检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Dong, Jiahua Zhang, Yue Wang, Qiuli Tong, Ruofeng Ying, Shihong Gong, Shaolin Zhang, Xuanpu Lin, Lanfen Chen, Yen-Wei College of Computer Science and Technology Zhejiang University Hangzhou China School of Biomedical Engineering Division of Life Sciences and Medicine University of Science and Technology of China Anhui Hefei China Suzhou Institute for Advanced Research University of Science and Technology of China Jiangsu Suzhou China 7T Magnetic Resonance Translational Medicine Research Center Department of Radiology Southwest Hospital Army Medical University Third Military Medical University Chongqing China Department of Radiology The First Affiliated Hospital College of Medicine Zhejiang University Hangzhou China College of Information Science and Engineering Ritsumeikan University Shiga Japan

Medical image segmentation is crucial in the field of medical imaging, aiding in disease diagnosis and surgical planning. Most established segmentation methods rely on supervised deep learning, in which clean and precise labels are essential for supervision and significantly impact the performance of models. However, manually delineated labels often contain noise, such as missing labels and inaccurate boundary delineation, which can hinder networks from correctly modeling target characteristics. In this paper, we propose a deep self-cleansing segmentation framework that can preserve clean labels while cleansing noisy ones in the training phase. To achieve this, we devise a gaussian mixture model-based label filtering module that distinguishes noisy labels from clean labels. Additionally, we develop a label cleansing module to generate pseudo low-noise labels for identified noisy samples. The preserved clean labels and pseudo-labels are then used jointly to supervise the network. Validated on a clinical liver tumor dataset and a public cardiac diagnosis dataset, our method can effectively suppress the interference from noisy labels and achieve prominent segmentation performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Bifurcation Analysis of Incompressible Fluid Flow by a High Order Mesh-Free Indicator with Padé Approximants 15th

Bifurcation Analysis of Incompressible Fluid Flow by a Hi...

引用

15th International Moroccan Congress of Mechanics, CMM 2022

作者： Rammane, M. Mesmoudi, S. Askour, O. Tri, A. Braikat, B. Damil, N. Laboratory of Materials Signals Systems and Physical Modeling Department of Physics Faculty of Sciences Agadir University Ibn Zohr BP 8106 Agadir80000 Morocco Hassan First University of Settat National School of applied Sciences LISA Laboratory Berrechid26100 Morocco Mathematics Computer Science and Communication Systems Laboratory National School of Applied Sciences of Safi Cadi Ayyad University BP 63 Safi Sidi Bouzid46000 Morocco Laboratory of Mechanics Faculty of Sciences Ain Chock Hassan II University of Casablanca Casablanca Morocco Km 7 Route d’El Jadida Casablanca Morocco Laboratory of Engineering and Materials Faculty of Sciences Ben M’sik Hassan II University of Casablanca B.P 7955 Sidi Othman Casablanca Morocco Central Casablanca Complex Systems and Interactions Research Center Green City Bouskoura27182 Morocco

ISBN: (纸本)9783031469725

In this work, a mesh-free indicator is proposed to detect the bifurcation points of incompressible viscous fluid flow in a 2D sudden expansion. This indicator is mainly based on the high order mesh-free algorithm (HO-MFA) to solve the nonlinear problems obtained from the linear stability analysis. The Padé approximants are then used to improve the validity range of the HO-MFA and to determinate the roots of the indicator. The combination of these mathematical tools allows us to determine the zero of the indicator corresponding to the critical point. The Lyapunov-Schmidt reduction is used to search all the bifurcated branches from the critical point. To show the accuracy of our model, comparisons of the obtained results with those of the literature are made. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Linear stability analysis

来源：评论

学校读者我要写书评

暂无评论

Navigation-GPT: A Robust and Adaptive Framework Utilizing Large Language Models for Navigation Applications

arXiv

引用

arXiv 2025年

作者： Ma, Feng Wang, Xiu-Min Chen, Chen Xu, Xiao-Bin Yan, Xin-Ping Wuhan University of Technology Wuhan China Intelligent Transportation Systems Research Center Wuhan University of Technology Wuhan China School of Computer Science & Engineering Wuhan Institute of Technology Wuhan China China-Austria Belt and Road Joint Laboratory on Artificial Intelligence and Advanced Manufacturing Hangzhou Dianzi University Hangzhou China Nanjing Smart Water Transport Technology Co. Ltd. Nanjing China

Existing navigation decision support systems often perform poorly when handling non-predefined navigation scenarios. Leveraging the generalization capabilities of large language model (LLM) in handling unknown scenarios, this research proposes a dual-core framework for LLM applications to address this issue. Firstly, through ReAct-based prompt engineering, a larger LLM core decomposes intricate navigation tasks into manageable sub-tasks, which autonomously invoke corresponding external tools to gather relevant information, using this feedback to mitigate the risk of LLM hallucinations. Subsequently, a fine-tuned and compact LLM core, acting like a first-mate is designed to process such information and unstructured external data, then to generates context-aware recommendations, ultimately delivering lookout insights and navigation hints that adhere to the International Regulations for Preventing Collisions at Sea (COLREGs) and other rules. Extensive experiments demonstrate the proposed framework not only excels in traditional ship collision avoidance tasks but also adapts effectively to unstructured, non-predefined, and unpredictable scenarios. A comparative analysis with DeepSeek-R1, GPT-4o and other SOTA models highlights the efficacy and rationality of the proposed framework. This research bridges the gap between conventional navigation systems and LLMs, offering a framework to enhance safety and operational efficiency across diverse navigation applications. © 2025, CC BY-SA.

关键词： Ships

来源：评论

学校读者我要写书评

暂无评论

Leveraging Augmented and Virtual Reality in Conjunction with Artificial Intelligence, 5G, and Edge Computing to Transform Immersive Experiences

Leveraging Augmented and Virtual Reality in Conjunction with...

引用

Smart Technologies, Communication and Robotics (STCR)

作者： G.Palanikumar V.Samuthira Pandi S.Banumathi G. Karthikeyan Jayant Giri Maram Y. Al-Safarini Department of Mathematics Sri Venkateswara College of Engineering (SVCE) Tamil Nadu Centre for Advanced Wireless Integrated Technology Chennai Institute of Technology Chennai Tamil Nadu India Department of Computer Science Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Veltech University - Deemed to be University Chennai Tamil Nadu India Department of VLSI Microelectronics Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Saveetha University Chennai Department of Mechanical Engineering Yeshwantrao Chavan College of Engineering Nagpur. Division of Research and Development Lovely Professional University Phagwara India Computer Science Department Zarqa University Zarqa Jordan University of Business and Technology Jeddah Saudi Arabia

ISBN: (数字)9798350357530

ISBN: (纸本)9798350357547

AR, VR, AI, 5G, and Edge Computing are converging to reshape immersive experiences across industries in terms of content creation, content delivery and content interaction. AR and VR have achieved remarkable progress so far in fields like the gaming industry, education, healthcare, and entertainment, and are already delivering immersive and realistic environments for users. Nonetheless, the real magic happens with their combination with AI, 5G and Edge Computing, which makes immersive experiences perform, scale and respond better to interactions. AI and AR/VR create a symbiotic relationship where AI designs intelligent interaction, personalizes user experience, and aids decision-making in AR/VR environments by analyzing user behaviors and context in real-time. Simultaneously, the rollout of 5G networks will provide ultra-low latency, high-speed data transfer, and immense connectivity, all of which are critical to rendering high-quality asynchronous immersive experiences. By processing data to the edge, close to the end-user, Edge Computing cuts latency to the minimal level and makes sure that interactions are fast and seamless enough to make immersive applications work. This paper discusses the convergence of AR/VR with the other digital technologies such as AI, 5G, and Edge computing and its impact on industries leading to more immersive, scalable and personalized experiences. In this report, we explore how these technologies make one another better, resulting in breakthroughs across fields like telemedicine, remote education, autonomous driving, and even virtual tourism. We also highlight the implications of this convergence in terms of data security, privacy considerations, and the requirements for computational resources. This paper encapsulates those concepts, discussing what comes next and what role immersive technologies will play in the next generation of human-computer interactions. Thus, the fusion of AR/VR, AI, 5G, and Edge Computing is enhancing user exp

关键词： 5G mobile communication Telemedicine Education Entertainment industry Medical services Rendering (computer graphics) Real-time systems Artificial intelligence Autonomous vehicles Edge computing

来源：评论

学校读者我要写书评

暂无评论

Creation of a p-type TlBiSe2 using photo-induced doping

引用

Physical Review Materials 2023年第11期7卷 114201-114201页

作者： Ryota Itaya Yuichiro Toichi Ryuya Nakanishi Narunori Ebara Yoshitaka Nakata Kentaro Kasai Kenta Kuroda Masashi Arita Isamu Yamamoto Keisuke Fukutani Kazuyuki Sakamoto Department of Applied Physics Osaka University Osaka 565-0871 Japan Graduate School of Science and Engineering Chiba University Chiba 263-8522 Japan Graduate School of Advanced Science and Engineering Hiroshima University Higashi-Hiroshima 739-8526 Japan International Institute for Sustainability with Knotted Chiral Meta Matter (SKCM2) Hiroshima University Higashi-Hiroshima 739-8526 Japan Hiroshima Synchrotron Radiation Center Hiroshima University Higashi-Hiroshima 739-0046 Japan Synchrotron Light Application Center Saga University Saga 840-8502 Japan Institute for Molecular Science National Institutes of Natural Sciences Okazaki 444-8585 Japan Center for Artificial Low Dimensional Electronic Systems Institute for Basic Science (IBS) Pohang 37673 Republic of Korea Center for Spintronics Research Network Graduate School of Engineering Science Osaka University Osaka 560-8531 Japan Spintronics Research Network Division Institute for Open and Transdisciplinary Research Initiatives Osaka University Osaka 565-0871 Japan

Owing to the location of the Dirac point, which is around the center of its wide bulk band gap, TlBiSe2 would be one of the most promising topological insulators for spintronics devices material. However, like many other topological insulators, defects, such as vacancy formed during the crystal growth, dope electrons into TlBiSe2 and make its bulk metallic. Here, we show the achievement of bulk insulating both n-type and p-type TlBiSe2 by photo-induced doping, a method carried out by a combination of photo-irradiation and H2O adsorption. We also show that the main trigger of this photo-induced doping is the excitation of the outermost d core level of the chalcogen atoms of the topmost layer as in the case of Bi2X3, where X=Se or Te.

关键词： Adsorption Doping effects Electronic structure Irradiation effects Surface states Topological insulators Topological materials Photoemission spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Adaptive Wavelet Filters as Practical Texture Feature Amplifiers for Parkinson’s Disease Screening in OCT

arXiv

引用

arXiv 2025年

作者： Zhang, Xiaoqing Shi, Hanfeng Li, Xiangyu Ye, Haili Xu, Tao Li, Na Hu, Yan Lv, Fan Chen, Jiangfan Liu, Jiang Center for High Performance Computing and Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China State Key Laboratory of Ophthalmology Optometry and Vision Science Wenzhou Medical University Wenzhou China Centre for Computational Science and Mathematical Modelling Coventry University Coventry United Kingdom School of Computer Science University of Nottingham Ningbo China Ningbo315100 China School of Ophthalmology and Optometry Wenzhou Medical University Wenzhou325035 China Department of Electronic and Information Engineering Changchun University Changchun130022 China

Parkinson’s disease (PD) is a prevalent neurodegenerative disorder globally. The eye’s retina is an extension of the brain and has great potential in PD screening. Recent studies have suggested that texture features extracted from retinal layers can be adopted as biomarkers for PD diagnosis under optical coherence tomography (OCT) images. Frequency domain learning techniques can enhance the feature representations of deep neural networks (DNNs) by decomposing frequency components involving rich texture features. Additionally, previous works have not exploited texture features for automated PD screening in OCT. Motivated by the above analysis, we propose a novel Adaptive Wavelet Filter (AWF) that serves as the Practical Texture Feature Amplifier to fully leverage the merits of texture features to boost the PD screening performance of DNNs with the aid of frequency domain learning. Specifically, AWF first enhances texture feature representation diversities via channel mixer, then emphasizes informative texture feature representations with the well-designed adaptive wavelet filtering token mixer. By combining the AWFs with the DNN stem, AWFNet is constructed for automated PD screening. Additionally, we introduce a novel Balanced Confidence (BC) Loss by mining the potential of sample-wise predicted probabilities of all classes and class frequency prior, to further boost the PD screening performance and trustworthiness of AWFNet. The extensive experiments manifest the superiority of our AWFNet and BC over state-of-the-art methods in terms of PD screening performance and trustworthiness. © 2025, CC BY-NC-SA.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Metabolic and oxidative responses in Helix aspersa to iron oxide nanoparticle exposure: individual and combined (Fe₂O₃/SiO₂) effects

引用

Journal of Nanoparticle research 2025年第6期27卷 1-14页

作者： Benamara, Amel Grara, Nedjoud Bensoltane, Samira Bouchaala, Laid Laouar, Amel Grara, Kamila Hemmami, Hadia Abdelghani, Boudjahem Aslam, Ali Abbas Ahmed, Mahmood Laboratory of Cellular Toxicology Faculty of Sciences University of Badji Mokhtar Annaba 23000 Algeria Department of Applied Biology Echahid Cheikh Larbi Tebessi University Tebessa 12400 Algeria Laboratory of Molecular and Cellular Biology Faculty of Natural and Life Sciences Earth and Universe Sciences P.O. Box 401 University 8 May 1945 Guelma Algeria Faculty of Medicine University of Badji Mokhtar Annaba 23000 Algeria Division of Environmental Innovation and Eco-Waste Management Environmental Research Center (CRE) Annaba Algeria Laboratory of Biochemistry and Environmental Toxicology Faculty of Sciences University of Badji Mokhtar Annaba 23000 Algeria Laboratory of Analysis and Control of Differential Equations Department of Mathematics P.O. Box 401 University 8 May 1945 Guelma 24000 Algeria Department of Process Engineering and Petrochemical Faculty of Technology University of El Oued P.O. Box 789 El Oued 39000 Algeria Faculty of Mathematics Computer and Materials Sciences Department of Materials Science Universityof 8 Mai Guelma 1945 Algeria Department of Chemistry Division of Science and Technology University of Education Lahore 54770 Pakistan

This study evaluates the toxicity of iron oxide nanoparticles (Fe2O3 NPs) alone and in combination with silica nanoparticles (SiO2 NPs) on Helix aspersa. Snails were exposed to escalating concentrations (0, 5000, 10,0... 详细信息

This study evaluates the toxicity of iron oxide nanoparticles (Fe₂O₃ NPs) alone and in combination with silica nanoparticles (SiO₂ NPs) on Helix aspersa. Snails were exposed to escalating concentrations (0, 5000, 10,000, 15,000 μg/g of flour) of Fe₂O₃ NPs and a mixture of Fe₂O₃ and SiO₂ NPs for 28 days to assess impacts on metabolic parameters, oxidative stress, and neurotoxicity. Fe₂O₃ NPs significantly increased protein levels;the mixture exhibited a more pronounced effect, with significantly increased protein levels, particularly in the hepatopancreas and kidneys. Lipid levels generally decreased across all treatments, suggesting significant metabolic disruption. Carbohydrate responses were tissue-specific and differed significantly between single and combined exposures, highlighting complex responses to nanoparticle treatments. Malondialdehyde (MDA), a marker of lipid peroxidation, demonstrated a significant increase in all treatments compared to the control group. The mixture treatment caused divergent MDA responses, with higher levels observed in the hepatopancreas and lower levels in the kidneys than in single NP treatments. Glutathione (GSH) levels showed complex tissue-specific changes with mixture exposure, with reductions in the hepatopancreas and increases in the kidney. Furthermore, glutathione S-transferase (GST), catalase (CAT), and glutathione peroxidase (GPx) were altered, reflecting cellular stress responses. Notably, acetylcholinesterase (AChE) activity, a marker of neurotoxicity, was significantly reduced in all treated groups. These findings demonstrate that Fe₂O₃ NPs, individually and combined with SiO₂ NPs, induce significant metabolic dysregulation, oxidative stress, and neurotoxicity in H. aspersa. This study underscores the potential ecological risks of NPs contamination and the importance of further

关键词： Helix aspersa Iron Nanoparticles Oxidative stress Silica Toxicity

来源：评论

学校读者我要写书评

暂无评论

On the dual advantage of placing observations through forward sensitivity analysis

arXiv

引用

arXiv 2023年

作者： Ahmed, Shady E. San, Omer Lakshmivarahan, Sivaramakrishnan Lewis, John M. Advanced Computing Mathematics and Data Division Pacific Northwest National Laboratory RichlandWA99354 United States School of Mechanical & Aerospace Engineering Oklahoma State University StillwaterOK74078 United States School of Computer Science University of Oklahoma NormanOK73019 United States Desert Research Institute RenoNV89512 United States

The four-dimensional variational data assimilation methodology for assimilating noisy observations into a deterministic model has been the workhorse of forecasting centers for over three decades. While this method provides a computationally efficient framework for dynamic data assimilation, it is largely silent on the important question concerning the minimum number and placement of observations. To answer this question, we demonstrate the dual advantage of placing the observations where the square of the sensitivity of the model solution with respect to the unknown control variables, called forward sensitivities, attains its maximum. Therefore, we can force the observability Gramian to be of full rank, which in turn guarantees efficient recovery of the optimal values of the control variables, which is the first of the two advantages of this strategy. We further show that the proposed strategy of placing observations has another inherent optimality: the square of the sensitivity of the optimal estimates of the control with respect to the observations (used to obtain these estimates) attains its minimum value, a second advantage that is a direct consequence of the above strategy for placing observations. Our analytical framework and numerical experiments on linear and nonlinear systems confirm the effectiveness of our proposed strategy. © 2023, CC BY.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Learning-based Control for PMSM Using Distributed Gaussian Processes with Optimal Aggregation Strategy

Learning-based Control for PMSM Using Distributed Gaussian P...

引用

Annual Conference of Industrial Electronics Society

作者： Zhenxiao Yin Xiaobing Dai Zewen Yang Yang Shen Georges Hattab Hang Zhao Robotics and Autonomous Systems Thrust The Hong Kong University of Science and Technology (Guangzhou) Guangzhou China Chair of Information-oriented Control Technical University of Munich Munich Germany Center for Artificial Intelligence in Public Health Research (ZKI-PH) Robert Koch Institute Berlin Germany Department of Mathematics and Computer Science Freie Universität Berlin Berlin Germany Department of Electronic & Computer Engineering The Hong Kong University of Science and Technology Hong Kong China

The growing demand for accurate control in varying and unknown environments has sparked a corresponding increase in the requirements for power supply components, including permanent magnet synchronous motors (PMSMs). To infer the unknown part of the system, machine learning techniques are widely employed, especially Gaussian process regression (GPR) due to its flexibility of continuous system modeling and its guaranteed performance. For practical implementation, distributed GPR is adopted to alleviate the high computational complexity. However, the study of distributed GPR from a control perspective remains an open problem. In this paper, a control-aware optimal aggregation strategy of distributed GPR for PMSMs is proposed based on the Lyapunov stability theory. This strategy exclusively leverages the posterior mean, thereby obviating the need for computationally intensive calculations associated with posterior variance in alternative approaches. Moreover, the straightforward calculation process of our proposed strategy lends itself to seamless implementation in high-frequency PMSM control. The effectiveness of the proposed strategy is demonstrated in the simulations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Estimation for Environmental Monitoring Using an Autonomous Underwater Vehicle

Adaptive Estimation for Environmental Monitoring Using an Au...

引用

IEEE Conference on Decision and Control

作者： Ziwen Yang Joana Fonseca Shanying Zhu Cailian Chen Xinping Guan Karl H. Johansson Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Digital Futures

This paper considers the problem of monitoring and adaptively estimating an environmental field, such as temperature or salinity, using an autonomous underwater vehicle (AUV). The AUV moves in the field and persistently measures environmental scalars and its position in its local coordinate frame. The environmental scalars are approximately linearly distributed over the region of interest, and an adaptive estimator is designed to estimate the gradient. By orthogonal decomposition of the velocity of the AUV, a linear time-varying system is equivalently constructed, and the sufficient conditions on the motion of the AUV are established, under which the global exponential stability of the estimation error system is rigorously proved. Furthermore, an estimate of the exponential convergence rate is given, and a reference trajectory that maximizes the estimate of the convergence rate is obtained for the AUV to track. Numerical examples verify the stability and efficiency of the system.

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：