检索结果-内蒙古大学图书馆

An Aggregated Convolutional Transformer Based on Slices and Channels for Multivariate Time Series Classification

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2023年第3期7卷 768-779页

作者： Wu, Yupeng Lian, Cheng Zeng, Zhigang Xu, Bingrong Su, Yixin Wuhan Univ Technol Sch Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan Peoples R China Educ Minist China Key Lab Image Proc & Intelligent Control Wuhan Peoples R China

Convolutional neural network has achieved remarkable success, and has excellent local feature extraction ability. Similarly, Transformer has been developed markedly in recent years, achieving excellent representation capabilities in terms of global features, which has aroused heated discussions. In terms of multivariate time series classification, most previous networks had convolution and long and short-term memory structures. This paper innovatively proposes a combination of Transformer-encoder and convolutional structures, which we refer to as the Multivariate time series classification Convolutional Transformer Network (MCTNet). The different advantages of convolutional neural network and self-attention are used to capture potential deep information in multivariate time series more accurately. The Transformer is considered to be data-hungry, and combined with the induction bias of the convolutional neural network to solve this problem, early features are extracted through the convolutional layers, and the both squeeze and excitation convolution encoder (BC-Encoder) structure is proposed. Attentional prototype learning is also used to mitigate the limited label problem. Moreover, a new network design that focuses on slices and channels is proposed, moving beyond the concept that the use of Transformer will require many parameters. Experimental results from 26 datasets of the well-known multivariate time series archive UEA show that the performance of our model is better than that of most state-of-the-art models.

关键词： Time series analysis Transformers Convolution Feature extraction Deep learning Convolutional neural networks Prototypes Convolutional Neural Network Transformer Encoder Slices and Channels Multivariate Time Series Classification

来源：评论

学校读者我要写书评

暂无评论

Discrete-Time controllability of Cartesian Product Networks

引用

IEEE TRANSACTIONS ON SIGNAL AND INFORMATION processing OVER NETWORKS 2024年 10卷 868-880页

作者： Liu, Bo Hu, Mengjie Huang, Junjie Zhang, Qiang Chen, Yin Su, Housheng Minzu Univ China Sch Informat Engn Minist Educ Key Lab Intelligent Anal & Secur Gover Beijing 100081 Peoples R China Inner Mongolia Univ Sch Math Sci Hohhot 010021 Peoples R China Univ Strathclyde Dept Elect & Elect Engn Glasgow City G1 1XW Scotland Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Image Proc & Intelligent Control Key Lab Educ Mini Autonomous Intelligent Unmanned Syst Engn Res Ctr Wuhan Peoples R China

This work studies the discrete-time controllability of a composite network formed by factor networks via Cartesian products. Based on the Popov-Belevitch-Hautus test and properties of Cartesian products, we derive the algebra-theoretic necessary and sufficient conditions for the controllability of the Cartesian product network (CPN), which is devoted to carry out a comprehensive study of the intricate interplay between the node-system dynamics, network topology and the controllability of the CPN, especially the intrinsic connection between the CPN and its factors. This helps us enrich and perfect the theoretical framework of controllability of complex networks, and gives new insight into designing a valid control scheme for larger-scale composite networks.

关键词： controllability Complex networks Observability Network systems Laplace equations Information processing Topology System performance Stability analysis Power system dynamics Cartesian product networks composite networks

来源：评论

学校读者我要写书评

暂无评论

CRNet: A Fast Continual Learning Framework With Random Theory

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2023年第9期45卷 10731-10744页

作者： Li, Depeng Zeng, Zhigang Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Inst Artificial Intelligence Wuhan 430074 Peoples R China Minist China Key Lab Image Proc & Intelligent Control Educ Wuhan 430074 Peoples R China

Artificial neural networks are prone to suffer from catastrophic forgetting. Networks trained on something new tend to rapidly forget what was learned previously, a common phenomenon within connectionist models. In this work, we propose an effective and efficient continual learning framework using random theory, together with Bayes' rule, to equip a single model with the ability to learn streaming data. The core idea of our framework is to preserve the performance of old tasks by guiding output weights to stay in a region of low error while encountering new tasks. In contrast to the existing continual learning approaches, our main contributions concern (1) closed-formed solutions with detailed theoretical analysis;(2) training continual learners by one-pass observation of samples;(3) remarkable advantages in terms of easy implementation, efficient parameters, fast convergence, and strong task-order robustness. Comprehensive experiments under popular image classification benchmarks, FashionMNIST, CIFAR-100, and imageNet, demonstrate that our methods predominately outperform the extensive state-of-the-art methods on training speed while maintaining superior accuracy and the number of parameters, in the class incremental learning scenario. Code is available at https://***/toil2sweet/CRNet.

关键词： Catastrophic forgetting continual learning incremental learning randomized learning technique random vector functional-link network

来源：评论

学校读者我要写书评

暂无评论

Improved genetic algorithm based on time windows decomposition for solving resource-constrained project scheduling problem

引用

AUTOMATION IN CONSTRUCTION 2022年第0期142卷

作者： Hua, Zhengming Liu, Zhenyuan Yang, Lijing Yang, Liu Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Educ Minist Image Proc & Intelligent Control Key Lab Wuhan 430074 Peoples R China

The resource-constrained project scheduling problem (RCPSP) is one of the project scheduling problems which are widely used in construction and many industrial disciplines. The challenge of the problem is to design some appropriate search mechanism for finding solutions in feasible space. An improved genetic algorithm based on time window decomposition is proposed in this paper. Three derivation methods are applied to increase population diversity. The sampling count allocation strategy and the use of destructive lower bounds improve the search efficiency. The computational experiments on PSPLIB show that the proposed approach is more effective than that only using the decomposition mechanism and is competitive in solving two real-life cases. This research illustrates that continuously changing the search subspaces has potential advantages, which may be useful for studying RCPSP using other evolutionary algorithms in future. Some other better results may be obtained by using machine learning methods to flexibly determine the sampling times for each individual.

关键词： Project scheduling Resource constrained Decomposition-based approach Genetic algorithm Extended serial scheduling scheme

来源：评论

学校读者我要写书评

暂无评论

Finite-Time Output Synchronization for Output-Coupled Reaction-Diffusion Neural Networks With Directed Topology

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2022年第3期9卷 1386-1394页

作者： Qiu, Qian Su, Housheng Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Hongshan 430074 Peoples R China Key Lab Image Proc & Intelligent Control Educ Min Wuhan 430074 Peoples R China

For output-coupled reaction-diffusion neural networks (RDNNs), the finite-time output synchronization (FTOS) issue is researched under directed topology in this paper. By virtue of the Lyapunov approach, inequality skills and important lemmas, the feedback control protocol is designed to obtain the FTOS criterion for coupled RDNNs with output coupling. Furthermore, to ensure that the output-coupled RDNNs realize output synchronization in finite time, a novel adaptive coupling weights control strategy and output feedback controller are proposed. Finally, the relevant simulation results are presented to demonstrate the correctness of our obtained theorems respectively.

关键词： Synchronization Couplings Topology Artificial neural networks Network topology Protocols Adaptive control FTOS directed topology coupled RDNNs output coupling adaptive coupling weights

来源：评论

学校读者我要写书评

暂无评论

ParamCrop: Parametric Cubic Cropping for Video Contrastive Learning

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2023年 25卷 9002-9014页

作者： Qing, Zhiwu Huang, Ziyuan Zhang, Shiwei Tang, Mingqian Gao, Changxin Jin, Rong Ang Jr, Marcelo H. Sang, Nong Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Natl Univ Singapore Adv Robot Ctr Singapore 119077 Singapore Alibaba Grp Hangzhou 311100 Peoples R China

The central idea of contrastive learning is to discriminate between different instances and force different views from the same instance to share the same representation. To avoid trivial solutions, augmentation plays an important role in generating different views, among which random cropping is shown to be effective for the model to learn a generalized and robust representation. Commonly used random crop operation keeps the distribution of the difference between two views unchanged along the training process. In this work, we show that adaptively controlling the disparity between two augmented views along the training process enhances the quality of the learned representations. Specifically, we present a parametric cubic cropping operation, ParamCrop, for video contrastive learning, which automatically crops a 3D cubic by differentiable 3D affine transformations. ParamCrop is trained simultaneously with the video backbone using an adversarial objective, so that it learns to increase the contrastive loss and thus gradually reduces the shared contents between two cropped views. Experiments show that this adaptive and gradual increase in the disparity yielded by ParamCrop is beneficial to learning a strong and generalized representation for downstream tasks, which is shown to be effective on multiple contrastive learning frameworks and video backbones.

关键词： Parametric cropping contrastive learning video representation learning

来源：评论

学校读者我要写书评

暂无评论

Distributed predefined-time algorithms for optimal solution seeking in multi-agent systems subject to input disturbances

引用

AUTOMATICA 2025年 174卷

作者： Xu, Jing-Zhe Liu, Zhi-Wei Ge, Ming-Feng Yang, Tao Chi, Ming He, Dingxin Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Minist Educ Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Minist Educ Wuhan 430074 Peoples R China China Univ Geosci Sch Mech Engn & Elect Informat Wuhan 430074 Peoples R China Northeastern Univ State Key Lab Synthet Automat Proc Ind Shenyang 110819 Peoples R China

This paper presents a novel incremental consensus-based algorithm for solving a class of distributed optimization problems in multi-agent systems, considering input disturbances, equality constraints, and box constraints. Traditional methods rely on average consensus to maintain the satisfaction of equality constraints throughout the entire evolution process. However, in practical applications, input disturbances can disrupt these equality constraints, rendering traditional methods ineffective. To address this challenge, the proposed algorithm combines integration sliding mode control technology with the observer methodology, creating a unified framework capable of handling input disturbances and preventing the system state from deviating beyond the solution space defined by the equality and box constraints. Moreover, the proposed algorithm offers the advantage of ensuring that all agents reach the optimal solution within a predefined time frame. This settling time can be directly adjusted by modifying one or more parameters. Finally, several numerical examples are validated to demonstrate the effectiveness and performance of the proposed algorithm. (c) 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.

关键词： Distributed optimization Disturbance rejection Predefined-time convergence Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

Optimal Decisions in the Closed-Loop Supply Chain considering Capacity Constraints and Stochastic Demand under the Cap-and-Trade Regulation

引用

COMPLEXITY 2022年第0期2022卷

作者： Wang, Jian Shao, Wenxuan Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Minist Educ Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China

In the current context of resource scarcity and increased pollution, enterprises need to better allocate capacity and achieve carbon emission reduction. We examine the optimal decision problem for a closed-loop supply chain (CLSC) considering capacity constraints and stochastic demand under a cap-and-trade system. A two-level CLSC comprising a supplier and a manufacturer is established. To make the model more realistic, we treat demand as a random variable, consider the manufacturer's production capacity within a certain upper limit, and allow the manufacturer to make investments to expand capacity to complete production demand. Based on this CLSC, the collection activities of the supplier and manufacturer are considered. Meanwhile, government carbon limits and carbon trading controls on the manufacturer are considered based on carbon reduction by enterprises. Through modeling and analysis, optimal decisions are derived for the amount of capacity investment, level of carbon emission reduction, and collection price variables. The results indicate that supplier collection has a positive effect on the sustainability of the CLSC. Moreover, the government's carbon quota and carbon trading control of manufacturers can effectively reduce the carbon emissions of the CLSC, encourage enterprises to reduce carbon emissions, and improve the sustainability of the CLSC.

关键词： Supply chains

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Affinity Propagation Based Natural image Matting

Multi-Task Affinity Propagation Based Natural Image Matting

引用

IEEE International Conference on image processing

作者： Renkai Zhang Nong Sang School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology China

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

image matting, aiming to accurately extract foreground objects by estimating their opacity against the background, has made remarkable progress through deep-learning approaches. Nevertheless, the majority of these methods require a user-defined auxiliary input, such as a trimap, which limits their applications in real-world scenarios. There are many auxiliary input-free methods that have been proposed by now, and some of them adopt a multi-task learning framework that includes a shared encoder and two separate decoders. However, these methods lack interactions between the two decoders, or interactions are implemented through simple summation or concatenation. Unfortunately, the integration of different features may cause negative transfer and limit the model performance due to the invisible information transmission process. To address the issue, we introduce the Pattern-Affinitive Propagation Module (PAP) to explicitly model cross-task propagation and task-specific propagation. Furthermore, image matting not only requires high-resolution detail features, but also semantic features. However, current CNN-based methods have limited receptive fields, making it challenging to capture global semantic features. Therefore, we design a module that integrates Dilated Convolution and Spectral Transformer (DSM), which can effectively capture global features and enhance global-local feature fusion. Extensive experiments on AM-2k and P3M-10k datasets demonstrate the superiority of our method.

关键词： Fuses Computational modeling Semantics Urban areas Information processing Multitasking Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Estimation and Utilization of the Geomagnetic Field Inhomogeneities Using the Relaxation Characteristics of the FID Signal in an Overhauser Magnetometer

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2024年 73卷 1页

作者： Luo, Wang Hu, Xiangyun Dong, Haobin Ge, Jian Liu, Lichao Feng, Ke Zhang, Yongchao Huang, Lishan She, Jinhua China Univ Geosci Sch Geophys & Geomat Wuhan 430074 Peoples R China Hubei Subsurface Multiscale Image Key Lab Wuhan 430074 Peoples R China China Univ Geosci Sch Automat Wuhan 430074 Peoples R China Hubei Key Lab Adv Control & Intelligent Automat Co Wuhan 430074 Peoples R China Minist Educ Engn Res Ctr Intelligent Technol Geoexplorat Wuhan 430074 Peoples R China Univ British Columbia Sch Engn Kelowna BC Canada

Accurate measurement of geomagnetic field inhomogeneity commonly necessitates the use of two or more magnetic sensors for differential measurements, and most of the geomagnetic sensors are unusable in large inhomogeneous fields. To address these issues, this article presents a new approach for estimating the geomagnetic field's inhomogeneities based on a single Overhauser magnetometer. First, we establish the improved free induction decay (FID) signal model by integrating the phases of all protons over the entire Overhauser sensor in arbitrary inhomogeneous fields, which enables the inversion of the geomagnetic field gradient using the relaxation characteristics of the FID signal. Then, we propose a composite algorithm designed to accurately derive the relaxation parameters of the FID signal by carefully extracting and denoising its envelope and after that calculate the gradient of the geomagnetic field by the above FID signal model. Moreover, we designed a specialized Overhauser magnetic sensor prototype for measuring geomagnetic gradients and conducted experiments on a dedicated experimental platform. The designed prototype successfully measured the magnetic gradient even under high gradients of up to 10 005 nT/m, yielding a measurement error of 15.83%, with one sensor in the experiments. In addition, we employed this method to successfully detect unexploded ordnance (UXO) using the transverse relaxation time of the FID signal as an indicator. This application further validates the effectiveness and practicality of our proposed methodology.

关键词： Magnetometers Magnetic resonance imaging Sensors Nonhomogeneous media Magnetic sensors Protons Magnetization Envelope extraction free induction decay (FID) signal geomagnetic field inhomogeneity Overhauser magnetometer unexploded ordnance (UXO) detection

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：