检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Song, Liang Wang, Guangming Liu, Jiuming Fu, Zhenyang Miao, Yanzi Wang, Hesheng Engineering Research Center of Intelligent Control for Underground Space Ministry of Education School of Information and Control Engineering Advanced Robotics Research Center China University of Mining and Technology Xuzhou221116 China Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China

In recent studies, the generalization of neural radiance fields for novel view synthesis task has been widely explored. However, existing methods are limited to objects and indoor scenes. In this work, we extend the generalization task to outdoor scenes, trained only on object-level datasets. This approach presents two challenges. Firstly, the significant distributional shift between training and testing scenes leads to black artifacts in rendering results. Secondly, viewpoint changes in outdoor scenes cause ghosting or missing regions in rendered images. To address these challenges, we propose a geometric correction module and an appearance correction module based on multi-head attention mechanisms. We normalize rendered depth and combine it with light direction as query in the attention mechanism. Our network effectively corrects varying scene structures and geometric features in outdoor scenes, generalizing well from object-level to unseen outdoor scenes. Additionally, we use appearance correction module to correct appearance features, preventing rendering artifacts like blank borders and ghosting due to viewpoint changes. By combining these modules, our approach successfully tackles the challenges of outdoor scene generalization, producing high-quality rendering results. When evaluated on four datasets (Blender, DTU, LLFF, Spaces), our network outperforms previous methods. Notably, compared to MVSNeRF, our network improves average PSNR from 19.369 to 25.989, SSIM from 0.838 to 0.889, and reduces LPIPS from 0.265 to 0.224 on Spaces outdoor scenes. © 2023, CC BY.

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Optimization of Ethanol Production Using State-Space Modeling and Optimal control Technology

Optimization of Ethanol Production Using State-Space Modelin...

引用

IEEE International Conference on Dependable Systems, Services and Technologies (DESSERT)

作者： Lyudmila Markina Bogdan Palchevskyi Roman Hrudetskyi Oleh Smoliankin Yuliia Melnychuk Nataliya Khrystynets Department of Automation and Computer-Integrated Technologies Lutsk National Technical University Lutsk Ukraine Department of Digital Educational Technologies Lutsk National Technical University Lutsk Ukraine Department of Computer Engineering and Cyber Security Lutsk National Technical University Lutsk Ukraine

in present paper we develop the automatic optimal control of the production process of dough mixture preparation, that can be used in the production of alcohol and fuel ethanol from grain raw materials. Known methods of automatic control of the dough preparation process are based on measuring a consumption of raw materials and a concentration of dough and regulating the water supply. We offer an improved method based on robust stabilization nonlinear process control that will ensure more stable operation of the system, smooth transitions of regimes and economy of used energy, improvement of a quality of the mixture dough, as well as final ethanol product. The optimal operating modes of experimental installation were investigated using state-space dynamical modelling technic and ethanol production process simulation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis of Magnetic Field Simulations of Magnetoelastic Sensors Quasi-Statically using COMSOL Multiphysics and MATLAB Software

Analysis of Magnetic Field Simulations of Magnetoelastic Sen...

引用

International Conference on Modern Electrical and Energy Systems (MEES)

作者： Šimon Gans Ján Molnár Vitalii Naida Mariia Maliakova Department of Theoretical and Industrial Electrical Engineering Technical University of Košice Košice Slovakia Department of Theoretical and Electrical Engineering Technical University of Košice Košice Slovakia Department of Automation and Computer Systems Kremenchuk Mykhailo Ostrohradskyi National University Kremenchuk Ukraine Department of Electrical Engineering Kremenchuk Mykhailo Ostrohradskyi National University Kremenchuk Ukraine

This work describes a procedure in which a transient simulation of electromagnetic fields can be done when the electrical conductivity of the ferromagnetic medium can be effectively neglected transforming it into a quasi-static problem. A pressductor-type magnetoelastic sensor simulation model was created. The sensor’s output consists of a change of the induced voltage in the secondary coil due to applied compressive stress. Induced voltage is proportional to the time-derivative of the magnetic flux flowing through the coil and therefore is transient in nature. However, transient analyses tend to be computationally expensive and can yield noisy outputs when the model is not sufficiently densely discretized and appropriate tolerances are chosen. To overcome this, a quasi-stationary analysis of the same system is introduced and computed using the COMSOL Multiphysics FEM simulation software with further processing in the MATLAB environment, and the results are compared.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tabular Dyna-Q Algorithm for Online Calculation of LQR Gains: A Simulation Study

Tabular Dyna-Q Algorithm for Online Calculation of LQR Gains...

引用

International Conference on engineering and Emerging Technologies (ICEET)

作者： Kian Farooghi Mahdieh Samadi Hamid Khaloozadeh Department of Systems and Control K. N. Toosi University of Technology Tehran Iran Faculty of Electrical and Computer Engineering University of Tabriz Tabriz Iran

ISBN: (数字)9798350316926

ISBN: (纸本)9798350316933

This paper presents a novel approach for the online calculation of Linear Quadratic Regulator (LQR) gains using the Tabular Dyna-Q algorithm. By leveraging Q-learning, this technique enables the determination of gains for unknown dynamic systems by using input-output data only. The proposed algorithm is particularly advantageous for situations where acquiring input-output data is expensive or time-consuming, as it effectively reduces computation time by reusing previous data. To validate the accuracy of the calculations and control scheme, a simulation example is provided. The results indicate the effectiveness of the Tabular Dyna-Q algorithm in accurately computing LQR gains and its potential application in real-world scenarios. This research contributes to advancing the field of control theory by offering an efficient and reliable method for online gain calculation in dynamic systems.

关键词： Q-learning Regulators System dynamics Heuristic algorithms Computational modeling Riccati equations Data collection

来源：评论

学校读者我要写书评

暂无评论

Joint Data Compression and Task Scheduling for LEO Satellite Networks

引用

IEEE Transactions on Vehicular Technology 2025年

作者： He, Lijun Li, Shiyin Jia, Ziye Wang, Juncheng Han, Zhu China University of Mining and Technology School of Information and Control Engineering Xuzhou221116 China Xidian University State Key Laboratory of Integrated Services Networks Shaanxi Xi'an710071 China Nanjing University of Aeronautics and Astronautics College of Electronic and Information Engineering Nanjing210000 China Hong Kong Baptist University Department of Computer Science China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

We investigate a joint data compression and task scheduling problem for Low Earth Orbit Satellite Networks (LEOSNs), to maximize the sum weights of tasks while simultaneously minimizing the total data loss. First, we propose a novel Multi-Resource Conflict Graph (MRCG) model to characterize the intertwined communication and computation allocation conflicts inherent in typical data offloading processes of LEOSNs. Leveraging the proposed MRCG model, we then formulate the studied problem for LEOSNs as a linear integer program, to maximize the normalized weighted sum of both the sum task weight and the total data loss. We further explore the intrinsic structure of the linear integer program to propose an efficient solution using the Semi-Definite Relaxation (SDR) technique. Finally, the simulation results underscore that the synergistic optimization of data compression and task scheduling significantly facilitates the data offloading efficiency of LEOSNs, and the performances surpass existing benchmarks across a broad range of system parameters. © 1967-2012 IEEE.

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

Prediction of protein N-terminal acetylation modification sites based on CNN-BiLSTM-attention model

引用

computers in Biology and Medicine 2024年 174卷 108330-108330页

作者： Ke, Jinsong Zhao, Jianmei Li, Hongfei Yuan, Lei Dong, Guanghui Wang, Guohua College of Computer and Control Engineering Northeast Forestry University Harbin150040 China College of Life Science Northeast Forestry University Harbin150040 China Department of Hepatobiliary Surgery Quzhou People's Hospital Quzhou324000 China

N-terminal acetylation is one of the most common and important post-translational modifications (PTM) of eukaryotic proteins. PTM plays a crucial role in various cellular processes and disease pathogenesis. Thus, the accurate identification of N-terminal acetylation modifications is important to gain insight into cellular processes and other possible functional mechanisms. Although some algorithmic models have been proposed, most have been developed based on traditional machine learning algorithms and small training datasets. Their practical applications are limited. Nevertheless, deep learning algorithmic models are better at handling high-throughput and complex data. In this study, DeepCBA, a model based on the hybrid framework of convolutional neural network (CNN), bidirectional long short-term memory network (BiLSTM), and attention mechanism deep learning, was constructed to detect the N-terminal acetylation sites. The DeepCBA was built as follows: First, a benchmark dataset was generated by selecting low-redundant protein sequences from the Uniport database and further reducing the redundancy of the protein sequences using the CD-HIT tool. Subsequently, based on the skip-gram model in the word2vec algorithm, tripeptide word vector features were generated on the benchmark dataset. Finally, the CNN, BiLSTM, and attention mechanism were combined, and the tripeptide word vector features were fed into the stacked model for multiple rounds of training. The model performed excellently on independent dataset test, with accuracy and area under the curve of 80.51% and 87.36%, respectively. Altogether, DeepCBA achieved superior performance compared with the baseline model, and significantly outperformed most existing predictors. Additionally, our model can be used to identify disease loci and drug targets. © 2024

关键词： Acetylation

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Extended Kalman Filter for State and Parameter Estimation in AUV Localization

An Adaptive Extended Kalman Filter for State and Parameter E...

引用

IEEE International Conference on Communications (ICC)

作者： Luca Iezzi Chiara Petrioli Stefano Basagni Department of Computer Control and Management Engineering Sapienza University of Rome Italy WSENSE Srl Rome Italy The Institute for the Wireless Internet of Things Northeastern University USA

Given their independence from operators and potentially unrestricted range of operations, Autonomous Underwater Vehicles (AUVs) are considered key enablers of a host of applications of the Blue Economy. A critical requirement for AUVs is that of being able to self-localize so that the data they collect are clearly marked with position information. Localization is challenging underwater, as GPS and other technologies that use radio frequencies do not work in water. This has brought to the development of solutions that often involve costly technology and operations that are impractical to use in many situations, such as when swift and affordable localization is required. In this paper, we present a method for localizing AUVs that lends itself to be used in such situations, while providing localization that is as accurate as that from more expensive methods. Our method is based on pre-deployed acoustic beacons (whose coordinates do not need to be known by the AUV) and on mainstream sensors usually available onboard most AUVs. It employs an adaptive Extended Kalman Filter (EKF) that exploits statistical techniques to overcome the inaccuracies of baseline EKF when the noise of the environment or of the instrumentation is time-varying or unknown. We demonstrate the effectiveness of our method for accurate AUV localization through simulations and experiments at sea with an AUV and commercial acoustic transducers. Our results show swift determination of the beacon positions and meter-level localization, suggesting that our method can be effectively used in most underwater applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Forecasting Chaotic Behavior of the Drill Bit in Real-Time Using a Dnn Model Integrated with Rock Surface Morphology

SSRN

引用

SSRN 2024年

作者： Deng, Pengfei Tan, Xing Bai, Yan Li, He School of Mechanical Engineering and Automation Northeastern University Shenyang110819 China State Key Laboratory of Mechanics and Control for Aerospace Structures Nanjing University of Aeronautics and Astronautics Nanjing210016 China Department of Mechanical and Aerospace Engineering Politecnico di Torino Corso Duca degli Abruzzi 24 Torino10129 Italy

The complex interaction between the drill bit and the rock renders the deep drilling system highly chaotic, making it difficult for mainstream time-series forecasting models and drilling dynamics models to accurately forecast the operational status of the drilling system in real time. In this paper, an SM-TCN-GRU-Attention (SMTGA) model that integrates the rock surface morphology (SM) model is proposed for real-time forecasting of the operating status of the drill bit in the deep drilling system. The proposed model can accurately forecast the operating status of the drill bit when drilling non-uniform rocks in real time. In this model, the TCN layer is used to extract the relationships and short-term features between the drill bit's status and the top drive system's status. The GRU layer is employed to capture the long-term features of the drilling system's operational status, while the Attention layer analyzes and adjusts the connections between various features. The SM model is used to permanently record the status of the rock and the regeneration effect, forecasting the bit-rock interaction. The SMTGA model was compared with the TGA model, the GRU model, the Transformer model, and other mainstream DNN models. The results indicate that the forecast accuracy, convergence speed, stability, and generalization ability of the SMTGA model are much higher than other models. In addition, the influence of hyperparameters on the forecast accuracy of the SMTGA model has also been studied. These results play an important role in forecasting and preventing adverse vibrations such as stick slip, impact, reversal, and rebound of the drill bit. © 2024, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Optimized Admittance control for Manipulators Interacting with Unknown Environment 25

Optimized Admittance Control for Manipulators Interacting wi...

引用

25th IEEE International Conference on Industrial Technology, ICIT 2024

作者： Kong, Haiyi Peng, Guangzhu Li, Guang Yang, Chenguang University Of Manchester Department Of Electrical And Electronic Engineering Oxford Rd ManchesterM13 9PL United Kingdom University Of The West Of England Bristol Robotics Laboratory BristolBS16 1QY United Kingdom School Of Automation Nanjing University Of Information Science And Technology Nanjing210044 China University Of Liverpool Department Of Computer Science LiverpoolL69 3BX United Kingdom

ISBN: (纸本)9798350340266

This paper considers the study scenario that the end-effector of a manipulator follows a desired trajectory and interacts with external environment. To maximize the interaction performance, admittance control is combined with adaptive dynamic programming (ADP). The optimal admittance parameters can be learned online without prior knowledge of the environment. A data-driven Hybrid Iteration is employed in the ADP, which can relax the initial stabilizing requirement and at the same time has a faster convergence rate compared with Value Iteration. In addition, a more accurate environment model is considered in the system control design, where a general iterative expression is proposed to describe the varying contour of the environment. At last, simulation and experimental studies are given to verify the effectiveness of the proposed method. © 2024 IEEE.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

Weighted Fusion of Multiple Classifiers for Human Activity Recognition

Weighted Fusion of Multiple Classifiers for Human Activity R...

引用

International Conference on Information Fusion

作者： Kezhu Zuo Xinde Li Jean Dezert Yilin Dong School of Cyber Science and Engineering Southeast University Nanjing China Key Laboratory of Measurement and Control of CSE School of Automation Southeast University Nanjing China The French Aerospace Lab ONERA DTIS/MIDL Palaiseau France College of Computer Science and Engineering Shanghai Maritime University Shanghai China

Human Activity Recognition (HAR) based on wear-able device has become a hot topic of research due to its wide range of applications in health-care, fitness and smart homes. However, the classification of some activities with similar sensor readings, such as standing and sitting, is usually more challenging for the design of efficient activity recognition algorithms. Considering the inconsistent performance of different classifiers, which can provide information complementary for individual classifier, we propose a novel multi-classifier fusion method based on belief functions (BFs) theory for HAR. Specifically, at first, four classifiers are trained using time-domain and frequency-domain features to obtain basic belief assignments (BBA) of activity, respectively. Then, three assessment criteria are utilized to evaluate the reliability of the classifiers and a scoring matrix is constructed. Next, the algorithm of Belief Function based the Technique for Order Preference by Similarity to Ideal Solution (BF-TOPSIS) is employed to calculate the weighting coefficients for each classifier. Finally, the discounting and Dempster’s rules are adopted to combine the multiple classifiers and further decision making. Several experiments were conducted to illustrate the performance of the proposed method using the UCI smartphone dataset, and the results show that the proposed method is more accurate than the state-of-art methods.

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：