检索结果-内蒙古大学图书馆

A Novel Texture Generation Super Resolution Model

Procedia Computer Science 2019年 162卷 924-931页

作者： Biao Li Yong Shi Sujuan Li Bo Wang Zhiquan Qi Jiabin Liu School of Economics and Management University of Chinese Academy of Sciences Beijing 101408 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China College of Information Science and Technology University of Nebraska at Omaha NE 68182 USA Department of Otology the First Affiliated Hospital of Zhengzhou University No. 1 eastern Jianshe road Zhengzhou Henan 450052 China School of Information Technology and Management University of International Business and Economics Beijing 100029 China Department of Computer Science and Engineering Texas A&M University TX 77843 USA

Recently, super-resolution methods pursue visual pleasant details attract more attention in academic circle. Unlike former accurate driving models, they leverage new losses measured the difference of features extracting from a pre-trained deep learning model. Moreover, the popular GANs structure are introduced to approach better outputs. In general, these new visual feeling promoting losses are constrained by the learning ability of model and effected by the weakness of GANs. In order to address these problems, we propose a novel SR method to generating abundant details. Based on former SR methods and texture generated models, we combine new model constructure and integrated loss function to achieve our goal. The new constructure derives from the very thought that more information from the LR input leads to more accurate results. The new integrated loss try to decrease the weakness of each one by corresponding loss.. Experiments show that our model achieves higher quality generations than former methods.

关键词： Super Resolution Multi Scale Smooth Loss Visual Quality

来源：评论

学校读者我要写书评

暂无评论

An Interlaboratory Comparison of Mid-Infrared Spectra Acquisition: Instruments and Procedures Matter

SSRN

引用

SSRN 2023年

作者： Safanelli, José Lucas Sanderman, Jonathan Bloom, Dellena Todd-Brown, Katherine Parente, Leandro L. Hengl, Tomislav Adam, Sean Albinet, Franck Ben-Dor, Eyal Boot, Claudia M. Bridson, James H. Chabrillat, Sabine Deiss, Leonardo Demattê, José A.M. Demyan, M. Scott Dercon, Gerd Doetterl, Sebastian van Egmond, Fenny Ferguson, Rich Garrett, Loretta G. Haddix, Michelle L. Haefele, Stephan M. Heilin, Maria Hernandez-Allica, Javier Huang, Jingyi Jastrow, Julie D. Karyotis, Konstantinos Machmuller, Megan Malefetsane, Khesuoe Margenot, Andrew Matamala, Roser Miesel, Jessica R. Mouazen, Abdul M. Nagel, Penelope Patel, Sunita Qaswar, Muhammad Ramakhanna, Selebalo Resch, Christian Robertson, A.H. Jean Roudier, Pierre Sabetizade, Marmar Shabtai, Itamar Sherif, Faisal Sinha, Nishant Six, Johan Summerauer, Laura Thomas, Cathy L. Toloza, Arsenio Tomczyk, Beata Tsakiridis, Nikolaos L. van Wesemael, Bas Woodings, Finnleigh Zalidis, George Żelazny, Wiktor R. Woodwell Climate Research Center FalmouthMA United States Department of Environmental Engineering Sciences University of Florida GainesvilleFL United States OpenGeoHub Foundation Wageningen Netherlands TU Bergakademie Freiberg Freiberg Germany Soil and Water Management and Crop Nutrition Laboratory Joint FAO/IAEA Centre of Nuclear Techniques in Food and Agriculture International Atomic Energy Agency Austria Remote Sensing Laboratory Department of Geography and Human Environment Porter School of Environment and Earth Science Tel Aviv University Tel Aviv69978 Israel Department of Chemistry Colorado State University Fort CollinsCO United States Scion Rotorua3046 New Zealand GFZ German research center for geosciences Potsdam Germany The Ohio State University WoosterOH United States Luiz de Queiroz College of Agriculture University of São Paulo SP Piracicaba Brazil The Ohio State University ColumbusOH United States Department of Environmental Systems Science ETH Zurich Zurich8092 Switzerland ISRIC World Soil Information Wageningen Netherlands USDA-NRCS Kellogg Soil Survey Laboratory LincolnNE United States Department of Soil and Crop Sciences Colorado State University Fort CollinsCO United States Sustainable Soils and Crops Rothamsted Research United Kingdom University of Wisconsin-Madison MadisonWI United States Environmental Science Division Argonne National Laboratory LemontIL United States Laboratory of Remote Sensing Spectroscopy GIS Department of Agriculture Aristotle University of Thessaloniki Thessaloniki54124 Greece Department of Agricultural Research Maseru Lesotho University of Illinois Urbana-Champaign UrbanaIL United States Michigan State University Department of Plant Soil and Microbial Sciences East LansingMI United States Department of Environment Ghent University Coupure Links 653 Gent9000 Belgium Persistence Data Mining Inc. La Jolla CA United States The James Hutton Institute Carigiebuckler AberdeenAB15 8QH Uni

Diffuse reflectance spectroscopy has been extensively employed to deliver timely and cost-effective predictions of a number of soil properties. However, although several soil spectral laboratories have been established worldwide, the distinct characteristics of instruments and operations still hamper further integration and interoperability across mid-infrared (MIR) soil spectral libraries. In this study, we conducted a large-scale ring trial experiment to understand the lab-to-lab variability of multiple MIR instruments. By developing a systematic evaluation of different mathematical treatments with modeling algorithms, including regular preprocessing and spectral standardization, we quantified and evaluated instruments' dissimilarity and how this impacts internal and shared model performance. We found that all instruments delivered good predictions when calibrated internally using the same instruments' characteristics and standard operating procedures by solely relying on regular spectral preprocessing that accounts for light scattering and multiplicative/additive effects, e.g., using standard normal variate (SNV). When performing model transfer from a large public library (the USDA NSSC-KSSL MIR library) to secondary instruments, good performance was also achieved by regular preprocessing (e.g., SNV) if both instruments shared the same manufacturer. However, significant differences between the KSSL MIR library and contrasting ring trial instruments responses were evident and confirmed by a semi-unsupervised spectral clustering. For heavily contrasting setups, spectral standardization was necessary before transferring prediction models. Non-linear model types like Cubist and memory-based learning delivered more precise estimates because they seemed to be less sensitive to spectral variations than global partial least square regression. In summary, the results from this study can assist new laboratories in building spectroscopy capacity utilizing existing MIR spect

关键词： Libraries

来源：评论

学校读者我要写书评

暂无评论

Publisher Correction: Global estimates on the number of people blind or visually impaired by cataract: a meta-analysis from 2000 to 2020

引用

Eye (London, England) 2024年第11期38卷 2229-2231页

作者： Konrad Pesudovs Hugh R. Taylor Tabassom Sedighi Rupert R. A. Bourne Shahina Pardhan Van Charles Lansingh John H. Kempen Ian Tapply Arthur G. Fernandes Maria Vittoria Cicinelli Alessandro Arrigo Nicolas Leveziel Serge Resnikoff Seth Flaxman Mukkharram M. Bikbov Tasanee Braithwaite Alain Bron Ching-Yu Cheng Monte A. Del Monte Joshua R. Ehrlich Leon B. Ellwein David Friedman João M. Furtado Gus Gazzard Ronnie George M. Elizabeth Hartnett Jost B. Jonas Rim Kahloun Moncef Khairallah Rohit C. Khanna Janet Leasher Julie-Anne Little Vinay Nangia Michal Nowak Tunde Peto Pradeep Ramulu Fotis Topouzis Mitiadis Tsilimbaris Ya Xing Wang Ningli Wang Paul Svitil Briant Theo Vos Katrin Burkart Kaleb Coberly Xiaochen Dai Stephen S. Lim Tomislav Mestrovic Ali H. Mokdad Christopher J. L. Murray Jaimie D. Steinmetz Awoke Misganaw Yohannes Habtegiorgis Abate Mohammad Abdollahi Mozhan Abdollahi Ayele Mamo Abebe Olumide Abiodun Richard Gyan Aboagye Woldu Aberhe Abrha Hasan Abualruz Hiwa Abubaker Ali Eman Abu-Gharbieh Salahdein Aburuz Tadele Girum Girum Adal Mesafint Molla Adane Isaac Yeboah Addo Qorinah Estiningtyas Sakilah Adnani Muhammad Sohail Afzal Muhammad Umair Shahin Aghamiri Bright Opoku Ahinkorah Aqeel Ahmad Sajjad Ahmad Ali Ahmadi Siamak Sabour Ayman Ahmed Haroon Ahmed Ahmad Samir Alfaar Abid Ali Syed Shujait Shujait Ali Awais Altaf Hubert Amu Emmanuel Manu Sofia Androudi Rodrigo Anguita Abhishek Anil Rimple Jeet Kaur Muhammad Aaqib Shamim Saeid Anvari Anayochukwu Edward Anyasodor Francis Appiah Jalal Arabloo Haleh Ayatollahi Mosab Arafat Damelash Areda Reza Arefnezhad Brhane Berhe Aregawi Akeza Awealom Asgedom Tahira Ashraf Seyyed Shamsadin Athari Bantalem Tilaye Tilaye Atinafu Birhan Tsegaw Taye Maha Moh’d Wahbi Atout Alok Atreya Ahmed Y. Azzam Hassan Babamohamadi Sara Bagherieh Yogesh Bahurupi Atif Amin Baig Shumaila Nargus Biswajit Banik Mainak Bardhan Saurav Basu Kavita Batra Nebiyou Simegnew Bayileyegn Fatemeh Bazvand Addisu Shunu Beyene Awoke Masrie Asrat Derese Devidas S. Bhagat Akshaya Srikanth Bhagavathula Pankaj Bh Medicine & Health University of New South Wales Sydney NSW Australia School of Optometry and Vision Science University of New South Wales Sydney NSW Australia School of Population and Global Health University of Melbourne Carlton VIC Australia Vision and Eye Research Institute Anglia Ruskin University Cambridge UK HelpMeSee Instituto Mexicano de Oftalmologia Santiago de Querétaro Mexico University of Miami Gables FL USA University of Utah Salt Lake City UT USA Chief Medical Office HelpMeSee New York NY USA Mexican Institute of Ophthalmology Queretaro Mexico Department of Ophthalmology Massachusetts Eye and Ear/Shepens Eye Research Institute/Harvard Medical School Boston MA USA Eye Unit MyungSung Christian Medical Center (MCM) Comprehensive Specialized Hospital and MyungSun Medical College Addis Ababa Ethiopia Department of Ophthalmology Addis Ababa University Addis Ababa Ethiopia Sight for Souls Bellevue WA USA Department of Ophthalmology Harvard University Boston MA USA Eye Unit MyungSung Medical College Addis Ababa Ethiopia Addenbrooke’s Hospital Cambridge UK Department of Ophthalmology Cambridge University Hospitals Cambridge UK Federal University of Sao Paolo Sao Paolo SP Brazil University of Calgary Calgary AB Canada Department of Ophthalmology and Visual Sciences Federal University of São Paulo Sao Paulo Brazil School of Medicine Vita-Salute San Raffaele University Milan Italy Department of Ophthalmology IRCCS San Raffaele Scientific Institute Milan Italy Department of Ophthalmology San Raffaele Scientific Institute Milano Italy IRCCS San Raffaele Scientific Institute Vita-Salute University Milan Italy Scientific Institute San Raffaele Hospital Vita-Salute University Milan Italy University of Poitiers Poitiers France CHU de Poitiers Poitiers France Ophthalmology Department CHU de Poitiers (Poitiers University Hospital) Poitiers France Unité 1084 National Institute of Health and Medical Research (INSERM) Poitiers France

来源：评论

学校读者我要写书评

暂无评论

Adaptive Structure-Constrained Robust Latent Low-Rank Coding for Image Recovery

Adaptive Structure-Constrained Robust Latent Low-Rank Coding...

引用

IEEE International Conference on data Mining (ICDM)

作者： Zhao Zhang Lei Wang Sheng Li Yang Wang Zheng Zhang Zhengjun Zha Meng Wang School of Computer Science and Technology Soochow University Suzhou China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) Hefei University of Technology School of Computer Science and Information Engineering Hefei University of Technology Hefei China Department of Computer Science University of Georgia Athens GA Bio-Computing Research Center Harbin Institute of Technology (Shenzhen) Shenzhen China School of Information Science and Technology University of Science and Technology of China Hefei China

In this paper, we propose a robust representation learning model called Adaptive Structure-constrained Low-Rank Coding (AS-LRC) for the latent representation of data. To recover the underlying subspaces more accurately, AS-LRC seamlessly integrates an adaptive weighting based block-diagonal structure-constrained low-rank representation and the group sparse salient feature extraction into a unified framework. Specifically, AS-LRC performs the latent decomposition of given data into a low-rank reconstruction by a block-diagonal codes matrix, a group sparse locality-adaptive salient feature part and a sparse error part. To enforce the block-diagonal structures adaptive to different real datasets for the low-rank recovery, AS-LRC clearly computes an auto-weighting matrix based on the locality-adaptive features and multiplies by the low-rank coefficients for direct minimization at the same time. This encourages the codes to be block-diagonal and can avoid the tricky issue of choosing optimal neighborhood size or kernel width for the weight assignment, suffered in most local geometrical structures-preserving low-rank coding methods. In addition, our AS-LRC selects the L2, 1-norm on the projection for extracting group sparse features rather than learning low-rank features by Nuclear-norm regularization, which can make learnt features robust to noise and outliers in samples, and can also make the feature coding process efficient. Extensive visualizations and numerical results demonstrate the effectiveness of our AS-LRC for image representation and recovery.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Memorization in overparameterized autoencoders

arXiv

引用

arXiv 2018年

作者： Radhakrishnan, Adityanarayanan Yang, Karren Belkin, Mikhail Uhler, Caroline Laboratory for Information & Decision Systems Institute for Data Systems and Society Massachusetts Institute of Technology Department of Computer Science and Engineering Ohio State University

The ability of deep neural networks to generalize well in the overparameterized regime has become a subject of significant research interest. We show that overparameterized autoencoders exhibit memorization, a form of inductive bias that constrains the functions learned through the optimization process to concentrate around the training examples, although the network could in principle represent a much larger function class. In particular, we prove that single-layer fully-connected autoencoders project data onto the (nonlinear) span of the training examples. In addition, we show that deep fully-connected autoencoders learn a map that is locally contractive at the training examples, and hence iterating the autoencoder results in convergence to the training examples. Finally, we prove that depth is necessary and provide empirical evidence that it is also sufficient for memorization in convolutional autoencoders. Understanding this inductive bias may shed light on the generalization properties of overparametrized deep neural networks that are currently unexplained by classical statistical theory. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

AI-skin: Skin disease recognition based on self-learning and wide data collection through a closed loop framework

arXiv

引用

arXiv 2019年

作者： Chen, Min Zhou, Ping Wu, Di Hu, Long Hassan, Mohammad Mehedi Alamri, Atif School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Data and Computer Science Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Big Data Analysis and Processing Guangzhou China Chair of Pervasive and Mobile Computing Information Systems Department College of Computer and Information Sciences King Saud University Riyadh11543 Saudi Arabia Chair of Pervasive and Mobile Computing Software Engineering Department CCIS King Saud University Riyadh11543 Saudi Arabia

There are a lot of hidden dangers in the change of human skin conditions, such as the sunburn caused by long-time exposure to ultraviolet radiation, which not only has aesthetic impact causing psychological depression and lack of selfconfidence, but also may even be life-threatening due to skin canceration. Current skin disease researches adopt the auto-classification system for improving the accuracy rate of skin disease classification. However, the excessive dependence on the image sample database is unable to provide individualized diagnosis service for different population groups. To overcome this problem, a medical AI framework based on data width evolution and self-learning is put forward in this paper to provide skin disease medical service meeting the requirement of real time, extendibility and individualization. First, the wide collection of data in the close-loop information flow of user and remote medical data center is discussed. Next, a data set filter algorithm based on information entropy is given, to lighten the load of edge node and meanwhile improve the learning ability of remote cloud analysis model. In addition, the framework provides an external algorithm load module, which can be compatible with the application requirements according to the model selected. Three kinds of deep learning model, i.e. LeNet-5, AlexNet and VGG16, are loaded and compared, which have verified the universality of the algorithm load module. The experiment platform for the proposed real-time, individualized and extensible skin disease recognition system is built. And the system's computation and communication delay under the interaction scenario between tester and remote data center are analyzed. It is demonstrated that the system we put forward is reliable and effective. Copyright © 2019, The Authors. All rights reserved.

关键词： data acquisition

来源：评论

学校读者我要写书评

暂无评论

The XRISM/Resolve View of the Fe K Region of Cyg X-3

引用

Astrophysical Journal Letters 2024年第2期977卷 L34-L34页

作者： Audard, Marc Awaki, Hisamitsu Ballhausen, Ralf Bamba, Aya Behar, Ehud Boissay-Malaquin, Rozenn Brenneman, Laura Brown, Gregory V. Corrales, Lia Costantini, Elisa Cumbee, Renata Trigo, María Díaz Done, Chris Dotani, Tadayasu Ebisawa, Ken Eckart, Megan E. Eckert, Dominique Eguchi, Satoshi Enoto, Teruaki Ezoe, Yuichiro Foster, Adam Fujimoto, Ryuichi Fujita, Yutaka Fukazawa, Yasushi Fukushima, Kotaro Furuzawa, Akihiro Gallo, Luigi García, Javier A. Gu, Liyi Guainazzi, Matteo Hagino, Kouichi Hamaguchi, Kenji Hatsukade, Isamu Hayashi, Katsuhiro Hayashi, Takayuki Hell, Natalie Hodges-Kluck, Edmund Hornschemeier, Ann Ichinohe, Yuto Ishida, Manabu Ishikawa, Kumi Ishisaki, Yoshitaka Kaastra, Jelle Kallman, Timothy Kara, Erin Katsuda, Satoru Kanemaru, Yoshiaki Kelley, Richard Kilbourne, Caroline Kitamoto, Shunji Kobayashi, Shogo Kohmura, Takayoshi Kubota, Aya Leutenegger, Maurice Loewenstein, Michael Maeda, Yoshitomo Markevitch, Maxim Matsumoto, Hironori Matsushita, Kyoko McCammon, Dan McNamara, Brian Mernier, François Miller, Eric D. Miller, Jon M. Mitsuishi, Ikuyuki Mizumoto, Misaki Mizuno, Tsunefumi Mori, Koji Mukai, Koji Murakami, Hiroshi Mushotzky, Richard Nakajima, Hiroshi Nakazawa, Kazuhiro Ness, Jan-Uwe Nobukawa, Kumiko Nobukawa, Masayoshi Noda, Hirofumi Odaka, Hirokazu Ogawa, Shoji Ogorzalek, Anna Okajima, Takashi Ota, Naomi Paltani, Stephane Petre, Robert Plucinsky, Paul Porter, Frederick S. Pottschmidt, Katja Sato, Kosuke Sato, Toshiki Sawada, Makoto Seta, Hiromi Shidatsu, Megumi Simionescu, Aurora Smith, Randall Suzuki, Hiromasa Szymkowiak, Andrew Takahashi, Hiromitsu Takeo, Mai Tamagawa, Toru Tamura, Keisuke Tanaka, Takaaki Tanimoto, Atsushi Tashiro, Makoto Terada, Yukikatsu Terashima, Yuichi Tsuboi, Yohko Tsujimoto, Masahiro Tsunemi, Hiroshi Tsuru, Takeshi Uchida, Hiroyuki Uchida, Nagomi Uchida, Yuusuke Uchiyama, Hideki Ueda, Yoshihiro Uno, Shinichiro Vink, Jacco Watanabe, Shin Williams, Brian J. Yamada, Satoshi Yamada, Shinya Yamaguchi, Hiroya Yamaoka, Kazutaka Yamasaki, Noriko Yamauchi, Makoto Yamauchi, Shig Department of Astronomy University of Geneva Versoix CH-1290 Switzerland Department of Physics Ehime University Ehime 790-8577 Japan Department of Astronomy University of Maryland College Park 20742 MD United States NASA Goddard Space Flight Center Greenbelt 20771 MD United States Center for Research and Exploration in Space Science and Technology NASA GSFC (CRESST II) Greenbelt 20771 MD United States Department of Physics University of Tokyo Tokyo 113-0033 Japan Department of Physics Technion Technion City Haifa 3200003 Israel Center for Space Sciences and Technology University of Maryland Baltimore County (UMBC) Baltimore 21250 MD United States Center for Astrophysics-Harvard-Smithsonian 02138 MA United States Lawrence Livermore National Laboratory 94550 CA United States Department of Astronomy University of Michigan 48109 MI United States SRON Netherlands Institute for Space Research Leiden Netherlands ESO Karl-Schwarzschild-Strasse 2 Garching bei München 85748 Germany Centre for Extragalactic Astronomy Department of Physics University of Durham South Road Durham DH1 3LE United Kingdom Institute of Space and Astronautical Science (ISAS) Japan Aerospace Exploration Agency (JAXA) Kanagawa 252-5210 Japan Department of Economics Kumamoto Gakuen University Kumamoto 862-8680 Japan Department of Physics Kyoto University Kyoto 606-8502 Japan Department of Physics Tokyo Metropolitan University Tokyo 192-0397 Japan Department of Physics Hiroshima University Hiroshima 739-8526 Japan Department of Physics Fujita Health University Aichi 470-1192 Japan Department of Astronomy and Physics Saint Mary's University B3H 3C3 NS Canada California Institute of Technology Pasadena 91125 CA United States European Space Agency (ESA) European Space Research and Technology Centre (ESTEC) Noordwijk 2200AG Netherlands Faculty of Engineering University of Miyazaki 1-1 Gakuen-Kibanadai-Nishi Miyazaki Miyazaki 889-2192 Japan RIKEN Nishina Ce

The X-ray binary system Cygnus X-3 (4U 2030+40, V1521 Cyg) is luminous but enigmatic owing to the high intervening absorption. High-resolution X-ray spectroscopy uniquely probes the dynamics of the photoionized gas in the system. In this Letter, we report on an observation of Cyg X-3 with the XRISM/Resolve spectrometer, which provides unprecedented spectral resolution and sensitivity in the 2-10 keV band. We detect multiple kinematic and ionization components in absorption and emission whose superposition leads to complex line profiles, including strong P Cygni profiles on resonance lines. The prominent Fe XXV Hea and Fe XXVI Lya emission complexes are clearly resolved into their characteristic fine-structure transitions. Self-consistent photoionization modeling allows us to disentangle the absorption and emission components and measure the Doppler velocity of these components as a function of binary orbital phase. We find a significantly higher velocity amplitude for the emission lines than for the absorption lines. The absorption lines generally appear blueshifted by ∼-500-600 km s^-1. We show that the wind decomposes naturally into a relatively smooth and large-scale component, perhaps associated with the background wind itself, plus a turbulent, denser structure located close to the compact object in its orbit. © 2024. The Author(s). Published by the American Astronomical Society.

关键词： High mass x-ray binary stars High resolution spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Bioinformatics Commons: The Cornerstone of Life and Health Sciences

引用

Genomics,Proteomics & Bioinformatics 2018年第4期16卷 223-225页

作者： Zhang Zhang Yu Xue Fangqing Zhao BIG Data Center and CAS Key Laboratory of Genome Sciences & Information Beijing Institute of Genomics Chinese Academy of Sciences Department of Bioinformatics & Systems Biology MOE Key Laboratory of Molecular Biophysics College of Life Science and Technology and the Collaborative Innovation Center for Biomedical Engineering Huazhong University of Science and Technology Beijing Institutes of Life Science Chinese Academy of Sciences

Bioinformatics, an interdisciplinary field that combines biology, mathematics, computer science, medicine, and health science, to integrate, analyze, and interpret biological data, is now becoming increasingly data-intensive. To dig out the treasure from big data powered by high-throughput sequencing technologies, it is highly dependent on Bioinformatics Commons that involves a variety of fundamental resources, includ-

关键词： Bioinformatics Commons The Cornerstone of Life and Health Sciences

来源：评论

学校读者我要写书评

暂无评论

Work in Progress – Establishing a Master Program in Cyber Physical systems: Basic Findings and Future Perspectives

Work in Progress – Establishing a Master Program in Cyber P...

引用

International Conference on Promising Electronic Technologies (ICPET)

作者： Isam Ishaq Rashid Jayousi Salaheddin Odeh Ezzaldeen Edwan Asmaa Shaheen Mohamed Elnaggar Ahmed Elagha Samy Salamah Christian Weber Hasan Abu Rasheed Raimund Kirner Martina Doolan Hamidreza Ahmadian Roman Obermaisser Dhiah el Diehn I. Abou-Tair Ala Khalifeh Sahel Alouneh Zaid Alhalhouli Khalid Alemerien Faiez Gargouri Bassem Bouaziz Nadia Aloui Mohammad Saleh Computer Engineering and Science Departments Al-Quds University Jerusalem Palestine Engineering Program and Computer Department Palestine Technical College - Deir El-Balah Deir El-Balah Palestine Institute of Knowledge Based Systems & Knowledge Management University of Siegen Siegen Germany University of Siegen Siegen Germany School of Engineering and Computer Science University of Hertfordshire Hatfield UK Chair of Embedded Systems University of Siegen Siegen Germany German Jordanian University Amman Jordan School of Electrical Engineering and Information Technology German Jordanian University Amman Jordan Computer and Information Technology Department Tafila Technical University Tafila Jordan Higher Institute of Computer Science and Multimedia University of Sfax Sfax Tunisia Higher Institute of Applied Sciences and Technology of Mateur University of Carthage Mateure Tunisia KTH Royal Institute of Technology Stockholm Sweden

This paper reports on the basic findings and future perspectives of a capacity building project funded by the European Union. The International Master of Science on Cyber Physical systems (MS@CPS) is a collaborative project that aims to establish a master program in cyber physical systems (CPS). A consortium composed of nine partners proposed the project. Three partners are European and from Germany, UK and Sweden; while the other six partners are from the South Mediterranean region and include: Palestine, Jordan and Tunisia. The consortium is led by the University of Siegen in Germany who also manages the implementation of the work packages. CPS is an emerging engineering subject with significant economic and societal implications, which motivated the consortium to propose the establishment of a master program to offer educational and training opportunities at graduate level in the fields of CPS. In this paper, CPS as a field of study is presented with an emphasis on its importance, especially with regard to meeting local needs. A brief description of the project is presented in conjunction with the methodology for developing the courses and their learning outcomes.

关键词： Computer science Internet of Things Industries knowledge engineering Embedded systems Europe Collaboration

来源：评论

学校读者我要写书评

暂无评论

Hierarchical deep convolutional neural networks for multi-category diagnosis of gastrointestinal disorders on histopathological images

arXiv

引用

arXiv 2020年

作者： Sali, Rasoul Adewole, Sodiq Ehsan, Lubaina Denson, Lee A. Kelly, Paul Amadi, Beatrice C. Holtz, Lori Ali, Syed Asad Moore, Sean R. Syed, Sana Brown, Donald E. Department of Systems and Information Engineering University of Virginia CharlottesvilleVA United States Department of Pediatrics School of Medicine University of Virginia CharlottesvilleVA United States School of Data Science University of Virginia CharlottesvilleVA United States Division of Gastroenterology Hepatology and Nutrition Cincinnati Children's Hospital Medical Center CincinnatiOH United States Blizard Institute Barts and The London School of Medicine Queen Mary University of London London United Kingdom Tropical Gastroenterology and Nutrition group University of Zambia School of Medicine Lusaka Zambia Department of Pediatrics School of Medicine Washington University Saint LouisMO United States Department of Pediatrics and Child Health Aga Khan University Karachi Pakistan

Deep convolutional neural networks (CNNs) have been successful for a wide range of computer vision tasks including image classification. A specific area of application lies in digital pathology for pattern recognition in tissue-based diagnosis of gastrointestinal (GI) diseases. This domain can utilize CNNs to translate histopathological images into precise diagnostics. This is challenging since these complex biopsies are heterogeneous and require multiple levels of assessment. This is mainly due to structural similarities in different parts of the GI tract and shared features among different gut diseases. Addressing this problem with a flat model which assumes all classes (parts of the gut and their diseases) are equally difficult to distinguish leads to an inadequate assessment of each class. Since hierarchical model restricts classification error to each sub-class, it leads to a more informative model compared to a flat model. In this paper we propose to apply hierarchical classification of biopsy images from different parts of the GI tract and the receptive diseases within each. We embedded a class hierarchy into the plain VGGNet to take advantage of the hierarchical structure of its layers. The proposed model was evaluated using an independent set of image patches from 373 whole slide images. The results indicate that hierarchical model can achieve better results compared to the flat model for multi-category diagnosis of GI disorders using histopathological images. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

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：