检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Qu, Xinghua Sun, Zhu Ong, Yew Soon Wei, Pengfei Gupta, Abhishek Computational Intelligence Lab School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore639798 Singapore Data Science and Artificial Intelligence Research Centre School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore Department of Computer Science National University of Singapore Singapore119077 Singapore A*STAR Singapore138634 Singapore

—Recent studies have revealed that neural network based policies can be easily fooled by adversarial examples. However, while most prior works analyze the effects of perturbing every pixel of every frame assuming white-box policy access, in this paper we take a more restrictive view towards adversary generation - with the goal of unveiling the limits of a model’s vulnerability. In particular, we explore minimalistic attacks by defining three key settings: (1) black-box policy access: where the attacker only has access to the input (state) and output (action probability) of an RL policy;(2) fractional-state adversary: where only several pixels are perturbed, with the extreme case being a single-pixel adversary;and (3) tactically-chanced attack: where only significant frames are tactically chosen to be attacked. We formulate the adversarial attack by accommodating the three key settings, and explore their potency on six Atari games by examining four fully trained state-of-the-art policies. In Breakout, for example, we surprisingly find that: (i) all policies showcase significant performance degradation by merely modifying 0.01% of the input state, and (ii) the policy trained by DQN is totally deceived by perturbation to only 1% frames. Copyright © 2019, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Equivalence of Additive-Combinatorial Linear Inequalities for Shannon Entropy and Differential Entropy

Equivalence of Additive-Combinatorial Linear Inequalities fo...

引用

作者： Makkuva, Ashok Vardhan Wu, Yihong Coordinated Science Lab Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign UrbanaIL61820 United States Department of Statistics and Data Science Yale University New HavenCT06511 United States

This paper addresses the correspondence between linear inequalities for Shannon entropy and differential entropy for sums of independent group-valued random variables. We show that any balanced (with the sum of coefficients being zero) linear inequality for Shannon entropy holds if and only if its differential entropy counterpart also holds;moreover, any linear inequality for differential entropy must be balanced. In particular, our result shows that recently proved differential entropy inequalities by Kontoyiannis and Madiman can be deduced from their discrete counterparts due to Tao in a unified manner. Generalizations to certain abelian groups are also obtained. Our proof of extending inequalities for Shannon entropy to differential entropy relies on a result of Rényi which relates the Shannon entropy of a finely discretized random variable to its differential entropy and also helps in establishing that the entropy of the sum of quantized random variables is asymptotically equal to that of the quantized sum;the converse uses the asymptotics of the differential entropy of convolutions with weak additive noise. © 1963-2012 IEEE.

关键词： Additives

来源：评论

学校读者我要写书评

暂无评论

Structured Information Extraction of Pathology Reports with Attention-based Graph Convolutional Network

Structured Information Extraction of Pathology Reports with ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jialun Wu Kaiwen Tang Haichuan Zhang Chunbao Wang Chen Li School of Computer Science and Technology Xi’an Jiaotong University Xi’an Shaanxi China National Engineering Lab for Big Data Analytics Xi’an Jiaotong University Xi’an Shaanxi China Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Tech.R&D Xi’an Jiaotong University Xi’an Shaanxi China School of Computer Science and Technology Qian Xuesen College Xi’an Jiaotong University Xi’an Shaanxi China the First Affiliated Hospital of Xi’an Jiaotong University Xi’an Shaanxi China

ISBN: (数字)9781728162157

ISBN: (纸本)9781728162164

Electronic medical data contains biochemical, imaging, pathological information during diagnosis and treatment. The pathology report is a kind of highly liberalized unstructured textual data, which is the basis and gold standard of cancer diagnosis and is very important for the prognosis and treatment of patients. The application of information extraction technology to pathological reports can obtain structured data that can be understood and analyzed by computers, helping pathologists make appropriate decisions. In this work, we proposed an attention-based graph convolutional network (GCN) for converting unstructured pathological reports into a structured form suitable for computer analysis to improve the current pathologist's workflow, collected medical data from different platforms, and provided more accurate assistance for diagnosis and treatment. We used pathology reports data from TCGA (The Cancer Genome Atlas) database with fine-grained annotations on 3632 pathology reports including four types of cancers. Our method performs better in our pathology report dataset with higher F1 score than traditional methods and deep learning methods. The results indicate that our method is robust, thus may work with other types of cancer pathology report.

关键词： Pathology Cancer Task analysis Annotations Information retrieval Medical diagnostic imaging data mining

来源：评论

学校读者我要写书评

暂无评论

Convergence of edge computing and deep learning: A comprehensive survey

arXiv

引用

arXiv 2019年

作者： Han, Yiwen Wang, Xiaofei Leung, Victor C.M. Niyato, Dusit Yan, Xueqiang Chen, Xu College of Intelligence and Computing Tianjin University Tianjin China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Electrical and Computer Engineering University of British Columbia Vancouver Canada School of Computer Science and Engineering Nanyang Technological University Singapore 2012 Lab of Huawei Technologies Shenzhen China School of Data and Computer Science Sun Yat-sen University Guangzhou China

Ubiquitous sensors and smart devices from factories and communities guarantee massive amounts of data and ever-increasing computing power is driving the core of computation and services from the cloud to the edge of the network. As an important enabler broadly changing people’s lives, from face recognition to ambitious smart factories and cities, artificial intelligence (especially deep learning) applications and services have experienced a thriving development process. However, due to efficiency and latency issues, the current cloud computing service architecture hinders the vision of "providing artificial intelligence for every person and every organization at everywhere". Thus, recently, a better solution is unleashing deep learning services from the cloud to the edge near to data sources. Therefore, edge intelligence, aiming to facilitate the deployment of deep learning services by edge computing, has received great attention. In addition, deep learning, as the main representative of artificial intelligence, can be integrated into edge computing frameworks to build intelligent edge for dynamic, adaptive edge maintenance and management. With regard to mutually benefited edge intelligence and intelligent edge, this paper introduces and discusses: 1) the application scenarios of both;2) the practical implementation methods and enabling technologies, namely deep learning training and inference in the customized edge computing framework;3) existing challenges and future trends of more pervasive and fine-grained intelligence. We believe that this survey can help readers to garner information scattered across the communication, networking, and deep learning, understand the connections between enabling technologies, and promotes further discussions on the fusion of edge intelligence and intelligent edge. Copyright © 2019, The Authors. All rights reserved.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Auxiliary Decoder and Classifier for Imbalanced Skin Disease Diagnosis

引用

Journal of Physics: Conference Series 2020年第1期1631卷

作者： Zili Xu Jiaxin Zhuang Rong Zhang Ruixuan Wang Xuemei Guo Wei-Shi Zheng School of Data and Computer Science Sun Yat-sen University Guangzhou Guangdong China Department of Computer Science and Engineering Southern University of Science and Technology Guangzhou Guangdong China Pazhou Lab Guangzhou Guangdong China

To date, deep learning has been widely adopted in medical diagnosis systems and made great achievements in real-world applications. However, in medical image-based intelligent diagnosis, the phenomenon of class imbalance often appears due to the substantially smaller available training data for rare diseases compared to common diseases, which usually degrade the performance of classification dramatically. In this paper, we propose a novel learning framework to effectively alleviate the impact of class imbalance, adding an auxiliary decoder to reconstruct original images and reusing the original CNN classifier to help the classifier more likely extract disease-relevant features for both rare and common diseases. Throughout experiments on two skin disease datasets support that the proposed framework outperforms strong baselines with a very explicit margin. The proposed method is also independent of network architecture so that it can be flexibly combined with different model structures. Besides, applying our proposed method with existing training strategies designed for class imbalance can still improve the classification performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Laser Pulses for Narrow-Band Inverse Compton Sources in the High-Intensity Regime

引用

Physical Review Letters 2019年第20期122卷 204802-204802页

作者： Daniel Seipt Vasily Yu. Kharin Sergey G. Rykovanov Helmholtz-Institut Jena Fröbelstieg 3 07743 Jena Germany Center for Ultrafast Optical Science University of Michigan Ann Arbor Michigan 48109 USA Research Institute Moscow R&D Lab Moscow Bersenevskaya nab. 6 119072 Russia Center for Computational and Data-Intensive Science and Engineering Skolkovo Institute of Science and Technology Nobel Str. 3 Skolkovo Russia

Scattering of ultraintense short laser pulses off relativistic electrons allows one to generate a large number of X- or gamma-ray photons with the expense of the spectral width—temporal pulsing of the laser inevitable leads to considerable spectral broadening. In this Letter, we describe a simple method to generate optimized laser pulses that compensate the nonlinear spectrum broadening and can be thought of as a superposition of two oppositely linearly chirped pulses delayed with respect to each other. We develop a simple analytical model that allows us to predict the optimal parameters of such a two-pulse—the delay, amount of chirp, and relative phase—for generation of a narrow-band γ-ray spectrum. Our predictions are confirmed by numerical optimization and simulations including three-dimensional effects.

关键词： Gamma-ray generation in plasmas High intensity laser-plasma interactions Strong electromagnetic field effects Radiation from moving charges

来源：评论

学校读者我要写书评

暂无评论

Green Channel and Top Hat based Image Enhancement for Diabetic Retinopathy Screening

引用

Journal of Physics: Conference Series 2021年第1期1997卷

作者： N A M Sharif A S M Azhar N H Harun J A Bakar A A Abdullah Y F Chong Data Science Res Lab School of Computing Universiti Utara Malaysia Kedah Malaysia School of Computing Universiti Utara Malaysia Kedah Malaysia Faculty of Electronic Engineering Technology Universiti Malaysia Perlis (UniMAP) Arau Perlis Malaysia Sports Engineering Research Centre (SERC) Universiti Malaysia Perlis 02600 Arau Perlis Malaysia.

Diabetic Retinopathy remains one of the most feared diabetes complications that could lead to blindness. Image processing techniques have been widely used all around the world for early detection of diabetic retinopathy. However, most techniques used do not focus on the low visual quality problems in the fundus image. Low visual quality of fundus image may lead to difficulty in evaluation by ophthalmologist before reading it out to the patients. Hence, Automated Screening for Diabetic Retinopathy was created to focus on image enhancement of the fundus image. In this study, two main algorithms for image processing have been used which are green channel conversion and top-hat filters. Green channel in fundus image is selected due to better contrast of the features and background compared to the red and blue channel. While Top-hat filter used to details out small features in the fundus image. The evaluation result of the techniques is compared by using Mean-Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR) and Entropy calculations to measure quality of the enhanced fundus images. Results of image enhancement techniques implemented has proved that quality of the fundus image is improved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic Generation of Medical Imaging Diagnostic Report with Hierarchical Recurrent Neural Network

Automatic Generation of Medical Imaging Diagnostic Report wi...

引用

IEEE International Conference on data Mining (ICDM)

作者： Changchang Yin Buyue Qian Jishang Wei Xiaoyu Li Xianli Zhang Yang Li Qinghua Zheng School of Computer Science and Technology Xi’an Jiaotong University Xi’an Shaanxi China National Engineering Lab for Big Data Analytics Xian Jiaotong University Xi’an China HP Labs Palo Alto CA USA

Medical images are widely used in the medical domain for the diagnosis and treatment of diseases. Reading a medical image and summarizing its insights is a routine, yet nonetheless time-consuming task, which often represents a bottleneck in the clinical diagnosis process. Automatic report generation can relieve the issues. However, generating medical reports presents two major challenges: (i) it is hard to accurately detect all the abnormalities simultaneously, especially the rare diseases; (ii) a medical image report consists of many paragraphs and sentences, which are longer than natural image captions. We present a new framework to accurately detect the abnormalities and automatically generate medical reports. The report generation model is based on hierarchical recurrent neural network (HRNN). We introduce a topic matching mechanism to HRNN, so as to make generated reports more accurate and diverse. The soft attention mechanism is also introduced to HRNN model. Experimental results on two image-paragraph pair datasets show that our framework outperforms all the state-of-art methods.

关键词： Medical diagnostic imaging Feature extraction Task analysis Diseases Recurrent neural networks Deep learning

来源：评论

学校读者我要写书评

暂无评论

Hypertrophic cardiomyopathy diagnosis based on cardiovascular magnetic resonance using deep learning techniques

Research Square

引用

Research Square 2021年

作者： Sharifrazi, Danial Alizadehsani, Roohallah Izadi, Navid Hoseini Roshanzamir, Mohamad Shoeibi, Afshin Khozeimeh, Fahime Sani, Fariba Alizadeh Sani, Zahra Alizadeh Hussain, Sadiq Harlapur, Chandrashekhar Gorriz, Juan M. Khosravi, Abbas Nahavandi, Saeid Sarrafzadegan, Nizal Islam, Sheikh Mohammed Shariful Department of Computer Engineering School of Technical and Engineering Shiraz Branch Islamic Azad University Shiraz Iran Deakin University Geelong Australia Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan84156-83111 Iran Department of Computer Engineering Faculty of Engineering Fasa University Fasa74617-81189 Iran Computer Engineering Department Ferdowsi University of Mashhad Mashhad Iran Faculty of Electrical and Computer Engineering Biomedical Data Acquisition Lab K. N. Toosi University of Technology Tehran Iran Mashhad University of Medical science Mashhad Iran Department of Cardiac MRI Omid Hospital Tehran Iran Dibrugarh University Assam786004 India Emergency Department Epworth Hospital Geelong Australia Department of Signal Theory Networking and Communications Universidad de Granada Spain Department of Psychiatry University of Cambridge United Kingdom Faculty of Medicine SPPH University of British Columbia VancouverBC Canada Isfahan Cardiovascular Research Center Cardiovascular Research Institute Isfahan University of Medical Sciences Khorram Ave Isfahan Iran Institute for Physical Activity and Nutrition School of Exercise and Nutrition Sciences Deakin University GeelongVIC3220 Australia Cardiovascular Division The George Institute for Global Health Newtown Australia Sydney Medical School University of Sydney Camperdown Australia

Hypertrophic cardiomyopathy (HCM) can lead to serious cardiac problems. HCM is often diagnosed by an expert using cardiovascular magnetic resonance (CMR) images obtained from patients. In this research, we aimed to develop a deep learning technique to automate HCM diagnosis. CMR images of 37421 healthy and 21846 HCM patients were obtained during two years. Images obtained from female patients form 53% of the collected dataset. The mean and standard deviation of the dataset patients’ age are 48.2 and 19.5 years, respectively. Three experts inspected images and determined whether a case has HCM or not. New data augmentation was used to generate new images by employing color filtering on the existing ones. To classify the augmented images, we used a deep convolutional neural network (CNN). To the best of our knowledge, this is the first time CNN is used for HCM diagnosis. We designed our CNN from scratch to reach acceptable diagnosis accuracy. Comparing the designed algorithm output with the experts’ opinions, the method could achieve accuracy of 95.23%, recall of 97.90%, and specificity of 93.06% on the original dataset. The same performance metrics for the designed algorithm on the augmented dataset were 98.53%, 98.70%, and 95.21%, respectively. We have also experimented with different optimizers (e.g. Adadelta and Adagrad) and other data augmentation methods (e.g. height shift and rotation) to further evaluate the proposed method. Using our data augmentation method, accuracy of 98.53% were achieved which is higher than the best accuracy (95.83%) obtained by the other data augmentation methods which have been evaluated. The upper bound on difference between true error rate and empirical error rate of the proposed method has also been provided in order to present better performance analysis. The advantages of employing the proposed method are elimination of contrast agent and its complications, decreased CMR examination time, lower costs for patients and cardiac imagi

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Investigation on Automatic data Acquisition of Well Logging Curve based on Color Recognition 4

Investigation on Automatic Data Acquisition of Well Logging ...

引用

2019 4th International Conference on Intelligent Computing and Signal Processing, ICSP 2019

作者： Wang, Han Ye, Zhihui Chen, Dong Zhu, Dandan Li, Shouding College of Safety and Ocean Engineering China University of PetroleumBeijing Beijing102249 China State Key Laboratory of Petroleum Resources and Prospecting College of Petroleum Engineering China University of PetroleumBeijing Beijing102249 China Beijing Key Lab of Petroleum Data Mining Department of Computer Science and Technology Beijing102249 China Institute of Geology and Geophysics Chinese Academy of Sciences Key Laboratory of Shale Gas and Geoengineering Institute of Geology and Geophysics Chinese Academy of Sciences Beijing100029 China University of Chinese Academy of Sciences Beijing100083 China Institutions of Earth Science Chinese Academy of Sciences Beijing100029 China

Well logging data are important to evaluate rock and fluid properties underground. Many well logging data, as functions of well depth, are conserved as figures in the literature. Digitizing technics should be applied when utilizing the well logging data. In order to address this problem, a method was proposed to automatically identify and acquire the well logging data from well logging curves. Based on the color recognition, this algorithm is able to extract curve features based on pixels. Comparing to other data digitizing methods, the background grid lines could be easily filtered and removed. The algorithm is verified by digitizing some typical well logging curves. This main contribution of this work is to provide a new and efficient way for data digitizing from well logging curves. © 2019 IOP Publishing Ltd. 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

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：