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

Texture development and surface reconstruction of BiVO_(4)photoanode via one-pot hydrothermal reaction for enhanced photoelectrochemical water splitting

引用

Journal of Advanced Ceramics 2025年第3期14卷 133-141页

作者： Sung Won Hwang Yoo Jae Jeong Runfa Tan Indhujasri Saravanan Hyun Soo Han Dong Hoe Kim In Sun Cho Department of Energy Systems Research Ajou UniversitySuwon 16499Republic of Korea Department of Material Science&Engineering Ajou UniversitySuwon 16499Republic of Korea Department of Mechanical Engineering Stanford UniversityStanford 94305USA Department of Material Science&Engineering Korea UniversitySeoul 02841Republic of Korea Materials Science and Engineering Program University of Colorado BoulderBoulder 80303USA

The simultaneous optimization of the bulk and surface characteristics of photoelectrodes is essential to maximize their photoelectrochemical(PEC)*** report a novel one-pot hydrothermal synthesis of textured and surface-reconstructed BiVO_(4)photoanodes(ts-BVO),achieving significant improvements in PEC water *** controlling precursor molarity and ethylene glycol(EG)addition,we developed a stepwise dual reaction(SDR)mechanism,which enables simultaneous bulk texture development and surface *** optimized CoBi/ts-BVO photoanode exhibited a photocurrent density of 4.3 mA∙cm^(−2)at 1.23 V *** hydrogen electrode(RHE)with a high Faradaic efficiency of 98%under one sun *** with nontextured BiVO_(4),the charge transport efficiency increased from 8%to 70%,whereas the surface charge transfer efficiency improved from 9%to 85%.These results underscore the critical role of both bulk and surface engineering in enhancing PEC *** findings offer a streamlined approach for improving the intrinsic properties of photoanodes in solar water splitting.

关键词： BiVO_(4) hydrothermal texture surface reconstruction ethylene glycol(EG) photoelectrochemical water splitting

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional surface topography analysis of die-sinking electrical discharge machined eco-friendly beryllium-free copper alloys

引用

The International Journal of Advanced Manufacturing Technology 2025年 1-43页

作者： Vijayan, Vipin Saju, Kaiprappady Kunchu Sundaresan, Jithin Division of Mechanical Engineering School of Engineering Cochin University of Science and Technology Kochi India Department of Mechanical Engineering Muthoot Institute of Technology and Science Ernakulam India Business Information Systems Program Information Systems Department School of Computing and Creative Arts Bina Nusantara University Jakarta Indonesia

Beryllium-copper alloys, the most widely used copper alloys, are utilised extensively in diverse sectors, including the electrical, electronics, instrumentation, metallurgy, aerospace, automotive, petrochemical, machinery manufacturing, and die and mould-making industries. The main drawback of these alloys is that they produce the toxic component, beryllium oxide, which can lead to a chronic lung disease known as berylliosis. Beryllium-free copper alloys, such as copper-nickel-silicon-chromium, are eco-friendly, less costly, and possess properties similar to those of beryllium-copper alloys. Hence, they are now replacing beryllium-copper alloys in the applications mentioned earlier. Due to their high strength and hardness, these alloys are often fabricated into components using unconventional machining techniques, such as electrical discharge machining. Electrical discharge machining is particularly advantageous in industrial applications where precisely controlled random surface textures on these alloys are required. However, despite the industrial significance, research on the electrical discharge machining process of copper-nickel-silicon-chromium alloys is scarce. Therefore, the current work aims to address this research gap by conducting an experimental investigation of the random surfaces generated on copper-nickel-silicon-chromium alloy components after the die-sinking electrical discharge machining process through a comprehensive three-dimensional surface topography analysis. Three-dimensional surface topography parameters overcome the drawbacks of two-dimensional roughness parameters by considering the majority of surface points. This work investigates the effects of input factors, including electrode material, dielectric fluid material, flushing condition, and current on nearly all relevant areal texture (3D) parameters. ANOVA is performed to study the level of significance of each input parameter. The regression analyses reveal that current is the most si

关键词：

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

Improving LED-Based Photoacoustic Image Quality Using an Optimized Deconvolution Technique

Improving LED-Based Photoacoustic Image Quality Using an Opt...

引用

Photons Plus Ultrasound: Imaging and Sensing 2025

作者： Ogawa, Ryuhei Sato, Naoto Saito, Atsushi Singh, Mithun Kuniyil Ajith Kawamoto, Hiroaki Sankai, Yoshiyuki Master’s Program in Intelligent and Mechanical Interaction Systems University of Tsukuba Tsukuba Japan Research & Development Division Cyberdyne Inc. Tsukuba Japan Research & Business Development Division Cyberdyne Inc. Rotterdam Netherlands Institute of Systems and Information Engineering University of Tsukuba Tsukuba Japan

ISBN: (纸本)9781510683860

LED-based photoacoustic imaging (PAI) with linear array ultrasound probes has gained attention due to its cost-effectiveness, safety, and potential for portable applications. However, its low signal-to-noise ratio (SNR) and limited visibility of blood vessel lumens remain challenges. To address these issues, we propose an innovative deconvolution approach that leverages the differential of the LED light pulse to enhance photoacoustic image quality. Our optimized reconstruction algorithm improves blood vessel visualization by applying deconvolution of the PA signals with the differential of the LED pulse, leading to improved lumen visibility and enhanced imaging of peripheral blood vessels in both 2D and potentially 3D. Our method precisely measures the LED pulse profile using the LED arrays integrated into our AcousticX system. The second differential of this pulse is then utilized as the point spread function (PSF) in the deconvolution process. This technique effectively enhances PA signals by emphasizing the leading and trailing edges of the pulse, thereby improving blood vessel visibility and overall image quality. To validate our approach, we conducted experiments using tissue-mimicking phantoms and human volunteers with the AcousticX system. The algorithm was tested offline in MATLAB and in real-time on the AcousticX platform. Results demonstrate substantial artifact suppression, improved SNR, and enhanced image contrast, ultimately enabling clearer visualization of the blood vessels. This advancement improves the competitiveness of LED-based PAI systems compared to laser-based alternatives and broadens their potential for clinical applications, accelerating their translation into medical practice. © 2025 SPIE.

关键词： Ultrasonic imaging

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

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：