检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Ferenczi, Bryce Burke, Michael Drummond, Tom Department of Electrical and Computer Systems Engineering Monash University Melbourne Australia Computing and Information Systems University of Melbourne Melbourne Australia

Various works have aimed at combining the inference efficiency of recurrent models and training parallelism of multi-head attention for sequence modeling. However, most of these works focus on tasks with fixed-dimension observation spaces, such as individual tokens in language modeling or pixels in image completion. To handle an observation space of varying size, we propose a novel algorithm that alternates between cross-attention between a 2D latent state and observation, and a discounted cumulative sum over the sequence dimension to efficiently accumulate historical information. We find this resampling cycle is critical for performance. To evaluate efficient sequence modeling in this domain, we introduce two multi-agent intention tasks: simulated agents chasing bouncing particles and micromanagement analysis in professional StarCraft II games. Our algorithm achieves comparable accuracy with a lower parameter count, faster training and inference compared to existing methods. © 2024, CC BY.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Efficient Resource Allocation Algorithm in Uplink OFDM-Based Cognitive Radio Networks

引用

Computers, Materials & Continua 2023年第5期75卷 3045-3064页

作者： Omar Abdulghafoor Musbah Shaat Ibraheem Shayea Ahmad Hamood Abdelzahir Abdelmaboud Ashraf Osman Ibrahim Fadhil Mukhlif Herish Badal Norafida Ithnin Ali Khadim Lwas Electronic&Telecommunications Engineering Department The American University of KurdistanDuhokKurdistan RegionIraq CTTC BarcelonaSpain Faculty of Electrical and Electronics Engineering Istanbul Technical UniversityIstanbulTurkey Department of Information Systems King Khalid UniversityMuhayel AseerSaudi Arabia Faculty of Computing and Informatics University Malaysia SabahKota KinabaluMalaysia Information Assurance and Security Research Group(IASRG) School of ComputingFaculty of EngineeringUniversiti Teknologi MalaysiaJohorMalaysia R&D Ministry of Industry and MineralsBaghdadIraq

The computational complexity of resource allocation processes,in cognitive radio networks(CRNs),is a major issue to be ***,the complicated solution of the optimal algorithm for handling resource allocation in CRNs makes it unsuitable to adopt in real-world applications where both cognitive users,CRs,and primary users,PUs,exist in the identical geographical ***,this work offers a primarily price-based power algorithm to reduce computational complexity in uplink scenarioswhile limiting interference to PUs to allowable ***,this paper,compared to other frameworks proposed in the literature,proposes a two-step approach to reduce the complexity of the proposed mathematical *** the first step,the subcarriers are assigned to the users of the CRN,while the cost function includes a pricing scheme to provide better power control algorithm with improved reliability proposed in the second *** main contribution of this paper is to lessen the complexity of the proposed algorithm and to offer flexibility in controlling the interference produced to the users of the primary networks,which has been achieved by including a pricing function in the proposed cost ***,the performance of the proposed power and subcarrier algorithm is confirmed for orthogonal frequency-division multiplexing(OFDM).Simulation results prove that the performance of the proposed algorithm is better than other algorithms,albeit with a lesser complexity of O(NM)+O(Nlog(N)).

关键词： Cognitive radio resource allocation OFDM pricing

来源：评论

学校读者我要写书评

暂无评论

Artifact-Based Domain Generalization of Skin Lesion Models 17th

Artifact-Based Domain Generalization of Skin Lesion Models

引用

17th European Conference on Computer Vision, ECCV 2022

作者： Bissoto, Alceu Barata, Catarina Valle, Eduardo Avila, Sandra Institute of Computing University of Campinas Campinas Brazil Institute for Systems and Robotics Instituto Superior Técnico Lisbon Portugal School of Electrical and Computing Engineering University of Campinas Campinas Brazil Recod.ai Lab University of Campinas Campinas Brazil

ISBN: (纸本)9783031250682

Deep Learning failure cases are abundant, particularly in the medical area. Recent studies in out-of-distribution generalization have advanced considerably on well-controlled synthetic datasets, but they do not represent medical imaging contexts. We propose a pipeline that relies on artifacts annotation to enable generalization evaluation and debiasing for the challenging skin lesion analysis context. First, we partition the data into levels of increasingly higher biased training and test sets for better generalization assessment. Then, we create environments based on skin lesion artifacts to enable domain generalization methods. Finally, after robust training, we perform a test-time debiasing procedure, reducing spurious features in inference images. Our experiments show our pipeline improves performance metrics in biased cases, and avoids artifacts when using explanation methods. Still, when evaluating such models in out-of-distribution data, they did not prefer clinically-meaningful features. Instead, performance only improved in test sets that present similar artifacts from training, suggesting models learned to ignore the known set of artifacts. Our results raise a concern that debiasing models towards a single aspect may not be enough for fair skin lesion analysis. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

DEGAS - Deformation Estimation based on Magnetic Gradient Tensor Contraction for Soft Robot Shape Servoing

DEGAS - Deformation Estimation based on Magnetic Gradient Te...

引用

IEEE International Conference on Soft Robotics (RoboSoft)

作者： Jelena Vuletić Bruno Marić Matko Orsag LARICS Laboratory for Robotics and Intelligent Control Systems University of Zagreb Faculty of Electrical Engineering and Computing Zagreb Croatia

ISBN: (数字)9798331520205

ISBN: (纸本)9798331520212

This work proposes the first derivation, implementation, and experimental validation of magnetic-based proprioceptive sensing method for soft robotic applications. In our proposed approach, the magnetic sensing system measures gradient tensor contractions that can be directly related to the shape of a deformable plastering tool. Custom-designed and 3D-printed plastering tool embeds two identical permanent magnets that generate a non-symmetric magnetic field tracked by the proposed sensor. Seamless real-time control is enabled with the sensor sampling rate of 1 kHz. Classical linear control is synthesized for the scraper bending angle and orientation control. The tool, sensor, and the proposed control system are validated on robotic plastering and painting tasks.

关键词： Magnetic field measurement Tensors Deformation Shape Propioception Estimation Bending Soft robotics Sensors Painting

来源：评论

学校读者我要写书评

暂无评论

Influence of donor age on liver transplantation outcomes: A multivariate analysis and comparative study

引用

World Journal of Gastrointestinal Surgery 2024年第2期16卷 331-344页

作者： Miran Bezjak Ivan Stresec Branislav Kocman Stipislav Jadrijević Tajana Filipec Kanizaj Miro Antonijević Bojana Dalbelo Bašić Danko Mikulić Department of Surgery University Hospital MerkurZagreb 10000Croatia Department of Electronics MicroelectronicsComputer and Intelligent SystemsFaculty of Electrical Engineering and ComputingZagreb 10000Croatia Department of Gastroenterology University Hospital MerkurZagreb 10000Croatia Development of Software Nanobit Ltd.Zagreb 10000Croatia

BACKGROUND The growing disparity between the rising demand for liver transplantation(LT)and the limited availability of donor organs has prompted a greater reliance on older liver ***,utilizing livers from elderly donors has been associated with outcomes inferior to those achieved with grafts from younger *** accounting for additional risk factors,we hypothesize that the utili-zation of older liver grafts has a relatively minor impact on both patient survival and graft *** To evaluate the impact of donor age on LT outcomes using multivariate analysis and comparing young and elderly donor *** In the period from April 2013 to December 2018,656 adult liver transplants were performed at the University Hospital *** multivariate Cox propor-tional hazards models were developed to independently assess the significance of donor *** age was treated as a continuous *** approach involved univariate and multivariate analysis,including variable selection and assessment of interactions and ***,to exemplify the similarity of using young and old donor liver grafts,the group of 87 recipients of elderly donor liver grafts(≥75 years)was compared to a group of 124 recipients of young liver grafts(≤45 years)from the *** rates of the two groups were estimated using the Kaplan-Meier method and the log-rank test was used to test the differences between *** Using multivariate Cox analysis,we found no statistical significance in the role of donor age within the constructed *** when retained during the entire model development,the donor age's impact on survival remained insignificant and transformations and interactions yielded no substantial effects on *** insigni-ficance and low coefficient values suggest that donor age does not impact patient survival in our ***,there was no statistical evidence that the five developed models did not adhe

关键词： Liver transplantation Elderly donors Survival analysis Postoperative complications Cox proportional hazard models

来源：评论

学校读者我要写书评

暂无评论

Graph-Based Decentralized Exploration and Semantic Inspection for Multi-Robot systems

Graph-Based Decentralized Exploration and Semantic Inspectio...

引用

International Conference on Unmanned Aircraft systems (ICUAS)

作者： Nada E. Abbas Tamara Petrovic Faculty of Electrical Engineering and Computing LARICS Laboratory for Robotics and Intelligent Control Systems University of Zagreb Zagreb Croatia

ISBN: (数字)9798331513283

ISBN: (纸本)9798331513290

This paper presents a decentralized graph-based exploration and inspection framework for Multi-Robot systems, designed to address challenges in subterranean and largescale environments. Unlike prior works that focus solely on exploration or inspection, this framework integrates volumetric exploration, semantic inspection, and dynamic task allocation into a unified decentralized system. A key novelty of this work is the seamless integration of these modules in a multi-robot setting, allowing UAVs to autonomously coordinate their tasks without relying on centralized control. The framework employs a hierarchical graph structure, utilizing a dense local graph for immediate navigation and a sparse global graph for long-term planning and repositioning. Extensive simulations in large-scale complex-shaped environments demonstrate that the proposed approach improves the completeness of the generated maps, reduces inconsistencies in the constructed mesh, and accelerates the overall exploration-inspection process compared to existing decentralized strategies.

关键词： Semantics Inspection Prediction algorithms Dynamic scheduling Aircraft navigation Robustness Planning Multi-robot systems Resource management Centralized control

来源：评论

学校读者我要写书评

暂无评论

Automation 5.0: The Key to systems Intelligence and Industry 5.0

引用

IEEE/CAA Journal of Automatica Sinica 2024年第8期11卷 1723-1727页

作者： Ljubo Vlacic Hailong Huang Mariagrazia Dotoli Yutong Wang Petros A.Ioannou Lili Fan Xingxia Wang Raffaele Carli Chen Lv Lingxi Li Xiaoxiang Na Qing-Long Han Fei-Yue Wang Institute of Intelligent and Integrated Systems and the School of Engineering and Built Environment Griffith UniversityNathanQLD 4111Australia Department of Aeronautical and Aviation Engineering The Hong Kong Polytechnic UniversityHong KongChina Department of Electrical and Information Engineering Polytechnic of Bari70126 BariItaly State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190and also with the Qingdao Academy of Intelligent IndustriesQingdao 266114China Department of Electrical Engineering-Systems University of Southern CaliforniaLos AngelesCA 90007 USA School of Automation Beijing Institute of TechnologyBeijing 100081China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049 Beijing Huairou Academy of Parallel Sensing Beijing 101499China School of Mechanical and Aerospace Engineering Nanyang Technological UniversitySingapore 639798Singapore Department of Electrical and Computer Engineering Purdue School of Engineering and TechnologyIndiana University-Purdue University IndianapolisIndianapolisIN 46202 USA Department of Engineering University of CambridgeCB21TN CambridgeU.K. School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyMelbourne VIC 3122Australia State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190 School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Dazhou Artificial Intelligence Institute Dazhouand the Faculty of Innovation EngineeringMacao University of Science and TechnologyMacao 999078China

AUTOMATION has come a long way since the early days of mechanization,i.e.,the process of working exclusively by hand or using animals to work with *** rise of steam engines and water wheels represented the first generation of industry,which is now called Industry Citation:***,***,***,***,***,***,***,***,***,***,***,Q.-***,and F.-***,“Automation 5.0:The key to systems intelligence and Industry 5.0,”IEEE/CAA ***,vol.11,no.8,pp.1723-1727,Aug.2024.

关键词： Automation machinery intelligence

来源：评论

学校读者我要写书评

暂无评论

Position and Attitude Control of Quadrotor UAV Based on a New Sliding Mode Control Strategy 42

Position and Attitude Control of Quadrotor UAV Based on a Ne...

引用

42nd Chinese Control Conference, CCC 2023

作者： Wu, Yinghua Zhang, Ancai Pan, Guangyuan Du, Yingxue Liu, Zhi School of Automation and Electrical Engineering Linyi University Shandong Linyi276005 China Universities of Shandong Key Laboratory of Complex Systems and Intelligent Computing Linyi University Shandong Linyi276005 China

ISBN: (纸本)9789887581543

A Quadrotor unmanned aerial vehicle (UAV) is a typical underactuated nonlinear mechanical system with six degrees of freedom (DOF) and four inputs. This paper develops a new sliding mode control (SMC) strategy to solve the position and attitude control problem for this multi-DOF underactuated system. First, the dynamic motion equation model of the Quadrotor UAV is established. Second, the first and fourth inputs are designed by using the traditional SMC method and a novel Gaussian geometric function reaching law. And then, we design the second and third inputs based on a hierarchical SMC method. And the stability of sliding mode surfaces are analyzed using Lyapunov theory. The designed four sliding controllers guarantee the flight control objective of the Quadrotor UAV to be achieved. And the Gaussian reaching law used in the design of controllers can effectively reduce the chattering phenomena in the sliding mode surfaces. Numerical examples verify the effectiveness of our developed control strategy. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Multi-food source differential salp swarm algorithm 23

Multi-food source differential salp swarm algorithm

引用

2023 International Conference on Computer, Vision and Intelligent Technology, ICCVIT 2023

作者： Lin, Anping Shi, Yaoting Zhang, Wenfen Liu, Dong Lan, Yulin School of Physics and Electronic Electrical Engineering Xiangnan University Chenzhou423000 China School of Computer and Artificial Intelligence Hunan Engineering Research Center of Advanced Embedded Computing and Intelligent Medical Systems Xiangnan University Chenzhou China

ISBN: (纸本)9798400708701

Salp swarm algorithm (SSA) divides the population into leaders and followers, and employs two different search methods to achieve steady convergence. However, the search methods adopted by SSA are relatively simple, hence SSA always trapped by local optima on complex multimodal problems. To improve the exploration of SSA, this paper proposes a multi-food source differential salp swarm algorithm (MFD-SSA) by transferring multi-leader mechanism and differential mutation strategy into SSA. MFD-SSA regards a portion of high fitness individuals as food sources and employ them for updating the position of leaders, the differential evolution mutation and the chaotic crossover are adopted to enhance swarm diversity. Then, the differential mutation and crossover operator are employed for enlarging search range. The MFD-SSA is tested on CEC2017 test suite and compared with five SSA variants and five other meta-heuristics. The test results indicate that MFD-SSA bears strong exploration, it outperforms five SSA variants and five meta-heuristics. On Planetary gear train design problem, MFD-SSA performs better than other five SSA variants too. © 2023 ACM.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Power transmission network planning under uncertainties

Power transmission network planning under uncertainties

引用

IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT Europe)

作者： Neven Vukadinović Ivica Pavić Ninoslav Holjevac Department of Energy and Power Systems University of Zagreb Faculty of Electrical Engineering and Computing Zagreb Republic of Croatia

ISBN: (数字)9798350390421

ISBN: (纸本)9798350390438

The optimization of load flow analysis is crucial for the efficient observation of the impact of new power plants into existing electricity power systems (EPS). The advent of integration of new energy sources has reduced construction timeline requirements to 4-5 years, creating a lag in the development of supporting electricity infrastructure. This paper explores the spatial and temporal dimensions of EPS development planning, illustrated through the example of two new connection requests to a transmission network, with emphasis on importance of load flow optimization and the potential failure analysis to meet the (N-1) contingency criterion, which ensures system reliability during outages. This paper underscores the necessity of strategic planning in EPS development to accommodate new generation units while maintaining system stability and reliability at the satisfactory levels.

关键词： Uncertainty Electricity Europe Power system stability Planning Power system reliability Complexity theory Reliability Artificial intelligence Optimization

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：