检索结果-内蒙古大学图书馆

IEEE Latin American Robotics Symposium, LARS

作者： Lucas Steuernagel Marcos R. O. A. Maximo Lucas A. Pereira Carlos A. A. Sanches Autonomous Computational Systems Lab (LAB-SCA) Computer Science Division Aeronautics Institute Of Technology Sao Jose dos Campos SP Brazil Goias Federal University Goiania GO Brazil Computer Science Division Aeronautics Institute of Technology Sao Jose dos Campos SP Brazil

ISBN: (数字)9780738111537

ISBN: (纸本)9781665419857

The current RoboCup Humanoid rules determine white balls, white goalposts and white field lines. In such an environment, the color-based heuristics algorithms used by RoboCup teams for computer vision do not present good detection performance. Convolutional neural networks (CNNs) are a straightforward solution to this challenge. Among the existing CNN-based techniques for object detection, the YOLO (You Only Look Once) algorithm is designed for real-time execution. In this paper, we created many neural networks architectures based upon YOLO so that we could identify which one had the best overall cost benefit between performance and execution time in a small humanoid robot. We assessed the algorithm's performance mainly by calculating the quantity of correct classifications and the mean average precision (mAP). A Convolutional Neural Network with an Inception-like module has showed promising results, running in real time on the robot's computer with Intel's OpenVINO inference framework. Getting right more than 88% of the classifications and achieving a mAP of 0.81, the developed neural network is prone to work effectively in the robot.

关键词： Robots computer architecture Microprocessors Robot kinematics Convolution Two dimensional displays Humanoid robots

来源：评论

学校读者我要写书评

暂无评论

Learning Through One Shot: A Phase by Phase Approach for COVID-19 Chest X-ray Classification

Learning Through One Shot: A Phase by Phase Approach for COV...

引用

IEEE EMBS Conference on Biomedical Engineering and sciences (IECBES)

作者： V.N. Manjunath Aradhya Mufti Mahmud M. Chowdhury D S Guru M. Shamim Kaiser Saiful Azad JSS Science and Technology University Mysuru India Nottingham Trent University Nottingham UK Qatar University Doha Qatar DoS in Computer Science University of Mysore Mysuru India Institute of Information Technology Jahangirnagar University Dhaka Bangladesh Faculty of Computing University Malaysia Pahang Pekan Malaysia

ISBN: (数字)9781728142456

ISBN: (纸本)9781728142463

Today globally, coronavirus disease (COVID-19) has infected over more than 81 million people and killed at least 1771K. This is an infectious disease caused by a newly discovered coronavirus. As a result, scientists and researchers around the globe are now trying to find out the path to battle this disease in the most effective way. Chest X-rays are a widely available modality for immediate care in diagnosing COVID-19. Detection and diagnosis of COVID-19 chest X-rays would be more precise for the current situation. In this paper, a phase by phase approach using the concept of one shot learning is introduced for effective classification of chest X-ray images. The proposed method utilizes the application of Entropy for selecting best describing images for effective learning purposes. The proposed model is evaluated on a publically available large dataset of size 24614 images comprising of three classes viz COVID-19, Normal and Non-COVID. The obtained results are promising and encouraging.

关键词： COVID-19 Training Infectious diseases Lung X-rays Entropy Testing

来源：评论

学校读者我要写书评

暂无评论

Alignment, Scale and Skew Correction for Optical Mark Recognition Documents Based 15

Alignment, Scale and Skew Correction for Optical Mark Recogn...

引用

15th Workshop of computer Vision, WVC 2019

作者： De Elias, Erik Miguel Tasinaffo, Paulo Marcelo Hirata, Roberto Computer Science Department Technological Institute of Aeronautics São José dos Campos Brazil São Paulo Brazil

ISBN: (纸本)9781728153377

Acquiring an OMR (Optical Mark Recognition) reading equipment can be impracticable to some companies or individuals due to its costs. Computational software solutions can be more attractive, but they require specific page format or page layout, such as specific marks to be used when recognizing any OMR document. In this paper, we propose a way to treat skew, translation, scale and alignment using a base document as reference due to the intrinsic characteristics of the problem. Key points are found by a pattern matching algorithm and used for the document image transformation. The method does not require specific layout, needing less formatting, allowing non-experts to create the form using ordinary software and scanners. Two experiments were executed: one with 40 images distorted randomly from a document clipping, and the second one with 1034 images of real student tests. Both experiments reached high overall accuracy. © 2019 IEEE.

关键词： Pattern matching

来源：评论

学校读者我要写书评

暂无评论

Revisiting Principles and Challenges in Natural Language Programming 1

引用

作者： Sales, Juliano Efson Freitas, André Oliveira, Douglas Koumpis, Adamantios Handschuh, Siegfried Department of Computer Science and Mathematics University of Passau Innstraße 43 Passau94032 Germany Institute of Computer Science University of St. Gallen Rosenbergstrasse 30 St. Gallen9000 Switzerland School of Computer Science University of Manchester Kilburn Building Oxford Road ManchesterM13 9PL United Kingdom Architecture and Analytics Group VLI Logística Rua dos Tapuias 49 Belo Horizonte Brazil Institute of Digital Enabling Bern University of Applied Sciences Brückenstrasse 73 Bern3005 Switzerland

ISBN: (数字)9783030539498

ISBN: (纸本)9783030539481;9783030539511

Automation has faced the risk of reducing its pace due to the shortage of information technology professionals. Although part of the programming demand can be addressed by simple compositions of high-level functions and data flows, non-technical professionals are still unable to build their own software given the intrinsic complexity of coding. Among other types of end-user development, natural language programming has emerged as a strong candidate to fill this gap by developing methods and tools to allow end users to program. The paper revisits some principles of evaluation of traditional programming languages and analyses the new challenges to deliver an effective end-user development platform based on aspects of natural language processing, human-computer interaction, software engineering, and programming education. We advocate that an effective end-user platform is essentially hybrid, combining features from different branches of the end-user development research, having, however, a search mechanism with semantic capabilities at its centre. © 2020, Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Deep-Strong Coupling between Cavity Photons and Terahertz TO Phonons in PbTe

Deep-Strong Coupling between Cavity Photons and Terahertz TO...

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Baydin, Andrey Manjappa, Manukumara Mishra, Sobhan Subhra Xu, Hongjing Tay, Fuyang Kim, Dasom Hernandez, Felix G.G. Rappl, Paulo H.O. Abramof, Eduardo Singh, Ranjan Kono, Junichiro Department of Electrical and Computer Engineering Rice University HoustonTX77005 United States Smalley-Curl Institute Rice University HoustonTX77005 United States Instrumentation and Applied Physics Department Indian Institute of Science Bangalore560012 India Center for Disruptive Photonic Technologies The Photonics Institute Nanyang Technological University 639798 Singapore Department of Physics and Astronomy Rice University HoustonTX77005 United States Applied Physics Graduate Program Smalley-Curl Institute Rice University HoustonTX77005 United States Instituto de Física Universidade de Sao Paulo SP Sao Paulo05508-090 Brazil Laboratorio Associado de Sensores e Materiais Instituto Nacional de Pesquisas Espaciais SP Sao Jose dos Campos12201-970 Brazil Division of Physics and Applied Physics School of Physical and Mathematical Sciences Nanyang Technological University 637371 Singapore Department of Material Science and NanoEngineering Rice University HoustonTX77005 United States

We have investigated the resonant coupling of photons with TO phonons in lead telluride in small-mode-volume terahertz cavities, observing a giant vacuum Rabi splitting on the order of the bare cavity-phonon frequency... 详细信息

ISBN: (纸本)9781957171258

关键词： Photons

来源：评论

学校读者我要写书评

暂无评论

The Good, the Bad, and the Ugly: Neural Networks Straight from JPEG

The Good, the Bad, and the Ugly: Neural Networks Straight fr...

引用

2020 IEEE International Conference on Image Processing, ICIP 2020

作者： Santos, Samuel Felipe dos Sebe, Nicu Almeida, Jurandy Instituto de Ciência e Tecnologia Universidade Federal de São Paulo - Unifesp 12247-014 São José dos Campos SP Brazil University of Trento - UniTn 38123 Dept. of Information Engineering and Computer Science TrentoTN Italy

ISBN: (纸本)9781728163956

Over the past decade, convolutional neural networks (CNNs) have achieved state-of-the-art performance in many computer vision tasks. They can learn robust representations of image data by processing RGB pixels. Since image data are often stored in a compressed format, from which JPEG is the most widespread, a preliminary decoding process is demanded. Recently, the design of CNNs for processing JPEG compressed data has gained attention from the research community. They process DCT coefficients instead of RGB pixels, saving computation for decoding JPEG images, however, at the cost of increasing the computational complexity of the network. In this paper, we examine how spatial resolution and JPEG quality impacts on the performance of a state-of-the-art CNN designed to operate directly on the JPEG compressed domain. To alleviate its computational complexity, we propose a Frequency Band Selection (FBS) technique to select the most relevant DCT coefficients before feeding them to the network. Experiments were conducted on a subset of the ImageNet dataset considering both fine- and coarse-grained image classification tasks. Results show that such networks are resilient to JPEG quality but are susceptible to spatial resolution. Also, our FBS can reduce the computational complexity of the network while retaining a similar accuracy. © 2020 IEEE.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Decision-making for 5x5 Very Small Size Soccer Teams

Decision-making for 5x5 Very Small Size Soccer Teams

引用

IEEE Latin American Robotics Symposium, LARS

作者： Thayna Pires Baldão Marcos R. O. A. Maximo Cecilia de Azevedo Castro Cesar Autonomous Computational Systems Lab (LAB-SCA) Computer Science Division Aeronautics Institute of Technology São José dos Campos SP Brazil Command & Control and Cyber Defense Lab (C2-CD Lab) Computer Science Division Aeronautics Institute of Technology São José dos Campos SP Brazil

ISBN: (数字)9780738111537

ISBN: (纸本)9781665419857

Due to the high dynamism of IEEE Very Small Size Soccer (VSSS) matches, the main differences between the teams are focused on their decision-making system, path planning methods, and control and positioning algorithms. A path planning algorithm that fits well in the context of IEEE VSSS differential robots is the univector field navigation. For the positioning of the robots the combination of Delaunay Triangulation and Gouraud Shading proves to be quite efficient. Regarding decision-making, behavior trees are a good approach, due to their modularity and easiness in changing player's actions. In addition, a system for changing player's roles is also important, in order to make a dynamic match possible. The techniques shown here are not novel in the context of robot soccer. In fact, this paper contribution lies in integrating them in a full working strategy for 5×5 VSSS, which ended up winning Latin American Robotics Competition (LARC) 2019.

关键词： Decision making Games Educational robots Robot sensing systems Navigation Sports Trajectory planning

来源：评论

学校读者我要写书评

暂无评论

Discovering Spatio-Temporal Patterns in Precision Agriculture Based on Triclustering 15th

Discovering Spatio-Temporal Patterns in Precision Agricultur...

引用

15th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2020

作者： Melgar-García, Laura Godinho, Maria Teresa Espada, Rita Gutiérrez-Avilés, David Brito, Isabel Sofia Martínez-Álvarez, Francisco Troncoso, Alicia Rubio-Escudero, Cristina Data Science & Big Data Lab Pablo de Olavide University Seville41013 Spain Department of Mathematical and Physical Sciences Polytechnic Institute of Beja Beja Portugal Center for Mathematics Fundamental Applications and Operations Research University of Lisboa Lisbon Portugal Associação dos Agricultores do Baixo Alentejo Beja Portugal Department of Engineering Polytechnic Institute of Beja Beja Portugal Instituto de Desenvolvimiento de Novas Tecnologias - Centre of Technology and Systems Lisbon Portugal Department of Computer Languages and Systems University of Seville Seville Spain

ISBN: (纸本)9783030578015

Agriculture has undergone some very important changes over the last few decades. The emergence and evolution of precision agriculture has allowed to move from the uniform site management to the site-specific management, with both economic and environmental advantages. However, to be implemented effectively, site-specific management requires within-field spatial variability to be well-known and characterized. In this paper, an algorithm that delineates within-field management zones in a maize plantation is introduced. The algorithm, based on triclustering, mines clusters from temporal remote sensing data. Data from maize crops in Alentejo, Portugal, have been used to assess the suitability of applying triclustering to discover patterns over time, that may eventually help farmers to improve their harvests. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Precision agriculture

来源：评论

学校读者我要写书评

暂无评论

Harmonizing DevOps Taxonomies - A Grounded Theory Study

Research Square

引用

Research Square 2022年

作者： Díaz, Jessica Pérez, Jorge Alves, Isaque Kon, Fabio Leite, Leonarado Meirelles, Paulo Rocha, Carla Madrid28031 Spain Department of Computer Science University of São Paulo R. do Matão 1010 São Paulo Brazil Federal University of ABC Center for Mathematics Computing and Cognition Av. dos Estados 5001 Santo André São Paulo Brazil Universidade de Brasília Faculdade do Gama Area Especial de Indústria Projeção A Gama Brazil

Context: DevOps responds to the growing need of companies to streamline the software development process and, thus, have experienced a widespread adoption in the past few years. However, successful adoption of DevOps requires companies to address important cultural and organizational changes. Understanding the organizational structure and characteristics of teams adopting DevOps is key, and comprehending the existing theories and representations of team taxonomies is critical to guide companies in a more systematic and structured DevOps adoption process. Objective: This paper presents empirical research on the structure of DevOps teams in software-producing organizations. The goal is to better understand the organizational structure and characteristics of teams adopting DevOps by harmonizing the existing knowledge. Method: To do this, we conducted a grounded theory study, analyzing existing studies on DevOps teams and taxonomies. Results: From the analysis, we built a substantive and analytic theory of DevOps taxonomies. The theory is substantive in that the scope of validity refers to the ten primary studies processed and analytic in that it analyzes "what is" rather than explaining causality or attempting predictive generalizations. A public repository with all the data related to the products resulting from the analysis and generation of the theory is available. Conclusions: We built a theory on DevOps taxonomies and tested whether it harmonizes the existing taxonomies, i.e., whether our theory can instantiate the others. This is the first step to define which taxonomies are best suited to approach DevOps culture and practices according to the companies’ objectives and capabilities. © 2022, CC BY.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Applied to IEEE Very Small Size Soccer Strategy

Deep Reinforcement Learning Applied to IEEE Very Small Size ...

引用

IEEE Latin American Robotics Symposium, LARS

作者： Thiago Filipe de Medeiros Marcos R. O. de A. Máximo Takashi Yoneyama Autonomous Computational Systems Lab (LAB-SCA) Computer Science Division Aeronautics Institute of Technology São José dos Campos SP Brazil Electronic Engineering Division Aeronautics Institute of Technology São José dos Campos SP Brazil

ISBN: (数字)9780738111537

ISBN: (纸本)9781665419857

This work concerns a virtual learning framework to train and develop specific behaviours for robots in the context of the IEEE Very Small Size Soccer competition based on Deep Reinforcement Learning. The agents are required to learn how to intercept the ball on the player's side of the field in the presence of an adversary robot nearby. The Proximal Policy Optimization algorithm, augmented by Curriculum Learning, is used during the training process. The performance of the trained agents was evaluated and compared to those, in the same scenario, but without the Curriculum Learning technique and also to agents following previously used heuristic behaviors. As a result, agents trained with Curriculum Learning outperformed, with an success rate of 79.90%, both agents trained without Curriculum Learning and agents that used the chosen heuristic behaviour, which attained a success rate of 72.10% and 45.50%, respectively.

关键词： Sports Meters Training Mobile robots Games Wheels Navigation

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：