检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Xu, Jialang Wang, Jiacheng Yu, Lequan Stoyanov, Danail Jin, Yueming Mazomenos, Evangelos B. The Wellcome/EPSRC Centre for Interventional and Surgical Sciences The Department of Medical Physics and Biomedical Engineering University College London London United Kingdom The Department of Computer Science School of Informatics Xiamen University Xiamen China The Department of Statistics and Actuarial Science The University of Hong Kong Hong Kong The Department of Biomedical Engineering The Department of Electrical and Computer Engineering National University of Singapore Singapore

Personalized federated learning (PFL) for surgical instrument segmentation (SIS) is a promising approach. It enables multiple clinical sites to collaboratively train a series of models in privacy, with each model tailored to the individual distribution of each site. Existing PFL methods rarely consider the personalization of multi-headed self-attention, and do not account for appearance diversity and instrument shape similarity, both inherent in surgical scenes. We thus propose PFedSIS, a novel PFL method with visual trait priors for SIS, incorporating global-personalized disentanglement (GPD), appearance-regulation personalized enhancement (APE), and shape-similarity global enhancement (SGE), to boost SIS performance in each site. GPD represents the first attempt at head-wise assignment for multi-headed self-attention personalization. To preserve the unique appearance representation of each site and gradually leverage the inter-site difference, APE introduces appearance regulation and provides customized layer-wise aggregation solutions via hypernetworks for each site’s personalized parameters. The mutual shape information of instruments is maintained and shared via SGE, which enhances the cross-style shape consistency on the image level and computes the shape-similarity contribution of each site on the prediction level for updating the global parameters. PFedSIS outperforms state-of-the-art methods with +1.51% Dice, +2.11% IoU, -2.79 ASSD, -15.55 HD95 performance gains. The corresponding code and models will be released at https://***/wzjialang/PFedSIS. Copyright © 2024, The Authors. All rights reserved.

关键词： Robotic surgery

来源：评论

学校读者我要写书评

暂无评论

HCA-NET: Hierarchical Context Attention Network for Intervertebral Disc Semantic Labeling

HCA-NET: Hierarchical Context Attention Network for Interver...

引用

IEEE International Symposium on Biomedical Imaging

作者： Afshin Bozorgpour Bobby Azad Reza Azad Yury Velichko Ulas Bagci Dorit Merhof Faculty of Informatics and Data Science University of Regensburg Germany Electrical Engineering and Computer Science Department South Dakota State University USA Faculty of Electrical Engineering and Information Technology RWTH Aachen University Germany Machine and Hybrid Intelligence Lab Northwestern University Chicago IL USA Fraunhofer Institute for Digital Medicine MEVIS Germany

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Accurate and automated segmentation of intervertebral discs (IVDs) in medical images is crucial for assessing spine-related disorders, such as osteoporosis, vertebral fractures, or IVD herniation. We present HCA-Net, a novel contextual attention network architecture for semantic labeling of IVDs, with a special focus on exploiting prior geometric information. Our approach excels at processing features across different scales and effectively consolidating them to capture the intricate spatial relationships within the spinal cord. To achieve this, HCA-Net models IVD labeling as a pose estimation problem, aiming to minimize the discrepancy between each predicted IVD location and its corresponding actual joint location. In addition, we introduce a skeletal loss term to reinforce the model’s geometric dependence on the spine. This loss function is designed to constrain the model’s predictions to a range that matches the general structure of the human vertebral skeleton. As a result, the network learns to reduce the occurrence of false predictions and adaptively improves the accuracy of IVD location estimation. Through extensive experimental evaluation on multi-center spine datasets, our approach consistently outperforms previous state-of-the-art methods on both MRI T1w and T2w modalities. The code-base is accessible to the public on GitHub.

关键词： Adaptation models Accuracy Spinal cord Semantics Pose estimation Predictive models Skeleton

来源：评论

学校读者我要写书评

暂无评论

Online dynamic trajectory optimization and control for a quadruped robot

arXiv

引用

arXiv 2020年

作者： Cebe, Oguzhan Tiseo, Carlo Xin, Guiyang Lin, Hsiu-Chin Smith, Joshua Mistry, Michael School of Informatics Institute of Perception Action and Behaviour University of Edinburgh 10 Crichton Street EdinburghEH8 9AB 10 United Kingdom Department of Electrical and Computer Engineering McGill University School of Computer Science Canada

Legged robot locomotion requires the planning of stable reference trajectories, especially while traversing uneven terrain. The proposed trajectory optimization framework is capable of generating dynamically stable base and footstep trajectories for multiple steps. The locomotion task can be defined with contact locations, base motion or both, making the algorithm suitable for multiple scenarios (e.g., presence of moving obstacles). The planner uses a simplified momentumbased task space model for the robot dynamics, allowing computation times that are fast enough for online replanning. This fast planning capability also enables the quadruped to accommodate for drift and environmental changes. The algorithm is tested on simulation and a real robot across multiple scenarios, which includes uneven terrain, stairs and moving obstacles. The results show that the planner is capable of generating stable trajectories in the real robot even when a box of 15 cm height is placed in front of its path at the last moment. Copyright © 2020, The Authors. All rights reserved.

关键词： Aerodynamics

来源：评论

学校读者我要写书评

暂无评论

Referenceless User Controllable Semantic Image Synthesis

arXiv

引用

arXiv 2023年

作者： Kim, Jonghyun Li, Gen Kim, Joongkyu AI Lab CTO Division LG Electronics Seoul Korea Republic of School of Informatics University of Edinburgh Edinburgh United Kingdom Dept. of Electrical and Computer Engineering Sungkyunkwan University Suwon Korea Republic of

Despite recent progress in semantic image synthesis, complete control over image style remains a challenging problem. Existing methods require reference images to feed style information into semantic layouts, which indicates that the style is constrained by the given image. In this paper, we propose a model named RUCGAN for user controllable semantic image synthesis, which utilizes a singular color to represent the style of a specific semantic region. The proposed network achieves reference-free semantic image synthesis by injecting color as user-desired styles into each semantic layout, and is able to synthesize semantic images with unusual colors. Extensive experimental results on various challenging datasets show that the proposed method outperforms existing methods, and we further provide an interactive UI to demonstrate the advantage of our approach for style controllability. The codes and UI are available at: https://***/BenjaminJonghyun/RUCGAN © 2023, CC BY-NC-SA.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Total Variation L1 Fidelity Salt-and-Pepper Denoising with Adaptive Regularization Parameter 5

Total Variation L1 Fidelity Salt-and-Pepper Denoising with A...

引用

5th NAFOSTED Conference on Information and computer Science, NICS 2018

作者： Thanh, Dang N. H. Surya Prasath, V.B. Thanh, Le Thi Department of Information Technology Hue College of Industry Hue530000 Viet Nam Division of Biomedical Informatics Cincinnati Childrens Hospital Medical Center CincinnatiOH45229 United States Division of Biomedical Informatics Cincinnati Children's Hospital Medical Center CincinnatiOH45229 United States Department of Biomedical Informatics College of Medicine University of CincinnatiOH45267 United States Department of Electrical Engineering and Computer Science University of Cincinnati OH45221 United States Department of Basic Sciences Ho Chi Minh City University of Transport Ho Chi Minh700000 Viet Nam

ISBN: (纸本)9781538679838

Total variation (TV) is an effective tool to solve the image denoising and many other image processing problems. For the denoising problem, it is necessary to create automatic image processing methods based on parameters estimation of the corresponding models. For TV image denoising problem, almost methods focus on TV-L2 norm. The works for parameter estimation of denoising model based on TV-L1 norm is very little. The denoising model with TV-L1 norm is impressive to treat the salt-and-pepper noise. In this paper, we propose a parameter estimation method based on characteristics of the salt-and-pepper noise. This method is especially effective for the images without very high contrast and with high noise level. We will handle the comparison to other salt-and-pepper denoising methods, such as TV-L1 method and the BPDF method to prove the effectiveness of the proposed parameter estimation method for the adaptive TVL1 denoising model. © 2018 IEEE.

关键词： Salt and pepper noise

来源：评论

学校读者我要写书评

暂无评论

Retracted: Implementation Method CUSUM to Determine the Accident Prone Areas in Web Based

Retracted: Implementation Method CUSUM to Determine the Acci...

引用

2018 Workshop on Multidisciplinary and Its Applications: Applied Mathematics, computer Science, Information Systems, and Information Technology, WMA-Mathcomtech 2018

作者： Dinata, Rozzi Kesuma Abdullah, Dahlan Hartono, H. Erliana, Cut Ita Riasti, Berliana Kusuma Iskandar, Akbar Sari, Ifit Novita Nurmawati, N. Nanuru, Ricardo Freedom Putri, Lusi Dwi Manurung, Rosida Tiurma Sriadhi, S. Saleh, A.A. Astari, T. Khaddafi, Muammar Department of Informatics Universitas Malikussaleh Aceh Indonesia Department of Computer Science STMIK IBBI Medan Indonesia Department of Industrial Engineering Universitas Malikussaleh Aceh Indonesia Department of Informatics Universitas Sebelas Maret Surakarta Indonesia Department of Informatics STMIK AKBA Makassar Indonesia Departement Of: Social Science Education Program Post Graduate Program Universitas Kanjuruhan Malang Malang Indonesia Faculty of Industry Technique University of 45 Surabaya Indonesia Universitas Kristen Indonesia Maluku Ambon Indonesia Department of Civil Engineering Universitas Lancang Kuning Pekanbaru Indonesia Graduate Program in Scientific Psychology Universitas Kristen Maranatha Indonesia Department of Electrical Engineering Universitas Negeri Medan Indonesia Statistics Financial and Social Sciences Research Group Indonesia Department of Elementary School Teacher Education STKIP Citra Bangsa Aceh Utara Indonesia Department of Accounting Universitas Malikussaleh Aceh Indonesia

At the Unit Laka Lantas Polres Lhokseumawe determining accident-prone areas on roads in Lhokseumawe still using manual systems. Determination of accident-prone areas are less effective because the police Unit Laka Lantas Polres Lhokseumawe just using the data of the last year and had to repeatedly calculate manually accident-prone areas based on the number of human casualties. In this study the system implementation CUSUM method (Cummulative Summary) to determine the accident-prone areas designed using the web-based programming language PHP. In this system there are three processes to determine areas prone to accidents, the accident rate calculations based on the weighted severity, blacksite calculations using the Z-Score method for determining areas prone to accident blackspots and calculations using the CUSUM method to determine the critical points of an accident. The data used are secondary data obtained from the Police Unit Laka Lantas Polres Lhokseumawe years 2009-2013. © Published under licence by IOP Publishing Ltd.

关键词： Accidents

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT SPECTRAL ANALYSIS IN THE MISSING DATA CASE USING SPARSE ML METHODS

EFFICIENT SPECTRAL ANALYSIS IN THE MISSING DATA CASE USING S...

引用

European Signal Processing Conference

作者： George-Othon Glentis Johan Karlsson Andreas Jakobsson Jian Li Dept. of Informatics and Telecommunications University of Peloponnese Dept. of Mathematics KTH Royal Institute of Technology Dept. of Mathematical Statistics Lund University Dept. of Electrical and Computer Engineering University of Florida

ISBN: (纸本)9781479946037

Given their wide applicability, several sparse high-resolution spectral estimation techniques and their implementation have been examined in the recent literature. In this work, we further the topic by examining a computationally efficient implementation of the recent SMLA algorithms in the missing data case. The work is an extension of our implementation for the uniformly sampled case, and offers a notable computational gain as compared to the alternative implementations in the missing data case.

关键词： Spectral estimation theory and methods Sparse Maximum Likelihood methods Fast algorithms

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of the practice of telecom operators in the realization of IPTV systems based on ITIL V3 reccomendations for the Supplier Management Process

Comparative analysis of the practice of telecom operators in...

引用

IEEE International Conference on Service-Oriented Computing and Applications (SOCA)

作者： Anel Tanovic Fahrudin Orucevic Department of IT Development of Multimedia Services BH Telecom d.o.o. Sarajevo Sarajevo Bosnia and Herzegovina Department of Computer Science and Informatics College of Electrical Engineering University of Sarajevo Sarajevo Bosnia and Herzegovina

For the business of an organization to be at a high level, it is necessary to define your relation with an external company (partner) which is going to be helpful in the complete or partial implementation of some project. The main motive for hiring a company as a partner in the process of realization is for finding a high quality solution, and saving your own human resources. The process which deals with the relations between your company and an external company in the IT industry, according to ITIL V3 methodology of leading IT services is Supplier Management. The aim of this document is to describe Supplier Management in the development of IPTV systems in Telecom operator, through the creation of a contract between Telecom operator and a external company which needs to implement and install IPTV systems, and also through the guidelines for performance control of a partnership company by the Telecom operator, during the project of application and installation of the IPTV system. The last chapter of the document includes an comparative analysis of the implementation of Supplier Management through the IPTV system of BH Telecom (the leading telecom operator in Bosnia and Herzegovina) with the recommendation of implementing the same according to ITIL V3 standards. The result of the comparative analysis has to be a sequence of recommendations for the improvement of relations with an external company which has implemented the IPTV system and which is responsible for the initial maintenance of the IPTV system, for the purpose of enabling high quality IPTV services to the end users of this Telecom operator. This contribution represents a continuation of scientific research and application of ITIL V3 standards which is lead in BH Telecom in order to adapt all of the systems under this standard with regard to previously published contributions in this field, a contribution entitled "Implementation of the Information System of the Telecom Operators Using the ITIL V3 Service Me

关键词：

来源：评论

学校读者我要写书评

暂无评论

Documentation of requirements for computer systems

Documentation of requirements for computer systems

引用

IEEE International Symposium on Requirements engineering

作者： A.J. van Schouwen D.L. Parnas J. Madey Bell Northern Research Limited Ottawa ONT Canada Communications Research Laboratory Department of Electrical and Computer Engineering McMaster University Hamilton ONT Canada Institute of Informatics University of Warmia and Mazury Warsaw Poland

A functional approach to specifying the requirements of a computer system is discussed. The method allows system requirements to be documented, whether the system is implemented using a computer and peripheral devices, or, for example, relays and analog components. The method is a refinement of the method used in the A-7 aircraft software requirements model document. The approach is illustrated with examples derived from a software requirements document for a water level monitoring system.< >

关键词： Documentation Software design computer peripherals Buildings Software systems Analog computers Relays computerized monitoring Aerospace engineering Design engineering

来源：评论

学校读者我要写书评

暂无评论

Detection of Gender and Age Category from Speech

Detection of Gender and Age Category from Speech

引用

World Symposium on Digital Intelligence for Systems and Machines (DISA)

作者： Renát Haluška Michal Popovič Matus Pleva Matthew Frohman Department of Electronics and Multimedia Communications Faculty of Electrical Engineering and Informatics Technical University Kosice Kosice Slovakia Department of computer science Perception and Robotics Group University of Maryland College Park MD United States

The main goal of this paper was to find out how the gender and age group acoustical models behave on audio data that is in no way related to the data corpora used to train and evaluate the models. These models could be used for early predator detection in minors’ audio chats. The datasets used for training were mainly composed of English speakers. One part was made up of speakers whose native language is English and the rest use English as a secondary language.

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：