检索结果-内蒙古大学图书馆

IEEE Conference on Wireless communications and Networking

作者： Tianyu Pang Fuhao Liu Xinpei Chen Jiansong Miao Junsheng Mu Zaodi Song School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China North Automatic Control Technology Institute Taiyuan China

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

With the explosive growth of user data in 6G networks, existing infrastructures face significant scalability and latency challenges. Mobile Edge Computing (MEC) partially alleviates these issues by deploying computational resources closer to users, but still struggles to fully meet the growing demands. Re-configurable Intelligent Surfaces (RIS) enhance communication performance by improving channel quality. However, optimizing resource allocation in RIS-aided MEC systems remains a critical challenge due to the complexity of real-time optimization of multiple parameters. Although Deep Reinforcement Learning (DRL) methods like Deep Deterministic Policy Gradient (DDPG) have been applied, they often suffer from Q-value overestimation and instability, resulting in suboptimal performance in dynamic environments. This paper focuses on a single-cell RIS-aided MEC network where multiple user devices offload computational tasks to an edge server. We propose an optimized resource allocation scheme using an improved Distributed Soft Actor-Critic (DSAC-T) algorithm. This approach jointly optimizes power control, computation offloading, edge computing resource allocation, and RIS phase shifts, aiming to minimize total offloading delay to ensure real-time service requirements. Simulation results demonstrate that DSAC-T outperforms multiple baseline methods (e.g., DDPG and SAC) in reducing offloading delay by 46.39% and 16.70%, respectively, while significantly enhancing system stability and convergence speed.

关键词： Heuristic algorithms Simulation Power control Stability analysis Real-time systems Delays Resource management Servers Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

Construction of Industry-Teaching-Innovation Cases for Robot Training under the Integration of Virtuality and Reality

Construction of Industry-Teaching-Innovation Cases for Robot...

引用

International Conference on Educational and Information technology (ICEIT)

作者： Jiang Jin-gang Xiong Jiang-long Wang Ya-ping Wang Kai-rui Shen Tao Bao Yudong National Experimental Teaching Demonstration Center for Mechanical Engineering Experiment and Practice Harbin University of Science and Technology Harbin China School of Mechanical and Power Engineering Harbin University of Science and Technology Harbin China School of Measurement and Communication Engineering Harbin University of Science and Technology Harbin China

ISBN: (数字)9798331540883

ISBN: (纸本)9798331540890

Aiming to address the current problems in robot training teaching, this paper focuses on the construction of industry-teaching-innovation cases for robot training under the integration of virtuality and reality, such as the disconnection between training content and industry practice, delays in digital transformation, and the lack of training resources. Relying on the intelligent manufacturing industry academy (IMIA), the teaching model integrates virtual simulation training with practical operation to enhance students' practical skills and innovative abilities. The study introduces complex technical challenges faced by enterprises in production, combining a dual-mentor system and a collaborative resource-sharing mechanism between school and enterprises. This ensures that students can master key skills required by enterprises during training, while innovation and entrepreneurship education is integrated throughout the whole training process to stimulate students' creative thinking and entrepreneurial mindset.

关键词： Training Manufacturing industries Technological innovation Service robots Digital transformation Entrepreneurship Production Delays Manufacturing Problem-solving

来源：评论

学校读者我要写书评

暂无评论

Flame region segmentation of a coal-fired power plant boiler burner through YOLOv8-MAH model

引用

Fuel 2025年 398卷

作者： Pu, Sixu Li, Jian Han, Zhezhe Zhu, Xiaoyu Xu, Chuanlong National Engineering Research Center of Power Generation Control and Safety School of Energy and Environment Southeast University Nanjing China School of Communication and Artificial Intelligence Nanjing Institute of Technology Nanjing China

Effective segmentation of flame regions in coal-fired power plant boiler burners is critical for enhancing combustion monitoring and operational safety. Traditional methods often suffers from the interference of complicated furnace environments, such as furnace background, adjacent burners and fly ash. This study introduces an advanced flame segmentation approach utilizing the YOLOv8 framework, improved by a multi-level augment head (MAH) and single-object tracking techniques to integrate shallow and deep feature information. Moreover, a convolutional block attention module (CBAM) is embedded in the backbone network to refine feature extraction, while the reparameterization and cross-stage feature reuse are applied in the neck network to bolster multi-scale feature fusion. Experimental results demonstrate that the improved model achieves a mean intersection over union (mIoU) of 82.6—an 8.8 increase over the original YOLOv8—while maintaining high computational efficiency with an inference time of 4.43 ms. Compared with other semantic segmentation models, the proposed model achieves superior accuracy and inference speed. Its performance is validated on a 660 MW opposed-fired boiler, where it can mitigate external disturbances and effectively segment the flame regions under varying load conditions. This method provides a reliable foundation for image-based flame detection systems, enabling real-time and precise monitoring of combustion conditions. © 2025 Elsevier Ltd

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Correction to: An advanced reinforcement learning control method for quadruped robots in typical urban terrains (International Journal of Machine Learning and Cybernetics, (2024), 10.1007/s13042-024-02478-9)

引用

International Journal of Machine Learning and Cybernetics 2025年 1-2页

作者： Yan, Chi Wang, Ning Gao, Hongbo Wang, Xinmiao Tang, Chao Zhou, Lin Li, Yuehua Wang, Yue School of Information Science and Technology University of Science and Technology of China No. 96 Jinzhai Road Anhui Hefei230026 China School of Information and Security Chongqing College of Mobile Communication No. 36 Dengying Avenue Qijiang District Sichuan Chongqing401520 China Institute of Advanced Technology University of Science and Technology of China No. 5089 Wangjiang West Road Anhui Hefei230088 China School of Electrical and Electronic Engineering Nanyang Technological University 50 Nanyang Avenue Nanyang639798 Singapore Zhejiang Lab Kechuang Avenue Zhongtai Sub-District Zhejiang Hangzhou311121 China College of Control Science and Engineering Zhejiang University Zhejiang Hangzhou310027 China

In this article, the affiliation details for Authors "Ning Wang2, Hongbo Gao1,3,4, Yuehua Li5, Yue Wang6" were interchanged and it is corrected now. Incorrect affiliation: 2Institute of Advanced technology, University of Science and technology of China, No. 5089 Wangjiang West Road, Hefei 230088, Anhui, China 3school of Electrical and Electronic engineering, Nanyang Technological University, 50 Nanyang Avenue, 639798 Nanyang, Singapore 4Zhejiang Lab, Kechuang Avenue, Zhongtai Sub-District, Hangzhou 311121, Zhejiang, China 5College of control Science and engineering, Zhejiang University, Hangzhou 310027, Zhejiang, China 6school of Information and Security, Chongqing College of Mobile communication, No. 36 Dengying Avenue, Qijiang District, Chongqing 401520, Sichuan, China Correct affiliation: 2school of Information and Security, Chongqing College of Mobile communication, No. 36 Dengying Avenue, Qijiang District, Chongqing 401520, Sichuan, China 3Institute of Advanced technology, University of Science and technology of China, No. 5089 Wangjiang West Road, Hefei 230088, Anhui, China 4school of Electrical and Electronic engineering, Nanyang Technological University, 50 Nanyang Avenue, 639798 Nanyang, Singapore 5Zhejiang Lab, Kechuang Avenue, Zhongtai Sub-District, Hangzhou 311121, Zhejiang, China 6College of control Science and engineering, Zhejiang University, Hangzhou 310027, Zhejiang, China The original article has been corrected. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis of Spiral Scanning Amplitude Modulation Methods for Two-photon Endomicroscopy 10

Analysis of Spiral Scanning Amplitude Modulation Methods for...

引用

10th Symposium on Novel Optoelectronic Detection technology and Applications

作者： Cui, Haodong Wang, Conghao Liu, Huilan Zhang, Xiulei Hu, Yanhui Fu, Qiang Wu, Runlong Wang, Aimin Feng, Lishuang School of Instrumentation and Optoelectronic Engineering Beihang University Beijing100191 China Beijing100191 China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Beijing Transcend Vivoscope Biotech Co. Ltd. Beijing100049 China Beijing Key Laboratory for Optoelectronics Measurement Technology Beijing Information Science and Technology University Beijing100192 China State Key Laboratory of Advanced Optical Communication System and Networks Department of Electronics Peking University Beijing100871 China

ISBN: (数字)9781510688155

ISBN: (纸本)9781510688148

Two-photon endomicroscopy is a high-resolution label-free imaging technique for biological tissues. This paper analyzes sinusoidal and triangular amplitude modulation methods for spiral scanning two-photon endomicroscopy. In the theoretical modeling section, the mathematical model of PZT fiber scanner is established, and the distortion of fiber scanning trajectory caused by two amplitude modulated sine wave signals is simulated and evaluated. In the experimental verification section, a test platform is constructed to measure the scanning trajectory distortion driven by these amplitude modulated sine wave signals. Finaly, spiral scanning two-photon endomicroscopic imaging of in-vivo GFP mice brain tissues using sinusoidal amplitude modulated signals are demonstrated. © 2025 SPIE.

关键词： Amplitude modulation

来源：评论

学校读者我要写书评

暂无评论

Feature extraction of composite faults in automotive transmission shaft bearings using optimized RVME parameters

引用

Zhendong yu Chongji/Journal of Vibration and Shock 2025年第13期44卷 317-326页

作者： Yu, Jun Zhang, Yanan Ping, Jingyan Shen, Tao Jin, Zheming Lin, Jiang Key Laboratory of Advanced Manufacturing and Intelligent Technology Harbin University of Science and Technology Harbin 150080 China BH Technology Group Co. Ltd. Taizhou 318054 China School of Mechatronics Engineering Henan University of Science and Technology Luoyang 471003 China School of Measurement and Communication Engineering Harbin University of Science and Technology Harbin 150080 China

Aiming at the problem of composite fault feature extraction of automotive transmission shaft bearings under strong background noise interference, a feature extraction method for composite faults of automotive transmission shaft bearings of optimizing recursive variational mode extraction parameters based on spider wasp optimizer (SWO) is proposed. SWO is used to determine the optimal values of penalty factor and center frequency. The effective weight kurtosis criterion is employed to select mode components for signal reconstruction, and reduce the interference of strong background noise. The introduction of a two-dimensional Chebyshev-Logistic-Infinite collapse map increases the diversity and randomness of the population, avoids SWO falling into local optima, shortens running time, and increases fault feature coefficient. The population is divided into multiple subgroups based on fast non-dominated sorting, and an adaptive grouping strategy is adopted to accelerate the convergence speed of SWO. The simulation analyses and experimental verification results show that this method can effectively suppress the interference noise in the signal, and achieve a good balance between convergence speed and optimization accuracy. © 2025 Chinese Vibration engineering Society. All rights reserved.

关键词： automotive transmission shaft bearing composite fault feature extraction recursive variational mode extraction spider wasp optimizer

来源：评论

学校读者我要写书评

暂无评论

Correction: Hybrid GNSS time-series prediction method based on ensemble empirical mode decomposition with long short-term memory

引用

Discover Applied Sciences 2025年第2期7卷 1-2页

作者： Zhou, Yu He, Xiaoxing Wang, Shengdao Hu, Shunqiang Sun, Xiwen Huang, Jiahui School of Civil and Surveying and Mapping Engineering Jiangxi University of Science and Technology Ganzhou China Division of Geodetic Science School of Earth Sciences The Ohio State University Columbus USA School of Geography and Environment Jiangxi Normal University Nanchang China School of Geophysics and Measurement-Control Technology East China University of Technology Nanchang China

来源：评论

学校读者我要写书评

暂无评论

Deciphering mechanisms of oxygen vacancy conducting channel-based LiSiOx artificial nociceptors

引用

Vacuum 2025年 238卷

作者： Li, Zewen Shi, Yao Song, Dianyou Wang, Fang Lin, Xin Wei, Junqing Feng, Yulin Hu, Kai Sun, Han Zhang, Kailiang Tianjin Key Laboratory of Film Electronic & Communication Devices School of Integrated Circuit Science and Engineering Tianjin University of Technology Tianjin300384 China School of Materials Science and Engineering Tianjin University of Technology Tianjin300384 China Key Laboratory of the Ministry of Education for Optoelectronic Measurement Technology and Instrument Beijing Information Science and Technology University Beijing100192 China

Simulating bio-nociceptors efficiently and stably on one single device will help solve challenge of insufficient perceptual capabilities of AI systems. However, the significant challenge associated with artificial nociceptor based on single memristor device lies in the unclear working mechanism, which restricts their further development and application. In this work, the LiSiOx functional layer thickness (15 nm) was first optimized to achieve stable threshold switching behavior (>1000 cycles) and proposed a multi-state oxygen vacancy conducting channel mechanism, systematically explaining the simulation of four nociceptive characteristics. Firstly, LiSiOx layer thickness was optimized and realized stable threshold switching behavior under 100 cycles and excellent endurance (>1000) with 15 nm thickness functional layer. Then, the sensitization degree achieved 300 % which as the key feature of nociceptors, and other features including threshold, adaptation, and relaxation were also simulated. More importantly, a multi-state oxygen vacancy conducting channels working mechanism was proposed to explain the four nociceptive simulation behaviors. This research established a foundation for investigating the working mechanisms of artificial nociceptor based on the oxygen vacancies conductive behavior and paved the way for developing intelligent human-computer interaction technology by building perceptual bio-electronic devices. © 2025 Elsevier Ltd

关键词： Artificial nociceptor Conduction mechanism LiSiOx Thickness optimized

来源：评论

学校读者我要写书评

暂无评论

Embodied Intelligence Empowering Customized Manufacturing: Architecture, Opportunities, and Challenges

引用

IEEE Access 2025年 13卷 92740-92755页

作者： Jinbiao Tan Jianhua Shi Ligang Wu Baotong Chen Hao Tang Chunhua Zhang Wujie Zhang Shiyong Wang Jiafu Wan School of Mechanical and Automotive Engineering South China University of Technology Guangzhou China School of Mechanical and Electrical Engineering Shanxi Datong University Datong China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Wuhan China Key Laboratory of Metallurgical Equipment and Control Technology Ministry of Education Wuhan University of Science and Technology Wuhan China School of Information and Communication Engineering Hainan University Haikou China

With the continued advancement of Artificial Intelligence (AI) technology in Customized Manufacturing (CM), the current intelligence model, which separates ‘perception’ from ‘execution,’ lacks adaptability and generalizability. Embodied Intelligence (EI), an emerging technology emphasizing real-time environmental interaction and feedback, is expected to enable integrated intelligent manufacturing systems characterized by ‘perception-cognition-execution-feedback,’ enhancing the performance and intelligence of multifactor systems like the Internet of Manufacturing Things (IoMT), equipment management, and resource scheduling. However, current AI systems in CM remain isolated and lack methods for environmental interaction with multi-source perception and feedback, hindering the development of autonomous, evolving intelligent systems. To address the environmental interaction bottlenecks among diverse production elements in CM, this paper proposes a Circular Embodied Intelligence Manufacturing (CEIM) architecture aimed at enabling the fusion of heterogeneous production-element information. The objective is to enhance environmental perception and establish autonomous system evolution mechanisms, thereby optimizing production decision-making. By integrating sensor data and AI model outputs, and leveraging the advanced reasoning capabilities of large language models (LLMs), CEIM facilitates the semantic fusion of multiple production elements—including IoMT, intelligent devices, and manufacturing resources—to enable the deployment of EI applications in CM. The implementation of CEIM is illustrated and validated through a case study on a customized gift box packaging platform. Finally, this paper discusses the opportunities and challenges of applying EI in manufacturing and aims to provide insights into the future development of EI-oriented manufacturing systems.

关键词： Manufacturing Production Artificial intelligence Computer architecture Decision making Data models Collaboration Robot sensing systems Optimization Job shop scheduling

来源：评论

学校读者我要写书评

暂无评论

Sea ice type identification method based on MEMS sensor network combined with PCA-BPMIV-GRU

引用

IEEE Transactions on Instrumentation and measurement 2025年

作者： Yang, Le Quan, Xiyu Zhang, Jiankui Liu, Yunjing Zhao, Shiqi Fu, Changzeng Zhan, Zhikun Li, Lianliang Lv, Xiaoyong Zhao, Yuliang Northeastern University at Qinhuangdao Hebei Key Laboratory of MicroNano Precision Optical Sensing and Measurement Technology The School of Control Engineering Qinhuangdao066004 China Northeastern University at Qinhuangdao College of Control Science and Engineering Qinhuangdao066099 China Northeastern University at Qinhuangdao College of Computer Science and Engineering Qinhuangdao066004 China

Sea ice poses a significant hazard to vessels navigating in high-latitude maritime regions. To effectively prevent the collision between ships and large sea ice (such as icebergs) and other similar accidents, it is crucial to identify sea ice and its types in a timely and accurate manner. However, traditional sea ice identification techniques, such as optical and radar remote sensing, are often limited by visibility conditions, suffering from poor accuracy, high measurement costs, and low identification efficiency. This paper proposes a sea ice identification method based on a vibration sensor network, combined with the PCA-BPMIV-GRU strategy, which achieves low cost, high efficiency, and high accuracy in sea ice type detection. Firstly, a cost-effective MEMS vibration sensor network is deployed to capture vibration information of sea ice. The data collected from six sensors at different locations at the same time are treated as independent samples to construct a dataset, which contains time-frequency domain characteristic data of three sea-ice types: broken ice, flat ice, and open water. Secondly, the dimension reduction and feature optimization of vibration data were carried out by combining Principal Component Analysis (PCA) and the improved Mean Influence Value Optimization algorithm (BPMIV). This integration of unsupervised and supervised algorithms effectively eliminated unnecessary feature information, significantly improving model identification efficiency. Finally, seven commonly used classification algorithms are compared for the identification of three types of sea ice, evaluating their identification accuracy and efficiency under different dimensionality reduction methods. The results confirm that the Gated Recurrent Unit (GRU) model achieves the best comprehensive performance. Experimental data shows that the proposed method reduces the number of features to 9, resulting in a 24.2 % decrease in parameters compared to the GRU model alone, while achieving

关键词： Frequency domain analysis

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：