检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Manso, Giuliano L. Knidel, Helder Krohling, Renato A. Ventura, José A. Labcin-Laboratory of Computing and Engineering Inspired by Nature UFES-Federal University of Espirito Santo Vitória Brazil PPGI-Graduate Program in Computer Science UFES Vitória Brazil Production Engineering Department UFES Vitória Brazil Incaper Rua Afonso Sarlo Vitória ES29052-010 Brazil

Generally, the identification and classification of plant diseases and/or pests are performed by an expert . One of the problems facing coffee farmers in Brazil is crop infestation, particularly by leaf rust Hemileia vastatrix and leaf miner Leucoptera coffeella. The progression of the diseases and or pests occurs spatially and temporarily. So, it is very important to automatically identify the degree of severity. The main goal of this article consists on the development of a method and its i implementation as an App that allow the detection of the foliar damages from images of coffee leaf that are captured using a smartphone, and identify whether it is rust or leaf miner, and in turn the calculation of its severity degree. The method consists of identifying a leaf from the image and separates it from the background with the use of a segmentation algorithm. In the segmentation process, various types of backgrounds for the image using the HSV and YCbCr color spaces are tested. In the segmentation of foliar damages, the Otsu algorithm and the iterative threshold algorithm, in the YCgCr color space, have been used and compared to k-means. Next, features of the segmented foliar damages are calculated. For the classification, artificial neural network trained with extreme learning machine have been used. The results obtained shows the feasibility and effectiveness of the approach to identify and classify foliar damages, and the automatic calculation of the severity. The results obtained are very promising according to experts. Copyright © 2019, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

An Implementation of Reinforcement Learning in Assembly Path Planning based on 3D Point Clouds

An Implementation of Reinforcement Learning in Assembly Path...

引用

2018 International Automatic Control Conference, CACS 2018

作者： Chang, Wen-Chung Andini, Dianthika Puteri Pham, Van-Toan Department of Electrical Engineering National Taipei University of Technology Taipei106 Taiwan International Graduate Program in Electrical Engineering and Computer Science National Taipei University of Technology Taipei106 Taiwan

ISBN: (纸本)9781538662786

3D point clouds consisting of a lot of informatively geometric data have been playing critical roles in many applications such as 3D segmentation, polyline annotation for lane tracking, and especially in manufacturing industry. In particular, this paper proposes to apply Reinforcement Learning (RL) to resolve an automated assembly task based on 3D point cloud data. To address this task, the proposed structure is separated into 2 stages including registration stage and assembly path planning stage. Firstly, in the registration stage, one of the objects is matched to an assembled model to determine the transformation between two 3D point clouds by using RANdom Sample Consensus (RANSAC) and Iterative Closet Point (ICP). Secondly, we employ Q-learning method to train a model to make optimal decisions in assemble path planning task. The entire optimized assembly path planning task has been successfully accomplished for typical objects. Finally, the performance of the approach developed in this paper has been validated by experiments. © 2018 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Simultaneous localization and mapping of a mobile robot with surveillance and flying cameras

Simultaneous localization and mapping of a mobile robot with...

引用

2018 SICE International Symposium on Control Systems, SICE ISCS 2018

作者： Chang, Wen-Chung Wu, Chia-Hung Huang, Yang-Cheng Andini, Dianthika Puteri Department of Electrical Engineering National Taipei University of Technology Taipei106 Taiwan International Graduate Program in Electrical Engineering and Computer Science National Taipei University of Technology Taipei106 Taiwan

ISBN: (纸本)9784907764586

Localization and exploration of robotic systems has been a highly active research area in recent years. In order to explore unknown environments with better precision, a robotic system employing surveillance and flying cameras is proposed in this paper. Specifically, a mobile robot equipped with an onboard monocular camera performs visual simultaneous localization and mapping with extended Kalman filtering (EKF-VSLAM) and moves from indoor to outdoor environments. To correct the estimation errors of the system during the task, a least squares-based correction approach is proposed. The proposed robotic system employs surveillance cameras in indoor environment and a flying camera in outdoor environment to correct estimation error from the onboard monocular camera. The proposed correction approach, integrated with the conventional EKF-VSLAM, has been validated by experiments demonstrating better precision. © 2018 The Society of Instrument and Control Engineers - SICE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Hypermedia Driven Application programming Interface for Learning Object Management 3

Hypermedia Driven Application Programming Interface for Lear...

引用

3rd International Conference on computer science and Computational Intelligence, ICCSCI 2018

作者： Darmadi, Herru Liawatimena, Suryadiputra Abbas, Bahtiar Saleh Trisetyarso, Agung Computer Science Department School of Computer Science Bina Nusantara University Jl. Kebun Jeruk Raya No 27 Jakarta Kemanggisan11480 Indonesia Computer Engineering Department Faculty of Engineering Bina Nusantara University Jl. Kebun Jeruk Raya No 27 JakartaKemanggisan11480 Indonesia Industrial Engineering Department BINUS Graduate Program Doctor Computer Science Bina Nusantara University Jl. Kebun Jeruk Raya No 27 Jakarta Kemanggisan11480 Indonesia Computer Science Department BINUS Graduate Program Doctor Computer Science Bina Nusantara University Jl. Kebun Jeruk Raya No 27 Jakarta Kemanggisan11480 Indonesia

The research purpose is to create a hypermedia driven API for learning object management. The research focuses on conception, design, implementation and evaluation of the learning object management hypermedia API. The hypermedia API was designed based on learning object models, hypermedia concepts, and related studies. Learning object model can be represented and manipulated as a hypermedia resource. It contains page resources with text and links to multimedia elements. The hypermedia API was designed using UML and represented in HTML5 because of its rich affordance. The implementation and evaluation phase were conducted by testing the API using three different client's software to prove the concept of hypermedia as the engine of application state for managing learning objects. The results show that the hypermedia API for learning object management is accessible, consistent, and discoverable by heterogonous client applications. © 2018 The Authors. Published by Elsevier Ltd.

关键词： HTML

来源：评论

学校读者我要写书评

暂无评论

Augmented Reality for Presenting Local Wisdom: Sumatera Utara Traditional House 3

Augmented Reality for Presenting Local Wisdom: Sumatera Utar...

引用

3rd International Conference on Computing and Applied Informatics 2018, ICCAI 2018

作者： Syahputra, M.F. Aulia, R. Sitompul, O.S. Andayani, U. Abdullah, D. Sriadhi, S. Nanuru, R.F. Utama, M.D. Manurung, R.T. Djanggih, H. Mouw, E. Department of Information Technology Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia Department of Informatics Universitas Malikussaleh Aceh Utara Indonesia Department of Electrical Engineering Universitas Negeri Medan Indonesia Universitas Kristen Indonesia Maluku Ambon Indonesia Graduate Program in Scientific Psychology Universitas Kristen Maranatha Indonesia Faculty of Law Universitas Tompotika Luwuk Banggai Indonesia Faculty of Social and Human Sciences Universitas Halmahera Indonesia

Augmented Reality is a technology that allows users to see the real world, with virtual objects placed on it or combined with the real world. Augmented Reality itself can be applied to various things, including as an educational media. In the field of education, technology can be used a culture introduction to society. One part of Indonesian culture is traditional houses. Traditional house is a building that symbolizes the culture of the local community. In North Sumatra itself, there are several traditional houses that have different forms. The use of Vuforia SDK in the construction of this application can display augmented objects in the form of 3-dimentional objects and also provide information on the house. This application will run on the Android mobile platform to make it easier for users to access it. In addition, users can choose their own objects to be used as markers to make the application use much easier. © 2019 Published under licence by IOP Publishing Ltd.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable Hyperbolic Polaritonics with Correlated Oxide Metasurfaces

Research Square

引用

Research Square 2021年

作者： Aghamiri, Neda Alsadat Hu, Guangwei Fali, Alireza Zhang, Zhen Li, Jiahan Balendhran, Sivacarendran Walia, Sumeet Sriram, Sharath Edgar, James H. Ramanathan, Shriram Alù, Andrea Abate, Yohannes Department of Physics and Astronomy University of Georgia AthensGA30602 United States Photonics Initiative Advanced Science Research Center City University of New York New YorkNY10031 United States Department of Electrical and Computer Engineering National University of Singapore Kent Ridge Singapore117583 Singapore School of Materials Engineering Purdue University West LafayetteIN47907 United States Tim Taylor Department of Chemical Engineering Kansas State University ManhattanKN 66506 United States School of Physics University of Melbourne ParkvilleVIC3010 Australia School of Engineering RMIT University MelbourneVIC Australia Functional Materials and Microsystems Research Group Micro Nano Research Facility RMIT University MelbourneVIC Australia ARC Centre of Excellence for Transformative Meta-Optical Systems RMIT University MelbourneVIC Australia Physics Program Graduate Center City University of New York New YorkNY10016 United States

Polaritons enable subwavelength confinement and highly anisotropic flows of light over a wide spectral range, holding the promise for applications in modern nanophotonic and optoelectronic devices. However, to fully realize their practical application potential, facile methods enabling nanoscale active control of polaritons are needed. Here, we introduce a hybrid polaritonic-oxide heterostructure platform consisting of van der Waals crystals, such as hexagonal boron nitride (hBN) or alpha-phase molybdenum trioxide (α-MoO3), transferred on nanoscale oxygen vacancy patterns on the surface of prototypical correlated perovskite oxide SmNiO3 (SNO). Using a combination of scanning probe microscopy and infrared nanoimaging techniques, we demonstrate nanoscale real-time reconfigurability of complex hyperbolic phonon polaritons patterned at the nanoscale with unmatched resolution. Hydrogenation and temperature modulation allow spatially localized conductivity modulation of SNO nanoscale patterns, enabling robust real-time modulation and nanoscale reconfiguration of hyperbolic polaritons. Our work paves the way towards nanoscale programmable metasurface engineering as a new paradigm for reconfigurable nanophotonic applications facilitated by a hybrid material platform exploiting extreme light-matter interactions in polaritonic systems. © 2021, CC BY.

关键词： Polariton

来源：评论

学校读者我要写书评

暂无评论

Loop Catalog: a comprehensive HiChIP database of human and mouse samples

引用

Genome biology 2025年第1期26卷 175页

作者： Joaquin Reyna Kyra Fetter Romeo Ignacio Cemil Can Ali Marandi Astoria Ma Nikhil Rao Zichen Jiang Daniela Salgado Figueroa Sourya Bhattacharyya Ferhat Ay Centers for Cancer Immunotherapy and Autoimmunity La Jolla Institute for Immunology La Jolla CA 92037 USA. Bioinformatics and Systems Biology Graduate Program University of California San Diego La Jolla CA 92093 USA. Shu Chien-Gene Lay Department of Bioengineering University of California San Diego La Jolla CA 92093 USA. Department of Mathematics University of California San Diego La Jolla CA 92093 USA. Department of Computer Science and Engineering University of California San Diego La Jolla CA 92093 USA. School of Biological Sciences University of California San Diego La Jolla CA 92093 USA. Centers for Cancer Immunotherapy and Autoimmunity La Jolla Institute for Immunology La Jolla CA 92037 USA. ferhatay@***. Bioinformatics and Systems Biology Graduate Program University of California San Diego La Jolla CA 92093 USA. ferhatay@***. Department of Pediatrics University of California San Diego La Jolla CA 92093 USA. ferhatay@***.

HiChIP enables cost-effective and high-resolution profiling of chromatin loops. To leverage the increasing number of HiChIP datasets, we develop Loop Catalog ( https://*** ), a web-based database featuring loop calls from over 1000 distinct human and mouse HiChIP samples from 152 studies plus 44 high-resolution Hi-C samples. We demonstrate its utility for interpreting GWAS and eQTL variants through SNP-to-gene linking, identifying enriched sequence motifs and motif pairs, and generating regulatory networks and 2D representations of chromatin structure. Our catalog spans more than 4.19M unique loops, and with embedded analysis modules, constitutes an important resource for the field.

关键词： Chromatin loops Database GWAS HiChIP SNP-to-gene linking

来源：评论

学校读者我要写书评

暂无评论

Developing self-adaptive microservice systems: Challenges and directions

arXiv

引用

arXiv 2019年

作者： Mendonça, Nabor C. Jamshidi, Pooyan Garlan, David Pahl, Claus Post Graduate Program in Applied Informatics University of Fortaleza FortalezaCE Brazil Computer Science and Engineering Department University of South Carolina ColumbiaSC United States School of Computer Science Carnegie Mellon University PittsburghPA United States Faculty of Computer Science Free University of Bozen-Bolzano Bozen-Bolzano Italy

A self-adaptive system can dynamically monitor and adapt its behavior to preserve or enhance its quality attributes under uncertain operating conditions. This article identifies key challenges for the development of microservice applications as self-adaptive systems, using a cloud-based intelligent video surveillance application as a motivating example. It also suggests potential new directions for addressing most of the identified challenges by leveraging existing microservice practices and technologies. Copyright © 2019, The Authors. All rights reserved.

关键词： Adaptive systems

来源：评论

学校读者我要写书评

暂无评论

THz generation by exchange-coupled spintronic emitters

npj Spintronics

引用

npj Spintronics 2024年第1期2卷 1-8页

作者： Roman Adam Derang Cao Daniel E. Bürgler Sarah Heidtfeld Fangzhou Wang Christian Greb Markus Büscher Claus M. Schneider Jing Cheng Debamitra Chakraborty Ivan Komissarov Roman Sobolewski Martin Mikulics Hilde Hardtdegen Peter Grünberg Institute Research Centre Jülich Jülich Germany College of Physics Qingdao University Qingdao China Faculty of Physics University Duisburg-Essen Duisburg Germany Institut für Laser- und Plasmaphysik Heinrich-Heine Universität Düsseldorf Düsseldorf Germany Materials Science Graduate Program University of Rochester Rochester NY USA Laboratory for Laser Energetics University of Rochester Rochester NY USA Department of Electrical and Computer Engineering University of Rochester Rochester NY USA Ernst Ruska Centre Research Centre Jülich Jülich Germany

The mechanism of THz generation in ferromagnet/metal (F/M) bilayers has been typically ascribed to the inverse spin Hall effect (ISHE). Here, we fabricated Pt/Fe/Cr/Fe/Pt multilayers containing two back-to-back spintronic THz emitters separated by a thin (tCr≤ 3nm) wedge-shaped Cr spacer. In such an arrangement, magnetization alignment of the two Fe films can be controlled by the interplay between Cr-mediated interlayer exchange coupling (IEC) and an external magnetic field. This in turn results in a strong variation of the THz amplitudeA, withA↑↓reaching up to 14 timesA↑↑(arrows indicate the relative alignment of the magnetization of the two magnetic layers). This observed functionality is ascribed to the interference of THz transients generated by two closely spaced THz emitters. Moreover, the magnetic field dependenceA(H) shows a strong asymmetry that points to an additional performance modulation of the THz emitter via IEC and multilayer design.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Boosting the Performance of MOEA/D-DRA with a Multi-Objective Hyper-Heuristic Based on Irace and UCB Method for Heuristic Selection

Boosting the Performance of MOEA/D-DRA with a Multi-Objectiv...

引用

Congress on Evolutionary Computation

作者： Lucas Prestes Myriam R. Delgado Ricardo Lüders Richard Gonçalves Carolina P. Almeida Graduate Program in Electrical and Computer Engineering UTFPR Computer Science Department UNICENTRO

Multi-Objective Evolutionary Algorithm based on Decomposition with Dynamical Resource Allocation (MOEA/D-DRA) is one of the most successful decomposition based multiobjective algorithm. Its main feature is a mechanism to allocate different computational effort proportional to the difficult of each subproblem. Despite its success, MOEA/D-DRA has a large set of parameters and operators, whose selection could be a difficult task. This paper aims at improving the performance of MOEA/D-DRA by means of a hyper-heuristic using two parameter/operator selection phases: one off-line strongly based on Iterated Race Automatic Algorithm Configuration (Irace) and another one (online) based on the Upper Confidence Bound (UCB) technique. The proposed approach is compared with the original MOEA/D-DRA, NSGAII and IBEA over 51 instances of 7 well known benchmarks (CEC 2009, GLT, LZ09, MOP, DTLZ, ZDT and WFG). Results show that Irace and UCB are interesting methods to support the hyper-heuristic functioning when selecting parameters/operators of MOEA/D-DRA in the addressed problems.

关键词： Optimization Evolutionary computation Resource management Sociology Statistics Tuning Task analysis

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：