检索结果-内蒙古大学图书馆

2018 International Conference on Image Processing, computer Vision, and Pattern Recognition, IPCV 2018

作者： Ninsiima, Flavia Delmira Owomugisha, Godliver Mwebaze, Ernest Makerere University School of Computing and Informatics Technology P.O. Box 7062 Kampala Uganda University of Groningen Johann Bernoulli Institute for Mathematics and Computer Science P.O. Box 407 Groningen9700 AK Netherlands Busitema University Faculty of Engineering P.O. Box 236 Tororo Uganda

ISBN: (纸本)1601324855

The most common form of symptom measurement in assessment of crop health is visual inspection of the plants. In this paper we discuss a prototypical symptom assessment method for assessing the amount of rot or necrosis in the cross-section of a cassava root tuber. Necrosis is largely associated with the presence of the viral disease Cassava Brown Streak Disease (CBSD), the most dangerous viral cassava disease in Sub-Saharan Africa now. Subjective assessment of symptoms tends to be sub-optimal leading to inaccurate estimates. We propose to automate this task by use of computer vision techniques to standardise the assessment of necrosis. Our work extends previous work in this area in two ways;(i) through the development of algorithms that segment out roots from noisy backgrounds and (ii) we provide improved techniques for identifying necrotic regions in the root as well as evaluating how accurate these methods are. © 2018 International Conference on Image Processing, computer Vision, and Pattern Recognition, IPCV *** right reserved.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Study and Implementation of Prosody Manipulation Method For Indonesian Speech Synthesis System

Study and Implementation of Prosody Manipulation Method For ...

引用

International Conference on Information technology Systems and Innovation (ICITSI)

作者： Salita Ulitia Prini Ary Setijadi Prihatmanto Didit Andri Jatmiko Research Center for Electronics and Telecommunication Indonesian Institute of Sciences Bandung Indonesia School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia Departement of Informatics Engineering Indonesian Computer University Bandung Indonesia

ISBN: (纸本)9781538656945;9781538656938

Speech Synthesis System is a system used to convert text in a language into a sound. The focus of this research is to produce a “humanization” of speech synthesis system pronunciation. The main requirement for Text To Speech system in this research are eSpeak, MBROLA idl database for Indonesia, Human Speech Corpus database which derived from the website that summarizes the words with the most common words used in a country, and three basic types of emotion or intonation that are designed for happy emotions, angry emotions, and sad emotions. The approach method used to develop an emotional filter is to manipulate prosody values (especially pitch and duration values) using predetermined level factors. The test results of Human Speech Corpus perception test for happy emotions are 95%, angry emotion is 96.25% and emotion sad is 98.75%. For the aspect of the clarity test, the audible sound accuracy with the original sentence is 93.3%, and for the clarity level each sentence is 62.8%. For the naturalness aspect to test the accuracy of emotional selection is 75.6% with every happy emotion is 90%, angry emotion is 73.3% and sad emotions of 60%.

关键词： Databases Standards Speech synthesis Synthesizers Speech coding Microsoft Windows

来源：评论

学校读者我要写书评

暂无评论

Preface

Advances in Intelligent Systems and Computing

引用

Advances in Intelligent Systems and Computing 2020年 945卷 v-vii页

作者： Kulczycki, Piotr Kacprzyk, Janusz Kóczy, László T. Mesiar, Radko Wisniewski, Rafal Faculty of Physics and Applied Computer Science AGH University of Science and Technology Krakow Poland Systems Research Institute Polish Academy of Sciences Warsaw Poland Systems Research Institute Polish Academy of Sciences Warsaw Poland Faculty of Engineering Sciences Széchenyi István University Győr Hungary Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics Budapest Hungary Department of Electronic Systems Aalborg University Aalborg Denmark Faculty of Civil Engineering Slovak University of Technology Bratislava Slovakia

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to "Detection and analysis of cerebral aneurysms based on X-ray rotational angiography - the CADA 2020 challenge" [Medical Image Analysis, April 2022, Volume 77, 102333]

引用

Medical image analysis 2025年 100卷 103363页

作者： Matthias Ivantsits Leonid Goubergrits Jan-Martin Kuhnigk Markus Huellebrand Jan Bruening Tabea Kossen Boris Pfahringer Jens Schaller Andreas Spuler Titus Kuehne Yizhuan Jia Xuesong Li Suprosanna Shit Bjoern Menze Ziyu Su Jun Ma Ziwei Nie Kartik Jain Yanfei Liu Yi Lin Anja Hennemuth Charité Universitätsmedizin Berlin Augustenburger Pl. 1 Berlin 13353 Germany. Electronic address: matthias.ivantsits@dhzc-charite.de. Charité Universitätsmedizin Berlin Augustenburger Pl. 1 Berlin 13353 Germany Einstein Center Digital Future Wilhelmstrae 67 Berlin 10117 Germany. Fraunhofer MEVIS Am Fallturm 1 Bremen 28359 Germany. Charité Universitätsmedizin Berlin Augustenburger Pl. 1 Berlin 13353 Germany. Helios Hospital Berlin-Buch Schwanebecker Chaussee 50 Berlin 13125 Germany. German Heart Centre Berlin Augustenburger Pl. 1 Berlin 13353 Germany DZHK (German Centre for Cardiovascular Research) Berlin Germany. Mediclouds Medical Technology Beijing China. School of Computer Science and Technology Beijing Institute of Technology Beijing China. Departments of Informatics Technical University Munich Germany TranslaTUM Center for Translational Cancer Research Munich Germany. TranslaTUM Center for Translational Cancer Research Munich Germany Department of Quantitative Biomedicine of UZH Zurich Switzerland. Department of Mathematics Nanjing University of Science and Technology Nanjing China. Department of Mathematics Nanjing University Nanjing China. Faculty of Engineering Technology University of Twente P.O. Box 217 Enschede 7500 AE the Netherlands. Jarvis Lab Tencent Shenzhen China Shenzhen United Imaging Research Institute of Innovative Medical Equipment Innovation Research Shenzhen China. Jarvis Lab Tencent Shenzhen China. Fraunhofer MEVIS Am Fallturm 1 Bremen 28359 Germany

来源：评论

学校读者我要写书评

暂无评论

Simulation-based efficient analysis of radio propagation model using on-demand routing protocols in the Indian automotive networks

引用

International Journal of Autonomous and Adaptive Communications Systems 2018年第1期11卷 68-68页

作者： Poonia, Ramesh C. Dadhich, Reena Gao, Xiao-Zhi Amity Institute of Information Technology Amity University Rajasthan India Department of Computer Science and Informatics University of Kota Rajasthan India Department of Electrical Engineering and Automation Aalto University Aalto Finland

VANET is the subset of mobile ad-hoc network, with the help of this we can communicate among nearby vehicles and between vehicle and also fixed road side equipment. The aim of this study is to perform the feasibility analysis of Nakagami propagation model for vehicular ad-hoc networks in the Indian automotive network. The main purpose of this paper is to present a simulation-based study of distinct propagation model for vehicular ad-hoc networks and to find the efficient analysis using on-demand routing protocols that can be more suitable in various scenarios, particularly on highways. We have used different parameters like throughput and packet drop for comparing the AODV, DSR and TORA protocols in VANETs. The research outputs will be useful in implementing efficient architecture on the realistic highway scenario, especially for four-wheeler traffic types. It will be advantageous to avoid congestion and highway road accidents due to speeds of the traffic, and road condition. Copyright © 2018 Inderscience Enterprises Ltd.

关键词： Packet loss

来源：评论

学校读者我要写书评

暂无评论

A frequent itemset hiding toolbox

arXiv

引用

arXiv 2018年

作者： Kagklis, Vasileios Stavropoulos, Elias C. Verykios, Vassilios S. Computer Engineering and Informatics Department University of Patras Greece Educational Content Methodology and Technology Laboratory Hellenic Open University Greece School of Science and Technology Hellenic Open University Greece

Advances in data collection and data storage technologies have given way to the establishment of transactional databases among companies and organizations, as they allow enormous amounts of data to be stored efficiently. Useful knowledge can be mined from these data, which can be used in several ways depending on the nature of the data. Quite often companies and organizations are willing to share data for the sake of mutual benefit. However, the sharing of such data comes with risks, as problems with privacy may arise. Sensitive data, along with sensitive knowledge inferred from this data, must be protected from unintentional exposure to unauthorized parties. One form of the inferred knowledge is frequent patterns mined in the form of frequent itemsets from transactional databases. The problem of protecting such patterns is known as the frequent itemset hiding problem. In this paper we present a toolbox, which provides several implementations of frequent itemset hiding algorithms. Firstly, we summarize the most important aspects of each algorithm. We then introduce the architecture of the toolbox and its novel features. Finally, we provide experimental results on real world datasets, demonstrating the efficiency of the toolbox and the convenience it offers in comparing different algorithms. Copyright © 2018, The Authors. All rights reserved.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Fractional Differential Equation Solvers in Octave/Matlab

Fractional Differential Equation Solvers in Octave/Matlab

引用

International Conference on Methods and Models in Automation and Robotics

作者： Marcin Sowa Aleksandra Kawala-Janik Waldemar Bauer Faculty of Electrical Engineering Silesian University of Technology Gliwice Poland Faculty of Electrical Engineering Automatic Control and Informatics Opole University of Technology Opole Poland Faculty of Electrical Engineering Automatics Computer Science and Biomedical Engineering AGH University of Science and Technology Kraków Poland

This paper concerns solvers for time fractional differential equations in Matlab and Octave. The main analysis revolves around a time step size adaptive solver basing on the numerical method called SubIval. The basis of SubIval is explained and formulae for the step size adaptivity are given. The solver is compared with others basing on: fractional linear multistep methods, product integration rules and the Grunwald-Letnikov approximation.

关键词： Fractional calculus Differential equations Electrical engineering Electronic mail Matlab Capacitors Coils

来源：评论

学校读者我要写书评

暂无评论

RETRACTED ARTICLE: Lung cancer prediction using higher-order recurrent neural network based on glowworm swarm optimization

引用

Neural Computing and Applications 2018年第9期32卷 4373-4386页

作者： Selvanambi, Ramani Natarajan, Jaisankar Karuppiah, Marimuthu Islam, SK Hafizul Hassan, Mohammad Mehedi Fortino, Giancarlo School of Computing Science and Engineering Vellore Institute of Technology (VIT) Vellore India Department of Computer Science and Engineering Indian Institute of Information Technology Kalyani Kalyani India Chair of Smart Cities Technology College of Computer and Information Sciences King Saud University Riyadh Saudi Arabia Department of Informatics Modeling Electronics and Systems University of Calabria Rende Italy

Therapeutic issues are commonly found in every single person. Tumor is a standout among the most unsafe sicknesses a human can ever had. It is exceptionally hard to distinguish it in its beginning times as its side effects seem just in the progressed stages. Subsequently, the early forecast of lung growth is compulsory for the analysis procedure, and it gives the higher possibilities for fruitful treatment. It is the most difficult approach to upgrade a patient’s possibility for survival. Henceforth, a higher-order neural network system called recurrent neural network with Levenberg–Marquardt model with the help of glowworm swarm optimization algorithm is proposed for managing multimodal disease information. The execution of the proposed strategies is tried with information and the benchmark dataset, and the outcomes demonstrate that the higher-order recurrent neural systems with glowworm swarm optimization give better accuracy of 98% in comparison with customary optimized neural network.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Understanding adversarial attacks on deep learning based medical image analysis systems

arXiv

引用

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

来源：评论

学校读者我要写书评

暂无评论

Kiloparsec-scale imaging of the CO(1-0)-traced cold molecular gas reservoir in a z∼3.4 submillimeter galaxy

arXiv

引用

arXiv 2022年

作者： Castillo, Marta Frias Rybak, Matus Hodge, Jacqueline van der Werf, Paul Riechers, Dominik A. Vieira, Daniel Rivera, Gabriela Calistro Martínez-Ramírez, Laura N. Walter, Fabian de Blok, Erwin Narayanan, Desika Wagg, Jeff Leiden Observatory Leiden University Niels Bohrweg 2 Leiden2333 CA Netherlands Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft Netherlands I. Physikalisches Institut Universität zu Köln Zülpicher Strasse 77 KölnD-50937 Germany Department of Astronomy Cornell University Space Sciences Building IthacaNY14853 United States Karl-Schwarzschild-Straße 2 Garching bei München 85748 Germany Instituto de Astrofísica Facultad de Física Pontificia Universidad Católica de Chile Av. Vicuna Mackenna 4860 Macul Santiago782-0436 Chile Escuela de Física Universidad Industrial de Santander Bucaramanga680002 Colombia Max Planck Institute for Astronomy Königstuhl 17 Heidelberg 69117 Germany National Radio Astronomy Observatory Pete V. Domenici Array Science Center P.O. Box O SocorroNM87801 United States Postbus 2 Dwingeloo7990 AA Netherlands Dept. of Astronomy Univ. of Cape Town Private Bag X3 Rondebosch7701 South Africa Kapteyn Astronomical Institute University of Groningen Postbus 800 Groningen9700 AV Netherlands Department of Astronomy University of Florida 211 Bryant Space Sciences Center GainesvilleFL32611 United States University of Florida Informatics Institute 432 Newell Drive CISE Bldg E251 GainesvilleFL32611 United States Cosmic Dawn Center The Niels Bohr Institute University of Copenhagen and DTU-Space Technical University of Denmark Denmark SKA Observatory Lower Withington Maccleseld CheshireSK11 9DL United Kingdom

We present a high-resolution study of the cold molecular gas as traced by CO(1-0) in the unlensed z∼3.4 submillimeter galaxy SMM J13120+4242, using multi-configuration observations with the Karl G. Jansky Very Large Array (JVLA). The gas reservoir, imaged on 0.39" (∼3 kpc) scales, is resolved into two components separated by ∼11 kpc with a total extent of 16 ±3 kpc. Despite the large spatial extent of the reservoir, the observations show a CO(1-0) FWHM linewidth of only 267 ±64 km s−1. We derive a revised line luminosity of L'CO(1-0) = (10 ± 3) × 1010 K km s−1 pc2 and a molecular gas mass of Mgas = (13 ± 3) ×1010 (αCO/1) M☉. Despite the presence of a velocity gradient (consistent with previous resolved CO(6-5) imaging), the CO(1-0) imaging shows evidence for significant turbulent motions which are preventing the gas from fully settling into a disk. The system likely represents a merger in an advanced stage. Although the dynamical mass is highly uncertain, we use it to place an upper limit on the CO-to-H2 mass conversion factor αCO of 1.4. We revisit the SED fitting, finding that this galaxy lies on the very massive end of the main sequence at z=3.4. Based on the low gas fraction, short gas depletion time and evidence for a central AGN, we propose that SMM J13120 is in a rapid transitional phase between a merger-driven starburst and an unobscured quasar. The case of SMM J13120 highlights the how mergers may drive important physical changes in galaxies without pushing them off the main sequence. Copyright © 2022, The Authors. All rights reserved.

关键词： Galaxies

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：