检索结果-内蒙古大学图书馆

Analysis of Mimetic Muscle Rehabilitation: Multi-platform Facemarks Detection 1

6th Computational Methods in Systems and Software, CoMeSySo 2022

作者： Tomeš, Jakub Vácha, Ondřej Štícha, Karel Kohout, Jan Mareš, Jan Department of Computing and Control Engineering University of Chemistry and Technology in Prague Technická 1905/5 Praha 616628 Czech Republic

ISBN: (数字)9783031214356

ISBN: (纸本)9783031214349

The paper deals with frameworks for the description of mimetic muscle rehabilitation of patients with facial palsy. Detection models on different platforms (Android, iOS, Windows) are compared: ARCore Augmented Faces, ARKit Face Tracking, and MediaPipe Face Mesh. They can provide data for further quantitative analysis of mimetic muscle dysfunction. The real-time nature of these facemark detectors allows for direct feedback in the form of automatic mimetic muscle detection to the patient during the rehabilitation session. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： ARCore ARKit Facemarks Facial palsy MediaPipe Mimetic exercises Rehabilitation

来源：评论

学校读者我要写书评

暂无评论

Suppression Strategy of Sub-synchronous Oscillation in OWF Connected to the Grid Through MMC-HVDC

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第4期9卷 2621-2641页

作者： Yan, Ren-Wu Fu, Fu-Wei Liu, Yun-Zhang Yu, Ning Zhang, Zhi-Hong College of Electronic Electrical and Physics Engineering Research Center for Smart Grid Simulation Analysis and Integrated Control Fujian University of Technology Fuzhou350118 China Department of Computing Sciences State University of New York Brockport College NY14420 United States

Currently, modular multilevel converter-based flexible direct current transmission technology (MMC-HVDC) is the prevalent method for connecting long-distance offshore wind farms (OWF) to large power grid systems. Due to unique meteorological conditions at sea and the utilization of substantial wind turbines, offshore doubly-fed wind turbines possess a higher axial elastic coefficient compared to their onshore counterparts. When linked to the grid via MMC-HVDC, two types of sub-synchronous oscillations oc-cur: natural torsional vibrations within the wind turbine shafting and sub-synchronous oscillations resulting from interactions between the wind turbine and devices in the MMC-HVDC converter control system. To address these issues, a MMC-HVDC grid connection model for offshore long-distance doubly-fed wind farms has been developed. A cloud computing platform-based wind farm data acquisition system is employed for remote wind turbine data collection. Eigenvalue analysis and participation factors are utilized to determine oscillation modes and corresponding strongly correlated state variables arising from interactions between wind turbine shaft torsional vibration and converter devices. Upon identifying the correlations of state variables, a suppression strategy involving a circulating current suppression DC control collaborative virtual resistance controller is proposed to mitigate sub-synchronous oscillations. The efficacy of the suggested suppression approach is validated using PSCAD/EMTDC electromagnetic transient simulation software. © 2024, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

Secondary and Primary Goal-Function-Based control in Inverter-Interfaced Microgrids 22

Secondary and Primary Goal-Function-Based Control in Inverte...

引用

22nd International Symposium on Power Electronics, Ee 2023

作者： Vekic, Marko Isakov, Ivana Rapaic, Milan Todorovic, Ivan Grabic, Stevan Basic, Mateo University of Novi Sad Department of Power Electronic and Telecommunication Engineering Novi Sad Serbia University of Novi Sad Department of Computing and Control Engineering Novi Sad Serbia University of Split Department of Power Engineering Split Croatia

ISBN: (纸本)9798350343175

In this paper a comprehensive, primary and secondary control of a grid-connected inverter in the role of microgrid interface unit is presented. A goal-function-based decentralized control structure is proposed as a core of the primary control. It secures the microgrid stability by constraining the frequency and node deviations across the grid while simultaneously supporting the desired active power exchange between prosumer nodes. To demonstrate its effectiveness, results obtained from the simulation model, which includes microgrid inverters' secondary control, primary control, and inner control loops together with appropriate LCL filter are presented. © 2023 IEEE.

关键词： Decentralized control

来源：评论

学校读者我要写书评

暂无评论

Enhancing Collaborative and Geometric Multi-Kernel Learning Using Deep Neural Network

引用

Computers, Materials & Continua 2022年第9期72卷 5099-5116页

作者： Bareera Zafar Syed Abbas Zilqurnain Naqvi Muhammad Ahsan Allah Ditta Ummul Baneen Muhammad Adnan Khan Department of Mechatronics and Control Engineering University of Engineering and TechnologyLahore54890Pakistan Department of Information Sciences Division of Science and TechnologyUniversity of EducationLahore54000Pakistan Riphah School of Computing&Innovation Faculty of ComputingRiphah International UniversityLahore CampusLahore54000Pakistan Department Software Gachon UniversitySeongnam13120Korea

This research proposes a method called enhanced collaborative andgeometric multi-kernel learning (E-CGMKL) that can enhance the CGMKLalgorithm which deals with multi-class classification problems with non-lineardata distributions. CGMKL combines multiple kernel learning with softmaxfunction using the framework of multi empirical kernel learning (MEKL) inwhich empirical kernel mapping (EKM) provides explicit feature constructionin the high dimensional kernel space. CGMKL ensures the consistent outputof samples across kernel spaces and minimizes the within-class distance tohighlight geometric features of multiple classes. However, the kernels constructed by CGMKL do not have any explicit relationship among them andtry to construct high dimensional feature representations independently fromeach other. This could be disadvantageous for learning on datasets with complex hidden structures. To overcome this limitation, E-CGMKL constructskernel spaces from hidden layers of trained deep neural networks (DNN).Due to the nature of the DNN architecture, these kernel spaces not onlyprovide multiple feature representations but also inherit the compositionalhierarchy of the hidden layers, which might be beneficial for enhancing thepredictive performance of the CGMKL algorithm on complex data withnatural hierarchical structures, for example, image data. Furthermore, ourproposed scheme handles image data by constructing kernel spaces from aconvolutional neural network (CNN). Considering the effectiveness of CNNarchitecture on image data, these kernel spaces provide a major advantageover the CGMKL algorithm which does not exploit the CNN architecture forconstructing kernel spaces from image data. Additionally, outputs of hiddenlayers directly provide features for kernel spaces and unlike CGMKL, do notrequire an approximate MEKL framework. E-CGMKL combines the consistency and geometry preserving aspects of CGMKL with the compositionalhierarchy of kernel spaces extracted from DNN hidde

关键词： CGMKL multi-class classification deep neural network multiplekernel learning hierarchical kernel spaces

来源：评论

学校读者我要写书评

暂无评论

Accelerating heterogeneous federated learning with closed-form classifiers 24

Accelerating heterogeneous federated learning with closed-fo...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Eros Fanì Raffaello Camoriano Barbara Caputo Marco Ciccone Department of Computing and Control Engineering Polytechnic University of Turin Italy Department of Computing and Control Engineering Polytechnic University of Turin Italy and Istituto Italiano di Tecnologia Genoa Italy Department of Computing and Control Engineering Polytechnic University of Turin Italy and CINI Consortium Rome Italy

Federated Learning (FL) methods often struggle in highly statistically heterogeneous settings. Indeed, non-IID data distributions cause client drift and biased local solutions, particularly pronounced in the final classification layer, negatively impacting convergence speed and accuracy. To address this issue, we introduce Federated Recursive Ridge Regression (FED3R). Our method fits a Ridge Regression classifier computed in closed form leveraging pre-trained features. FED3R is immune to statistical heterogeneity and is invariant to the sampling order of the clients. Therefore, it proves particularly effective in cross-device scenarios. Furthermore, it is fast and efficient in terms of communication and computation costs, requiring up to two orders of magnitude fewer resources than the competitors. Finally, we propose to leverage the FED3R parameters as an initialization for a softmax classifier and subsequently fine-tune the model using any FL algorithm (FED3R with Fine-Tuning, FED3R+FT). Our findings also indicate that maintaining a fixed classifier aids in stabilizing the training and learning more discriminative features in cross-device settings. Official website: https://***/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Secure control and filtering for industrial metaverse

引用

Frontiers of Information Technology & Electronic engineering 2024年第2期25卷 179-181页

作者： Qing-Long HAN Derui DING Xiaohua GE School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyMelbourneVIC 3122Australia Department of Control Science and Engineering University of Shanghai for Science and TechnologyShanghai 200093China

Metaverse can be regarded as a socialized and virtualized cyberspace parallel yet interactive to the real *** from the rapid development of cloud computing and digital twins,metaverse is transforming traditional control and filtering para‐digms of industrial automation systems into cyberphysical social *** this scenario,future industrial automation systems could be an integration of real-world ones and virtual twins combined with great computational power within a certain temporal and spatial range.

关键词： interactive filtering Secure

来源：评论

学校读者我要写书评

暂无评论

Simplified control Strategies for Power Converters in a Grid-Connected Hybrid DC-AC Microgrid

Simplified Control Strategies for Power Converters in a Grid...

引用

2023 International Conference on Future Energy Solutions, FES 2023

作者： Busarello, Tiago Davi Curi Simões, Marcelo Godoy Laaksonen, Hannu Kauhaniemi, Kimmo Federal University of Santa Catarina Department of Control Automation and Computing Engineering Blumenau Brazil University of Vaasa School of Technology and Innovations Vaasa Finland

ISBN: (纸本)9798350332308

Many typical converter control strategies used in microgrids are complex or require modifications in the power structure. The complexities are due coupling effects among controllers and time-delay caused in exchanging information in the system. This paper proposes simplified control strategies for power converters in a grid-connected hybrid DC-AC microgrid, aiming to ensure precise voltage and current regulation. The used controllers are proportional-resonant, integral-double-lead, proportional-integral and single integral controller. In this paper, the methodology for tuning each controller is carefully described in detail and recommendation for choosing their bandwidth is given. Then, the designed controllers are discretized through the Backward-Euler approximation. The power converters of the microgrid are an inverter, a Buck, a Boost and a bidirectional DC-DC. A case study is conducted through simulations with Matlab/Simulink. Results show that the controlled variables follow their reference signals with negligible steady-state error, proving the efficacy of the simplified control strategies and allowing an stable operation of the microgrid. © 2023 IEEE.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

Deep Forest-Based Fall Detection in Internet of Medical Things Environment

引用

Computer Systems Science & engineering 2023年第6期45卷 2377-2389页

作者： Mohamed Esmail Karar Omar Reyad Hazem Ibrahim Shehata College of Computing and Information Technology Shaqra UniversityP.O.Box 33Shaqra11961Saudi Arabia Department of Industrial Electronics and Control Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Computer Science Department Faculty of Computers and Artificial IntelligenceSohag UniversitySohag82524Egypt Department of Computer and Systems Engineering Faculty of EngineeringZagazig UniversityZagazig44519Egypt

This article introduces a new medical internet of things(IoT)framework for intelligent fall detection system of senior people based on our proposed deep forest *** cascade multi-layer structure of deep forest classifier allows to generate new features at each level with minimal hyperparameters compared to deep neural ***,the optimal number of the deep forest layers is automatically estimated based on the early stopping criteria of validation accuracy value at each generated *** suggested forest classifier was successfully tested and evaluated using a public SmartFall dataset,which is acquired from three-axis accelerometer in a *** includes 92781 training samples and 91025 testing samples with two labeled classes,namely non-fall and *** results of our deep forest classifier demonstrated a superior performance with the best accuracy score of 98.0%compared to three machine learning models,i.e.,K-nearest neighbors,decision trees and traditional random forest,and two deep learning models,which are dense neural networks and convolutional neural *** considering security and privacy aspects in the future work,our proposed medical IoT framework for fall detection of old people is valid for real-time healthcare application deployment.

关键词： Elderly population fall detection wireless sensor networks internet of medical things deep forest

来源：评论

学校读者我要写书评

暂无评论

Hamiltonian learning using machine-learning models trained with continuous measurements

引用

Physical Review Applied 2024年第4期22卷 044080页

作者： Kris Tucker Amit Kiran Rege Conor Smith Claire Monteleoni Tameem Albash Department of Applied Mathematics Department of Computer Science Center for Quantum Information and Control Department of Electrical and Computer Engineering Paris France Center for Computing Research

We build upon recent work on the use of machine-learning models to estimate Hamiltonian parameters using continuous weak measurement of qubits as input. We consider two settings for the training of our model: (1) supervised learning, where the weak-measurement training record can be labeled with known Hamiltonian parameters, and (2) unsupervised learning, where no labels are available. The first has the advantage of not requiring an explicit representation of the quantum state, thus potentially scaling very favorably to a larger number of qubits. The second requires the implementation of a physical model to map the Hamiltonian parameters to a measurement record, which we implement using an integrator of the physical model with a recurrent neural network to provide a model-free correction at every time step to account for small effects not captured by the physical model. We test our construction on a system of two qubits and demonstrate accurate prediction of multiple physical parameters in both the supervised context and the unsupervised context. We demonstrate that the model benefits from larger training sets, establishing that it is “learning,” and we show robustness regarding errors in the assumed physical model by achieving accurate parameter estimation in the presence of unanticipated single-particle relaxation.

关键词： Entanglement detection Nonlocality Quantum parameter estimation Machine learning Weak measurements

来源：评论

学校读者我要写书评

暂无评论

High-performance and Multi-functional control of Transformerless Single-phase Smart Inverter for Grid-connected PV System

引用

Journal of Modern Power Systems and Clean Energy 2021年第6期9卷 1386-1394页

作者： Kamran Zeb Saif Ul Islam Waqar Uddin Imran Khan Muhammad Ishfaq Tiago Davi Curi Busarello H.J.Kim Department of Electrical Engineering Pusan National University School of Electrical Engineering and Computer Science National University of Sciences and Technology Department of Control Automation and Computing EngineeringFederal University of Santa Catarina Blumenau

Highly reliable and flexible control is required for distributed generation(DG) to efficiently connect to the *** inverters play a key role in the control and integration of DG into the power grid and provide advanced functionalities. In this paper, an energy-based single-phase voltage-source smart inverter(SPV-SSI) of 5 k VA is designed and analyzed in detail. SPV-SSI is capable of supplying the power to local load and the utility load up to the rated capacity of the inverter, injecting the power into the grid, storing the energy in lead-acid battery bank, controlling the voltage at the point of common coupling(PCC) during voltage sags or faults, and making decisions on real-time pricing information obtained from the utility grid through advanced metering. The complete design of smart inverter in dq frame, bi-directional DC-DC buck-boost converter, IEEE standard 1547 based islanding and recloser, and static synchronous compensator(STATCOM) functionalities is presented in this paper. Moreover, adaptive controllers, i. e., fuzzy proportional-integral(F-PI) controller and fuzzy-sliding mode controller(F-SMC) are designed. The performances of F-PI controller and F-SMC are superior, stable, and robust compared with those of conventionally tuned PI controllers for voltage control loop(islanded mode) and current control loop(grid-connected mode).

关键词： Distributed generation(DG) inverter convert-er fuzzy-sliding mode controller(F-SMC) fuzzy proportionalintegral(F-PI)controller

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：