检索结果-内蒙古大学图书馆

Understanding adversarial attacks on deep learning based medical image analysis systems

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Ma, Xingjun Niu, Yuhao Gu, Lin Wang, Yisen Zhao, Yitian Bailey, James Lu, Feng State Key Laboratory of VR Technology and Systems School of CSE Beihang University Beijing China School of Computing and Information Systems The University of Melbourne ParkvilleVIC3010 Australia Beijing Advanced Innovation Center for Big Data-Based Precision Medicine Beihang University Beijing China National Institute of Informatics Tokyo101-8430 Japan Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Cixi Instuitue of Biomedical Engineering Ningbo Institute of Industrial Technology Chinese Academy of Sciences Ningbo China

Deep neural networks (DNNs) have become popular for medical image analysis tasks like cancer diagnosis and lesion detection. However, a recent study demonstrates that medical deep learning systems can be compromised by carefully-engineered adversarial examples/attacks with small imperceptible perturbations. This raises safety concerns about the deployment of these systems in clinical settings. In this paper, we provide a deeper understanding of adversarial examples in the context of medical images. We find that medical DNN models can be more vulnerable to adversarial attacks compared to models for natural images, according to two different viewpoints. Surprisingly, we also find that medical adversarial attacks can be easily detected, i.e., simple detectors can achieve over 98% detection AUC against state-of-the-art attacks, due to fundamental feature differences compared to normal examples. We believe these findings may be a useful basis to approach the design of more explainable and secure medical deep learning systems. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

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

学校读者我要写书评

暂无评论

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

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

学校读者我要写书评

暂无评论

SSRN

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

Roadmap for Optical Tweezers

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Volpe, Giovanni Maragò, Onofrio M. Rubinzstein-Dunlop, Halina Pesce, Giuseppe Stilgoe, Alexander B. Volpe, Giorgio Tkachenko, Georgiy Truong, Viet Giang Chormaic, Síle Nic Kalantarifard, Fatemeh Elahi, Parviz Käll, Mikael Callegari, Agnese Marqués, Manuel I. Neves, Antonio A.R. Moreira, Wendel L. Fontes, Adriana Cesar, Carlos L. Saija, Rosalba Saidi, Abir Beck, Paul Eismann, Jörg S. Banzer, Peter Fernandes, Thales F.D. Pedaci, Francesco Bowen, Warwick P. Vaippully, Rahul Lokesh, Muruga Roy, Basudev Thalhammer, Gregor Ritsch-Marte, Monika García, Laura Pérez Arzola, Alejandro V. Castillo, Isaac Pérez Argun, Aykut Muenker, Till M. Vos, Bart E. Betz, Timo Cristiani, Ilaria Minzioni, Paolo Reece, Peter J. Wang, Fan McGloin, David Ndukaife, Justus C. Quidant, Romain Roberts, Reece P. Laplane, Cyril Volz, Thomas Gordon, Reuven Hanstorp, Dag Marmolejo, Javier Tello Bruce, Graham D. Dholakia, Kishan Li, Tongcang Brzobohatý, Oto Simpson, Stephen H. Zemánek, Pavel Ritort, Felix Roichman, Yael Bobkova, Valeriia Wittkowski, Raphael Denz, Cornelia Kumar, G.V. Pavan Foti, Antonino Donato, Maria Grazia Gucciardi, Pietro G. Gardini, L. Bianchi, G. Kashchuk, A. Capitanio, M. Paterson, Lynn Jones, P.H. Berg-Sørensen, Kirstine Barooji, Younes F. Oddershede, Lene B. Pouladian, Pegah Preece, Daryl Adiels, Caroline Beck De Luca, Anna Chiara Magazzù, A. Ciriza, D. Bronte Iatì, M.A. Swartzlander, Grover A. Department of Physics University of Gothenburg Gothenburg41296 Sweden CNR IPCF Istituto per i Processi Chimico-Fisici Messina Italy ARC CoE for Engineered Quantum Systems School of Mathematics and Physics The University of Queensland Australia Department of Chemistry University College London 20 Gordon Street LondonWC1H 0AJ United Kingdom Dipartimento di Fisica Università degli studi di Napoli Federico II Italy Okinawa Institute of Science and Technology Graduate University Japan Department of Health Technology Technical University of Denmark Lyngby Denmark Physics Department Boğaziçi University Istanbul Turkey Chalmers University of Technology Gothenburg Sweden Departamento de Física de Materiales IFIMAC Instituto Nicolás Cabrera Universidad Autónoma de Madrid Spain Santo André São Paulo Brazil Tratamento de dados geofísicos Tecnologia e processamento de geologia e geofísica Exploração Petrobras - Petróleo Brasileiro S.A. Rio de Janeiro Rio de Janeiro Brazil Pernambuco Recife Brazil Ceará Fortaleza Brazil Campinas São Paulo Brazil Dipartimento di Scienze Matematiche e Informatiche Scienze Fisiche e Scienze della Terra Università di Messina Italy Institute of Optics Information and Photonics University Erlangen-Nuremberg Staudtstr. 7/B2 ErlangenD-91058 Germany Max Planck Institute for the Science of Light Staudtstr. 2 ErlangenD-91058 Germany Institute of Physics University of Graz NAWI Graz Universitätsplatz 5 Graz8010 Austria Centre de Biologie Structurale CNRS INSERM Univ.Montpellier France Indian Institute of Technology Madras India Institute for Biomedical Physics Medical University of Innsbruck Austria Instituto de Física Universidad Nacional Autónoma de México Ciudad de MéxicoC. P. 04510 Mexico Departamento de Física Universidad Autónoma Metropolitana-Iztapalapa San Rafael Atlixco 186 Ciudad de México09340 Mexico Third Institute of Physics - Biophysics Georg August University Göttingen Germany Department of Electrical

Optical tweezers are tools made of light that enable contactless pushing, trapping, and manipulation of objects ranging from atoms to space light sails. Since the pioneering work by Arthur Ashkin in the 1970s, optical tweezers have evolved into sophisticated instruments and have been employed in a broad range of applications in life sciences, physics, and engineering. These include accurate force and torque measurement at the femtonewton level, microrheology of complex fluids, single micro- and nanoparticle spectroscopy, single-cell analysis, and statistical-physics experiments. This roadmap provides insights into current investigations involving optical forces and optical tweezers from their theoretical foundations to designs and setups. It also offers perspectives for applications to a wide range of research fields, from biophysics to space exploration. Copyright © 2022, The Authors. All rights reserved.

关键词： Optical tweezers

Author Correction:data augmentation in microscopic images for material data mining

学校读者我要写书评

暂无评论

npj Computational Materials 2020年第1期6卷 476-476页

作者： Boyuan Ma Xiaoyan Wei Chuni Liu Xiaojuan Ban Haiyou Huang Hao Wang Weihua Xue Stephen Wu Mingfei Gao Qing Shen Michele Mukeshimana Adnan Omer Abuassba Haokai Shen Yanjing Su Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology Beijing Beijing China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China Beijing Key Laboratory of Knowledge Engineering for Materials Science Beijing China Institute for Advanced Materials and Technology University of Science and Technology Beijing Beijing China School of Materials Science and Engineering University of Science and Technology Beijing Beijing China School of Materials Science and Technology Liaoning Technical University Liaoning China The Institute of Statistical Mathematics Research Organization of Information and Systems Tachikawa Tokyo Japan National Intellectual Property Administration Beijing China Faculty of Engineering Sciences University of Burundi Bujumbura Burundi Faculty of Engineering and Technology Palestine Technical University – Kadoorie Tulkarem Palestine College of Information Science and Engineering China University of Petroleum Beijing China Key Lab of Petroleum Data Mining China University of Petroleum Beijing China

The original version of this article omitted the following from the Acknowledgements:“This work was supported by Beijing Top Discipline for Artificial Intelligent science and engineering,University of science and Tec... 详细信息

关键词： HTML knowledge mining

Using discriminant analysis to detect intrusions in external communication for self-driving vehicles

学校读者我要写书评

暂无评论

Digital Communications and Networks 2017年第3期3卷 180-187页

作者： Khattab M.Ali Alheeti Anna Gruebler Klaus McDonald-Maier Embedded and fntelligent Systems Research Laboratory School of Computer Science and Electronic Engineering Universi~ of Essex Wivenhoe ParkColchester C04 3SQ UK University of Anbar College of Computer Science and Information Technology Anbar-Iraq Data Science atAltViz in London - Data Scientist UK School of Computer Science and Electronic Engineering University of Essex Colchester C04 3SQ UK

Security systems are a necessity for the deployment of smart vehicles in our society. Security in vehicular ad hoe networks is crucial to the reliable exchange of information and control data. In this paper, we propose an intelligent Intrusion Detection System （IDS） to protect the external communication of self-driving and semi self-driving vehicles. This technology has the ability to detect Denial of Service （DOS） and black hole attacks on vehicular ad hoe networks （VANETs）. The advantage of the proposed IDS over existing security systems is that it detects attacks before they causes significant damage. The intrusion prediction technique is based on Linear Discriminant Analysis （LDA） and Quadratic Diseriminant Analysis （QDA） which are used to predict attacks based on observed vehicle behavior. We perform simulations using Network Simulator 2 to demonstrate that the IDS achieves a low rate of false alarms and high accuracy in detection.

关键词： Secure communication Vehicle ad hoc networks IDS Self-driving vehicles Linear and quadratic discriminant analysis

Aesthetic Attributes Assessment of Images

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Jin, Xin Wu, Le Zhao, Geng Li, Xiaodong Zhang, Xiaokun Ge, Shiming Zou, Dongqing Zhou, Bin Zhou, Xinghui Department of Cyber Security Beijing Electronic Science and Technology Institute Beijing100070 China Cetc Big Data Research Institute Co. Ltd. Guiyang Guizhou550018 China Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China SenseTime Research Beijing100084 China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Peng Cheng Laboratory Beijing100191 China

Image aesthetic quality assessment has been a relatively hot topic during the last decade. Most recently, comments type assessment (aesthetic captions) has been proposed to describe the general aesthetic impression of an image using text. In this paper, we propose Aesthetic Attributes Assessment of Images, which means the aesthetic attributes captioning. This is a newformula of image aesthetic assessment, which predicts aesthetic attributes captions together with the aesthetic score of each attribute. We introduce a new dataset named DPC-Captions which contains comments of up to 5 aesthetic attributes of one image through knowledge transfer from a full-annotated small-scale dataset. Then, we propose Aesthetic Multi-Attribute Network (AMAN), which is trained on a mixture of fully-annotated small-scale PCCD dataset and weakly-annotated large-scale DPC-Captions dataset. Our AMAN makes full use of transfer learning and attention model in a single framework. The experimental results on our DPC-Captions and PCCD dataset reveal that our method can predict captions of 5 aesthetic attributes together with numerical score assessment of each attribute. We use the evaluation criteria used in image captions to prove that our specially designed AMAN model outperforms traditional CNN-LSTM model and modern SCA-CNN model of image captions. Copyright © 2019, The Authors. All rights reserved.

关键词： Long short-term memory

Ensuring data confidentiality via plausibly cdeniable encryption and secure deletion-a survey

学校读者我要写书评

暂无评论

网络空间安全科学与技术（英文版） 2018年第1期1卷 25-44页

作者： Qionglu Zhang Shijie Jia Bing Chang Bo Chen Data Assurance and Communication Security Research Center Chinese Academy of Sciences Beijing China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of SciencesBeijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Data Assurance and Communication Security Research Center Chinese Academy of Sciences Beijing China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of SciencesBeijing China School of Information Systems Singapore Management University Singapore Singapore Department of Computer Science Michigan Technological University Houghton USA

Ensuring confidentiality of sensitive data is of paramount importance,since data leakage may not only endanger data owners' privacy,but also ruin reputation of businesses as well as violate various regulations like HIPPA and Sarbanes-Oxley *** provide confidentiality guarantee,the data should be protected when they are preserved in the personal computing devices (i.e.,confidentiality during theirlifetime);and also,they should be rendered irrecoverable after they are removed from the devices (i.e.,confidentiality after their lifetime).Encryption and secure deletion are used to ensure data confidentiality during and after their lifetime,*** work aims to perform a thorough literature review on the techniques being used to protect confidentiality of the data in personal computing devices,including both encryption and secure *** for encryption,we mainly focus on the novel plausibly deniable encryption (PDE),which can ensure data confidentiality against both a coercive (i.e.,the attacker can coerce the data owner for the decryption key) and a non-coercive attacker.

关键词： data confidentiality Plausibly deniable encryption Secure deletion

Effect of spatial and temporal traffic statistics on the performance of wireless networks

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Wang, Gang Zhong, Yi Li, Rongpeng Ge, Xiaohu Quek, Tony Q.S. Mao, Guoqiang School of Electronic Information and Communications Huazhong University of Science and Technology Wuhan China Zhejiang University Hangzhou China Information Systems Technology and Design Singapore University of Technology and Design Singapore School of Electrical and Data Engineering University of Technology Sydney SydneyNSW Australia

The traffic in wireless networks has become diverse and fluctuating both spatially and temporally due to the emergence of new wireless applications and the complexity o f scenarios. The purpose of this paper is to quantitatively analyze the impact of the wireless traffic, which fluctuates both spatially and temporally, on the performance of the wireless networks. Specially, we propose to combine the tools from stochastic geometry and queueing theory to model the spatial and temporal fluctuation of traffic, which to our best knowledge has seldom been evaluated analytically. We derive the spatial and temporal statistics, the total arrival rate, the stability of queues and the delay of users by considering two different spatial properties of traffic, i.e., the uniformly and non-uniformly distributed cases. The numerical results indicate that although the fluctuation of traffic (reflected by the variance of total arrival rate) when the users are clustered is much fiercer than that when the users are uniformly distributed, the stability performance is much better. Our work provides a useful reference for the design of wireless networks when the complex spatio-temporal fluctuation of the traffic is considered. Copyright © 2018, The Authors. All rights reserved.

关键词： Queueing theory