检索结果-内蒙古大学图书馆

CRNet: A Fast Continual Learning Framework With Random Theory

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

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

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

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

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

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

A hybrid SNN-STLSTM method for human error assessment in the high-speed railway system

引用

ADVANCED ENGINEERING INFORMATICS 2024年 60卷

作者： Zhou, Jian-Lan Guo, Zhi-Ming Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Hubei Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Wuhan 430074 Hubei Peoples R China Shenzhen Huazhong Univ Sci & Technol Res Inst Shenzhen 518057 Peoples R China

Over the years, many state-of-the-art technologies have reinforced safety in the high-speed railway driving process. However, the accident rate has not dropped significantly with the advanced technology onboard. The leading cause of this phenomenon is adverse human performance. The crucial aspects contributing to human performance are performance shaping factors (PSFs). The existing expert judgment techniques evaluate human error probabilities depending on the descriptions of PSFs' influences on human performance. However, they cannot perform dynamic human error assessment with the real-time fluctuations of PSF interventions. To overcome this deficiency, we propose a deep learning -based method considering the instantaneous effect and time -dependent influence of PSF interventions on human performance and matching different neural network characteristics to human cognitive processes. The proposed SNN-STLSTM method combines the spiking neural network (SNN) auto -encoder and the sparse -temporal long short-term memory (STLSTM) network. The unsupervised SNN, a brain -like computational model, simulates the human brain's response when PSF interventions occur instantaneously. Meanwhile, an auto -encoder architecture integrating the unsupervised SNN makes the representations learned by SNN more meaningful. In addition, for the irregularity of PSF interventions, the standard LSTM is extended to the architecture STLSTM to predict the long-term effects of PSFs on human performance. Finally, a case study of the Wuhan-Guangzhou (WH-GZ) high-speed railway (HSR) shows how Monte Carlo simulation based on Fault Tree Analysis is used to assess and collect human error data and then how PSF and human error data are used to train the whole framework. The comparative experiment and ablation study indicate that the proposed SNN-STLSTM method outperforms other artificial intelligence approaches. This study provides insightful findings that help to understand how and what aspects affect h

关键词： Human error assessment Performance shaping factors Long short-term memory network Spiking neural network High-speed railway system

来源：评论

学校读者我要写书评

暂无评论

Distributed Two-Layer Predictive control of AC Microgrid Clusters With Communication Delays

引用

IEEE TRANSACTIONS ON SMART GRID 2025年第3期16卷 2040-2051页

作者： Yang, Tao Lai, Jingang Yu, Chang Wang, Xiaoping Xiao, Qiang Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Educ Minist China Wuhan 430074 Peoples R China Wuhan Univ Sci & Technol Sch Informat Sci & Engn Wuhan 430000 Peoples R China

This paper proposes a two-layer distributed network predictive control strategy for AC microgrids (MGs) clusters with communication delays. The strategy involves establishing a two-layer communication network to regulate the voltage/frequency of all distributed generators (DGs) within the MG cluster to predefined reference values while ensuring consistency in incremental costs across individual MGs. Furthermore, a multi-step predictive controller is designed, where delay information in the controller is replaced by the latest predictions, enabling proactive compensation for delays. Stability analysis of the closed-loop AC MG clusters is conducted and the response matching condition is derived between the second and tertiary levels. Finally, real-time simulations on an OPAL-RT platform are performed for AC MG clusters, validating the robustness of the proposed control method against communication delays.

关键词： Delays Costs Voltage control Communication networks Predictive control Pins Microgrids Frequency control Stability analysis Topology AC microgrid cluster distributed two-layer predictive control active compensation communication delay

来源：评论

学校读者我要写书评

暂无评论

Event-triggered integral sliding mode control of two-time-scale systems

引用

NONLINEAR DYNAMICS 2025年第2期113卷 1263-1277页

作者： Yu, Tian-Tian Wang, Yan-Wu Yang, Wu Lei, Yan Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Minist Educ Wuhan 430074 Peoples R China GuangXi Univ Sch Elect Engn Nanning 530004 Peoples R China Southwest Univ Sch Elect & Informat Engn Chongqing Key Lab Gener Technol & Syst Serv Robot Chongqing 400715 Peoples R China

This paper investigates the H-infinity performance of two-time-scale systems with nonlinear uncertainty and external disturbance via the event-triggered integral sliding mode control (ETISMC) strategy. To facilitate the analysis of the sliding mode surface's reachability and the design of the event-triggered (ET) integral sliding mode controller, the epsilon-dependent integral sliding function with the event-triggered mechanism is constructed. Based on H-infinity control theory, the integral sliding mode controller gain and the ET parameter matrix are co-designed through the solution of a set of linear matrix inequalities. The proposed event-triggered mechanism can avoid Zeno behavior. Furthermore, an adaptive ETISMC strategy is proposed to address the unknown upper bounds of uncertainty and external disturbance. Finally, the effectiveness, applicability, and advantages of the control strategies are verified by simulations and comparative analysis.

关键词： Two-time-scale system H-infinity performance Event-triggered mechanism Integral sliding mode control Adaptive control

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Latent Feature-Guided Multi-Step Diffusion Model for Electricity Theft Detection With Imbalanced and Missing Data

引用

IEEE TRANSACTIONS ON SMART GRID 2025年第3期16卷 2439-2450页

作者： Yang, Honggang Lian, Cheng Xu, Bingrong Ding, Ruijin Zhao, Pengbo Zeng, Zhigang Wuhan Univ Technol Sch Automat Wuhan 430074 Peoples R China Chinese Acad Sci Inst Hydrobiol State Key Lab Breeding Biotechnol & Sustainable Aq Wuhan 430072 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Educ Mini Wuhan 430074 Peoples R China

The widespread adoption of advanced metering infrastructure has provided abundant data, enabling the integration of deep learning techniques into smart grids. However, it has also led to more sophisticated and concealed methods of electricity theft. Due to the challenges posed by data imbalance and missing values caused by device malfunctions and communication issues, existing deep learning models often perform poorly. To address these issues, this paper proposes a multi-step training framework named DING, which incorporates diffusion generation, self-supervised pre-training, normalized condition imputation, and generation-balanced fine-tuning. First, sufficient balanced smart meter data is generated using a diffusion model. Second, a pre-trained encoder is trained on the generated data, extracting unbiased low-dimensional features that can be used for downstream classification tasks and as conditions to guide the training of the imputation model. Next, an imputation model is trained based on a diffusion state-space equation. Finally, fine-tuning is performed on the balanced data. Experiments on a real dataset from the State Grid Corporation of China demonstrate that the proposed method outperforms previous models for both electricity theft detection and imputation tasks.

关键词： Imputation Electricity Time series analysis Data models Smart meters Feature extraction Training Deep learning Diffusion models Mathematical models Diffusion model electricity theft detection imbalanced data time series imputation

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

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

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：