检索结果-内蒙古大学图书馆

Nonlinear Value Function Approximation Method with Easy Hyperparameter Tuning and Convergence Guarantee

IEEE Access 2025年 13卷 30117-30126页

作者： Watabe, Yuuya Shibuya, Takeshi University of Tsukuba Master's Program in Intelligent and Mechanical Interaction Systems Ibaraki305-8577 Japan University of Tsukuba Institute of Systems and Information Engineering Ibaraki305-8577 Japan

Reinforcement Learning is a branch of machine learning to learn control strategies that achieve a given objective through trial-And-error in the environment. Because this can be applicable even when the state transition function of the control object is unknown or it is difficult to create its model properly, this can reduce the designer's burden. Reinforcement learning repeats evaluating a policy and improving it based on that evaluation. An algorithm called value function approximation is used in this evaluation. Value function approximation is a general term for algorithms of approximating a function called value function, which maps an arbitrary state to how much reward can be obtained in the future when acting according to a policy from that state. Value function approximation should have high approximation accuracy and hyperparameter easy to tune. Although various value function approximation methods have been proposed so far, some of them does not have convergent guarantee and the others' hyperparameter tuning is difficult. The purpose of this paper is to propose a value function approximation method that have convergence guarantee even with nonlinear function approximator and whose hyperparameter tuning is easy and to verify its performance through numerical experiments. To this end, we focused on GTD2 method, which is one of the value function approximation methods that has convergence guarantee even with a nonlinear function approximator. GTD2 method has the drawback that its hyperparameter is difficult to tune appropriately so that the approximation does not diverge during learning. Therefore, we firstly clarified the cause of the divergence of GTD2 method. Secondly, based on this cause, we proposed Normalized and Regularized GTD2 (NRGTD2) method, that incorporates a method for suppressing divergence into GTD2 method. Finally, through numerical experiments, it was clarified that the proposed method suppresses the divergence and can achieve better approxim

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Throughput and Quality Optimized Down-Selection of Overlay Measurement Markers for Robust Control of the Maximum Overlay Error in a Pattern Layer in Photolithography Processes

引用

IEEE Transactions on Semiconductor Manufacturing 2025年第2期38卷 251-262页

作者： Graff, Noah Djurdjanovic, Dragan The University of Texas at Austin Graduate Program in Dynamic Systems & Controls Walker Department of Mechanical Engineering AustinTX78712 United States The University of Texas at Austin Walker Department of Mechanical Engineering AustinTX78712 United States

This paper presents a metaheuristic optimization-based approach for selecting a pre-determined number of measurement markers from the set of available markers that optimizes the performance of the recently introduced robust L∞ norm overlay control algorithm, which robustly minimizes the worst overlay error across a given pattern layer. This optimization is then used in a Design of Experiments (DOE) setting to build a tractable regression model of a customizable objective function encompassing cost effects of quality losses and throughput benefits resulting from the down-selection of markers selected for robust overlay control. Using this model, one can rapidly determine the optimal proportion of markers for any set of cost parameters, and the optimal subset forming this proportion of available markers can be down-selected to maximize performance of the resulting robust overlay controller. Overlay data and models from a semiconductor manufacturing fab were used to evaluate the newly proposed inspection and control strategy. Results clearly indicate that the novel strategic down-selection of measurement markers coupled with robust overlay control could lead to vastly improved throughputs without decreasing quality relative to what can be achieved using traditional Run-to-Run (R2R) control. Feasibility of the novel DOE-based optimization was demonstrated for two scenarios of cost-effect parameters. © 1988-2012 IEEE.

关键词： Throughput

来源：评论

学校读者我要写书评

暂无评论

The Centrifugal Nuclear Thermal Rocket: Foundations, Challenges, and Progress

The Centrifugal Nuclear Thermal Rocket: Foundations, Challen...

引用

AIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Thomas, Dale Houts, Michael Wang, Dean Hollingsworth, Keith Frederick, Robert Cassibry, Jason Department of Industrial & Systems Engineering and Engineering Management The University of Alabama in Huntsville HuntsvilleAL35899 United States Space Nuclear Propulsion Program Office NASA Marshall Space Flight Center HuntsvilleAL35812 United States Department of Mechanical & Aerospace Engineering The Ohio State University ColumbusOH43210 United States Department of Mechanical & Aerospace Engineering and Interim Dean of the Honors College The University of Alabama in Huntsville HuntsvilleAL35899 United States Department of Mechanical & Aerospace Engineering Propulsion Research Center The University of Alabama in Huntsville HuntsvilleAL35899 United States Department of Mechanical & Aerospace Engineering The University of Alabama in Huntsville HuntsvilleAL35899 United States

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

The Centrifugal Nuclear Thermal Rocket (CNTR) is a Nuclear Thermal Propulsion (NTP) concept designed to heat propellant directly by the reactor fuel. The primary difference between the CNTR concept and traditional NTP systems is that rather than using traditional solid fuel elements, the CNTR uses liquid fuel with the liquid contained in rotating cylinders by centrifugal force. If the concept can be successfully realized, the CNTR would have a high specific impulse (up to 1800 s) at high thrust, which may enable (i) viable near-term human Mars exploration by reducing round-trip times to 420 days and (ii) direct injection orbits for scientific rendezvous missions to the Solar System outer planets and Kuiper Belt objects. Research is presently underway to determine resolutions for the significant engineering challenges that the CNTR concept presents. These challenges, the study plans to address them, and progress have been described previously;this paper provides an update on progress to date for the overall research effort, including strategies and key results on revision of a reference configuration, definition of key parameters which allows integration of the results of various analyses, and reviews strategies to mitigate the problem of Uranium vapor saturating the propellant exhaust and significantly impacting the CNTR’s specific impulse. Analyses and experiments, both underway and planned, to update estimates of engine key performance parameters including specific impulse, thrust and thrust to weight ratio along with the identification of selected design margins within the engine itself are described – all toward the goal of enabling plans for a laboratory demonstration of a single Centrifugal Fuel Element. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Rockets

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Cuffless Blood Pressure Estimation Accuracy at Each Heartbeat During Exercise 6th

Evaluation of Cuffless Blood Pressure Estimation Accuracy a...

引用

6th International Conference on Biomedical and Health Informatics, ICBHI 2024

作者： Ono, Kouki Maeda, Yuka Yoshimura, Takumi Huang, Ming Tamura, Toshiyo Master’s Program in Intelligent and Mechanical Interaction Systems University of Tsukuba Tsukuba305-8577 Japan Institute of Systems and Information Engineering University of Tsukuba Tsukuba305-8577 Japan Medical and Welfare Engineering Tokyo Metropolitan College of Industrial Technology Tokyo116-8523 Japan School of Data Science Nagoya City University Nagoya467-8501 Japan Future Robotics Organization Waseda University Tokyo169-8050 Japan

ISBN: (纸本)9783031863226

Continuous blood pressure monitoring is crucial because of its dynamic nature, influenced by factors such as physical activity and mental stress. Although cuffless blood pressure estimation is a promising technique for continuous monitoring, its accuracy during drastic fluctuations, especially during exercise, remains insufficiently validated. In this study, we evaluated a simple Pulse Arrival Time based blood pressure estimation method and several improved methods for sharp fluctuations induced by exercise. Sixteen subjects in the experiment, with data from 13 valid for analysis. The proposed method achieved an average correlation of 0.527 in systolic blood pressure, suggesting that cuffless blood pressure estimation could be applied to estimate continuous blood pressure variability during exercise. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Blood pressure

来源：评论

学校读者我要写书评

暂无评论

Extension-type flexible pneumatic actuator with a large extension force using a cross-link mechanism based on pantographs

引用

Sensors and Actuators A: Physical 2025年 390卷

作者： Shimooka, So Tadachi, Kazuma Kamegawa, Tetsushi Faculty of Environmental Life Natural Science and Technology Okayama University 3-1-1 Tsushima-naka Kita-ku Okayama Japan Mechanical and Systems Engineering Program School of Engineering Okayama University 3-1-1 Tsushima-naka Kita-ku Okayama Japan

In this study, we propose an extension-type flexible pneumatic actuator (EFPA) with a high extension force and no buckling. In a previous study, soft actuators that extended in the axial direction by applying a supply pressure were unable to generate the extension's pushing force because the actuators buckled owing to their high flexibility. To generate a pushing force, the circumferential stiffness of an extension-type flexible soft actuator must be reinforced. Therefore, a cross-linked EFPA (CL-EFPA) was developed, inspired by a pantograph that restrains the EFPA three-dimensionally using the proposed link mechanism. The proposed CL-EFPA consists of three EFPAs and a cross-linking mechanism for integrating each EFPA circumference. The pushing force of the CL-EFPA is approximately 3.0 times compared with that generated by the previous EFPA with plates to restrain its plane. To perform various bending motions, attitude control was performed using an analytical model and a system that included valves, sensors, and controllers. © 2025 The Authors

关键词： Buckling

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Framework for Neonatal Asphyxia Detection through Video Analysis

引用

IEEE Access 2025年 13卷 74689-74704页

作者： Kurnianingsih Nobukawa, Sou Widyawati, Melyana Nurul Pramana, Cipta Aji, Nurseno Bayu Thohari, Afandi Nur Aziz Hendrawati, Dwiana Sato-Shimokawara, Eri Kubota, Naoyuki Department of Electrical Engineering Politeknik Negeri Semarang H. Soedarto Tembalang Central Java Semarang50275 Indonesia Department of Computer Science Chiba Institute of Technology 2-17-1 Tsudanuma Chiba Narashino275-0016 Japan Department of Postgraduate Program Poltekkes Kemenkes Semarang Jl. Tirto Agung Pedalangan Kecamatan Banyumanik Central Java Semarang50268 Indonesia Department of Obstetrics and Gynecology KRMT Wongsonegoro Hospital Jl. Tembalang Central Java Semarang50272 Indonesia Department of Mechanical Engineering Politeknik Negeri Semarang H. Soedarto Tembalang Central Java Semarang50275 Indonesia Graduate School of Systems Design Tokyo Metropolitan University 6-6 Asahigaoka Hino Tokyo191-0065 Japan

Identifying asphyxia using computer vision in real-world settings poses challenges due to varying video quality, diverse lighting conditions, and subtle color changes in the newborn's skin. This study presents an end-to-end framework for automated neonatal asphyxia detection using time series video analysis and makes three key contributions. First, the proposed framework integrates YOLOv8-based instance segmentation with advanced feature extraction across multiple color spaces and texture analysis to detect neonatal asphyxia through the multi-modal analysis of skin features in video streams. Second, we introduce a new quality-aware temporal analysis framework that includes adaptive quality assessment for evaluating frames in real time, multi-stage feature stability tracking across temporal windows, hysteresis-based decision logic for ensuring temporal consistency, and LightGBM classification with comprehensive feature engineering to assess severity. Third, we provide a curated time series video dataset of 12,973 frames from 45 neonates, of which some were healthy, and some had asphyxia of varying severity. The findings show that the YOLOv8-based instance segmentation achieved a mean average precision (mAP@0.5) of 0.925 for accurate skin region isolation, and the LightGBM classifier outperformed traditional models with an accuracy of 0.998 and an F1-score of 0.998. The system maintains real-time processing at 30 FPS for normal and mild asphyxia cases with a minor reduction to 20 FPS in more challenging scenarios and exhibits robust temporal stability across severity levels, with consistency scores above 0.90. This framework has the potential to enhance neonatal care through continuous monitoring and timely intervention. © 2025 Institute of Electrical and Electronics Engineers Inc.. 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

Following marginal stability manifolds in quasilinear dynamical reductions of multiscale flows in two space dimensions

引用

Physical Review E 2025年第2期111卷 025105-025105页

作者： Alessia Ferraro Gregory P. Chini T. M. Schneider Emergent Complexity in Physical Systems Laboratory (ECPS) École Polytechnique Fédérale de Lausanne CH-1015 Lausanne Switzerland Nordita Royal Institute of Technology and Stockholm University Stockholm 106 91 Sweden Department of Mechanical Engineering and Program in Integrated Applied Mathematics University of New Hampshire Durham New Hampshire 03824 USA

We derive a two-dimensional (2D) extension of a recently developed formalism for slow-fast quasilinear (QL) systems subject to fast instabilities. The emergent dynamics of these systems is characterized by a slow evolution of (suitably defined) mean fields coupled to marginally stable, fast fluctuation fields. By exploiting this scale separation, an efficient hybrid fast-eigenvalue/slow-initial-value solution algorithm can be developed in which the amplitude of the fast fluctuations is slaved to the slowly evolving mean fields to ensure marginal stability—and temporal scale separation—is maintained. For 2D systems, the fluctuation eigenfunctions are labeled by their Fourier wave numbers characterizing spatial variability in that extended spatial direction, and the marginal mode(s) must coincide with the fastest-growing mode(s) over all admissible Fourier wave numbers. Here we derive an ordinary differential equation governing the slow evolution of the wave number of the fastest-growing fluctuation mode that simultaneously must be slaved to the mean dynamics to ensure the mode has zero growth rate. We illustrate the procedure in the context of a 2D model partial differential equation that shares certain attributes with the equations governing strongly stratified shear flows and other strongly constrained forms of geophysical turbulence in extreme parameter regimes. The slaved evolution follows one or more marginal stability manifolds, which constitute select state-space structures that are not invariant under the full flow dynamics yet capture quasicoherent structures in physical space in a manner analogous to invariant solutions identified in, e.g., transitionally turbulent shear flows. Accordingly, we propose that marginal stability manifolds are central organizing structures in a dynamical systems description of certain classes of multiscale flows in which scale separation justifies a QL approximation of the dynamics.

关键词： Shear flow

来源：评论

学校读者我要写书评

暂无评论

Correction: Materials laboratories of the future for alloys, amorphous, and composite materials (MRS Bulletin, (2025), 50, 2, (190-207), 10.1557/s43577-024-00846-y)

引用

MRS Bulletin 2025年 1-2页

作者： Banerjee, Sarbajit Meng, Y. Shirley Minor, Andrew M. Zhang, Minghao Zaluzec, Nestor J. Chan, Maria K.Y. Seidler, Gerald McComb, David W. Agar, Joshua Mukherjee, Partha P. Melot, Brent Chapman, Karena Guiton, Beth S. Klie, Robert F. McCue, Ian D. Voyles, Paul M. Robertson, Ian Li, Ling Chi, Miaofang Destino, Joel F. Devaraj, Arun Marquis, Emmanuelle A. Segre, Carlo U. Liu, Huinan H. Yang, Judith C. Momeni, Kasra Misra, Amit Abdolrahim, Niaz Medvedeva, Julia E. Cai, Wenjun Sehirlioglu, Alp Dizbay-Onat, Melike Mehta, Apurva Graham-Brady, Lori Maruyama, Benji Rajan, Krishna Warner, Jamie H. Taheri, Mitra L. Kalinin, Sergei V. Reeja-Jayan, B. Schwarz, Udo D. Simon, Sindee L. Brown, Craig M. Department of Chemistry and Department of Materials Science & Engineering Texas A & M University College Station United States Pritzker School of Molecular Engineering The University of Chicago Chicago United States Department of Materials Science & Engineering University of California Berkeley Berkeley United States National Center for Electron Microscopy Molecular Foundry Lawrence Berkeley National Laboratory Berkeley United States Center for Nanoscale Materials Argonne National Laboratory Lemont United States Department of Physics University of Washington Seattle United States Department of Materials Science & Engineering The Ohio State University Columbus United States Department of Mechanical Engineering and Mechanics Drexel University Philadelphia United States School of Mechanical Engineering Purdue University West Lafayette United States Department of Chemistry University of Southern California Los Angeles United States Department of Chemistry Stony Brook University The State University of New York Stony Brook United States Department of Chemistry University of Kentucky Lexington United States Department of Physics University of Illinois at Chicago Chicago United States Department of Materials Science & Engineering Northwestern University Evanston Bangladesh Department of Materials Science & Engineering University of Wisconsin–Madison Madison United States Department of Materials Science and Engineering University of Pennsylvania Philadelphia United States Department of Mechanical Engineering and Materials Science Duke University Durham United States Department of Chemistry Creighton University Omaha United States Physical and Computational Sciences Directorate Pacific Northwest National Laboratory Richland United States Department of Materials Science & Engineering University of Michigan–Ann Arbor Ann Arbor United States Department of Physics Illinois Institute of Technology Chicago United States Department of Bioengineering and the Mater

This article was updated to correct Minghao Zhang’s affiliation from "Pritzker School of Molecular engineering, The University of Chicago, Chicago, USA" to "Pritzker School of Molecular engineering, The University of Chicago, Chicago, USA;Argonne National Laboratory, Lemont, USA." Argonne National Laboratory was left off the original publication. © The Author(s) 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Heterogeneity of the Dominant Causes of Performance Loss in End-of-Life Cathodes and Their Consequences for Direct Recycling

引用

Advanced Energy Materials 2025年第0期

作者： Popeil, Melissa Usseglio-Viretta, Francois L.E. Pu, Xiaofei Gasper, Paul Dutta, Nikita Wang, Evelyna Allen, Eva Mangum, John S. Sunderlin, Nathaniel Fink, Kae Allen, Jeffery M. Weddle, Peter J. DeCaluwe, Steven C. Finegan, Donal P. Mines/NREL Advanced Energy Systems Graduate Program Colorado School of Mines GoldenCO80401 United States National Renewable Energy Laboratory GoldenCO80401 United States Argonne National Laboratory LemontIL60439 United States Department of Mechanical Engineering Colorado School of Mines GoldenCO80401 United States

Recycling Li-ion batteries from electric vehicles is critical for reducing costs and supporting the development of a domestic battery supply chain. Direct recycling of cathodes, like LiNixMnyCozO2 (NMC), is attractive due to its low cost, energy use, and emissions compared to traditional recycling techniques. However, a comprehensive understanding of the active material properties at end-of-life is needed to guide direct recycling processes and the performance-dependent reuse applications. Here, NMC material from an end-of-life commercial pouch cell is characterized and bench-marked against pristine non-cycled counterparts with respect to capacity, impedance, crystallography, morphology, and microstructure to identify major degradation modes and understand variability in the end-of-life material. The spatial heterogeneity of each property throughout the cell is also quantified. While the degraded material demonstrated similar capacity as the pristine, its impedance and rate capability are severely diminished. Furthermore, samples from the periphery of the electrode layers showed more severe performance loss compared to samples extracted from central regions. The dominant culprit of performance loss is the material microstructure, where the magnitude of particle cracking showed the strongest correlation to the impedance components that are most unfavorably impacted. This work suggests severe cracks in cathode active materials are the primary challenge that direct recycling methods must overcome. © 2025 The Author(s). Advanced Energy Materials published by Wiley-VCH GmbH.

关键词： battery NMC recycling

来源：评论

学校读者我要写书评

暂无评论

Green synthesis of Ni, Co-based oxides for water oxidation applications

引用

Materials Science in Semiconductor Processing 2025年 195卷

作者： Andrade, Verônica de M. Lopes, Sávio M. Raimundo, Rafael A. Alves, Ricardo F. Araújo, Allan J.M. Vieira, Pamala S. da Silva, Fausthon F. Morales, Marco A. Macedo, Daniel A. Fagg, Duncan P. Souza, Glageane da S. Academic Unit of Biology and Chemistry Federal University of Campina Grande PB Cuité58175-000 Brazil Materials Science and Engineering Graduate Program UFPB João Pessoa58051-900 Brazil TEMA - Centre for Mechanical Technology and Automation Department of Mechanical Engineering University of Aveiro Aveiro3810-193 Portugal Federal University of Paraíba Department of Mechanical Engineering PB João Pessoa58051-900 Brazil LASI - Intelligent Systems Associate Laboratory Guimarães4800-058 Portugal Materials Science and Engineering Postgraduate Program Federal University of Rio Grande do Norte Natal59078-970 Brazil Department of Chemistry Federal University of Paraíba Paraíba João Pessoa58051-900 Brazil Department of Theoretical and Experimental Physics Federal University of Rio Grande do Norte RN Natal59078-970 Brazil

This work reports new Ni,Co-oxides based nanoparticles as electrocatalysts for the Oxygen Evolution Reaction (OER), considering the growing demand for renewable energy, as well as the search for sustainable alternatives in the production of nanoparticle materials. Ni,Co-based nanoparticles were obtained via proteic sol-gel method, with Agar-Agar from red seaweed (Rhodophyta) as polymerizing agent, and characterized by using X-ray diffraction techniques (including Rietveld refinement), Field emission scanning electron microscopy and vibrational spectroscopy (infrared and Raman). All structural analyses indicated that the crystalline phases NiO, Ni0.9Co0.1O and (Ni,Co)O-Co3O4 were obtained. Electrochemical techniques were applied to investigate the OER electrocatalytic performance, with the (Ni,Co)O-Co3O4 electrocatalyst showing the lowest overpotential (356 mV vs. RHE at J = 10 mA cm−2) and a Turnover Frequency (TOF) of 9.97 × 10−3 mol O2 s−1 at just 500 mV vs. RHE. Furthermore, all prepared electrocatalysts showed excellent chemical stability up to 15 h, as indicated in chronopotentiometry data. © 2025 Elsevier Ltd

关键词： Rietveld refinement

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：