检索结果-内蒙古大学图书馆

Distribution and ecological risks of microplastics in a tropical tourism island area in Hainan,China

学校读者我要写书评

暂无评论

Journal of Oceanology and Limnology 2025年第2期43卷 433-445页

作者： Weijie BIAN Rui SUN Yurui LI Shuguo LÜ Dongwei YANG Hongbo LI Yingxu ZENG Min LIU Yazhou Bay Innovation Institute/Key Laboratory for Coastal Marine Eco-environment Process and Carbon Sink of Hainan Province/Modern Marine Ranching Engineering Research Center of Hainan/College of Ecology and Environment Hainan Tropical Ocean UniversitySanya 572022China Hainan Academy of Environmental Science Haikou 571126China Key Laboratory of Island Tourism Resource Data Mining and Monitoring Ministry of Culture and TourismHainan Tropical Ocean UniversitySanya 572022China National Marine Environmental Monitoring Center Dalian 116023China

Microplastics are a widely distributed pollutant that threatens the growth and health of marine *** to the mainland,island ecosystems with unique characteristics are fragile and sensitive to natural and human *** investigated the characteristics and ecological risks of microplastics in the soils of Wuzhizhou Island,Hainan,China,and its surrounding nearshore sediments affected by human *** show that the microplastic abundance in soil was 1116.67 items/kg;the particles were fragmented in size of less than 2 mm,the main polymer types were polypropylene(PP),polyethylene(PE),and polybutylene(PB),in transparent,gray,green,or *** microplastic abundances in nearshore sediments of Wuzhizhou Island and the surrounding Haitang Bay were 274.67 and 755.17 items/kg,respectively;the particles were mainly fibrous,less than 1 mm in size,the main polymer types were rayon and polyethylene terephthalate(PET),mostly *** abundance of microplastics showed a decreasing trend from shore to *** in the supratidal and intertidal zones differed in mainly the abundance and *** microplastics in land soil were from tourism activities and infrastructure while the those in nearshore sediments came from not only tourism but also domestic sewage and fishing *** ecological risk of microplastics in the terrestrial soils of Wuzhizhou Island was higher than that in its surrounding nearshore *** findings help to gain a deeper understanding of microplastic pollution in the island subjected to intensive human activities,and provide a scientific basis for subsequent in-situ toxicology research on microplastics and plastic pollution control.

关键词： microplastic occurrence characteristic ecological risk tropical tourism island

CD-SEM Anomaly Detection Through Machine Learning and Generative AI

学校读者我要写书评

暂无评论

CD-SEM Anomaly Detection Through Machine Learning and Genera...

IEEE/SEMI Conference and Workshop on Advanced Semiconductor Manufacturing

作者： Susan Sun Xiaoyan Zhuo Phong Nguyen Todd Smith Jinhua Ding Troy Stansell Amit Srivastava Yousef Hanif Data Science Micron Technology Inc. Manassas VA USA Lithography Process Eng Micron Technology Inc. Manassas VA USA Data Science Micron Technology Inc. Singapore Product Quality Assurance Micron Technology Inc. Manassas VA USA

ISBN: (数字)9798331531850

ISBN: (纸本)9798331531867

In a complex semiconductor manufacturing environment, critical dimension scanning electron microscope (CD-SEM) images are captured at metrology step to monitor structural measurements and detect anomaly to meet the stringent process control requirements. This paper focuses on advanced CD-SEM image processing and anomaly detection using machine learning and generative AI models, which include computer vision (CV) image processing, Residual Neural Network (ResNet) deep learning and Generative Adversarial Network (GAN) model for various use cases. The applications of these models during in-line monitoring are crucial to identify potential process issues for yield and quality improvement.

关键词： Deep learning Semiconductor device measurement Generative AI Image processing Computational modeling Semiconductor device manufacture Generative adversarial networks Servers Anomaly detection Monitoring

Multi-agent Scheduling for Shared Manufacturing Systems

学校读者我要写书评

暂无评论

Procedia Computer science 2025年 253卷 727-736页

作者： Ege Duran Cemalettin Ozturk Barry O’Sullivan SFI Centre for Research Training in AI School of Computer Science & IT University College Cork Ireland Department of Process Energy & Transport Engineering Munster Technological University Cork Ireland Insight SFI Research Centre for Data Analytics School of Computer Science & IT University College Cork Ireland

Advances in digitization and resource-sharing business models have created new opportunities for manufacturing companies, enhancing competitiveness and resilience. However, these benefits bring computational challenges in efficiently planning and scheduling shared resources. Therefore, there is a need for scalable and quick solutions for practical applications. Shared manufacturing systems share characteristics with parallel machine scheduling, allowing for the application of advancements from this domain. This research focuses on Multi-Agent Parallel Machine Scheduling (MAPMS) in shared manufacturing, specifically addressing scenarios involving two parallel machines and distinct agents managing exclusive, set of non-overlapping orders. The study introduces a novel multi-objective mixed integer programming (MIP) model for order scheduling across multiple facilities, accounting for sequence-dependent setup times between orders. It also proposes a new heuristic method designed for industrial use. Benchmark instances demonstrate the practicality of both the MIP model and heuristic, contributing valuable insights into MAPMS challenges in shared manufacturing environments.

关键词： Multiagent systems Scheduling planning parallel machine

An Enhanced Multi-Scale Collaborative Learning Network for Medical Image Segmentation in Internet of Medical Things

学校读者我要写书评

暂无评论

IEEE Internet of Things Journal 2025年

作者： Yang, Aimin Li, Jiahao Bai, Yunjie Li, Jie Yang, Xingwang North China University of Science and Technology College of Science Hebei Tangshan063210 China North China University of Science and Technology Hebei Key Laboratory of Data Science and Application Hebei Tangshan063210 China North China University of Science and Technology Hebei Engineering Research Center of Iron Ore Optimization and Iron Pre-Process Intelligence Tangshan063210 China

Multi-organ segmentation in the abdomen is a key area in medical image segmentation and is essential for accurate diagnosis and treatment of diseases. The diversity of abdominal organs, differences in size, and ambiguous boundaries pose significant challenges to segmentation tasks, making it difficult for existing models to meet clinical demands in complex scenarios. To address this, this paper proposes a Multi-Scale Collaborative Learning Network (MSCL-Net) in conjunction with a medical Internet of Things (IoMT) platform, aiming to enhance the accuracy of abdominal organ segmentation. The introduction of IoMT technology dramatically expands the channels for obtaining medical image data. By collecting massive amounts of data in real-time from various scenarios, such as outpatient clinics and hospitals, doctors can quickly use the segmentation model to obtain preliminary segmentation results of CT images, which specialists can rapidly correct. This workflow improves clinical work efficiency and provides a large volume of highquality data for training the model, further enhancing its accuracy. Regarding model design, the Feature Space Module is used for global feature extraction, the Feature Extraction Module captures local semantic information at different scales, and the Feature Aggregation Module performs deep integration of local and global information. A considerable number of experimental results based on the Synapse dataset demonstrate that MSCL-Net outperforms existing advanced algorithms and achieves 81.71% in the Dice Similarity Coefficient (DSC) and 17.81 in the Hausdorff Distance at 95% (HD95) metrics, demonstrating its outstanding ability in medical image segmentation. © 2014 IEEE.

关键词： Diagnosis

Enhancing Machine Learning Potentials through Transfer Learning across Chemical Elements

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Röcken, Sebastien Zavadlav, Julija Department of Engineering Physics and Computation TUM School of Engineering and Design Technical University of Munich Germany Munich Data Science Institute Munich Institute for Integrated Materials Energy and Process Engineering Technical University of Munich Germany

Machine Learning Potentials (MLPs) can enable simulations of ab initio accuracy at orders of magnitude lower computational cost. However, their effectiveness hinges on the availability of considerable datasets to ensure robust generalization across chemical space and thermodynamic conditions. The generation of such datasets can be labor-intensive, highlighting the need for innovative methods to train MLPs in data-scarce scenarios. Here, we introduce transfer learning of potential energy surfaces between chemically similar elements. Specifically, we leverage the trained MLP for silicon to initialize and expedite the training of an MLP for germanium. Utilizing classical force field and ab initio datasets, we demonstrate that transfer learning surpasses traditional training from scratch in force prediction, leading to more stable simulations and improved temperature transferability. These advantages become even more pronounced as the training dataset size decreases. The out-of-target property analysis shows that transfer learning leads to beneficial but sometimes adversarial effects. Our findings demonstrate that transfer learning across chemical elements is a promising technique for developing accurate and numerically stable MLPs, particularly in a data-scarce regime. Copyright © 2025, The Authors. All rights reserved.

关键词： Potential energy surfaces

LARGE-SCALE THERMO-MECHANICAL SIMULATION OF LASER BEAM WELDING USING HIGH-PERFORMANCE COMPUTING: A QUALITATIVE REPRODUCTION OF EXPERIMENTAL RESULTS

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Bevilacqua, Tommaso Gumenyuk, Andrey Habibi, Niloufar Hartwig, Philipp Klawonn, Axel Lanser, Martin Rethmeier, Michael Scheunemann, Lisa Schröder, Jörg Department of Mathematics and Computer Science University of Cologne Germany Berlin Germany Institute of Mechanics Department of Civil Engineering University Duisburg-Essen Germany Center for Data and Simulation Science University of Cologne Germany Department of Mechanical and Process Engineering RPTU Kaiserslautern-Landau Germany

Laser beam welding is a non-contact joining technique that has gained significant importance in the course of the increasing degree of automation in industrial manufacturing. This process has established itself as a suitable joining tool for metallic materials due to its non-contact processing, short cycle times, and small heat-affected zones. One potential problem, however, is the formation of solidification cracks, which particularly affects alloys with a pronounced melting range. Since solidification cracking is influenced by both temperature and strain rate, precise measurement technologies are of crucial importance. For this purpose, as an experimental setup, a Controlled Tensile Weldability (CTW) test combined with a local deformation measurement technique is used. The aim of the present work is the development of computational methods and software tools to numerically simulate the CTW. The numerical results are compared with those obtained from the experimental CTW. In this study, an austenitic stainless steel sheet is selected. A thermo-elastoplastic material behavior with temperature-dependent material parameters is assumed. The time-dependent problem is first discretized in time and then the resulting nonlinear problem is linearized with Newton’s method. For the discretization in space, finite elements are used. In order to obtain a sufficiently accurate solution, a large number of finite elements has to be used. In each Newton step, this yields a large linear system of equations that has to be solved. Therefore, a highly parallel scalable solver framework, based on the software library PETSc, was used to solve this computationally challenging problem on a high-performance computing architecture. Finally, the experimental results and the numerical simulations are compared, showing to be qualitatively in good *** Codes 65M55, 65M60, 74F05 Copyright © 2025, The Authors. All rights reserved.

关键词： Laser beam welding

Safety Control of Switched Systems via Multiple Barrier Functions

学校读者我要写书评

暂无评论

IEEE Transactions on Automatic Control 2025年

作者： Long, Lijun Huang, Chunxiao Sun, Zhendong Northeastern University College of Information Science and Engineering Shenyang110819 China Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110819 China Ministry of Education Key Laboratory of Data Analytics and Optimization for Smart Industry Northeastern University China

This paper is concerned with the problem of safety control for switched systems, where different safe sets are allowed for different subsystems and safety is not necessarily possessed for subsystems. A necessary and sufficient condition is presented for safety of switched systems by exploiting a multiple barrier functions (MBFs) method. To reveal the relationship about safety between subsystems and switched systems, an extended Nagumo's Theorem in the switched systems framework is derived. Also, several switched control design conditions are respectively provided to ensure safety of switched systems. Based on the union of MBFs and multiple Lyapunov functions (MLFs), a novel safety-critical control framework is established to simultaneously ensure safety and stability of switched systems. Also, an auxiliary cost function is introduced to transform the safety-critical optimal control (SCOC) problem of switched systems into the one of non-switched systems. Finally, three examples are illustrated to demonstrate the effectiveness of the proposed methods. © 1963-2012 IEEE.

关键词： Lyapunov functions

Releasing Differentially Private Event Logs Using Generative Models

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wangelik, Frederik Pourbafrani, Mahsa Rafiei, Majid van der Aalst, Wil M.P. Chair of Process and Data Science RWTH Aachen University Aachen Germany

In recent years, the industry has been witnessing an extended usage of process mining and automated event data analysis. Consequently, there is a rising significance in addressing privacy apprehensions related to the inclusion of sensitive and private information within event data utilized by process mining algorithms. State-of-the-art research mainly focuses on providing quantifiable privacy guarantees, e.g., via differential privacy, for trace variants that are used by the main process mining techniques, e.g., process discovery. However, privacy preservation techniques designed for the release of trace variants are still insufficient to meet all the demands of industry-scale utilization. Moreover, ensuring privacy guarantees in situations characterized by a high occurrence of infrequent trace variants remains a challenging endeavor. In this paper, we introduce two novel approaches for releasing differentially private trace variants based on trained generative models. With TraVaG, we leverage Generative Adversarial Networks (GANs) to sample from a privatized implicit variant distribution. Our second method employs Denoising Diffusion Probabilistic Models that reconstruct artificial trace variants from noise via trained Markov chains. Both methods offer industry-scale benefits and elevate the degree of privacy assurances, particularly in scenarios featuring a substantial prevalence of infrequent variants. Also, they overcome the shortcomings of conventional privacy preservation techniques, such as bounding the length of variants and introducing fake variants. Experimental results on real-life event data demonstrate that our approaches surpass state-of-the-art techniques in terms of privacy guarantees and utility preservation. © 2025, CC BY.

关键词： Differential privacy

Invariance Pair-Guided Learning: Enhancing Robustness in Neural Networks

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Surner, Martin Khelil, Abdelmajid Bothmann, Ludwig Institute for Data and Process Science Landshut University of Applied Sciences Am Lurzenhof 1 Landshut Bavaria84036 Germany Computer Science Department Landshut University of Applied Sciences Am Lurzenhof 1 Landshut Bavaria84036 Germany Department of Statistics LMU Munich Ludwigstraße 33 Munich80539 Germany Munich Germany

Out-of-distribution generalization of machine learning models remains challenging since the models are inherently bound to the training data distribution. This especially manifests, when the learned models rely on spurious correlations. Most of the existing approaches apply data manipulation, representation learning, or learning strategies to achieve generalizable models. Unfortunately, these approaches usually require multiple training domains, group labels, specialized augmentation, or pre-processing to reach generalizable models. We propose a novel approach that addresses these limitations by providing a technique to guide the neural network through the training phase. We first establish input pairs, representing the spurious attribute and describing the invariance, a characteristic that should not affect the outcome of the model. Based on these pairs, we form a corrective gradient complementing the traditional gradient descent approach. We further make this correction mechanism adaptive based on a predefined invariance condition. Experiments on ColoredMNIST, Waterbird-100, and CelebA datasets demonstrate the effectiveness of our approach and the robustness to group shifts. © 2025, CC BY-SA.

关键词： Contrastive Learning