检索结果-内蒙古大学图书馆

Prediction of transmission spectrum from photonic energy band via autoencoder network

IEEE Photonics Technology Letters 2025年

作者： Mo, Wenqin Zhu, Yaling Yin, Yuanxing Dong, Kaifeng Jin, Fang Song, Junlei China University of Geosciences School of Automation Wuhan430074 China China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China China University of Geosciences Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

Optical topological insulators, as an emerging type of photonic material, present substantial benefits for optical communication. The advanced pattern recognition capabilities of deep learning have propelled the inverse design of topological photonic structures into a hot area of research. However, existing methods encounter difficulties with the analysis of intricate band structures. Therefore, we construct a deep learning model capable of handling two-dimensional data of photonic energy band. Utilizing an autoencoder network, our model indirectly trains the photonic energy band and transmission spectrum, by converting them into feature coding. It integrates a transmission spectrum autoencoder and a photonic energy band autoencoder, processing energy band data to predict the corresponding transmission spectrum. The results indicate that compared to convolutional neural network (CNN), our model can accurately predict transmission spectrum, and perform better on both evaluation metrics of RMSE and R2. This work enhances prediction accuracy by leveraging energy band diagrams to constrain optical properties. © 1989-2012 IEEE.

关键词： Topological insulators

来源：评论

学校读者我要写书评

暂无评论

Dynamic gesture tracking using wearable data gloves with flexible FBGs

引用

Sensors and Actuators A: Physical 2025年 390卷

作者： Qian, Muyun Yan, Haitang Wang, Wanying Sun, Zelin Dong, Yaohui Wei, Xinyuan Wang, Hanbin School of Electrical and Information Engineering Anhui University of Technology Anhui Ma'anshan243002 China Anhui Province Engineering Laboratory of Intelligent Demolition Equipment Anhui Ma'anshan243032 China Key Laboratory of Multidisciplinary Management and Control of Complex Systems of Anhui Higher Education Institutes Anhui University of Technology Anhui Ma'anshan243002 China Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Anhui Hefei230009 China School of Intelligent Electromechanical Engineering Zhongyuan University of Technology Henan Zhengzhou450007 China

Existing wearable data gloves for gesture recognition often face challenges in achieving both high precision and real-time performance. To address these limitations, we propose a data glove design incorporating fiber Bragg gratings (FBGs) encapsulated in flexible materials and positioned near the interphalangeal joints. This setup enables effective gesture recognition. First, the principle of fiber grating curvature sensing is derived, followed by curvature calibration of the FBG data glove through flexible encapsulation. An experimental platform was constructed to assess the glove's performance in static and dynamic digital gesture recognition. Calibration results demonstrate a linear correlation between wavelength drift and curvature changes, with a comprehensive sensitivity of 0.0126 nm/°. Static and dynamic experimental findings confirm that the FBG sensors effectively monitor wavelength shifts induced by finger curvature variations. Analysis of different digital gestures at various time intervals revealed the wavelength offsets corresponding to the straightening and bending states of each finger. The five FBG sensors, encapsulated in flexible materials and positioned at the proximal interphalangeal joints, capture curvature changes across the five fingers, enabling accurate, real-time recognition of both static and dynamic gestures. This study highlights the potential of the developed wearable data glove for tracking and recognizing fine movements of the human hand. © 2025 Elsevier B.V.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Distributed multi-timescale algorithm for nonconvex optimization problem: A control perspective

引用

Neural Networks 2025年 186卷 107257页

作者： Shi, Xiasheng Liu, Jian Sun, Changyin School of Artificial Intelligence Anhui University Hefei230106 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China School of Automation Southeast University Nanjing210096 China

The distributed nonconvex constrained optimization problem with equality and inequality constraints is researched in this paper, where the objective function and the function for constraints are all nonconvex. To solve this problem from a control perspective, a virtual reference-based convex penalty function is added to the augmented Lagrangian function. Then, based on the primal–dual technique, a two-timescale distributed approach is designed based on the consensus scheme. The slower subsystem aims to ensure the optimality, and the faster subsystem intends to guarantee the stability. Finally, three cases are presented to illustrate the approach's effectiveness. © 2025 Elsevier Ltd

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

Utilizing semantically enhanced self-supervised graph convolution and multi-head attention fusion for herb recommendation

引用

Artificial Intelligence in Medicine 2025年 164卷 103112-103112页

作者： Tang, Xianlun Tang, Yuze Liu, Xinran Zhang, Haochuan Dang, Xiaoyuan Wang, Ying Xu, Zihui Chongqing Key Laboratory of Complex Systems and Autonomous Control Chongqing University of Posts and Telecommunications Chongqing400065 China School of Intelligent Engineering Chongqing College of Mobile Communication Chongqing401520 China Big Data and Internet of Things School Chongqing Vocational Institute of Engineering Chongqing402260 China Xinqiao Hospital Army Medical University Chongqing400037 China

Traditional Chinese herbal medicine has long been recognized as an effective natural therapy. Recently, the development of recommendation systems for herbs has garnered widespread academic attention, as these systems significantly impact the application of traditional Chinese medicine. However, existing herb recommendation systems are limited by data sparsity, insufficient correlation between prescriptions, and inadequate representation of symptoms and herb characteristics. To address these issues, this paper introduces an approach to herb recommendation based on semantically enhanced self-supervised graph convolution and multi-head attention fusion (BSGAM). This method involves efficient embedding of entities following fine-tuning of BERT;leveraging the attributes of herbs to optimize feature representation through a residual graph convolution network and self-supervised learning;and ultimately employing a multi-head attention mechanism for feature integration and recommendation. Experiments conducted on a publicly available traditional Chinese medicine prescription dataset demonstrate that our method achieves improvements of 6.80%, 7.46%, and 6.60% in F1-Score@5, F1-Score@10, and F1-Score@20, respectively, compared to baseline methods. These results confirm the effectiveness of our approach in enhancing the accuracy of herb recommendations. © 2025 Elsevier B.V.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Efficient surrogate-based optimization method and application based on collaborative improvement aggregation strategy

引用

Kongzhi yu Juece/control and Decision 2025年第6期40卷 1975-1984页

作者： Xiao, Tian-Li Wu, Feng Lin, Cheng-Long School of Management Science and Engineering Anhui University of Technology Ma’anshan243002 China Key Laboratory of Multidisciplinary Management and Control of Complex Systems of Anhui Higher Education Institutes Anhui University of Technology Ma’anshan243002 China School of Economics and Management Anhui Polytechnic University Wuhu241000 China School of Economics and Management Nanjing University of Science and Technology Nanjing210094 China

To address the problem that greedy characteristics lead to slow convergence and low accuracy problems of surrogate-based optimization solutions in the later stage, a collaborative improvement aggregation strategy is proposed, which is extended to an efficient surrogate-based optimization method for expensive black-box problems. The proposed strategy integrates probability improvement and mean improvement criteria using Chebyshev decomposition and achieves a balance between global exploration and local search capabilities through random weight coefficients. In addition, the differences between surrogate-based optimization and surrogate-assisted optimization methods are analyzed from the perspective of candidate point sets, further exploring the role of randomness in optimization design. The experimental results show that this method can effectively improve the convergence accuracy of the optimized solution in black-box problems. Compared with similar techniques, the proposed method has higher convergence accuracy and stronger robustness of optimized solutions. © 2025 Northeast University. All rights reserved.

关键词： Tabu search

来源：评论

学校读者我要写书评

暂无评论

Hand Gesture Recognition from an Open-Set Perspective

引用

IEEE Transactions on Multimedia 2025年

作者： Zhou, Jun Xu, Chi Cheng, Li China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China University of Alberta Vision and Learning Laboratory Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada

Existing hand gesture recognition methods predominantly rely on a close-set assumption, which in essence limits the viewpoints, gesture categories, and hand shapes at test time to closely resemble those seen during training. This requirement is however rarely met in practice, as images are often captured from unconstrained viewpoints, with novel gestures and unseen hand shapes that can differ significantly from the training data. This motivates us to investigate an open-set hand gesture recognition problem, where hand gestures are still recognizable from unconstrained viewpoints, and novel gesture classes and hand shapes can be incrementally learned with just a few examples. To address this, we propose a viewpoint influence elimination network that extracts view-independent features, significantly improving performance in scenarios with unconstrained viewpoints. Moreover, a joint-weighted classification scheme is introduced to augment the cosine similarity metric for evaluating few-shot incremental learning of novel gestures and shapes. Finally, as existing hand gesture recognition datasets primarily adhere to the close-set assumption, a new hand gesture recognition dataset, OHG, is introduced in this paper, that includes a wide range of viewpoints, diverse gesture classes, and distinct hand shapes. Experimental hand gesture recognition results demonstrate the superior performance of our approach in both unconstrained viewpoint and few-shot incremental learning scenarios. The source code and the OHG dataset are to be made available at https://***/zhoujun-7/OSHGR. © 1999-2012 IEEE.

关键词： Palmprint recognition

来源：评论

学校读者我要写书评

暂无评论

Rethinking iterative stereo matching from a diffusion bridge model perspective

引用

Pattern Recognition 2025年 167卷

作者： Yuguang Shi Sifan Zhou Wei Wang Xiaobo Lu School of Automation Southeast University Nanjing 210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing 210096 China

Stereo matching is vital for 3D perception in vision and robotics. Although iteration-based stereo matching has demonstrated competitive performance, it also has inherent limitations, such as the discrete nature of the iteration process, which can lose geometric structure information, and the dependence on a large number of iterations. In this paper, we present a novel iterative-based framework, named Diffusion Models for Iterative Optimization (DMIO). DMIO introduces a Time-based Update Network (T-UN) that embeds time encoding into sub-modules within the update network. This approach correlates temporal and disparity outputs and effectively integrates diffusion models into the iterative framework. This design enables DMIO to allow features containing fine details to be transmitted during the update process and can be seamlessly embedded into most iterative methods. We further design a Motion Agent Attention (MAA) module in the update network, which generates a set of attention weights for the local cost volume to filter redundant information. In addition, we introduce channel attention into the context network, which can generate more expressive features to improve accuracy. Experiments on several public benchmarks for stereo matching show that DMIO achieves over an 8.5% improvement over competing method and requires only 8 iterations to achieve state-of-the-art performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved Rao-Blackwellized particle filter for simultaneous robot localization and person-tracking with single mobile sensor

引用

控制理论与应用（英文版） 2011年第4期9卷 472-478页

作者： Kun QIAN Xudong MA Xianzhong DAI Fang FANG Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing Jiangsu 210096 China

A probabilistic algorithm is proposed for the problem of simultaneous robot localization and peopletracking （SLAP） using single onboard sensor in situations with sensor noise and global uncertainties over the observer＇s pose. By the decomposition of the joint distribution according to the Rao-Blackwell theorem, posteriors of the robot pose are sequentially estimated over time by a smoothed laser perception model and an improved resampling scheme with evolution strategies; the conditional distribution of the person＇s position is estimated using unscented Kalman filter （UKF） to deal with the nonlinear dynamic of human motion. Experiments conducted in a real indoor service robot scenario validate the favorable performance of the positional accuracy as well as the improved computational efficiency.

关键词： Mobile robot localization People tracking Rao-Blackwellized particle filter Unscented Kalman filter Service robot

来源：评论

学校读者我要写书评

暂无评论

Distributed Asymptotic Consensus in Directed Networks of Nonaffine systems With Nonvanishing Disturbance

引用

IEEE/CAA Journal of Automatica Sinica 2021年第6期8卷 1133-1140页

作者： Qingling Wang Changyin Sun School of Automation Southeast UniversityNanjing 210096 Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of EducationNanjing 210096China

In this paper the distributed asymptotic consensus problem is addressed for a group of high-order nonaffine agents with uncertain dynamics,nonvanishing disturbances and unknown control directions under directed networks.A class of auxiliary variables are first introduced which forms second-order filters and induces all measurable signals of agents’*** view of this property,a distributed robust integral of the sign of the error(DRISE)design combined with the Nussbaum-type function is presented that guarantees not only the desired asymptotic consensus,but also the uniform boundedness of all closed-loop *** with the traditional sliding mode control(SMC)technique,the main feature of our approach is that the integral operation in the proposed control algorithm is designed to be adopted in a continuous manner and ensures less chattering *** results for a group of Duffing-Holmes chaotic systems are employed to verify our theoretical analysis.

关键词： Asymptotic consensus nonaffine systems nonvanishing disturbance Nussbaum-type functions unknown control directions

来源：评论

学校读者我要写书评

暂无评论

EXPONENTIAL STABILITY OF LINEAR DISTRIBUTED PARAMETER SWITCHED systems WITH TIME-DELAY

引用

Journal of systems Science & complexity 2014年第2期27卷 263-275页

作者： BAO Leping FEI Shumin YU Lei The School of Automation and Key Laboratory of Measurement and Control of Complex Systems of Engineer-ing Southeast University The School of Mechanical and Electric Engineering Soochow University

In this paper, the exponential stability analysis for ODE switched systems with time delay is extended to distributed parameter switched systems(DPSS) in Hilbert space. For a given family of exponential stable subsystems, this paper focuses on finding conditions to guarantee the overall DPSS' exponential stability. Based on semigroup theory, by applying piecewise Lyapunov-Krasovskii functionals method incorporated average dwell time approach, sufficient conditions for exponential stability are derived. These conditions are given in the form of linear operator inequalities(LOIs)where the decision variables are operators in Hilbert space, and the stability properties depend on switching rule. Being applied to heat switched propagation equations, these LOIs are reduced to standard Linear Matrix Inequalities(LMIs). Finally, a numerical example is given to illustrate the effectiveness of the proposed result.

关键词： Exponential stability LMIs PDEs on abstract space switched systems.

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：