检索结果-内蒙古大学图书馆

Estimation of the Impact of Dimensionality Reduction of the Feature Space on the Efficiency of Movements Classification Based on Surface Electromyography 5

Estimation of the Impact of Dimensionality Reduction of the ...

引用

5th International Conference on Neural Networks and Neurotechnologies, NeuroNT 2024

作者： Kuznetsov, Ivan V. Ponomarchuk, Yulia V. Far Eastern State Transport University Department of Computer Science and Computer Graphics Khabarovsk Russia Far Eastern State Transport University Faculty of Control Automation and Telecommunications Khabarovsk Russia

ISBN: (纸本)9798350363739

One of the actual tasks of movement classification based on electromyography is the choice of the most informative set of features characterizing the movements. Increasing the number of features may decrease the learning performance of classifiers and reduce the efficiency of gesture classification. This paper is devoted to study the possibilities of improving the movement's classification efficiency by using the feature space dimensionality reduction methods. Classifiers based on Support Vector Machines (SVM)., Decision Trees (DT)., Random Forest (RF) and K-nearest neighbors (KNN) were considered., and Principal Component Analysis method (PCA) was used to dimensionality reduction. 3% improvement in classification performance was achieved using PCA and KNN. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Single-channel ultrahigh frequency moisture meter with direct measurement of moisture content of bulk materials

Single-channel ultrahigh frequency moisture meter with direc...

引用

2024 International Conference Automatics and Informatics, ICAI 2024

作者： Kalandarov, Palvan I. Ubaydullayeva, Shakhnoza R. Ismailov, Mirhalil A. Nikolov, Nikola N. Alexandrova, Mariela Tashkent Inst. of Irrigation and Agricultural Mechanization Engineers National Research University Department "Automation and Control of Technology Process in Production" Tashkent Uzbekistan Faculty of Computer Science and Automation Technical University of Varna Department of Automation Varna Bulgaria

ISBN: (纸本)9798350353907

The article discusses the theoretical foundations of the design of a single-channel ultrahigh frequency moisture meter with direct measurement of the moisture content of bulk materials. In accordance with the requirements of the methodology for selecting efficiency criteria, it is necessary to develop structural diagrams of measuring devices. For these purposes, the standard deviation of the random error is determined, characterizing the accuracy. It includes the main components: sensitivity error, zero error and additive component. Mathematical models of structures are constructed and the standard deviation of random errors, which are caused by certain parameters and additive fluctuations, is calculated. A single-parameter ultrahigh-frequency method for determining the moisture content is proposed. This method provides high accuracy of a single-channel ultrahigh frequency moisture meter with direct measurement of the moisture content of bulk materials. The measuring device can be used in the agricultural industry, where humidity is one of the important parameters, starting with harvesting and ending with the release of finished products. © 2024 IEEE.

关键词： Moisture meters

来源：评论

学校读者我要写书评

暂无评论

Research and Analysis of the Method for Measuring the Moisture Content of Cottonmaterials at Ultrahigh Frequencies

Research and Analysis of the Method for Measuring the Moistu...

引用

2023 International Conference Automatics and Informatics, ICAI 2023

作者： Kalandarov, Palvan I. Turkmenov, Khasan E. Ubaydullayeva, Shakhnoza R. Nikolov, Nikola N. Alexandrova, Mariela I. 'Tashkent Institute of Irrigation and Agricultural Mechanization Engineers' National Research University Department 'Automation and Control of Technology Process in Production' Tashkent Uzbekistan Technical University of Varna Faculty of Computer Science and Automation Department of Automation Varna Bulgaria

ISBN: (纸本)9798350312911

The article provides a theoretical analysis of the ultrahigh frequency (microwave) method of humidity measurement, discusses the problems of instrumentation of the method in question, and proposes a scheme of an experimental installation. Bulk cotton materials were selected as the objects of research. The electromagnetic wave radiation is analyzed during measurement and the evaluation of electrophysical characteristics requires the study of the functional dependence of the amplitude and phase shift on the mass ratio of humidity, mathematical models for various bulk cotton materials describing the joint effect of humidity, material density on the attenuation and phase shift of the passing wave are obtained. © 2023 IEEE.

关键词： Humidity control

来源：评论

学校读者我要写书评

暂无评论

automation of Technological Processes for controlling Grain Moisture in the Flowu

Automation of Technological Processes for Controlling Grain ...

引用

2023 International Conference Automatics and Informatics, ICAI 2023

作者： Kalandarov, Palvan I. Ubaydullayeva, Shakhnoza R. Gaziyeva, Rano T. Nikolov, Nikola N. Alexandrova, Mariela I. 'Tashkent Institute of Irrigation and Agricultural Mechanization Engineers' National Research University Department 'Automation and Control of Technology Process in Production' Tashkent Uzbekistan Technical University of Varna Faculty of Computer Science and Automation Department of Automation Varna Bulgaria

ISBN: (纸本)9798350312911

The paper deals with the problems of grain wounding requires large energy costs, requiring a multi-stage process of grain processing, installation and perfect and reliable automation systems for the storage and processing of raw materials, theoretical and experimental studies and the results of the use of the microwave method in measuring the moisture content of grain and grain materials. The method under consideration is based on the principle of selective absorption of microwave radiation energy by water in materials and its derivatives. By the degree of absorption of radiation, the concentration of moisture is judged. The paper investigates the amplitude and phase methods of the passing wave in free space. The influence of the elastic properties of the material under study on the electrical characteristics of the microwave wave, suggesting fundamentally new ways of measuring the attenuation and phase shift of the electromagnetic wave, including discrete conversion of the signal of the primary converter, which does not require rigid metrological support and the use of a phase shift, is substantiated. Information on the values of the thickness of the material is analyzed in order to correct the influence of this value, consisting of two parameters: the signal of the passing wave, the attenuation and phase shift which characterizes the humidity and the additional signal - the phase wave reflected from the front surface of the materials and carrying information about its thickness. © 2023 IEEE.

关键词： automation

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Group Formation control of Cyber-Physical Systems via Distributed Cloud Computing

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical Systems 2025年 3卷 341-350页

作者： Ren, Hongru Long, Yinren Li, Hongyi Huang, Tingwen Guangdong University of Technology School of Automation Guangdong-Hong Kong Joint Laboratory for Intelligent Decision and Cooperative Control Guangdong Provincial Key Laboratory for Intelligent Decision and Cooperative Control Guangzhou510006 China Southwest University College of Electronic and Information Engineering Chongqing400715 China Shenzhen University of Advanced Technology Faculty of Computer Science and Control Engineering Shenzhen518055 China

This paper investigates the group formation control problem for cyber-physical systems (CPSs) with random communication constraints. The distributed cloud computing system is constructed to divide agents into groups and establish communication between agents. A data-driven predictive control strategy is proposed by combining networked predictive control and model-free adaptive control method. The desired group formation control performance can be achieved and the three-channel random communication constraints of CPSs are actively compensated. Thisstrategy does not require the system model and relies solely on the system's I/O data for adaptive learning. Further analyses concludes the conditions for simultaneous reach stability and group formation of the closed-loop CPSs using the data-driven predictive control strategy. The effectiveness of the proposed strategy is validated by simulation results. © 2023 IEEE.

关键词： Distributed cloud

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach for Faults Recognition of Dissolved Oxygen Sensor in Wastewater Treatment Plants 28

A Deep Learning Approach for Faults Recognition of Dissolved...

引用

28th IEEE International Conference on Emerging Technologies and Factory automation, ETFA 2023

作者： Ghinea, Liliana Maria Miron, Mihaela Ratnaweera, Harsha Electrical Engineering and Electronics Faculty of Automation Computers Department of Automatic Control and Electrical Engineering Department Galaţi Romania Computers Electrical Engineering and Electronics Faculty of Automation Department of Computer Science and Information Technology Galaţi Romania Norwegian University of Life Sciences Faculty of Science and Technology Oslo Norway

ISBN: (纸本)9798350339918

Fault diagnosis in wastewater treatment plants (WWTPs) is important to protect communities and ecosystems from toxic elements discharged into water. In this sense, fault identification of sensors plays an important role as they are the key components of the water plants control, especially because environmental legislation is very strict when referring to failures or anomalies in WWTPs. This paper analyzes the performances of two Deep Learning models, a Feedforward Neural Network (FFNN) and a 1D Convolution Neural Network (1DCNN) for identifying five operating states of the dissolved oxygen (DO) sensor: normal and faulty (bias, stuck, spike and precision degradation faults). The experiments were conducted on the Benchmark Simulator Model No 2 (BSM2) developed by the IWA Task Group. The performance of the Deep Learning (DL) classifiers was evaluated via accuracy, precision, recall, and F1-score metrics. The best overall classification accuracy was obtained by FFNN, 98.32% for training and 98.30% for testing. © 2023 IEEE.

关键词： Wastewater treatment

来源：评论

学校读者我要写书评

暂无评论

Adaptive Prescribed-Time Neural control of Nonlinear Systems via Dynamic Surface Technique

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第10期5卷 4948-4958页

作者： Wang, Ping Yu, Chengpu Lv, Maolong Zhao, Zilong Beijing Institute of Technology School of Automation Beijing100081 China Beijing Institute of Technology Chongqing Innovation Center Chongqing401120 China Air Force Engineering University College of Air Traffic Control and Navigation Xi'an710051 China Delft University of Technology Faculty of Electrical Engineering Mathematics and Computer Science Delft2628 CD Netherlands

The adaptive practical prescribed-time (PPT) neural control is studied for multiinput multioutput (MIMO) nonlinear systems with unknown nonlinear functions and unknown input gain matrices. Unlike existing PPT design schemes based on backstepping, this study proposes a novel PPT control framework using the dynamic surface control (DSC) approach. First, a novel nonlinear filter (NLF) with an adaptive parameter estimator and a piecewise function is constructed to effectively compensate for filter errors and facilitate prescribed-time convergence. Based on this, a unified DSC-based adaptive PPT control algorithm, augmented with a neural networks (NNs) approximator, is developed, where NNs are used to approximate unknown nonlinear system functions. This algorithm not only addresses the inherent computational complexity explosion associated with traditional backstepping methods but also reduces the constraints on filter design parameters compared to the DSC algorithm that relies on linear filters. The simulation showcases the effectiveness and superiority of the devised scheme by employing a two-degree-of-freedom robot manipulator. © 2024 IEEE.

关键词： Flexible manipulators

来源：评论

学校读者我要写书评

暂无评论

Texture Analysis of Breast US Images Using Morphological Transforms, Hausdorff Dimension and Bagging Ensemble Method 32

Texture Analysis of Breast US Images Using Morphological Tra...

引用

32nd Mediterranean Conference on control and automation, MED 2024

作者： Tabacaru, Gigi Moldovanu, Simona Barbu, Marian 'Dunarea de Jos' University of Galati Faculty of Automation Computers Electrical Engineering and Electronics Department of Automatic Control and Electrical Engineering Romania 'Dunarea de Jos' University of Galati Computer Science and Information Technology Faculty of Automation Computers Electrical Engineering and Electronics Romania Dunarea de Jos University of Galati The Modelling & Simulation Laboratory Galati800008 Romania

ISBN: (纸本)9798350395440

In this work, an attempt is made for the first time to use the measurement pattern generated by morphological transformation quantified by Hausdorff fractal dimension (HFD) and classified with ensemble learning based on bagging. The proposed work uses three morphological transformations for image preprocessing: hit-and-miss transform (HMT), white (WHT), and black top-hat (BHT). The pattern texture of US breast images is described by extracting the HFD from the regions of interest (ROI) after the ultrasound (US) images have been preprocessed. The main objective of this study was achieved by comparatively analyzing the classification performance of features using the Random Forest (RF), Extra Trees (ET) classifier, and bagging ensemble method based on XGBoot classifier. In presented study, the XGBoost classifier and BHT image processing method give an accuracy of 89.8% in a binary classification, benign versus malignant breast cancer. © 2024 IEEE.

关键词： Fractal dimension

来源：评论

学校读者我要写书评

暂无评论

Quantifying controllability for Nonlinear State-Dependent Riccati Equation control

Quantifying Controllability for Nonlinear State-Dependent Ri...

引用

2022 International Russian automation Conference, RusAutoCon 2022

作者： Hu, Yuhui Neusypin, Konstantin Avenirovich Shen, Kai Bauman Moscow State Technical University Faculty of Computer Science and Control Systems Moscow Russia Beijing Institute of Technology School of Automation Beijing China

ISBN: (数字)9781665466554

ISBN: (纸本)9781665466554

Degree of controllability (DOC) characterizes how controllable a given system is and thus quantifying controllability can facilitate the control system synthesis and optimization. In this paper, the controllability of nonlinear input-affine systems and the state-dependent-coefficient (SDC) factorization are first reviewed. A computational procedure based on the scalarization of the controllability Gramian is proposed to quantify the controllability of both system and state variables of the SDC factored system for state-dependent Riccati equation (SDRE) control. The simulation of coordinate satellite control is carried out to validate the effectiveness of the proposed DOC criterion. It is shown that SDC-parameterized models with higher DOC can promote the performance of the SDRE control algorithm. © 2022 IEEE.

关键词： controllability

来源：评论

学校读者我要写书评

暂无评论

Predictive maintenance for electrical motors: Current approach and usage of artificial intelligence algorithms

Predictive maintenance for electrical motors: Current approa...

引用

International Conference on Methods and Models in automation and Robotics (MMAR)

作者： Tomasz Herzog Krzysztof Bartecki Faculty of Electrical Engineering Automatic Control and Computer Science Opole University of Technology Opole Poland Rockwell Automation Power Control Business Katowice Poland

ISBN: (数字)9798350362343

ISBN: (纸本)9798350362350

The article presents the current approach in artificial intelligence methods used in predictive maintenance for electrical motors. The study focuses on presenting data classification methods for fault detection and isolation using data from condition monitoring systems. We discuss the advantages and disadvantages of using machine learning methods like perceptron and Support Vector Machine (SVM) for fault classification problems. Our conclusion shows great interest in machine learning methods combined with condition monitoring systems. Our future research will focus on comparing SVM, perceptron networks, and other methods, such as K-nearest neighbors, with their possibility for implementation in embedded firmware systems.

关键词： Support vector machines Condition monitoring Accuracy Fault detection Artificial neural networks Machine learning Prediction algorithms

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：