterdam The Netherlands Amsterdam Movement Science & Institute for Brain and Behavior Amsterdam Faculty of Behavioural and Movement Sciences Vrije Universiteit Amsterdam The Netherlands School of Mathematical Sciences University of Nottingham Nottingham United Kingdom

Large-scale neurophysiological networks are often reconstructed from band-pass filtered time series derived from magnetoencephalography (MEG) data. Common practice is to reconstruct these networks separately for different frequency bands and to treat them independently. Recent evidence suggests that this separation may be inadequate, as there can be significant coupling between frequency bands (interlayer connectivity). A multilayer network approach offers a solution to analyze frequency-specific networks in one framework. We propose to use a recently developed network reconstruction method in conjunction with phase oscillator models to estimate interlayer connectivity that optimally fits the empirical data. This approach determines interlayer connectivity based on observed frequency-specific time series of the phase and a connectome derived from diffusion weighted imaging. The performance of this interlayer reconstruction method was evaluated in-silico. Our reconstruction of the underlying interlayer connectivity agreed to very high degree with the ground truth. Subsequently, we applied our method to empirical resting-state MEG data obtained from healthy subjects and reconstructed two-layered networks consisting of either alpha-to-beta or theta-to-gamma band connectivity. Our analysis revealed that interlayer connectivity is dominated by a multiplex structure, i.e. by one-to-one interactions for both alpha-to-beta band and theta-to-gamma band networks. For theta-gamma band networks, we also found a plenitude of interlayer connections between distant nodes, though weaker connectivity relative to the one-to-one connections. Our work is an stepping stone towards the identification of interdependencies across frequency-specific networks. Our results lay the ground for the use of the promising multilayer framework in this field with more-informed and justified interlayer connections.

关键词： multiplex networks magnetoencephalography multilayer brain networks phase oscillators Kuramoto model neural mass model multilayer networks

来源：评论

学校读者我要写书评

暂无评论

Developments and applications of the OPTIMADE API for materials discovery, design, and data exchange

arXiv

引用

arXiv 2024年

作者： Evans, Matthew L. Bergsma, Johan Merkys, Andrius Andersen, Casper W. Andersson, Oskar B. Beltrán, Daniel Blokhin, Evgeny Boland, Tara M. Balderas, Rubén Castañeda Choudhary, Kamal Díaz, Alberto Díaz García, Rodrigo Domínguez Eckert, Hagen Eimre, Kristjan Montero, María Elena Fuentes Krajewski, Adam M. Mortensen, Jens Jørgen Duarte, José Manuel Nápoles Pietryga, Jacob Qi, Ji de Jesús Trejo Carrillo, Felipe Vaitkus, Antanas Yu, Jusong Zettel, Adam de Castro, Pedro Baptista Carlsson, Johan Cerqueira, Tiago F.T. Divilov, Simon Hajiyani, Hamidreza Hanke, Felix Jose, Kevin Oses, Corey Riebesell, Janosh Schmidt, Jonathan Winston, Donald Xie, Christen Yang, Xiaoyu Bonella, Sara Botti, Silvana Curtarolo, Stefano Draxl, Claudia Cobas, Luis Edmundo Fuentes Hospital, Adam Liu, Zi-Kui Marques, Miguel A.L. Marzari, Nicola Morris, Andrew J. Ong, Shyue Ping Orozco, Modesto Persson, Kristin A. Thygesen, Kristian S. Wolverton, Chris Scheidgen, Markus Toher, Cormac Conduit, Gareth J. Pizzi, Giovanni Gražulis, Saulius Rignanese, Gian-Marco Armiento, Rickard Chemin des Étoiles 8 Louvain-la-Neuve1348 Belgium Matgenix SRL 185 Rue Armand Bury Gozée6534 Belgium École Polytechnique Fédérale de Lausanne Avenue de Forel 3 Lausanne1015 Switzerland Institute of Biotechnology Life Sciences Center Vilnius University Sauletekio av. 7 VilniusLT-10257 Lithuania SINTEF P.O. Box 4760 Torgarden TrondheimNO-7465 Norway Materials Design and Informatics unit Department of Physics Chemistry and Biology Linköping University Sweden Baldiri i Reixac 10-12 Barcelona08028 Spain Tilde Materials Informatics Straßmannstraße 25 Berlin10249 Germany Materials Platform for Data Science Sepapaja 6 Tallinn15551 Estonia Computational Atomic-Scale Materials Design Technical University of Denmark Kgs. Lyngby Denmark Av. Miguel de Cervantes 120 Complejo Industrial Chihuahua Chihuahua Chih. 31136 Mexico Material Measurement Laboratory National Institute of Standards and Technology GaithersburgMD20899 United States Department of Mechanical Engineering and Materials Science Duke University DurhamNC27708 United States Center for Extreme Materials Duke University DurhamNC27708 United States École Polytechnique Fédérale de Lausanne Lausanne1015 Switzerland Universidad Autónoma de Chihuahua Facultad de Ciencias Quimicas Chihuahua31125 Mexico Department of Materials Science and Engineering The Pennsylvania State University University ParkPA16802 United States Department of Materials Science and Engineering Northwestern University EvanstonIL60208 United States Department of NanoEngineering University of California 9500 Gilman Drive La Jolla San DiegoCA92093-0448 United States National Institute for Materials Science 1-2-1 Sengen Ibaraki Tsukuba305-0047 Japan Dassault Systèmes Germany GmbH Am Kabellager 11-13 Cologne51063 Germany CFisUC Department of Physics University of Coimbra Rua Larga Coimbra3004-516 Portugal Dassault Systèmes 22 Science Park CB4 0FJ United Kingdom Theory of Condensed Matter Cavendis

The Open Databases Integration for Materials Design (OPTIMADE) application programming interface (API) empowers users with holistic access to a growing federation of databases, enhancing the accessibility and discoverability of materials and chemical data. Since the first release of the OPTIMADE specification (v1.0), the API has undergone significant development, leading to the v1.2 release, and has underpinned multiple scientific studies. In this work, we highlight the latest features of the API format, accompanying software tools, and provide an update on the implementation of OPTIMADE in contributing materials databases. We end by providing several use cases that demonstrate the utility of the OPTIMADE API in materials research that continue to drive its ongoing development. © 2024, CC BY.

关键词： Electronic data interchange

来源：评论

学校读者我要写书评

暂无评论

MULTI-TASK LEARNING WITH LOW-RANK MATRIX FACTORIZATION FOR HYPERSPECTRAL NONLINEAR UNMIXING

MULTI-TASK LEARNING WITH LOW-RANK MATRIX FACTORIZATION FOR H...

引用

IEEE International Geoscience and Remote Sensing Symposium

作者： Yuanchao Su Jun Li Hairong Qi Paolo Gamba Antonio Plaza Javier Plaza Guangdong Provincial Key Laboratory of Urbanization and Geo-simulation Sun Yat-sen University Guangzhou China Department of Electrical Engineering and Computer Science University of Tennessee Knoxville TN USA Department of Electrical Computer and Biomedical Engineering University of Pavia Italy Department of Technology of Computers and Communications University of Extremadura Caceres Spain

Nonlinear unmixing of hyperspectral images has been a very challenging research problem, as it needs to consider the physical interactions between the sunlight scattered by multiple materials. In this paper, we propose a new approach for nonlinear unmixing which is based on multi-task learning (MTL) with low-rank matrix factorization (LRMF). The proposed approach establishes two tasks to conduct the unmixing problem under a nonlinear mixing model. In the first task, we employ LRMF to obtain endmember signatures and their corresponding abundance fractions simultaneously. Then, the second task uses LRMF to solve interactions from multiple scattering. The effectiveness of the proposed method is verified by using real hyperspectral data. Compared with other state-of-the-art nonlinear unmixing algorithms, the proposed approach demonstrates very competitive performance.

关键词： Hyperspectral imaging Task analysis Scattering Matrix decomposition Linear programming Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Significance of the nonlocal optical response of metal nanoparticles in describing the operation of plasmonic lasers

引用

Physical Review B 2019年第11期99卷 115405-115405页

作者： Dasuni Lelwala Gamacharige Sarath D. Gunapala Mark I. Stockman Malin Premaratne Advanced Computing and Simulation Laboratory (AχL) Department of Electrical and Computer Systems Engineering Monash University Clayton Victoria 3800 Australia Jet Propulsion Laboratory California Institute of Technology Pasadena California 91109 USA Department of Physics and Astronomy Georgia State University Atlanta Georgia 30303 USA

A metal nanoparticle (MNP) coupled to a quantum emitter (QE) is a versatile composite nanostructure with unique chemical and physical properties which has been studied intensively, owing to its vast range of promising applications in nanoscience and nanotechnology. When pumped into a higher gain level, an MNP-QE composite nanostructure functions as a nanoplasmonic counterpart of a conventional laser, which is capable of operating at subwavelengths. The theory of plasmonic lasers is hitherto developed on the local optical response of the MNP, disregarding the nanoscale effects of its free electrons. In this paper, we perform a comprehensive quantum mechanical analysis of a complex MNP-QE composite nanostructure, capturing the size-dependent nonclassical effects through the nonlocal optical response of the MNP. Our study reveals that the nonlocal correction introduces significant deviations to the plasmon statistics of the hybrid particle suggested by the local calculations, becoming more prominent when the number of QEs coupled to the MNP increases. Furthermore, for the typical material parameter values used in the literature, we observed the initiation of quenching effects at lower pumping rates than suggested by the local response formalism. In essence, nonlocally assessed plasmon statistics of MNP-QE composite nanostructures demand the concerted coupling of an even higher number of QEs to compensate the deterioration in coherence and to sustain lasing.

关键词： Hybrid quantum systems Plasmonics Nanoparticles

来源：评论

学校读者我要写书评

暂无评论

Cavity quantum electrodynamic analysis of spasing in nanospherical dimers

引用

Physical Review B 2019年第8期100卷 085439-085439页

作者： Tharindu Warnakula Sarath D. Gunapala Mark I. Stockman Malin Premaratne Advanced Computing and Simulation Laboratory (AXL) Department of Electrical and Computer Systems Engineering Monash University Clayton Victoria 3800 Australia Jet Propulsion Laboratory California Institute of Technology Pasadena California 91109 USA Department of Physics and Astronomy Georgia State University Atlanta Georgia 30303 USA

We present a detailed cavity quantum electrodynamic model of a nanospherical dimer and use it to analyze bright hybrid spasing modes there. Using an approximate numerical scheme, we model the complete spasing system as an open quantum system under the Lindblad dissipator formalism. We show that while in general the longitudinal dimer setups display higher intensity spasing as compared with transverse dimers, the latter actually consistently lead to output with higher coherence. Intriguingly, and somewhat counterintuitively, we find that transverse dimers only reach peak output at an intermediate dimer separation at which field confinement is not the strongest. We show that this is due to low radiative decay rates of transverse dimers with significant dimer gaps. We also find that transverse dimers outperform longitudinal dimers in terms of output intensity in a weakly pumped sparse gain medium made of dimers with relatively large separations. Moreover, in all the configurations considered, we find that the second-order coherence of the spasing output shows a peaked behavior just before the threshold, suggesting that the coherence is a useful indicator of spasing. Even though the scheme we describe is focused on dimers, owing to the generic form of the analysis presented, it can be easily extended to investigate spasing in the bright modes of multiple coupled plasmon sources.

关键词： Hybrid quantum systems Plasmonics Nanoparticles

来源：评论

学校读者我要写书评

暂无评论

Developing a scenario-based video game generation framework: Preliminary results

arXiv

引用

arXiv 2019年

作者： Surer, Elif Erkayaoglu, Mustafa Öztürk, Zeynep Nur Yücel, Furkan Bıyık, Emin Alp Altan, Burak Şenderin, Büşra Oguz, Zeliha Gürer, Servet Şebnem Düzgün, H. Department of Modeling and Simulation Graduate School of Informatics Middle East Technical University Ankara Turkey Department of Mining Engineering Middle East Technical University Ankara Turkey Department of Computer Engineering Bilkent University Ankara Turkey Department of Modeling and Simulation Graduate School of Informatics Middle East Technical University Ankara Turkey Department of Modeling and Simulation Graduate School of Informatics Middle East Technical University Ankara Turkey Department of Modeling and Simulation Graduate School of Informatics Middle East Technical University Ankara Turkey Department of Modeling and Simulation Graduate School of Informatics Middle East Technical University Ankara Turkey Department of Psychology Bilkent University Ankara Turkey Department of Mining Engineering Middle East Technical University Ankara Turkey Colorado School of Mines Brown Hall 268 CO80401 United States

Emergency training and planning provide structured curricula, rule-based action items, and interdisciplinary collaborative entities to imitate and teach real-life tasks. This rule-based structure enables the curricula to be transferred into other systematic learning platforms such as serious games - games that have additional purposes rather than only entertainment. Serious games aim to educate, cure, and plan several real-life tasks and circumstances in an interactive, efficient, and user-friendly way. Although emergency training includes these highly structured and repetitive action responses, a general framework to map the training scenarios' actions, roles, and collaborative structures to game mechanics and game dialogues, is still not available. To address this issue, in this study, a scenario-based game generator, which maps domain-oriented tasks to game rules and game mechanics, was developed. Also, two serious games (i.e., Hospital game and BioGarden game) addressing the training mechanisms of Chemical, Biological, Radiological, Nuclear, and Explosives (CBRNe) domain, were developed by both the game developers and the scenario-based game generator for comparative analysis. The results show that although the game generator uses higher CPU time, memory usage, and rendering time, it highly outperforms the game development pipeline performance of the developers. Thus, this study is an initial attempt of a game generator which bridges the CBRNe practitioners and game developers to transform real-life training scenarios into video games efficiently and quickly. Copyright © 2019, The Authors. All rights reserved.

关键词： Serious games

来源：评论

学校读者我要写书评

暂无评论

Adjustment submersible cages for optimal fish farming: improved spatiotemporal Lotka–Volterra model for n species in partitioned area

引用

International Journal of Dynamics and Control 2018年第3期6卷 919-928页

作者： Bouaine, Amine Rachik, Mostafa Laboratory of Analysis Modeling and Simulation Faculty of sciences Ben M’Sik Department of Mathematics and Computer Science Hassan II University BP 7955 Sidi Othman Casablanca Morocco Department of Industrial Engineering École Nationale Supérieure de Mines de Rabat Rabat Morocco

The first goal of this research is to set improved spatiotemporal discrete Lotlka–Volterra model including n different species which occupy three dimensional area Ω and obey to any complex marine food chain. The area Ω is partitioned into R subregions, each subregion includes at least two species, and each species can occupy more than one subregion. The next concern is to increase production of special species which survive in a target subregion, taking into account the financial cost and the severe consequences on the environment. So, we propose two different approaches: optimal farming intra-subregion and optimal farming inter-subregions. One the one hand, we develop optimal program of farming intra-subregion in order to rise the growth rate of the concerned species. On the other hand, we aim to protect the concerned species by optimal adjustment of grids constituting the submersible cage in order to control the local interaction between the target subregion and its neighboring subregions. To the best of our knowledge, it’s the first time when permeability of submersible cages will be modeled and introduced in predator–prey models. To end, adequate numerical illustrations are implemented and discussed to prove the effectiveness of each approach. © 2017, Springer-Verlag Berlin Heidelberg.

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

Operational Research: Methods and Applications

arXiv

引用

arXiv 2023年

作者： Petropoulos, Fotios Laporte, Gilbert Aktas, Emel Alumur, Sibel A. Archetti, Claudia Ayhan, Hayriye Battarra, Maria Bennell, Julia A. Bourjolly, Jean-Marie Boylan, John E. Breton, Michèle Canca, David Charlin, Laurent Chen, Bo Cicek, Cihan Tugrul Cox, Louis Anthony Currie, Christine S.M. Demeulemeester, Erik Ding, Li Disney, Stephen M. Ehrgott, Matthias Eppler, Martin J. Erdogan, Güneş Fortz, Bernard Franco, L. Alberto Frische, Jens Greco, Salvatore Gregory, Amanda J. Hämäläinen, Raimo P. Herroelen, Willy Hewitt, Mike Holmström, Jan Hooker, John N. Işık, Tugçe Johnes, Jill Kara, Bahar Y. Karsu, Özlem Kent, Katherine Köhler, Charlotte Kunc, Martin Kuo, Yong-Hong Letchford, Adam N. Leung, Janny Li, Dong Li, Haitao Lienert, Judit Ljubić, Ivana Lodi, Andrea Lozano, Sebastián Lurkin, Virginie Martello, Silvano McHale, Ian G. Midgley, Gerald Morecroft, John D.W. Mutha, Akshay Oguz, Ceyda Petrovic, Sanja Pferschy, Ulrich Psaraftis, Harilaos N. Rose, Sam Saarinen, Lauri Salhi, Said Song, Jing-Sheng Sotiros, Dimitrios Stecke, Kathryn E. Strauss, Arne K. Tarhan, Istenç Thielen, Clemens Toth, Paolo Van Woensel, Tom Vanden Berghe, Greet Vasilakis, Christos Vaze, Vikrant Vigo, Daniele Virtanen, Kai Wang, Xun Weron, Rafal White, Leroy Yearworth, Mike Yıldırım, E. Alper Zaccour, Georges Zhao, Xuying School of Management University of Bath Bath United Kingdom Makridakis Open Forecasting Center University of Nicosia Nicosia Cyprus Department of Decision Sciences HEC Montréal Montreal Canada Molde University College Molde Norway Cranfield School of Management Cranfield University Cranfield United Kingdom Department of Management Sciences University of Waterloo Waterloo Canada ESSEC Business School in Paris Department of Information Systems Decision Sciences and Statistics Cergy France H. Milton Stewart School of Industrial and Systems Engineering Georgia Institute of Technology Atlanta United States Centre for Decision Research Leeds University Business School University of Leeds Leeds United Kingdom Université du Québec à Montréal Montreal Canada Centre for Marketing Analytics and Forecasting Lancaster University Management School Lancaster University Lancaster United Kingdom School of Engineering Department of Industrial Engineering and Management Science I University of Seville Seville Spain Mila-Quebec AI Institute Montreal Canada Warwick Business School University of Warwick Coventry United Kingdom Department of Industrial Engineering Atilim University Ankara Turkey Department of Business Analytics University of Colorado School of Business Denver United States Cox Associates Denver United States Mathematical Sciences University of Southampton Southampton United Kingdom Faculty of Economics and Business Research Center for Operations Management KU Leuven Leuven Belgium Durham University Business School Durham University Durham United Kingdom Center for Simulation Analytics and Modelling University of Exeter Business School Exeter United Kingdom Department of Management Science Lancaster University Management School Lancaster University Lancaster United Kingdom University of St. Gallen St. Gallen Switzerland HEC - Management School of the University of Liège Liège Belgium Département d'Informatique Université Libre de Bruxelles Bruss

Throughout its history, Operational Research has evolved to include a variety of methods, models and algorithms that have been applied to a diverse and wide range of contexts. This encyclopedic article consists of two main sections: methods and applications. The first aims to summarise the up-to-date knowledge and provide an overview of the state-of-the-art methods and key developments in the various subdomains of the field. The second offers a wide-ranging list of areas where Operational Research has been applied. The article is meant to be read in a nonlinear fashion. It should be used as a point of reference or first-port-of-call for a diverse pool of readers: academics, researchers, students, and practitioners. The entries within the methods and applications sections are presented in alphabetical order. The authors dedicate this paper to the 2023 Turkey/Syria earthquake victims. We sincerely hope that advances in OR will play a role towards minimising the pain and suffering caused by this and future catastrophes. © 2023, CC BY.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Colour histogram analysis for skin lesions discrimination 19

Colour histogram analysis for skin lesions discrimination

引用

19th International Multidisciplinary Scientific Geoconference, SGEM 2019

作者： Damian, Felicia Anisoara Moldovanu, Simona Moraru, Luminita Faculty of Sciences and Environment Dunarea de Jos University of Galati Galati Romania Department of Computer Science and Information Technology Technical College Dumitru Motoc Galati Galati Romania Faculty of Automatic Control Computers Electrical Engineering and Electronics Dunarea de Jos University of Galati Galati Romania Modelling and Simulation Laboratory Dunarea de Jos University of Galati Galati Romania

One of the risk factors in skin cancer is unprotected exposure to UV radiation. Melanoma is the deadliest form of skin cancer but also curable if it is diagnosed in the early stages. This study uses a histogram analysis technique to investigate and classify two common skin lesions, nevi and melanoma. The colour feature investigated is the optimal threshold values in RGB space. Also, a boundary limit of the skin lesions is performed using a colour histogram analysis and the optimal threshold determination. A statistical analysis of the relevant threshold values for R, G and B histograms to establish a sound colour separation between benign and malignant lesions is performed. Monochromatic channel threshold values are clustered using K-means and the validity of clustering is assessed by silhouette method. The proposed method technique is evaluated using 120 colour digital images (60 melanomas and 60 nevi) from the Digital Archive of the department of Dermatology of the University Medical Center in Groningen (UMCG)1. The reported results suggest red as the lesion representative colour in dermoscopic images. The pixel values for red channel are strongly related to the skin lesion type. © SGEM 2019.

关键词： Dermatology

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：