检索结果-内蒙古大学图书馆

A novel approach to spectral moisture interference correction for nitrogen and soil organic matter inversion in native black soils: Bayesian-optimized dynamic moisture mitigation

引用

Ecological Informatics 2025年 90卷

作者： Jiaze Tang Qisong Wang Dan Liu Junbao Li Ruifeng Zhang Meiyan Zhang Jinwei Sun Electrical Measurement Technology and Intelligent Control Institute School of Instrumentation Science and Engineering Harbin Institute of Technology Harbin 150080 China A Information Countermeasure Technique Institute School of Computer Science and Technology Harbin Institute of Technology Harbin 150080 China

In recent years, portable near-infrared spectrometers have emerged as viable alternatives to conventional chemical methods for measuring total nitrogen (TN) and soil organic matter (SOM). Advances in unmanned aerial vehicle technology have enabled low-altitude aerial surveys, facilitating the quantification of TN and SOM in agricultural soils—an approach beneficial for applications such as fertilizer management. However, most studies rely on laboratory-based analyses using high-precision and nonimaging spectrometers that test dried and processed soil samples. This preference stems from the significant impact of moisture on soil reflectance spectra, particularly in moisture-rich black soils. To address this challenge, this study investigated the in situ quantitative inversion of TN and SOM contents in moist black soil using a high-throughput hyperspectral imaging system. We introduced the Bayesian-optimized dynamic moisture mitigation (BO-DMM) method—an approach that effectively corrected moisture-induced spectral distortions. The BO-DMM method reduced moisture interference, calibrating the spectral angle of moist soil spectra to shrink by 50 % toward that of dry soil spectra. To further assess the effectiveness of the BO-DMM method, we integrated it with different machine learning models to test soil properties and predict the TN and SOM contents. The results indicated that BO-DMM significantly enhanced the prediction accuracy of different soil properties across different models, providing a robust strategy to mitigate environmental interference in soil spectroscopy. This advancement paves the way for additional accurate field-based soil assessments.

关键词： Nitrogen content Soil organic matter Bayesian-optimized dynamic moisture mitigation Hyperspectral imaging Soil moisture Machine learning

来源：评论

学校读者我要写书评

暂无评论

Structural reduction of CRNs with linear sub-CRNs

引用

IFAC-PapersOnLine 2021年第14期54卷 149-154页

作者： Katalin M. Hangos György Lipták Gábor Szederkényi Systems and Control Laboratory Computer and Automation Research Institute P.O. Box 63 H-1518 Budapest Hungary Department of Electrical Engineering and Information Systems University of Pannonia Veszprém Hungary Faculty of Information Technology and Bionics Péter Pázmány Catholic University Budapest Hungary

A novel systems theory-based structural reduction method is proposed in this paper that can be applied to chemical reaction networks (CRNs) including subsystems consisting of linear reactions, i.e. a linear sub-CRN. The reduced model is a delayed CRN with distributed delays having less complexes (monomials) and reactions than the original model. The reduction is based on the fact that the input/output response of a linear sub-CNR can be seen as a time-delayed input to output relationship, therefore linear sub-CNRs can be interpreted as reactions with distributed delay from their input to their output complexes. The practically important example of a kinetic model describing the spread of the COVID-19 epidemic is used as a case study to illustrate the basic concepts and the computation method.

关键词： Delay Model reduction Chemical Reaction Networks COVID

来源：评论

学校读者我要写书评

暂无评论

FIRE: a dataset for feedback integration and refinement evaluation of multimodal models 24

FIRE: a dataset for feedback integration and refinement eval...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Pengxiang Li Zhi Gao Bofei Zhang Tao Yuan Yuwei Wu Mehrtash Harandi Yunde Jia Song-Chun Zhu Qing Li Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology and State Key Laboratory of General Artificial Intelligence BIGAI State Key Laboratory of General Artificial Intelligence BIGAI and State Key Laboratory of General Artificial Intelligence Peking University State Key Laboratory of General Artificial Intelligence BIGAI Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology and Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University Department of Electrical and Computer System Engineering Monash University Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University and Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology State Key Laboratory of General Artificial Intelligence BIGAI and State Key Laboratory of General Artificial Intelligence Peking University and Department of Automation Tsinghua University

ISBN: (纸本)9798331314385

Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction. In this paper, we build FIRE, a feedback-refinement dataset, consisting of 1.1M multi-turn conversations that are derived from 27 source datasets, empowering VLMs to spontaneously refine their responses based on user feedback across diverse tasks. To scale up the data collection, FIRE is collected in two components: FIRE-100K and FIRE-1M, where FIRE-100K is generated by GPT-4V, and FIRE-1M is freely generated via models trained on FIRE-100K. Then, we build FIRE-Bench, a benchmark to comprehensively evaluate the feedback-refining capability of VLMs, which contains 11K feedback-refinement conversations as the test data, two evaluation settings, and a model to provide feedback for VLMs. We develop the FIRE-LLaVA model by fine-tuning LLaVA on FIRE-100K and FIRE-1M, which shows remarkable feedback-refining capability on FIRE-Bench and outperforms untrained VLMs by 50%, making more efficient user-agent interactions and underscoring the significance of the FIRE dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Sliding Mode control Strategies for Positioning Systems: An Experimental Assessment

Event-Triggered Sliding Mode Control Strategies for Position...

引用

International Workshop on Advanced Motion control (AMC)

作者： Andrej Sarjaš Martin Steinberger Dušan Gleich Martin Horn Faculty of Electrical Engineering and Computer Science University of Maribor Maribor Slovenia Graz University of Technology Institute of Automation and Control Graz Austria

ISBN: (数字)9781728131894

ISBN: (纸本)9781728131900

The paper presents experimental assessments of different event-triggered sliding mode control strategies. The main purpose of the event-triggered control approach is to reduce the system utilization and relax the scheduling of the tasks on real-time systems. Event triggering is a real-time implementation technique, where the execution of the controller is not fixed to a preselected sampling time. The stability and performance of the controlled system need to be preserved with regard to the sporadic nature of the controller update. Sliding mode controllers are employed in the context of event-triggering to achieve robustness with respect to matched perturbations. Three different sliding mode event-triggered strategies are evaluated on the real-time positioning system. All the obtained experimental results are compared to a time-triggered version. The results confirm that event-triggering sliding mode control is well suited and reduce the system use drastically.

关键词： Tracking Computational modeling Real-time systems Stability analysis Robustness Task analysis Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

MatchMesh: Knowledge-based 3D Point Cloud Meshing Using Divide-and-conquer Deformation

MatchMesh: Knowledge-based 3D Point Cloud Meshing Using Divi...

引用

2020 IEEE International Conference on Networking, Sensing and control, ICNSC 2020

作者： Tang, Ying Sun, Shengtao Wu, Ben Department of Electrical and Computer Engineering Rowan University GlassboroNJ08028 United States State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Institute of Smart Education Qingdao Academy of Intelligent Industries Qingdao China

ISBN: (纸本)9781728168531

The reconstruction of surface mesh from point cloud is compute-intensive but also very important step in the remanufacturing and personalization industries. With more 3D scanners providing lower cost and higher resolution, further detailed point clouds can be gathered without so much effort as before. In manufacturing, there are databases which contain the origin 3D design models of the products. How to utilize the design model data for swift production of related products remains a problem for remanufacturing and customization. In order to develop a knowledge-based way of handling this problem, editing or deforming an existing mesh to match the target is an effective way of easing the workload. In this paper, we introduce a divide-and -conquer process which segments the depth scan data and then find the best match in the database as its source of deformation. The segmentation is performed on 3D point level using global features extracted by 3D CNN. After that we find best match to our knowledge with the same features to acquire a fast meshing of the target object by deforming the existing parts from the match. The deformation of parts are being done sequentially. For further performance improvement, we present a deformation training method employing transfer learning on segment editing process. © 2020 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Analysis of Electro-mechanical Actuator Transmission Clearance under High-temperature Conditions

Analysis of Electro-mechanical Actuator Transmission Clearan...

引用

International Conference on Fluid Power and Mechatronics (FPM)

作者： Zhicheng Liu Tian Yu Rui Hong Li Liu Hao Su Jionghui Lin Chaofan Jiang Yaoxing Shang School of Automation Science and Electrical Engineering Beihang University Beijing China Technology on Aircraft Control Laboratory Beihang University Beijing China Research Institute for Frontier Science Beihang University Beijing China Tianmushan Laboratory Xixi Octagon City Yuhang District Hangzhou China Chengdu Aircraft Design and Research Institute Chengdu China Ningbo Institute of Technology Beihang University Ningbo China Key Laboratory of Advanced Aircraft Systems (Beihang University) Ministry of Industry and Information Technology

ISBN: (数字)9798350304947

ISBN: (纸本)9798350304954

More Electric Aircraft with electro-mechanical actuator(EMA) or electro-hydrostatic actuator(EHA) is the development trend of new aircraft. In high temperature conditions, the transmission clearance of EMA transmission system may change because of thermal deformation. If the transmission clearance decreases, the EMA may get stuck; If the transmission clearance increases, it will affect the control accuracy of the aircraft control. This paper investigates the transmission clearance of EMA transmission system when subjected to the combined effects of an external high-temperature environment and internal heat sources. To calculate the temperature distribution of EMA transmission system, A heat transfer model of the EMA is established. Based on this temperature distribution, the EMA transmission clearance can be calculated. an EMA dynamic model, involved nonlinear clearance, is established to analysis the effects of the transmission clearance on the actuator's output performance. This research provides a reference for studying the design clearances of EMA under high temperature conditions.

关键词： Deformable models Temperature distribution Analytical models Thermodynamics Gears Deformation Time series analysis

来源：评论

学校读者我要写书评

暂无评论

Retrospective for the Dynamic Sensorium Competition for predicting large-scale mouse primary visual cortex activity from videos 38

Retrospective for the Dynamic Sensorium Competition for pred...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Turishcheva, Polina Fahey, Paul G. Vystrčilová, Michaela Hansel, Laura Froebe, Rachel Ponder, Kayla Qiu, Yongrong Willeke, Konstantin F. Bashiri, Mohammad Baikulov, Ruslan Zhu, Yu Ma, Lei Yu, Shan Huang, Tiejun Li, Bryan M. De Wulf, Wolf Kudryashova, Nina Hennig, Matthias H. Rochefort, Nathalie L. Onken, Arno Wang, Eric Ding, Zhiwei Tolias, Andreas S. Sinz, Fabian H. Ecker, Alexander S. Institute of Computer Science and Campus Institute Data Science University of Göttingen Germany Department of Neuroscience Center for Neuroscience and Artificial Intelligence Baylor College of Medicine HoustonTX United States Department of Ophthalmology Byers Eye Institute Stanford University School of Medicine StanfordCA United States Stanford Bio-X Stanford University StanfordCA United States Wu Tsai Neurosciences Institute Stanford University StanfordCA United States International Max Planck Research School for Intelligent Systems Tübingen Germany Institute for Bioinformatics and Medical Informatics Tübingen University Germany lRomul Russia Institute of Automation Chinese Academy of Sciences China Beijing Academy of Artificial Intelligence China The Alan Turing Institute United Kingdom School of Informatics University of Edinburgh United Kingdom Centre for Discovery Brain Sciences University of Edinburgh United Kingdom Simons Initiative for the Developing Brain University of Edinburgh United Kingdom Department of Electrical Engineering Stanford University StanfordCA United States Max Planck Institute for Dynamics and Self-Organization Göttingen Germany

Understanding how biological visual systems process information is challenging because of the nonlinear relationship between visual input and neuronal responses. Artificial neural networks allow computational neuroscientists to create predictive models that connect biological and machine vision. Machine learning has benefited tremendously from benchmarks that compare different models on the same task under standardized conditions. However, there was no standardized benchmark to identify state-of-the-art dynamic models of the mouse visual system. To address this gap, we established the SENSORIUM 2023 Benchmark Competition with dynamic input, featuring a new large-scale dataset from the primary visual cortex of ten mice. This dataset includes responses from 78,853 neurons to 2 hours of dynamic stimuli per neuron, together with behavioral measurements such as running speed, pupil dilation, and eye movements. The competition ranked models in two tracks based on predictive performance for neuronal responses on a held-out test set: one focusing on predicting in-domain natural stimuli and another on out-of-distribution (OOD) stimuli to assess model generalization. As part of the NeurIPS 2023 Competition Track, we received more than 160 model submissions from 22 teams. Several new architectures for predictive models were proposed, and the winning teams improved the previous state-of-the-art model by 50%. Access to the dataset as well as the benchmarking infrastructure will remain online at ***. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stator Current Calculation and Validation for DFIGs with Multiple control Strategies Under Weak Grid Faults

引用

IEEE Transactions on Industry Applications 2025年

作者： Chen, Dawei Li, Canbing Liu, Sheng Liu, Xubin Liu, Jianzhe Fan, Feilong Wei, Juan Shanghai Jiao Tong University Key Laboratory of Control of Power Transmission and Conversion Shanghai200240 China Central South University School of Automation Changsha410083 China Hunan University College of Electrical and Information Engineering Changsha410082 China

This paper investigates the fault current characteristics of doubly-fed induction generators (DFIGs) in weak grid scenarios, addressing the limitations of existing methods that assume a predefined voltage dip and neglect the influence of DFIGs on post-fault voltage. A transient fault voltage model is proposed to accurately capture the interaction between DFIGs and weak grid impedance, which significantly affects fault current calculation. The model introduces an additional pole to account for fault voltage transients, addressing computational errors in low grid strength conditions. Furthermore, a fault current expression for DFIGs under severe faults, particularly after crowbar activation, is derived, revealing the impact of external grid impedance on transient fault currents. Case studies with expanded fault scenarios and hardware-in-loop experiments demonstrate the superiority of the proposed method over existing approaches in weak grid applications. © 1972-2012 IEEE.

关键词： Hardware-in-the-loop simulation

来源：评论

学校读者我要写书评

暂无评论

Constraint Selection in Optimization-Based controllers

arXiv

引用

arXiv 2025年

作者： Lee, Haejoon Rousseas, Panagiotis Panagou, Dimitra Department of Robotics University of Michigan Ann ArborMI United States Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Department of Aerospace Engineering University of Michigan Ann ArborMI United States

Human-machine collaboration often involves constrained optimization problems for decision-making processes. However, when the machine is a dynamical system with a continuously evolving state, infeasibility due to multiple conflicting constraints can lead to dangerous outcomes. In this work, we propose a heuristic-based method that resolves infeasibility at every time step by selectively disregarding a subset of soft constraints based on the past values of the Lagrange multipliers. Compared to existing approaches, our method requires the solution of a smaller optimization problem to determine feasibility, resulting in significantly faster computation. Through a series of simulations, we demonstrate that our algorithm achieves performance comparable to state-of-the-art methods while offering improved computational efficiency. © 2025, CC BY.

关键词： Lagrange multipliers

来源：评论

学校读者我要写书评

暂无评论

Nonsingular field-of-view constrained cooperative guidance with improved time-to-go estimation

引用

Chinese Journal of Aeronautics 2025年

作者： Xiaofei YANG Yunjie WU Weibo XIA Xiaodong LIU Haibin DUAN School of Automation Science and Electrical Engineering Beihang University Beijing 100191 China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing 100191 China Beĳing Aerospace Automatic Control Institute Beĳing 100854 China

This paper proposes a distributed nonsingular cooperative guidance law for multiple flight vehicles with Field-of-View (FOV) constraints. First, a novel time-to-go estimation is developed based on a FOV-constrained Proportional Navigation Guidance (FPNG) law. Then, the FPNG law is augmented with a cooperative guidance term to achieve consensus of time-to-go with predefined-time convergence prior to the impact time. A continuous auxiliary function is introduced in the bias term to avoid the singularity of guidance command. Moreover, the proposed guidance law is extended to the three-dimensional guidance scenarios and the moving target with the help of a predicted interception point. Finally, several numerical simulations are conducted, and the results verify the effectiveness, robustness, and advantages of the proposed cooperative guidance law.

关键词： Flight vehicles Cooperative guidance Field-of-view constraints Time-to-go estimation Predefined-time convergence

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：