检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Xu, Yiming Li, Jiaxin Peng, Yiheng Ding, Yan Wei, Hualiang Yingcai Honors College University of Electronic Science and Technology of China Chengdu China Key Laboratory of Dynamics and Control of Flight Vehicle Ministry of Education School of Aerospace Engineering Beijing Institute of Technology Beijing100081 China School of Computer Science and Technology Donghua University Shanghai China Department of Automatic Control and Systems Engineering University of Shefield ShefieldS1 3JD United Kingdom

Multi-person pose estimation is a fundamental and challenging problem to many computer vision tasks. Most existing methods can be broadly categorized into two classes: top-down and bottom-up methods. Both of the two types of methods involve two stages, namely, person detection and joints detection. Conventionally, the two stages are implemented separately without considering their interactions between them, and this may inevitably cause some issue intrinsically. In this paper, we present a novel method to simplify the pipeline by implementing person detection and joints detection simultaneously. We propose a Double Embedding (DE) method to complete the multi-person pose estimation task in a global-to-local way. DE consists of Global Embedding (GE) and Local Embedding (LE). GE encodes different person instances and processes information covering the whole image and LE encodes the local limbs information. GE functions for the person detection in top-down strategy while LE connects the rest joints sequentially which functions for joint grouping and information processing in A bottom-up strategy. Based on LE, we design the Mutual Refine Machine (MRM) to reduce the prediction difficulty in complex scenarios. MRM can effectively realize the information communicating between keypoints and further improve the accuracy. We achieve the competitive results on benchmarks MSCOCO, MPII and CrowdPose, demonstrating the effectiveness and generalization ability of our method. Copyright © 2021, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Unattended detection in neural OCT image sequences of disease markers

引用

AIP Conference Proceedings 2022年第1期2519卷

作者： V. Anbarasu Sharanabasappa C. Gandage Z. Vakil V. Antony Asir Daniel 1Department of Computer Science and Engineering SRM Institute of Science and Technology Kattankulathur Tamil Nadu India 2Department of Computer Science and Engineering Poojya Doddappa Appa College of Engineering Hyderabad Karnataka India 3Department of Electronics and Communication Engineering Malla Reddy Institute of Engineering and Technology Hyderabad Telangana India 4Francis Xavier Engineering College Tirunelveli Tamil Nadu India

In treatment, initial diagnosis and the treatment of illness, detection, and quantitative analysis of markers in medical images are important. Supervised computer education allows results to be identified and exploited a priori after the samples of instruction by experts are annotated. But due to the number of required examples of instruction and the restriction of the marker language to recognized individuals, monitoring does not scale well. In this proof of concept research, we suggest unattended recognition of anomalies as marker applicants in retinal optical coherent imagery without a prior description restriction. We classify and categorize marker applicants that often appear in the data and prove that these markers provide a predictive value for the disease detection role. A cautious qualitative study of the established data control indicators shows, in patients with early and late-age macular degeneration, how their quantifiable frequency fits our present knowledge of the diseases. A deep denoise auto encoder is trained in multi-scaled images, and any anomalies are detected in new data with the one-class support vector machine. The anomaly cluster distinguishes stable groups. With these markers, the precision of 81,40% is measured as safe, early AMD, and late AMD cases. The model obtained a region under the Receiver operator of hackney in a second binary classification experiment with publicly accessible safe and mid-Dexter datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FES based wrist tremor suppression using multi-periodic repetitive control ⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 10135-10140页

作者： Zan Zhang Bing Chu Yanhong Liu D.H. Owens School of Electrical Engineering Zhengzhou University Zhengzhou China Department of Electronics and Computer Science university of southampton Southampton SO17 1BJ UK Department of Automatic Control and Systems Engineering The University of Sheffield Mappin Street Sheffield S1 3JD UK

Tremor is a very common motor disorder, mainly manifested as involuntary, periodic and rhythmic movement in any part of the body, especially in hands and upper-limbs, which seriously affects the life quality of patients. Functional electrical stimulation (FES) has been shown a promising technique to suppress tremor. Most existing FES based design methods assume tremor is a single frequency signal which however is a highly idealized simplification of the real case which contains multiple-frequency or even a frequency band, therefore limiting their practical performance. To address this problem, this paper proposes a controller design method based on multi-periodic repetitive control that is capable of suppressing tremor signal with multiple frequencies. Simulation and experimental results verify the effectiveness of the proposed method.

关键词： Functional electrical stimulation (FES) tremor suppression multi-periodic repetitive control simulation experimental verification

来源：评论

学校读者我要写书评

暂无评论

An intelligent road traffic data management for upgrading real time performance

引用

AIP Conference Proceedings 2022年第1期2426卷

作者： MD. Rafeeq V. Harsha Shastri Ba Anandh V. Shanmugasundaram Prathipati Ratna Kumar D. Jyothsna 1Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Hyderabad Telangana India. 2Department of Computer Science Department Of Computer Science and Engineering Loyola Academy Secunderabad-500010 Telangana India 3Department of Electronics PSG College of Arts & Science Coimbatore - 641 014 Tamilnadu India. 4Department of Electrical and Electronics Engineering Sona College of Technology Salem - 636005 Tamilnadu India.

The distributed road traffic simulation is an important tool for control and analysis of large road traffic networks (e.g., an entire city or even state). For performing the simulation, it is necessary to divide the simulated road traffic network into sub networks, which are then simulated as processes on computers (nodes) of the distributed computer. To ensure a good performance of the distributed road traffic simulation, two aspects should be considered during the division of the road traffic network - the load-balancing of the resulting sub-networks and the minimization of the inter process communication [1, 2]. Legacy transportation systems are among the most important systems that need to be addressed in a proper manner. Congestion is considered as one of the common problems, especially during peak times of the day because of the weakness of the absorptive capacity of the roads network and the inefficiency of the transportation system to meet the required demands of the increasing traffic size

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multiple shooting for large-scale optimal control problems governed by the Navier-Stokes equations

引用

AIP Conference Proceedings 2022年第1期2425卷

作者： Liang Fang Stefan Vandewalle Johan Meyers 1Department of Mechanical Engineering KU Leuven Celestijnenlaan 300A B3001 Leuven Belgium 2Department of Computer Science KU Leuven Celestijnenlaan 200A B3001 Leuven Belgium

This research proposes and analyzes a multiple shooting based parallel-in-time algorithm for large scale time-dependent optimal control problems governed by the Navier-Stokes equations. The sequential quadratic programming (SQP) method is adopted for solving the equality constrained optimization problem introduced by the multiple shooting strategy. A quasi-Newton method is used, that employs a line search algorithm using an L1 merit function, and a watchdog strategy is used to avoid the Maratos effect. The Karush–Kuhn–Tucker (KKT) system is solved by using a preconditioned conjugate gradient (PCG) method. A block-diagonal preconditioner based on Schur complement is considered, which allows parallel computation in the time domain. For use in the PCG solver, efficient KKT matrix-vector multiplications are studied. The Hessian and inverse Hessian matrix-vector multiplications are approximated by a damped L-BFGS update. The constraint Jacobian matrix-vector multiplications are calcu- lated by linearized and adjoint solvers. Preliminary numerical results for a 2D velocity tracking problem are presented that show a promising efficiency of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

3D Hierarchical Refinement and Augmentation for Unsupervised Learning of Depth and Pose from Monocular Video

arXiv

引用

arXiv 2021年

作者： Wang, Guangming Zhong, Jiquan Zhao, Shijie Wu, Wenhua Liu, Zhe Wang, Hesheng Department of Automation Institute of Medical Robotics Key Laboratory of System Control and Information Processing Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China Department of Engineering Mechanics Shanghai Jiao Tong University Shanghai200240 China Department of Computer Science and Technology University of Cambridge CambridgeCB2 1TN United Kingdom

Depth and ego-motion estimations are essential for the localization and navigation of autonomous robots and autonomous driving. Recent studies make it possible to learn the per-pixel depth and ego-motion from the unlabeled monocular video. A novel unsupervised training framework is proposed with 3D hierarchical refinement and augmentation using explicit 3D geometry. In this framework, the depth and pose estimations are hierarchically and mutually coupled to refine the estimated pose layer by layer. The intermediate view image is proposed and synthesized by warping the pixels in an image with the estimated depth and coarse pose. Then, the residual pose transformation can be estimated from the new view image and the image of the adjacent frame to refine the coarse pose. The iterative refinement is implemented in a differentiable manner in this paper, making the whole framework optimized uniformly. Meanwhile, a new image augmentation method is proposed for the pose estimation by synthesizing a new view image, which creatively augments the pose in 3D space but gets a new augmented 2D image. The experiments on KITTI demonstrate that our depth estimation achieves state-of-the-art performance and even surpasses recent approaches that utilize other auxiliary tasks. Our visual odometry outperforms all recent unsupervised monocular learning-based methods and achieves competitive performance to the geometry-based method, ORB-SLAM2 with back-end optimization. Copyright © 2021, The Authors. All rights reserved.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Creating a cost-effective network of operational resources for wireless networks

引用

AIP Conference Proceedings 2023年第1期2523卷

作者： Venkateshwara Prasad Bhadrappa Haralayya R. Aruna Jayashree A. Kethsy Prabavathy S. Selvarasu 1Department of Management Studies Sri Sairam Engineering College Chennai Tamil Nadu India. 2Department of Management Studies Lingaraj Appa Engineering College Bidar Karnataka India. 3Department of Electronics and Communication Engineering Rajalakshmi Institute of Technology Chennai Tamil Nadu India. 4Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore Tamil Nadu India. 5Department of Electronics and Communication Engineering Muthayammal Engineering College Tamil Nadu India

Wireless Sensor Networks (WSNs) gives human civilization a stunning and clever landscape. Connections between different sensors also strategies in the Internet of Things (IoT) contribute to high energy feasting. Study into liveliness conservation and methods of energy-saving are also important. Sustainability in an energy-efficient way due to the sensors' partial power is important for wireless sensors in an IoT network. This paper aims to analyze an IoT network of remote monitoring and access points. Wireless battery charging power delivery methods are getting more mature. The electrical power supply is operated by a charging car for wireless sensors. The data sharing of the IoT network situation is a minimization challenge to conserve electric energy. A three-stage process obtains the solution. A Reboot Artificial Bee Community (RABC) approach is proposed to solve the sub-problems of the data transfer model. The RABC approach has been shown to converge asymptotically to the optimization process. computer modelling demonstrates that energy consumption can be reduced with a strong, robust function using the proposed approach in the intentional network scenario.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stability estimates for a third order of accuracy difference scheme elliptic overdetermined multi-point problem

引用

AIP Conference Proceedings 2021年第1期2334卷

作者： Charyyar Ashyralyyev Gulzipa Akyuz 1Department of Mathematical Engineering Gumushane University 29100 Gumushane Turkey 2Department of Computer Technology TAU Ashgabat 744000 Turkmenistan

In this work, we discuss a third order of accuracy difference scheme for approximate solution of the elliptic overdeter-mined multi-point problem in the Hilbert space. Functional operator approach is used to study existence and uniqueness of solution of difference problem. Stability, almost coercive stability and coercive stability estimates for solution of difference scheme are established.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An improved E-passport system with secured IoT and wireless communication technology

引用

AIP Conference Proceedings 2022年第1期2452卷

作者： T. Vignesh K. K. Thyagharajan R. Beaulah Jeyavathana Prasanna Kumar R. 1Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India 2Department of ECE R.M.D Engineering College Chennai India 3Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Thandalam Chennai India 4Department of Computer Science and Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Chennai India

A stepped forward E-Passports with IoT devices assumes an essential element in momentum research. Additionally, getting the data, placed away on E-Passport is also an essential difficulty. In this paper, we've got proposed a stepped forward far- off E-Visa framework with simple stage protection. The number one aim of this advanced system is to devise and foster an excessive stage tremendous far-off identity and Savvy card which conveys the identity subtleties and visa limits. Radio Frequency Identification (RFID) is a programmed ID innovation this is using Radio recurrence signals. Utilizing RFID labels as opposed to identity and visa information to conquer the paper works and document lacking difficulty with IoT devices improvements the superior protection highlights of an identity. Also, this advanced system provides high level security in customer information storage.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Internet security protocol for secure data transmission using OSPF and BGP

引用

AIP Conference Proceedings 2022年第1期2463卷

作者： D. Ravikumar M. Prasath Nikhil U. Kumar V. Devi P. Vijayalakshmi 1Department of Electronics and Communication Engineering Kings Engineering College Chennai India 2Departments of Electronics & Communication Engineering Vels Institute of Science Technology & Advanced Studies (VISTAS) Chennai India 3Departments of Computer Applications Gurunanak College Chennai India

Internet Protocol Security (IPsec) is a secure network protocol suite that authenticates and encrypts data packets to offer safe encrypted communication between two computers over an IP network. It’s a protocol that’s utilized in virtual private networks. In this proposed work, we are providing secure path for better packet transmission between transmitter and receiver. For safe and secure data transmission, we are developing two routing algorithms namely Open Shortest Path First and Border Gateway Protocol which are designed for packaging along with switch routing. This embedded algorithm of both OSPF and BGP protocols enhances Internet Protocol security for secure data transmission in networking domain.

关键词：

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：