检索结果-内蒙古大学图书馆

GTINet: Global Topology-Aware Interactions for Unsupervised Point Cloud Registration

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2024年第7期34卷 6363-6375页

作者： Jiang, Yinuo Zhou, Beitong Liu, Xiaoyu Li, Qingyi Cheng, Cheng Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control MOE Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China

Point cloud registration is a critical task in various 3D applications. Supervised approaches are restricted by the difficulty and cost of acquiring ground-truth annotations. Thus, unsupervised point cloud registration has emerged as a promising alternative. However, existing unsupervised methods often overlook the importance of feature interactions, leading to feature matching ambiguity. To address these challenges, we propose an unsupervised point cloud registration framework termed Global Topology-aware Interactions Network (GTINet), which contains a global structural relations (GSR) module and a contextual topological interactions (CTI) module. The GSR module transforms local features into global features through global graph convolutions. Based on the obtained global features, the CTI module learns geometric feature similarities and relative positional knowledge for both the source and target point clouds. The CTI module further learns contextual feature interactions through topology-aware attention layers. By improving the discriminativeness of features, our GTINet reduces the feature matching ambiguity caused by local structural similarity. Extensive experiments demonstrate that our method achieves state-of-the-art unsupervised registration performance on the ModelNet40, 7Scene, and KITTI datasets. Our work provides a novel perspective for conducting unsupervised point cloud registration. We will release our code for future research.

关键词： Point cloud compression Feature extraction Circuits and systems Context modeling Training Three-dimensional displays Pipelines Unsupervised point cloud registration feature extraction global structural features contextual interactions

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Dynamic Process Robust Monitoring Based on Spatiotemporal Preserving Projections With Rank-Order Distance

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2023年 72卷 1页

作者： Wang, Zhaojing Yan, Xiaoyun Li, Zhenwei Pan, Xiong Wang, Yang Wuhan Text Univ Hubei Prov Engn Res Ctr Intelligent Text & Fash Sch Comp Sci & Artificial Intelligence Wuhan 430200 Hubei Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Minist Educ Wuhan 430074 Hubei Peoples R China

The prevalence of nonlinear dynamic characteristics and the interference of outliers are common occurrences in modern industrial systems. However, previous studies have inadequately considered the impact of these factors on process monitoring. This article introduces a hybrid framework, referred to as spatiotemporal preserving projections (STPPs), for fault detection in complex processes. First, the conventional global and local preserving projection (GLPP) has been modified to address the constraints of hyperparameters and improve resilience. This is accomplished by proposing a strategy based on sparse representation to automatically determine local neighborhood in the global and local weight matrices. In addition, a rank-order distance (ROD)-based index is formulated to cope with outliers in the local weight matrix construction. Second, the modified GLPP is combined with slow feature analysis (SFA) to form the STPP method. This enables simultaneous preservation of spatial and temporal data structures in dimension reduction, further enhancing monitoring accuracy. Finally, a numerical case and a wastewater treatment process demonstrate that the proposed STPP-based approach outperforms other relevant methods in fault detection.

关键词： Nonlinear dynamic process rank-order distance (ROD) robust monitoring sparse representation spatiotemporal preserving projections (STPPs)

来源：评论

学校读者我要写书评

暂无评论

Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting 38

Vision Transformer Off-the-Shelf: A Surprising Baseline for ...

引用

38th AAAI Conference on Artificial Intelligence (AAAI) / 36th Conference on Innovative Applications of Artificial Intelligence / 14th Symposium on Educational Advances in Artificial Intelligence

作者： Wang, Zhicheng Xiao, Liwen Cao, Zhiguo Lu, Hao Huazhong Univ Sci & Technol Minist Educ Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China

ISBN: (纸本)1577358872

Class-agnostic counting (CAC) aims to count objects of interest from a query image given few exemplars. This task is typically addressed by extracting the features of query image and exemplars respectively and then matching their feature similarity, leading to an extract-then-match paradigm. In this work, we show that CAC can be simplified in an extract-and-match manner, particularly using a vision transformer (ViT) where feature extraction and similarity matching are executed simultaneously within the self-attention. We reveal the rationale of such simplification from a decoupled view of the self-attention. The resulting model, termed CACViT, simplifies the CAC pipeline into a single pretrained plain ViT. Further, to compensate the loss of the scale and the order-of-magnitude information due to resizing and normalization in plain ViT, we present two effective strategies for scale and magnitude embedding. Extensive experiments on the FSC147 and the CARPK datasets show that CACViT significantly outperforms state-of-the-art CAC approaches in both effectiveness (23:60% error reduction) and generalization, which suggests CACViT provides a concise and strong baseline for CAC. Code will be available.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Safety-Critical control With control Barrier Function Based on Disturbance Observer

引用

IEEE TRANSACTIONS ON AUTOMATIC control 2024年第7期69卷 4750-4756页

作者： Sun, Jiankun Yang, Jun Zeng, Zhigang Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Educ Minist China Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Loughborough Univ Dept Aeronaut & Automot Engn Loughborough LE11 3TU Leics England

In this article, we investigate the continuous and sampled-data safety-critical control problems with control barrier functions in the presence of time-varying disturbances. To this end, a nonlinear disturbance observer is first designed to estimate the disturbance, and the continuous safe control design of the nominal systems is formulated as a quadratic program. We then design a continuous composite controller by integrating the disturbance compensation term and the state feedback term computed via solving the quadratic program, such that the undesirable influence of time-varying disturbances on both control performance and safety property can be effectively attenuated. It shows that under the proposed continuous control method, the robust safety property of dynamical systems can be strictly guaranteed in the presence of time-varying disturbances. Moreover, the results on the continuous safe control are extended into the sampled-data case, where the control input keeps the same in the intersample time intervals. A practical example of adaptive cruise control is introduced, and the simulation results are presented to verify the superiorities of the proposed control method.

关键词： Safety Dynamical systems control design Time-varying systems control systems Disturbance observers Estimation error control barrier function disturbance/uncertain estimation and attenuation nonlinear disturbance observer safety-critical control

来源：评论

学校读者我要写书评

暂无评论

Mixture of Experts for EEG-Based Seizure Subtype Classification

引用

IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING 2023年 31卷 4781-4789页

作者： Du, Zhenbang Peng, Ruimin Liu, Wenzhong Li, Wei Wu, Dongrui Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Belt & Rd Joint Lab Measurement & Control Technol Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Minist Educ Image Proc & Intelligent Contr Wuhan 430074 Peoples R China

Epilepsy is a pervasive neurological disorder affecting approximately 50 million individuals worldwide. Electroencephalogram (EEG) based seizure subtype classification plays a crucial role in epilepsy diagnosis and treatment. However, automatic seizure subtype classification faces at least two challenges: 1) class imbalance, i.e., certain seizure types are considerably less common than others;and 2) no a priori knowledge integration, so that a large number of labeled EEG samples are needed to train a machine learning model, particularly, deep learning. This paper proposes two novel Mixture of Experts (MoE) models, Seizure-MoE and Mix-MoE, for EEG-based seizure subtype classification. Particularly, Mix-MoE adequately addresses the above two challenges: 1) it introduces a novel imbalanced sampler to address significant class imbalance;and 2) it incorporates a priori knowledge of manual EEG features into the deep neural network to improve the classification performance. Experiments on two public datasets demonstrated that the proposed Seizure-MoE and Mix-MoE outperformed multiple existing approaches in cross-subject EEG-based seizure subtype classification. Our proposed MoE models may also be easily extended to other EEG classification problems with severe class imbalance, e.g., sleep stage classification.

关键词： EEG mixture of experts seizure subtype classification class imbalance

来源：评论

学校读者我要写书评

暂无评论

A Novel Sequence-to-Sequence-Based Deep Learning Model for Multistep Load Forecasting

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2025年第1期36卷 638-652页

作者： Lu, Renzhi Bai, Ruichang Li, Ruidong Zhu, Lijun Sun, Mingyang Xiao, Feng Wang, Dong Wu, Huaming Ding, Yuemin Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Minist Educ Key Lab Syst Control & Informat Proc Shanghai 200240 Peoples R China East China Univ Sci & Technol Key Lab Smart Mfg Energy Chem Proc Minist Educ Shanghai 200237 Peoples R China Wuhan Univ Sci & Technol Hubei Key Lab Mech Transmiss & Mfg Engn Wuhan 430081 Peoples R China Shanghai Elect Grp Co Ltd Cent Acad Shanghai 200070 Peoples R China Kanazawa Univ Inst Sci & Engn Kakuma Kanazawa Ishikawa 9201192 Japan Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat State Key Lab Intelligent Mfg Equipment & Technol Wuhan 430074 Peoples R China Zhejiang Univ Dept Control Sci & Engn State Key Lab Ind Control Technol Hangzhou 310027 Peoples R China North China Elect Power Univ State Key Lab Alternate Elect Power Syst Renewabl Beijing 102206 Peoples R China North China Elect Power Univ Sch Control & Comp Engn Beijing 102206 Peoples R China Minist Educ Key Lab Intelligent Control & Optimizat Ind Equip Dalian 116024 Peoples R China Dalian Univ Technol Sch Control Sci & Engn Dalian 116024 Peoples R China Tianjin Univ Ctr Appl Math Tianjin 300072 Peoples R China Univ Navarra Tecnun Sch Engn San Sebastian 20018 Spain

Load forecasting is critical to the task of energy management in power systems, for example, balancing supply and demand and minimizing energy transaction costs. There are many approaches used for load forecasting such as the support vector regression (SVR), the autoregressive integrated moving average (ARIMA), and neural networks, but most of these methods focus on single-step load forecasting, whereas multistep load forecasting can provide better insights for optimizing the energy resource allocation and assisting the decision-making process. In this work, a novel sequence-to-sequence (Seq2Seq)-based deep learning model based on a time series decomposition strategy for multistep load forecasting is proposed. The model consists of a series of basic blocks, each of which includes one encoder and two decoders;and all basic blocks are connected by residuals. In the inner of each basic block, the encoder is realized by temporal convolution network (TCN) for its benefit of parallel computing, and the decoder is implemented by long short-term memory (LSTM) neural network to predict and estimate time series. During the forecasting process, each basic block is forecasted individually. The final forecasted result is the aggregation of the predicted results in all basic blocks. Several cases within multiple real-world datasets are conducted to evaluate the performance of the proposed model. The results demonstrate that the proposed model achieves the best accuracy compared with several benchmark models.

关键词： Load modeling Predictive models Load forecasting Forecasting Autoregressive processes Data models Time series analysis Decomposition strategy long short-term memory (LSTM) neural network multistep load forecasting sequence-to-sequence (Seq2Seq) model temporal convolution network (TCN)

来源：评论

学校读者我要写书评

暂无评论

A Time-Independent control Method for Variable-Speed Load-Bearing Walking with Suspended Backpack

A Time-Independent Control Method for Variable-Speed Load-Be...

引用

第43届中国控制会议

作者： Zhiyuan He Yu Cao Yifei Guo Jian Huang Hubei Key Laboratory of Brain-inspired Intelligent Systems Key Laboratory for Image Processing and Intelligent ControlSchool of Artificial Intelligence and AutomationHuazhong University of Science and Technology

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Walking with a load brings a significant burden to human shoulders,resulting in increasing metabolic energy consumption and the risk of skeleton and muscle *** backpack has been widely conducted for load-bearing walking,but exiting time-dependent control methods and event-based control methods are unable to exploit the characteristics of human gait *** this case,a time-independent control(TIC) method capable of eliminating the time dependence and adapting to variable speed is *** on the dynamical model of human-backpack system,an assistance profile along with the parameter optimization method are introduced which allows the backpack to reduce the burden on human shoulders during load-bearing *** the simulation evaluation,the proposed TIC method is compared with an impedance controller based time-dependent method and a locked backpack,under both constant speed and variable speed *** results demonstrates that the TIC case achieves an 89.1% reduction in dynamic load on shoulder under the condition of constant speed and a 78.2% reduction under the condition of variable speed,compared with the LOCKED case.

关键词： suspended backpack load carriage time-independent control

来源：评论

学校读者我要写书评

暂无评论

A Discrete Artificial Bee Colony Algorithm for Stochastic Vehicle Scheduling

引用

Complex System Modeling and Simulation 2022年第3期2卷 238-252页

作者： Yuanyuan Li Yindong Shen Jingpeng Li Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhan 430074China Division of Computer Science and Mathematics University of StirlingStirlingFK94LAUK

Vehicle scheduling plays a profound role in public ***,stochastic vehicle scheduling may lead to more robust *** solve the stochastic vehicle scheduling problem(SVSP),a discrete artificial bee colony algorithm(DABC)is *** to the discreteness of SVSP,in DABC,a new encoding and decoding scheme with small dimensions is designed,whilst an initialization rule and three neighborhood search schemes(i.e.,discrete scheme,heuristic scheme,and learnable scheme)are devised individually.A series of experiments demonstrate that the proposed DABC with any neighborhood search scheme is able to produce better schedules than the benchmark results and DABC with the heuristic scheme performs the best among the three proposed search schemes.

关键词： public transportation stochastic vehicle scheduling discrete artificial bee colony search scheme

来源：评论

学校读者我要写书评

暂无评论

Source-Free Cluster Adaptation for Privacy-Preserving Machinery Fault Diagnosis

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2023年 72卷 1页

作者： Zhu, Mengliang Zeng, Xiangyu Liu, Jie Yang, Chaoying Zhou, Kaibo Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat MOE Key Lab Image Informat Proc & Intelligent Cont Belt & Rd Joint Lab Measurement & Control Technol Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Civil & Hydraul Engn Wuhan 430074 Peoples R China

Unsupervised domain adaptation (UDA) has been widely exploited for machinery fault diagnosis (MFD). However, existing UDA approaches always require direct access and sharing to the labeled source domain, raising privacy concerns. In this article, a practical and challenging scenario, source-free UDA (SFUDA), is considered for privacy-preserving MFD. In SFUDA, only a pretrained source model is provided for the unlabeled target domain, and the source data are inaccessible during adaptation. A novel SFUDA approach, namely source-free cluster adaptation (SF-CA), is proposed, which consists of source domain generalization (SDG) and target model adaptation (TMA). SDG aims to obtain a well-generalized source model for TMA. Specifically, the adaptive R-drop is proposed for SDG, where an entropy-aware weighted consistency training strategy is introduced to regularize dropout. TMA enforces cluster assumption for adaptation, where the structure exploration regularizations are proposed to learn structural information. Besides, selective self-training is introduced to alleviate model collapse during TMA. Finally, discriminative and tight-clustered target features can be obtained for SFUDA. Extensive experiments are conducted on three public datasets and one practical dataset. The experimental results show the effectiveness of SF-CA for privacy-preserving MFD and the feasibility of cluster assumption enforcement for SFUDA.

关键词： Cluster assumption enforcement (CAE) machinery fault diagnosis (MFD) privacy-preserving source-free unsupervised domain adaptation (SFUDA)

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation

Hierarchical Spatio-temporal Decoupling for Text-to-Video Ge...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Qing, Zhiwu Zhang, Shiwei Wang, Jiayu Wang, Xiang Wei, Yujie Zhang, Yingya Gao, Changxin Sang, Nong Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Wuhan Peoples R China Alibaba Grp Hangzhou Peoples R China Fudan Univ Shanghai Peoples R China

ISBN: (纸本)9798350353013;9798350353006

Despite diffusion models having shown powerful abilities to generate photorealistic images, generating videos that are realistic and diverse still remains in its infancy. One of the key reasons is that current methods intertwine spatial content and temporal dynamics together, leading to a notably increased complexity of text-to-video generation ( T2V). In this work, we propose HiGen, a diffusion model-based method that improves performance by decoupling the spatial and temporal factors of videos from two perspectives, i.e., structure level and content level. At the structure level, we decompose the T2V task into two steps, including spatial reasoning and temporal reasoning, using a unified denoiser. Specifically, we generate spatially coherent priors using text during spatial reasoning and then generate temporally coherent motions from these priors during temporal reasoning. At the content level, we extract two subtle cues from the content of the input video that can express motion and appearance changes, respectively. These two cues then guide the model's training for generating videos, enabling flexible content variations and enhancing temporal stability. Through the decoupled paradigm, HiGen can effectively reduce the complexity of this task and generate realistic videos with semantics accuracy and motion stability. Extensive experiments demonstrate the superior performance of HiGen over the state-of-the-art T2V methods. We have released our source code and models.

关键词：

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：