检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Kiessner, Ann-Kathrin Schirrmeister, Robin Tibor Gemein, Lukas A.W. Boedecker, Joschka Ball, Tonio Neuromedical AI Lab Department of Neurosurgery Medical Center – University of Freiburg Faculty of Medicine University of Freiburg Engelbergerstr. 21 Freiburg79106 Germany University of Freiburg Georges-Köhler-Allee 201 Freiburg79110 Germany Autonomous Intelligent Systems Computer Science Department University of Freiburg Faculty of Engineering Georges-Köhler-Allee 80 Freiburg79110 Germany Neurorobotics Lab Computer Science Department University of Freiburg Faculty of Engineering Georges-Köhler-Allee 80 Freiburg79110 Germany

Automated clinical EEG analysis using machine learning (ML) methods is a growing EEG research area. Previous studies on binary EEG pathology decoding have mainly used the Temple University Hospital (TUH) Abnormal EEG Corpus (TUAB) which contains approximately 3,000 manually labelled EEG recordings. To evaluate and eventually even improve the generalisation performance of machine learning methods for EEG pathology, decoding larger, publicly available datasets is required. A number of studies addressed the automatic labelling of large open-source datasets as an approach to create new datasets for EEG pathology decoding, but little is known about the extent to which training on larger, automatically labelled dataset affects decoding performances of established deep neural networks. In this study, we automatically created additional pathology labels for the Temple University Hospital (TUH) EEG Corpus (TUEG) based on the medical reports. We generated a dataset of 15,300 newly labelled recordings, which we call the TUH Abnormal Expansion Corpus (TUABEX), and which is five times larger than the TUAB. Since the TUABEX contains more pathological (75%) than non-pathological (25%) recordings, we then selected a balanced subset of 8,879 recordings, the TUH Abnormal Expansion Balanced Corpus (TUABEXB). To investigate how training on a larger, automatically labelled dataset affects the decoding performance of deep neural networks, we applied four established deep convolutional neural networks (ConvNets) to the task of pathological versus non-pathological classification and compared the performance of each architecture after training on different datasets. The results show that training on the automatically labelled TUABEXB dataset rather than training on the manually labelled TUAB dataset increases accuracies on TUABEXB and even for TUAB itself for some architectures. We argue that automatically labelling of large open-source datasets can be used to efficiently utilise the massiv

关键词： Pathology

来源：评论

学校读者我要写书评

暂无评论

Open and Closed Source Models for LLM-Generated Metaheuristics Solving engineering Optimization Problem 28th

Open and Closed Source Models for LLM-Generated Metaheuris...

引用

28th European Conference on Applications of Evolutionary Computation, EvoApplications 2025, held as part of EvoStar 2025

作者： Senkerik, Roman Viktorin, Adam Kadavy, Tomas Kovac, Jozef Janku, Peter Pekar, Libor Guzowski, Hubert Smolka, Maciej Byrski, Aleksander Pluhacek, Michal A.I.Lab Faculty of Applied Informatics Tomas Bata University Zlin Czech Republic Department of Automation and Control Engineering Faculty of Applied Informatics Tomas Bata University Zlin Czech Republic Faculty of Computer Science AGH University of Krakow Krakow Poland Center of Excellence in Artificial Intelligence AGH University of Krakow Krakow Poland

ISBN: (纸本)9783031900648

This paper explores the applicability of generative AI (genAI), specifically Large Language Models (LLMs), for the automatic generation and configuration of metaheuristic algorithms to address a real-world engineering problem: the optimal parameter estimation of time-delay systems in interconnected heating-cooling loops. The study introduces a pioneering workflow and iterative architecture with feedback within the emerging field of genAI-driven optimization for real optimization problems, eliminating the need for manually crafted or modified algorithms. This automated system empowers domain experts in engineering to solve complex optimization problems with minimal knowledge of optimization algorithms, lowering the barrier to entry for sophisticated algorithm use. We demonstrate how LLMs can generate effective optimizers under conditions like connstrained optimization problems where the solution lies near the boundaries of the search space. Four state-of-the-art LLMs (closed and open-sourced) have been selected for experiments. These are GPT-4o, GPT-4o mini, Claude Sonnet 3.5 and Llama 3.1. All studied LLMs generated metaheuristics that outperformed the initialization baseline optimization method (Random Search and CMA-ES). Notably, the Claude Sonnet 3.5 model generated a metaheuristic with the best mean results, almost matching the performance of the tuned state-of-the-art DISH algorithm, as an example of adaptive Differential Evolution. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Time of arrival

来源：评论

学校读者我要写书评

暂无评论

A fast and effective maximum power point tracking method under various weather conditions for grid-connected photovoltaic systems

A fast and effective maximum power point tracking method und...

引用

IEEE Conference on Power Electronics and Renewable Energy (CPERE)

作者： Karam Khairullah Mohammed Saad Mekhilef Muhyaddin Rawa Control and Mechatronics Engineering Department School of Electrical Engineering Universiti Teknologi Malaysia Johor Bahru Malaysia School of Software and Electrical Engineering Faculty of Science Engineering and Technology Swinburne University of Technology Hawthorn VIC Australia Smart Grids Research Group Center of Research Excellence in Renewable Energy and power Systems King Abdulaziz University Jeddah Saudi Arabia Department Of Electrical and computer Engineering Faculty of engineering K. A Care Energy Research and Innovation Center King Abdulaziz University Jeddah Saudi Arabia

Photovoltaic systems (PV) are exposed to various weather conditions during the day and getting the maximum power of a PV system is one of its major challenges. While the conventional methods take time to track the maximum power accompanying the fluctuation around the maximum power. Consequently, several metaheuristic algorithms have been presented to overcome the fluctuating around the maximum power. On the other hand optimization methods will search into entire the PV curve to extract the maximum power. This leads to unnecessary search points during the uniform shading conditions which decrease the convergence speed towards the maximum power. In overcoming the tracking time issues as well as the capacity to distinguish between uniform and partial shading conditions, a quick and efficient tracking technique connected to the grid system was presented in this paper. The proposed system, has been tested using MATLAB/SIMULINK, which includes a boost converter to track the maximum power with a sampling time of 0.05 seconds, While a voltage source converter (VSC) is used to transfer the power generated by solar panels to the grid. The simulation results demonstrated that the proposed method was successfully implemented, with an average tracking time of 0.412 s for different weather conditions. Moreover, the comparison with the conventional method of perturb and observe (P& O) has been presented to evaluate the proposed method’s efficiency.

关键词： Maximum power point trackers Renewable energy sources Fluctuations Simulation Optimization methods Power electronics Solar panels

来源：评论

学校读者我要写书评

暂无评论

Quantized Event-Based Sampled-Data Nonlinear control for PEM Fuel Cell Air Supply

Quantized Event-Based Sampled-Data Nonlinear Control for PEM...

引用

IEEE Conference on Decision and control

作者： P. Salucci M. Di Ferdinando M.D. Di Benedetto A. Balluchi S. Di Gennaro P. Pepe Department of Information Engineering Computer Science and Mathematics University of L’Aquila Via Vetoio Loc. Coppito L’Aquila Italy Center of Excellence DEWS Via Vetoio Loc. Coppito L’Aquila Italy Pure Power Control S.r.l. Via Carbonia 8 Cascina Pisa Italy

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

The problem of oxygen starvation avoidance in air-feed proton exchange membrane fuel cells is widely known and studied in the literature because it crucially affects the performances of the overall system. To address this problem, many nonlinear control techniques have been provided which, however, do not take into account the effects on the performances induced by the digital hardware commonly used for the practical implementation of control strategies. In this paper, a methodology for the design of quantized sampled-data event-based stabilizers is proposed for a class of time-varying non-linear systems and applied to the problem of oxygen starvation and maximum net power achievement in Proton Exchange Membrane Fuel Cells (PEMFCs). In particular, by exploiting a Lyapunov-based approach and the stabilization in the sample-and-hold sense theory, it is shown that there exist a suitably fast sampling and an accurate quantization of the input/output channels such that the digital event-triggered implementation of a proposed continuous-time stabilizer ensures the semi-global practical stability property of the related closed-loop system. In the theory developed here, time-varying sampling periods and non-uniform quantization of the input/output channels are allowed. Simulations confirm the effectiveness of the theoretical results.

关键词： Protons Quantization (signal) Accuracy Event detection Design methodology Fuel cells Stability analysis Closed loop systems Time-varying systems Numerical stability

来源：评论

学校读者我要写书评

暂无评论

Mesenchymal stem cells loaded on 3D-printed gradient poly(e-caprolactone)/methacrylated alginate composite scaffolds for cartilage tissue engineering

引用

Regenerative Biomaterials 2021年第3期8卷 70-83页

作者： Yanyan Cao Peng Cheng Shengbo Sang Chuan Xiang Yang An Xiaochun Wei Zhizhong Shen Yixia Zhang Pengcui Li Key Lab of Advanced Transducers and Intelligent Control System of the Ministry of Education MicroNano System Research CenterCollege of Information and ComputerTaiyuan University of TechnologyTaiyuan 030024China College of Information Science and Engineering Hebei North UniversityZhangjiakou 075000China Shanxi Key Laboratory of Bone and Soft Tissue Injury Repair Department of OrthopedicsThe Second Hospital of Shanxi Medical UniversityTaiyuan 030001China Department of Plastic Surgery Peking University Third HospitalBeijing 100191China Department of Biomedical Engineering College of Biomedical EngineeringTaiyuan University of TechnologyTaiyuan 030024China

Cartilage has limited self-repair ability due to its avascular,alymphatic and aneural *** combination of three-dimensional(3D)printing and tissue engineering provides an up-and-coming approach to address this ***,we designed and fabricated a tri-layered(superficial layer(SL),middle layer(ML)and deep layer(DL))stratified scaffold,inspired by the architecture of collagen fibers in native cartilage *** scaffold was composed of 3D printed depth-dependent gradient poly(e-caprolactone)(PCL)impregnated with methacrylated alginate(ALMA),and its morphological analysis and mechanical properties were *** prove the feasibility of the composite scaffolds for cartilage regeneration,the viability,proliferation,collagen deposition and chondrogenic differentiation of embedded rat bone marrow mesenchymal stem cells(BMSCs)in the scaffolds were assessed by Live/dead assay,CCK-8,DNA content,cell morphology,immunofluorescence and real-time reverse transcription polymerase chain ***-loaded gradient PCL/ALMA scaffolds showed excellent cell survival,cell proliferation,cell morphology,collagen II deposition and hopeful chondrogenic differentiation compared with three individual-layer ***,our study demonstrates the potential use of the gradient PCL/ALMA construct for enhanced cartilage tissue engineering.

关键词： three-dimensional printing cartilage tissue engineering PCL methacrylated alginate bone marrow mesenchymal stem cells

来源：评论

学校读者我要写书评

暂无评论

GNN-Based Beamforming for Sum-Rate Maximization in MU-MISO Networks

arXiv

引用

arXiv 2023年

作者： Li, Yuhang Lu, Yang Ai, Bo Dobre, Octavia A. Ding, Zhiguo Niyato, Dusit School of Computer and Information Technology Collaborative Innovation Center of Railway Traffic Safety Beijing Jiaotong University Beijing100044 China State Key Laboratory of Rail Traffic Control and Safety the School of Electronics and Information Engineering Beijing Jiaotong University Beijing100044 China Faculty of Engineering and Applied Science Memorial University St. John’sNLA1C 5S7 Canada Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi United Arab Emirates Department of Electrical and Electronic Engineering University of Manchester Manchester United Kingdom School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore

The advantages of graph neural networks (GNNs) in leveraging the graph topology of wireless networks have drawn increasing attentions. This paper studies the GNN-based learning approach for the sum-rate maximization in multiple-user multiple-input single-output (MU-MISO) networks subject to the users’ individual data rate requirements and the power budget of the base station. By modeling the MU-MISO network as a graph, a GNN-based architecture named CRGAT is proposed to directly map the channel state information to the beamforming vectors. The attention-enabled aggregation and the residual-assisted combination are adopted to enhance the learning capability and avoid the oversmoothing issue. Furthermore, a novel activation function is proposed for the constraint due to the limited power budget at the base station. The CRGAT is trained in an unsupervised learning manner with two proposed loss functions. An evaluation method is proposed for the learning-based approach, based on which the effectiveness of the proposed CRGAT is validated in comparison with several convex optimization and learning based approaches. Numerical results are provided to reveal the advantages of the CRGAT including the millisecond-level response with limited optimality performance loss, the scalability to different number of users and power budgets, and the adaptability to different system settings. Copyright © 2023, The Authors. All rights reserved.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

3D Generative Models: A Survey

arXiv

引用

arXiv 2022年

作者： Shi, Zifan Peng, Sida Xu, Yinghao Geiger, Andreas Liao, Yiyi Shen, Yujun Department of Computer Science and Engineering the Hong Kong University of Science and Technology Hong Kong School of Software Technology Zhejiang University China Department of Information Engineering the Chinese University of Hong Kong Hong Kong Autonomous Vision Group University of Tubingen Tubingen AI Center Germany College of Information Science & Electronic Engineering Zhejiang University China Ant Group China

Generative models aim to learn the distribution of observed data by generating new instances. With the advent of neural networks, deep generative models, including variational autoencoders (VAEs), generative adversarial networks (GANs), and diffusion models (DMs), have progressed remarkably in synthesizing 2D images. Recently, researchers started to shift focus from 2D to 3D space, considering that 3D data is more closely aligned with our physical world and holds immense practical potential. However, unlike 2D images, which possess an inherent and efficient representation (i.e., a pixel grid), representing 3D data poses significantly greater challenges. Ideally, a robust 3D representation should be capable of accurately modeling complex shapes and appearances while being highly efficient in handling high-resolution data with high processing speeds and low memory requirements. Regrettably, existing 3D representations, such as point clouds, meshes, and neural fields, often fail to satisfy all of these requirements simultaneously. In this survey, we thoroughly review the ongoing developments of 3D generative models, including methods that employ 2D and 3D supervision. Our analysis centers on generative models, with a particular focus on the representations utilized in this context. We believe our survey will help the community to track the field’s evolution and to spark innovative ideas to propel progress towards solving this challenging task. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Coverage Probability Analysis of RIS-Assisted High-Speed Train Communications

Coverage Probability Analysis of RIS-Assisted High-Speed Tra...

引用

IEEE Conference on Wireless Communications and Networking

作者： Changzhu Liu Ruisi He Yong Niu Bo Ai Zhu Han Meilin Gao Zhangdui Zhong State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China Research Center of Networks and Communications Peng Cheng Laboratory Shenzhen China Department of Electrical and Computer Engineering University of Houston Houston USA Beijing National Research Center for Information Science and Technology Tsinghua University China

Reconfigurable intelligent surface (RIS) has received increasing attention due to its capability of extending cell coverage by reflecting signals toward receivers. This paper considers a RIS-assisted high-speed train (HST) communication system to improve coverage probability. We derive the closed-form expression of coverage probability. Moreover, we analyze impacts of some key system parameters, including transmission power, signal-to-noise ratio threshold, and horizontal distance between base station and RIS. Simulation results verify the efficiency of RIS-assisted HST communications in terms of coverage probability.

关键词： Wireless communication Base stations Closed-form solutions Simulation Receivers Downlink Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Medical Image Registration and Its Application in Retinal Images: A Review

arXiv

引用

arXiv 2024年

作者： Nie, Qiushi Zhang, Xiaoqing Hu, Yan Gong, Mingdao Liu, Jiang Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Center for High Performance Computing Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Singapore Eye Research Institute 169856 Singapore State Key Laboratory of Ophthalmology Optometry and Visual Science Eye Hospital Wenzhou Medical University Wenzhou325027 China

Medical image registration is vital for disease diagnosis and treatment with its ability to merge diverse information of images, which may be captured under different times, angles, or modalities. Although several surveys have reviewed the development of medical image registration, these surveys have not systematically summarized methodologies of existing medical image registration methods. To this end, we provide a comprehensive review of these methods from traditional and deep learning-based directions, aiming to help audiences understand the development of medical image registration quickly. In particular, we review recent advances in retinal image registration at the end of each section, which has not attracted much attention. Additionally, we also discuss the current challenges of retinal image registration and provide insights and prospects for future research. © 2024, CC BY-NC-SA.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An Optimal Distributed Algorithm with Operator Extrapolation for Stochastic Aggregative Games

arXiv

引用

arXiv 2022年

作者： Wang, Tongyu Yi, Peng Chen, Jie Department of Control Science and Engineering Tongji University Shanghai201804 China The Shanghai Research Institute for Intelligent Autonomous Systems Shanghai201804 China The Institute of Advanced Study Tongji University Shanghai201804 China Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai China Shanghai Institute of Intelligent Science and Technology Tongji University Shanghai200092 China

This work studies Nash equilibrium seeking for a class of stochastic aggregative games, where each player has an expectation-valued objective function depending on its local strategy and the aggregate of all players' strategies. We propose a distributed algorithm with operator extrapolation, in which each player maintains an estimate of this aggregate by exchanging this information with its neighbors over a time-varying network, and updates its decision through the mirror descent method. An operator extrapolation at the search direction is applied such that the two step historical gradient samples are utilized to accelerate the convergence. Under the strongly monotone assumption on the pseudo-gradient mapping, we prove that the proposed algorithm can achieve the optimal convergence rate of O(1/k) for Nash equilibrium seeking of stochastic games. Finally, the algorithm performance is demonstrated via numerical simulations. © 2022, CC BY.

关键词： Extrapolation

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：