检索结果-内蒙古大学图书馆

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Haoming Liu Xinhua Li Ye Zou Yuting Yang Zhi Fang Youchen Wang Data Technology and Applications Department Beijing Institute of Computer Technology and Application Beijing China Department of Automation Tsinghua University Beijing China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

THz imaging has gained widespread attention due to its high penetration ability and safety. However, THz systems deployed on robotic platforms are limited by their low resolution and high noise levels, which restrict their appeal in low-level human visual perception and application in high-level visual downstream tasks. In this research, we proposed an algorithmic framework featuring a $\mathbf{U}$-shaped feature extraction network and an image reconstruction module. Based on this, we introduced a multi-task loss function for joint learning. Through lightweight design, the framework is made deployable on low-power robotic platforms. We have also proposed a THz dataset suitable for multi-task applications. This framework has demonstrated exceptional performance in multi-level visual applications.

关键词： Visualization Mechatronics Image resolution Imaging Multitasking Safety Robots Image reconstruction Visual perception Noise level

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection technology for Cloud Manufacturing System based on Data Denoising and Feature Optimization 19

Anomaly Detection Technology for Cloud Manufacturing System ...

引用

19th IEEE International Conference on Networking, Sensing and Control, ICNSC 2022

作者： Zhao, Longbo Li, Bo Hu Jia, Juan Wu, Tong School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Beijing Institute of Computer Technology and Application Department of Intelligent Manufacturing Beijing100854 China

ISBN: (纸本)9781665472432

Aiming at the problem that the traditional anomaly detection method based on threshold cannot effectively detect sensor numerical anomalies in cloud manufacturing system, this work proposes a new method to detect some sensor numerical anomalies form the industrial control system. It is the central part of a cloud manufacturing system. Firstly, this work constructs a Savitzky-Golay (S-G) filter to reduce data noises. Furthermore, an extreme learning machine based on genetic algorithm (GA-ELM) model is proposed to detect sensor numerical anomalies form the industrial control system. The genetic algorithm (GA) is used to reduce feature dimensions from 51 to 10 and the extreme learning machine algorithm (ELM) is used for classification to achieve the purpose of anomaly detection. Finally, using the public dataset called Secure Water Treatment (SWaT), the classification accuracy is 98.96%. It shows a better performance of the proposed method. © 2022 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Fixed-Time Fuzzy Adaptive Tracking Control for High-Order Systems with Unknown Nonlinearities and Control Directions

引用

International Journal of Fuzzy Systems 2023年第4期25卷 1546-1558页

作者： Yu, Le-Yuan Sun, Zong-Yao Meng, Qing-hua Chen, Chih-Chiang Li, Jiao-Jiao School of Mathematics and Computer Application Technology Jining University Shandong Qufu273155 China Institute of Automation Qufu Normal University Shandong Qufu273165 China School of Mechanical Engineering Hangzhou Dianzi University Zhejiang Hangzhou310018 China Department of Systems and Naval Mechatronic Engineering National Cheng Kung University Tainan70101 Taiwan

This paper presents a fixed-time tracking controller for a class of high-order nonlinear systems with completely unknown nonlinearities and unknown control directions. To perform the high-order practical tracking control objective, which is quite different from both the low-order control ones and the asymptotic stabilization ones, a coordinate transformation related to tracking error is introduced to make the tracking error be constrained to a prescribed interval including the origin in a fixed time by employing a finite-time stable function. A unique adaptive parameter is adopted to approximate the unknown nonlinear functions by applying fuzzy logic functions. Nussbaum functions are utilized to determine the unknown control directions. Based on the domination technique and the method of adding a power integrator, the provided controller can guarantee all the states of the closed-loop systems and control signal are bounded. Three simulation examples show the feasibility and efficiency of the proposed tracking control strategy. © 2023, The Author(s) under exclusive licence to Taiwan Fuzzy Systems Association.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Model Predictive Control Method for Ten-Switch Three-Phase Three-Level Inverter 50

Model Predictive Control Method for Ten-Switch Three-Phase T...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Guler, Naki Fesli, Ugur Komurcugil, Hasan Bayhan, Sertac Technology Faculty Gazi University Ankara Turkey Renewable Energy and Smart Grids Application and Research Center Gazi University Ankara Turkey Electronic and Automation Department Technical Sciences Vocational School Gazi University Ankara Turkey Department of Computer Engineering Eastern Mediterranean University Famagusta Via Mersin 10 Turkey Qatar Environment and Energy Research Institute Hamad Bin Khalifa University Doha Qatar

ISBN: (纸本)9781665464543

This paper proposes a multi-objective model predictive control (MPC) for a grid-connected ten-switch three-phase three-level inverter. The main objective of the proposed MPC method is to control the grid current. In addition, the voltage balancing of the DC capacitors in the ten-switch three-level inverter is essential to generate voltage levels properly. Therefore, two objectives need to be achieved simultaneously. The multi-objective cost function feature of the MPC method is used to achieve these objectives. The simulation studies are performed using MATLAB/Simulink environments to investigate the effectiveness of the proposed MPC method. The results show that the proposed control method exhibits accurate performance under steady-state conditions and fast dynamic responses under transient conditions. Moreover, the grid current spectrums show that the total harmonic distortion is 2.21% in normal operation, and it is under the desired limits, even with a 50% parameter mismatch in filter inductance. © 2024 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection technology for Cloud Manufacturing System based on Data Denoising and Feature Optimization

Anomaly Detection Technology for Cloud Manufacturing System ...

引用

IEEE International Conference on Networking, Sensing and Control

作者： Longbo Zhao Bo Hu Li Juan Jia Tong Wu School of Automation Science and Electrical Engineering Beihang University Beijing China Department of Intelligent Manufacturing Beijing Institute of Computer Technology and Application Beijing China

ISBN: (纸本)9781665472449

关键词： Cloud computing Extreme learning machines Industrial control Time series analysis Filtering algorithms Feature extraction Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimal Treatment Planning in Real-Time Using AI and Multi-Objective Optimization for Chronic Disease Management

Optimal Treatment Planning in Real-Time Using AI and Multi-O...

引用

Cognitive Computing in Engineering, Communications, Sciences and Biomedical Health Informatics (IC3ECSBHI), International Conference on

作者： Ashish Sharma Neetu Dixit Vishal Mittal Jai Narayan Shukla Abhishek Kumar Gupta Sujeet Kumar Department Of Technology JIET Jodhpur Rajasthan India Department of Computer Application RBMI Greater Noida India University School of Automation and Robotics Guru Govind Singh Indraprastha University India Mangalmay institute of management and technology U.P. India Department of Information Technology Jagannath International Management School New Delhi GL BAJ AJ Institute of Management Gr.Noida U.P India

ISBN: (数字)9798331518523

ISBN: (纸本)9798331518530

The rapid increase of global health burden from chronic diseases, like type 2 diabetes, hypertension, cancer, etc. Developing an individualized treatment plan for these diseases is fundamental to improving patient prognosis. Unfortunately, traditional treatment planning takes a long time, and it can be an expensive process that might not consider the particular patient requirements/preferences. This study aims to develop a novel method involving artificial intelligence (AI) and multi-objective optimization-based treatment planning using real-time data. The authors suggested a tool for combining clinical data, patient-specific information, and treatment guidelines to build personalized interventions aligned with medical efficacy and the preferred trade-offs from patients. This AI will work at processing the data for each patient on an ongoing basis and updating treatment plans in real time to ensure they stay dynamic and adaptive. In addition, the multi-objective optimization approach will enable better plan tailoring to patient-specific objectives regarding quality of life, medication compliance, and cost-effectiveness. This project's projected impacts are considerable and can transform chronic disease management by improving treatment effectiveness, reducing patient and selfmanagement burdens and burden on healthcare systems with overall improved patient outcomes.

关键词： Hypertension Medical services Transforms Real-time systems Planning Diabetes Artificial intelligence Optimization Medical diagnostic imaging Cancer

来源：评论

学校读者我要写书评

暂无评论

The Importance of Being Earnest: Multiple Heterogeneous Container Loading with a Simple Genetic Algorithm 28th

The Importance of Being Earnest: Multiple Heterogeneous Con...

引用

28th European Conference on applications of Evolutionary Computation, Evoapplications 2025, held as part of EvoStar 2025

作者： Rusin, Francesco Fiala, Jan Sanker, Julian Bhattarai, Suyesh Ekárt, Anikó Department of Engineering and Architecture University of Trieste Trieste Italy Institute of Automation and Computer Science Brno University of Technology Brno Czech Republic Yale College Yale University New Haven United States Mechatherm International Limited Cradley Heath United Kingdom Aston Centre for Artificial Intelligence Research and Application Aston University Birmingham United Kingdom

ISBN: (纸本)9783031900617

In this study we address the complex practical problem of multiple heterogeneous container loading with a simple genetic algorithm. We demonstrate that with a well-chosen representation including a heuristic and a suitable fitness function the other aspects of the genetic algorithm do not need extensive work for good results. Following systematic study of our method on synthetically generated data, we visually showcase the solution for a company-based problem instance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Model Predictive Control Method for Ten-Switch Three-Phase Three-Level Inverter

Model Predictive Control Method for Ten-Switch Three-Phase T...

引用

Annual Conference of Industrial Electronics Society

作者： Naki Guler Ugur Fesli Hasan Komurcugil Sertac Bayhan Electrical and Electronic Engineering Technology Faculty Gazi University Ankara Turkey Renewable Energy and Smart Grids Application and Research Center Gazi University Ankara Turkey Electronic and Automation Department Technical Sciences Vocational School Gazi University Ankara Turkey Department of Computer Engineering Eastern Mediterranean University Famagusta Turkey Qatar Environment and Energy Research Institute Hamad Bin Khalifa University Doha Qatar

ISBN: (数字)9781665464543

ISBN: (纸本)9781665464550

关键词： Industrial electronics Total harmonic distortion Capacitors Cost function Inverters Steady-state Voltage control Transient analysis MATLAB Predictive control

来源：评论

学校读者我要写书评

暂无评论

An IoT and Information Mining Algorithm-Based Self-Monitoring and Analysis System for Solar Power Plants

An IoT and Information Mining Algorithm-Based Self-Monitorin...

引用

Advance Computing and Innovative Technologies in Engineering (ICACITE), International Conference on

作者： Ali Hadi Abdulwahid Kruti Jani Navdeep Dhaliwal Rajesh Singh A. Bhasha Jayapal Lande Control and Automation Engineering Department Engineering Technical College Southern Technical University Basra Iraq Shri Chimanbhai Patel Post Graduate Institute of Computer Application Ahmedabad Lovely Professional University Phagwara Uttaranchal Institute of Technology Uttaranchal University India Dept of IT St. Martin's Engineering College Secunderabad Telangana India School of Computer Science and Artificial Intelligence SR University Warangal Telangana India

Because of their affordability and sustainability, renewable sources of energy are receiving a lot of study interest. Particularly, solar power plants are regarded as a type of renewable sources of energy that may be employed in many areas since, while requiring less space than traditional systems, they demand less money for installation and maintenance. The majority of small generating units control space occupancy by putting the machinery on an exposed terrace. However, acres of land is needed for the building of huge power producing stations. It is difficult for human workers to maintain such a huge region of a power plant. The suggested algorithm would assist human workers in identifying the consistency of energy production and failure or faulty areas in solar energy systems using IoT and database mining (DM) techniques. This enables immediate fault repair action to be taken, which increases producing station effectiveness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Examining the Fourier Spectrum of Speech Signal from a Time-Frequency Perspective for Automatic Depression Level Prediction

引用

IEEE Transactions on Affective Computing 2025年

作者： Niu, Mingyue Tao, Jianhua He, Yongjun Zhang, Shiqing Li, Ming YanShan University School of Information Science and Engineering Qinhuangdao066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province China Tsinghua University Department of Automation Bejing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China Harbin Institute of Technology School of Computer Science and Technology Harbin150001 China Taizhou University Institute of Intelligent Information Processing Taizhou318000 China Zhejiang Normal University Zhejiang Key Laboratory of Intelligent Education Technology and Application Jinhua321004 China Zhejiang Institute of Optoelectronics Jinhua321004 China

Currently, many studies use Fourier amplitude spectra of speech signals to predict depression levels. However, those works often treat Fourier amplitude spectra as images or sequences to capture depression cues using convolutional neural networks or multilayer perceptrons. Therefore, they ignore the complex element composition and time-frequency attributes of Fourier spectra, which is not conducive to capturing the differences among individuals with different depression levels. For this reason, we construct a Time-Frequency Self-Embedding (TFSE) module, which not only stores the correlation relationship among real (imaginary) parts of Fourier spectra of different subjects from the time-frequency perspective, but also maintain the physical properties of data through the weight embedding process. Besides, Global Average Pooling (GAP) or linear layers are difficult to balance both temporal and frequency dimensions in the vectorization process. Therefore, we construct a Time-Frequency Tensor Vectorization (TFTV) module, which summarizes each channel along time and frequency dimensions, and then generates the vectorization result by integrating various channels. In this way, we combine TFSE and TFTV modules to form our SpectrumFormer model for predicting depression levels. Evaluation indicators on AVEC 2013 and AVEC 2014 depression databases imply the progressiveness of our model. © 2010-2012 IEEE.

关键词： Depression level prediction Real and imaginary parts Tensor vectorization Time-frequency attributes

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：