检索结果-内蒙古大学图书馆

26th International Conference on Industrial Technology, ICIT 2025

作者： Yang, Fan Huang, Yuening Zhai, Chao Zhang, Hehong China University of Geosciences School of Automation Wuhan Campus China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China Rice University George R. Brown School of Engineering and Computing HoustonTX United States Fuzhou University School of Computer and Data Science Fuzhou China

ISBN: (纸本)9798331521950

This paper presents an interactive motion control method based on reinforcement learning, designed to assist children with autism who have social motor impairments through a mirror game intervention. The virtual teacher uses the Deep Deterministic Policy Gradient (DDPG) algorithm to optimize its actions, guiding the participant to follow a Lissajous trajectory. To ensure safety, a motion-correction mechanism was developed, which automatically adjusts actions when the predicted trajectory surpasses predefined safety boundaries. The reward function considers both the distance between the virtual teacher and the target trajectory, as well as the distance between the virtual teacher and the participant, with dynamic adjustments applied by the motion-correction mechanism. Experimental results demonstrate that the virtual teacher effectively guides the participant towards the target trajectory while adhering to safety constraints. © 2025 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Windowed Visibility Graph Fourier Transform and its Application in Gearbox Composite Fault Diagnosis

SSRN

引用

SSRN 2024年

作者： Gao, Yiyuan Chen, Mang Yu, Dejie Du, Wenliao Gong, Xiaoyun Henan Provincial Key Laboratory of Intelligent Manufacturing of Mechanical Equipment Zhengzhou University of Light Industry Zhengzhou450002 China Henan International Joint Laboratory of Complex Mechanical Equipment Intelligent Monitoring and Control Zhengzhou University of Light Industry Zhengzhou450002 China State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan University Changsha410082 China

The essence of gearbox composite fault diagnosis lies in the effective isolation of distinct fault components. Building upon this, the windowed visibility graph Fourier transform (WVGFT) is incorporated into the analysis of gearbox vibration signals. Since the gear and bearing fault components are respectively projected onto the low-order and high-order regions by WVGFT, they can be reconstructed by the corresponding vertex-graph spectrum coefficients. For a more effective extraction of fault components in gearboxes, the low-order threshold of the extracted gear fault component is optimized using the artificial fish swarm, and the high-order threshold of the extracted bearing fault component is optimized by the change rate of signal kurtosis. Finally, the Hilbert envelope demodulation analysis is applied for diagnosing the gear and bearing faults in gearboxes. The validity of our presented approach is fully confirmed through the simulation and experimental signals. © 2024, The Authors. All rights reserved.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Fast and Accurate Mapping Method for OPGW Tower Based on M-OTDR 22

Fast and Accurate Mapping Method for OPGW Tower Based on M-O...

引用

22nd International Conference on Optical Communications and Networks, ICOCN 2024

作者： Ruofan, Wang Hongren, Li Xinying, Zhao Shuai, Tong Ningmu, Zou Xuping, Zhang Huanhuan, Liu Fei, Xiong Yixin, Zhang College of Engineering and Applied Sciences Nanjing University Nanjing210023 China Nanjing University Key Laboratory of Intelligent Optical Sensing and Manipulation Nanjing210093 China School of Information Science and Engineer Shandong University Qingdao266237 China Shcnzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Inner Mongolia DT Electric Power Design Hohhot010010 China

ISBN: (纸本)9798350367652

This paper describes how distributed optical fiber sensing (DOFS) technology, combined with dark optical fibers within the current optical fiber composite overhead ground wire (OPGW), enables online monitoring and early warning of abnormalities in high-voltage overhead transmission lines. Achieving this goal requires an accurate mapping of the optical cable length to the actual GPS coordinates of the tower. The current tower positioning techniques have drawbacks like low identification rates, high positioning variation, and long calibration times. They are also restricted by particular weather conditions. This study presented a multi-parametric optical time domain reflectance sensing (M-OTDR) system that synchronizes the monitoring of temperature, strain, vibration, and other physical parameters along the fiber optic cable in order to address these problems. Additionally, the study proposed four reference positioning functions. An in-field test was carried out on a 220kV high-voltage transmission line in Fujian Province, PRC. The results showed that the proposed method could guarantee speedy and accurate placement of high-voltage overhead transmission line towers. © 2024 IEEE.

关键词： Optical fibers

来源：评论

学校读者我要写书评

暂无评论

St-Tnet: An Spatio-Temporal Joint Transformer Network for Csi Feedback in Fdd-Mimo Systems

SSRN

引用

SSRN 2024年

作者： Wang, Linyu Cao, Yize Xiang, Jianhong Harbin Engineering University China College of Information and Communication Engineering Harbin Engineering University Harbin150001 China Key Laboratory of Advanced Ship Communication and Information Technology Harbin Engineering University Harbin150001 China Agile and Intelligent Computing Key Laboratory Chengdu610000 China

In recent years, deep learning methods have been shown to have strong potential and superiority in reducing channel state information (CSI) feedback overhead and further improving feedback accuracy to maximize the performance benefits of massive MIMO in frequency division duplex (FDD) mode. As the CSI matrices are transformed into sequences for input to the Transformer model, the rearrangement leads to the loss of the original physical location relationships. Based on this problem, this paper proposes a transformer decoder based on spatio-temporal joint (ST-T). We employ a spatial attention mechanism to compensate for this information loss and focus on key spatial features more accurately, further exploiting the potential of single- and two-layer transformers in reconstructing CSI matrices. The results are validated by simulations based on DCRNet and CLNet encoders, which show that higher performance can be achieved with lower computational load compared to other lightweight models. © 2024, The Authors. All rights reserved.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

Vibration absorption of parallel-coupled nonlinear energy sink under shock and harmonic excitations

引用

Applied Mathematics and Mechanics(English Edition) 2021年第8期42卷 1135-1154页

作者： Jian’en CHEN Wei ZHANG Jun LIU Wenhua HU Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical EngineeringTianjin University of TechnologyTianjin 300384China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of TechnologyTianjin 300384China Beijing Key Laboratory of Nonlinear Vibrations and Strength of Mechanical Structures College of Mechanical EngineeringBeijing University of TechnologyBeijing 100124China

Nonlinear energy sink(NES)can passively absorb broadband energy from primary *** multiple NESs connected in parallel exhibit superior performance to single-degree-of-freedom(SDOF)*** this work,a linear coupling spring is installed between two parallel NESs so as to expand the application scope of such vibration *** vibration absorption of the parallel and parallel-coupled NESs and the system response induced by the coupling spring are *** results show that the responses of the system exhibit a significant difference when the heavier cubic oscillators in the NESs have lower stiffness and the lighter cubic oscillators have higher ***,the efficiency of the parallel-coupled NES is higher for medium shocks but lower for small and large shocks than that of the parallel *** parallel-coupled NES also shows superior performance for medium harmonic excitations until higher response branches are *** performance of the parallel-coupled NES and the SDOF NES is *** is found that,regardless of the chosen SDOF NES parameters,the performance of the parallel-coupled NES is similar or superior to that of the SDOF NES in the entire force range.

关键词： coupling influence nonlinear energy sink(NES) vibration absorption

来源：评论

学校读者我要写书评

暂无评论

Cascaded adaptive aberration-eliminating multimode fiber imaging

引用

advanced Photonics 2025年第02期 135-143页

作者： Zhong Wen Qilin Deng Quanzhi Li Yizhou Tan Jingshan Zhong Chiming Zhang Jiahe Zhang Clemens F.Kaminski Ying Gu Xu Liu Qing Yang Zhejiang University College of Optical Science and Engineering State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University International Research Center for Advanced Photonics Zhejiang University ZJU-Hangzhou Global Scientific and Technological Innovation Center Chinese PLA General Hospital The First Medical Center Department of Laser Medicine Chinese PLA General Hospital Hainan HospitalLaser Medicine Center Zhejiang Laboratory Research Center for Intelligent Manufacturing Computing University of Cambridge Department of Chemical Engineering and Biotechnology

In vivo microscopic imaging inside a biological lumen such as the gastrointestinal tract, respiratory airways, or within blood vessels has faced significant technological challenges for decades. A promising candidate technology is the multimode fiber(MMF) endoscope, which enables minimally invasive diagnostics at a resolution reaching the cellular level. However, for in vivo imaging applications deep inside a biological lumen, sample-induced aberrations and the dynamic dispersion in the MMF make the MMF endoscope a chaotic system with many unknowns, where multiple minor fluctuations can couple and compound into intractable problems. We introduce a dynamically encoding, cascaded, optical, and ultrathin polychromatic light-field endoscopy(DECOUPLE) to tackle this challenge. DECOUPLE includes an adaptive aberration correction that can accurately track and control MMF behavior in the spatial-frequency domain to compensate for chaos introduced during complex dynamic imaging processes. We demonstrate the flexibility and practicality of DECOUPLE for noninvasive volumetric imaging in two colors for light passing through various highly aberrating samples including 120-μm-thick onion epidermal slices and 80-μm-thick layers of fat emulsions. To summarize, we represent a significant step toward practical in vivo imaging deep within biological tissue.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Aspect-Level Sentiment Classification of Chinese Patient Comments Based on Pre-trained Sentiment Embedding

Aspect-Level Sentiment Classification of Chinese Patient Com...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Shan, Yongxue Zhong, Zhaoqian Che, Chao Jin, Bo Wei, Xiaopeng Dalian University Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian China Dalian University of Technology School of Innovation and Entrepreneurship Dalian China School of Computer Science and Technology Dalian University of Technology Dalian China

ISBN: (纸本)9781665401265

With the development of information technology, online health care service platforms have collected a large amount of patient comment information. Through fine-grained sentiment classification of this information, we can provide references for patients to seek medical treatment and help doctors understand their work. Therefore, we proposed a model that integrated pre-trained emotional information and semantic information at the word and character level for aspect-level sentiment classification. Specifically, we employed adversarial learning for training sentiment word embeddings and the two-layer bidirectional long short-term memory network to extract the sentiment embedding of the entire sentence in a specific aspect. We also combined the pre-trained sentiment feature vector with the structured semantic information by linear weighting and the multi-head self-attention mechanism, enabling the model to pay more attention to the information most relevant to a given aspect category. We performed experiments on the Chinese patient comments data set constructed by our research team and the proposed model outperformed the state-of-the-art methods, which proved the effectiveness of the proposed model for aspect-level sentiment classification of Chinese patient comments. © 2021 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

design of low-weight, small-size and high-efficiency equalization circuits based on switched-capacitors 4

Design of low-weight, small-size and high-efficiency equaliz...

引用

2022 4th International Conference on Electronic Engineering and Informatics, EEI 2022

作者： Ding, Yanhong Zhao, Xin Li, Kun Liu, Qing Shi, Gengxin School of Integrated Circuit Science and Engineering Tianjin University of Technology Tianjin China Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin University of Technology Tianjin China China Electronics Technology Group Corporation Tianjin China

ISBN: (纸本)9783800759231

An any cell to any cell equalization circuit, which is based on switched capacitors and energy bus, is proposed in this paper. In this equalization topology, any high voltage cell can directly transfer the power to any low voltage cell through energy bus. With the increasing miniaturisation and integration of circuit boards, the topology proposed in this paper reduces the size of the circuit by varying the capacitance and frequency in order to further reduce the area and weight of the circuit. At the same time compared with the equalization circuit using transformers or inductance devices, this circuit has the characteristics of low cost, low-weight, small-size, easy integration and simple control scheme and it is suitable for applictions such as aerospace and unmanned aerial vehicles. The feasibility of the circuit topology is verified by formula demonstration and simulation results. © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： Cells

来源：评论

学校读者我要写书评

暂无评论

EKIGCN: External Knowledge Injected Graph Convolutional Networks for Aspect-based Sentiment Analysis

EKIGCN: External Knowledge Injected Graph Convolutional Netw...

引用

IEEE International Conference on Cloud computing and Intelligence Systems (CCIS)

作者： Xuefeng Shi Min Hu Fuji Ren Piao Shi Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology Hefei China University of Electronic Science and Technology of China Chengdu Sichuan China

Aspect-based sentiment analysis (ABSA) is a challenging subtask in the natural language processing community, which aims to determine the sentiment polarity about the corresponding specific aspect terms. In existing works, external knowledge has been proven effective to improve the ABSA tasks’ performance. However, it is still essential to study further to find a universal method for ABSA tasks. Therefore, we propose an external knowledge-injected graph convolutional network (EKIGCN) to enhance the sentiment representation with commonsense. Specifically, Sentic Net is leveraged to provide external knowledge to construct an affective dependency graph. In order to fully exploit the effectiveness of affective knowledge, a shallow mutual interaction is utilized to fuse the learned contextual representation and the graph. Besides, to make EKIGCN sensitive to aspect terms, an aspect-aware multi-head attention module is also employed to enhance the corresponding relations between aspect and contextual words. Extensive experiments are conducted on three popular datasets to validate the effectiveness of our proposed model, and the results outperform the mentioned state-of-the-art methods in ABSA tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Constrained Probabilistic Pareto Dominance for Expensive Constrained Multiobjective Optimization Problems

引用

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： Zhang, Zhiyao Wang, Yong Sun, Guangyong Pang, Tong Tang, Ke School of Automation Central South University Changsha China State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle Hunan University Changsha China Guangdong Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering and the Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China

This paper proposes a new parameterless constraint-handling technique, named constrained probabilistic Pareto dominance (CPPD), for expensive constrained multiobjective optimization problems (CMOPs). In CPPD, when comparing two solutions, in terms of each original objective, we design a new objective for each solution, which is the negative product of two probabilities calculated based on the predicted fitness mean values and the uncertainty information provided by Kriging models: 1) the probability that this solution satisfies all constraints, denoted as PoF, and 2) the probability that this solution is better than the other on the original objective, denoted as PoB. It is evident that for each solution, PoF and PoB indicate its feasibility and its optimality on the corresponding original objective, respectively. Then, Pareto dominance based on new objectives is executed. As a result, both competitive feasible solutions and promising infeasible solutions with good diversity can be preserved by CPPD. These two kinds of solutions can help the population to exploit the located feasible parts and to explore new feasible parts, respectively. Further, based on CPPD, we develop a Pareto-based Kriging-assisted constrained multiobjective evolutionary algorithm (called PEA) to deal with expensive CMOPs with two or three objectives. Finally, PEA is generalized to solve expensive constrained many-objective optimization problems, named PEA+. The effectiveness of CPPD, PEA, and PEA+ is verified by comprehensive experiments. IEEE

关键词： Evolutionary 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：