检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Qu, Jingxiang Liu, Ryan Wen Zhao, Chenjie Guo, Yu Xu, Sendren Sheng-Dong Zhu, Fenghua Lv, Yisheng The Hubei Key Laboratory of Inland Shipping Technology School of Navigation Wuhan University of Technology Wuhan430063 China The State Key Laboratory of Maritime Technology and Safety Wuhan430063 China The Automation and Control Center The Graduate Institute of Automation and Control National Taiwan University of Science and Technology Taipei106335 Taiwan The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

The accurate and efficient vessel draft reading (VDR) is an important component of intelligent maritime surveillance, which could be exploited to assist in judging whether the vessel is normally loaded or overloaded. The computer vision technique with an excellent price-to-performance ratio has become a popular medium to estimate vessel draft depth. However, the traditional estimation methods easily suffer from several limitations, such as sensitivity to low-quality images, high computational cost, etc. In this work, we propose a multi-task learning-enabled computational method (termed MTL-VDR) for generating highly reliable VDR. In particular, our MTL-VDR mainly consists of four components, i.e., draft mark detection, draft scale recognition, vessel/water segmentation, and final draft depth estimation. We first construct a benchmark dataset related to draft mark detection and employ a powerful and efficient convolutional neural network to accurately perform the detection task. The multi-task learning method is then proposed for simultaneous draft scale recognition and vessel/water segmentation. To obtain more robust VDR under complex conditions (e.g., damaged and stained scales, etc.), the accurate draft scales are generated by an automatic correction method, which is presented based on the spatial distribution rules of draft scales. Finally, an adaptive computational method is exploited to yield an accurate and robust draft depth. Extensive experiments have been implemented on the realistic dataset to compare our MTL-VDR with state-of-the-art methods. The results have demonstrated its superior performance in terms of accuracy, robustness, and efficiency. The computational speed exceeds 40 FPS, which satisfies the requirements of real-time maritime surveillance to guarantee vessel traffic safety. Copyright © 2023, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Joint Masked Reconstruction and Contrastive Learning for Mining Interactions Between Proteins

arXiv

引用

arXiv 2025年

作者： Li, Jiang Wang, Xiaoping School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Institute of Artificial Intelligence Huazhong University of Science and Technology Wuhan430074 China Hubei Key Laboratory of Brain-Inspired Intelligent Systems Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Ministry of Education Wuhan430074 China

Protein-protein interaction (PPI) prediction is an instrumental means in elucidating the mechanisms underlying cellular operations, holding significant practical implications for the realms of pharmaceutical development and clinical treatment. Presently, the majority of research methods primarily concentrate on the analysis of amino acid sequences, while investigations predicated on protein structures remain in the nascent stages of exploration. Despite the emergence of several structure-based algorithms in recent years, these are still confronted with inherent challenges: (1) the extraction of intrinsic structural information of proteins typically necessitates the expenditure of substantial computational resources;(2) these models are overly reliant on seen protein data, struggling to effectively unearth interaction cues between unknown proteins. To further propel advancements in this domain, this paper introduces a novel PPI prediction method jointing masked reconstruction and contrastive learning, termed JmcPPI. This methodology dissects the PPI prediction task into two distinct phases: during the residue structure encoding phase, JmcPPI devises two feature reconstruction tasks and employs graph attention mechanism to capture structural information between residues;during the protein interaction inference phase, JmcPPI perturbs the original PPI graph and employs a multi-graph contrastive learning strategy to thoroughly mine extrinsic interaction information of novel proteins. Extensive experiments conducted on three widely utilized PPI datasets demonstrate that JmcPPI surpasses existing optimal baseline models across various data partition schemes. The associated code can be accessed via https://***/lijfrankopen/JmcPPI. Copyright © 2025, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Finite-Time Robust Synchronization of Delayed Competitive Neural Networks via Sliding-Mode control

Finite-Time Robust Synchronization of Delayed Competitive Ne...

引用

第40届中国控制会议

作者： Xingxing Tan Leimin Wang Xili Chen Jiajun Cheng Shan Jiang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

In this paper, based on the sliding-mode control, the finite-time synchronization of delayed competitive neural networks with external disturbances is investigated. Firstly, a controller and two sliding-mode surfaces are designed. Then, by utilizing the finite-time stability theory, the error states of drive and response delayed competitive neural networks are able to reach the designed surfaces in a finite time and then keep on the surfaces, where the states of equivalent system will approach zero in a finite time. Finally, a numerical example is presented to illustrate the effectiveness of the theoretical results.

关键词： Competitive neural networks finite-time synchronization sliding-mode control disturbance

来源：评论

学校读者我要写书评

暂无评论

Hand Detection and Gesture Classification based on Transformer

Hand Detection and Gesture Classification based on Transform...

引用

Chinese automation Congress (CAC)

作者： Genghui Pei Chi Xu Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems School of Automation China University of Geosciences Engineering Research Center of Intelligent Technology for Geo-Exploration Ministy of Education Wuhan China Engineering Research Center of Intelligent Technology for Geo-Geo-Exploration Ministy of Education Wuhan China

Hand detection and gesture recognition are an important branch of artificial intelligence, which are widely used in daily life, such as interaction between human and machines, communication using signals, virtual reality and so on. In order to realize gesture recognition in unconstrained situations, we propose a novel end-to-end model based on Transformer, which can detect multiple hands in a picture. Our network can be roughly divided into the following three stages. In the first stage, we will extract feature maps of different layers by convolutional network from monocular RGB images. In the second stage, features are sent into the codec module based on Transformer, and hand detection is further carried out through multi-layer perceptrons with the decoding vectors as the input. In the third stage, we combine the attention weight maps obtained in the second step with the features of different layers in the first step to complete the gesture recognition task. From the experiment results, our network accurately identifies the positions of multiple hands in the picture and correctly recognizes hand gestures.

关键词： Solid modeling Codecs automation Gesture recognition Virtual reality Transformers Feature extraction

来源：评论

学校读者我要写书评

暂无评论

An improved dissipativity criterion for singular systems with time-varying delays via a state decomposition method

An improved dissipativity criterion for singular systems wit...

引用

第40届中国控制会议

作者： Yang Li Yong He School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

This paper is concerned with the dissipativity analysis of singular systems with time-varying delays. Firstly, an improved augmented Lyapunov-Krasovsii functional(ALKF) is constructed based on the state decomposition method. Then, the derivative of the ALKF is estimated by applying the auxiliary function integral inequality and the extended reciprocally convex inequality. As a result, an improved dissipativity criterion with less conservativeness is established. Finally, numerical examples are given to show the superiority of the proposed method.

关键词： Singular systems dissipativity analysis time-varying delays state decomposition method

来源：评论

学校读者我要写书评

暂无评论

Takeaway Method Based on the Crowdsensing Path Planning System: A Study on the Use of Idle Bicycle Resources for Delivery

SSRN

引用

SSRN 2023年

作者： Xiong, Yonghua Zeng, Hongrui Yu, Anjun Hiroaki, Kurokawa She, Jinhua School of Automation China University of Geosciences Wuhan430074 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 Jiangxi Ganyue Expressway Co. Ltd. Jiangxi330200 China School of Engineering Tokyo University of Technology Tokyo192-0982 Japan

Due to the surge in takeaway demand, full-time delivery riders are facing challenges in completing their tasks on time. To address this issue, this study proposed a takeaway delivery method based on Crowdsensing. This strategy uses idle bicycle riders as resources to complete delivery tasks at a lower cost. To decrease the total delivery cost of merchants, the idle bicycle path planning model was established. The path planning problem of the proposed model is characterized by multiple riders, random locations, open deliveries, and pickup and delivery crossovers. Further, it belongs to the NP-hard problem. To solve this path planning model, a takeaway delivery-based genetic algorithm was designed. Order-preserving initialization was utilized to construct the initial population. The order crossover algorithm and adaptive mutation algorithm were introduced to overcome slow convergence and prevent the probability of falling into the local optimal solution of the traditional algorithm. The experimental results showed that the proposed takeaway delivery-based genetic algorithm had a fast convergence and high accuracy. Moreover, it can effectively solve the path planning model, thereby reducing merchant delivery cost and improving delivery timeliness. The method proposed in this paper has a significant application value. © 2023, The Authors. All rights reserved.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A Spatio-Temporal Scale Based Affective Neural Network for Emotion Detection in Conversation

A Spatio-Temporal Scale Based Affective Neural Network for E...

引用

Chinese automation Congress (CAC)

作者： Jiang Li Xiaoping Wang Shanglin Lei Zhigang Zeng School of Artificial Intelligence and Automation Huazhong University of Science and Technology (HUST) Wuhan China Institute of Artificial Intelligence Huazhong University of Science and Technology (HUST) Wuhan China Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan China Key Laboratory of Brain-inspired Intelligent Systems Hubei Province Wuhan China

Emotion Detection in Conversation (EDC) has been implemented in numerous domains and is under increasing attention. The EDC task is highly challenging due to the need to incorporate both the context of the utterance and the identity of the participant. Some existing EDC approaches employ redundant network structures and inadequately model contextual utterances, resulting in limited performance gains. In this work, we devise a Spatio-Temporal scale based Affective neural Network (STANet) in a simplistic and efficacious manner. STANet consists of two main components, i.e., spatial scale network and temporal scale network, which are applied to extract spatial scale and temporal scale information in the conversation, respectively. Prior to spatio-temporal scale modeling, we encode the identity information of participants to examine its impact on the performance of emotion detection. We conduct substantial comparative experiments and ablation studies on three conversational emotion datasets, and the results demonstrate that our STANet realizes superior performance without taking advantage of external knowledge.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multimodal Emotion Recognition Based on Multi-Scale Facial Features and Cross-Modal Attention 26

Multimodal Emotion Recognition Based on Multi-Scale Facial F...

引用

26th International Conference on Industrial Technology, ICIT 2025

作者： Bao, Chengao Chen, Luefeng Li, Min Wu, Min Pedrycz, Witold Hirota, Kaoru School of Automation China University of Geosciences Wuhan430074 China School of Automation Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6R 2G7 Canada Tokyo Institute of Technology Yokohama226-8502 Japan Tokyo Institute of Technology Tokyo226-8502 Japan

ISBN: (纸本)9798331521950

A multi-modal emotion recognition method based on facial multi-scale features and cross-modal attention (MS-FCA) network is proposed. The MSFCA model improves the traditional single-branch ViT network into a two-branch ViT architecture by using classification tokens in each branch to interact with picture embeddings in the other branch, which facilitates effective interactions between different scales of information. Subsequently, audio features are extracted using ResNet18 network. The cross-modal attention mechanism is used to obtain the weight matrices between different modal features, making full use of inter-modal correlation and effectively fusing visual and audio features for more accurate emotion recognition. Two datasets are used for the experiments: eNTERFACE'05 and REDVESS dataset. The experimental results show that the accuracy of the proposed method on the eNTERFACE'05 and REDVESS datasets is 85.42% and 83.84% respectively, which proves the effectiveness of the proposed method. © 2025 IEEE.

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

Tracking Performance of Networked systems with Limited Bandwidth and Colored Noise

Tracking Performance of Networked Systems with Limited Bandw...

引用

Chinese automation Congress (CAC)

作者： Bin Zhang Xiaowei Jiang Li Sun Xianhe Zhang School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai China School of Statistics and Mathematics Zhongnan University of Economics and Law Wuhan China School of Electrical Engineering and Automation Hubei Normal University Huangshi China

This study investigated the optimal tracking performance (OTP) of multi-input multi-output (MIMO), discrete- time networked control systems (NCSs). The limits of tracking performance (TP) under the influences of bandwidth, encoding- decoding, and additive coloured Gaussian noise (ACGN) are derived using the techniques of coprime decomposition and all-pass decomposition. The results reveal the negative impact of non-minimum phase (NMP) zeros and unstable poles of the plant as well as network communication constraints on the TP of NCSs. Finally, a numerical simulation is discussed and verifies our conclusions.

关键词： Networked control systems Gaussian noise Bandwidth Numerical simulation Downlink Decoding Colored noise

来源：评论

学校读者我要写书评

暂无评论

Data-driven control of consensus tracking for discrete-time multi-agent systems

引用

Journal of the Franklin Institute 2023年第7期360卷 4661-4674页

作者： Xiufeng Zhang Gang Wang Jian Sun Faculty of Mechanical and Electrical Engineering Kunming University of Science and Technology Kunming 650504 China Yunnan International Joint Laboratory of Intelligent Control and Application of Advanced Equipment Kunming 650504 China School of Automation Beijing Institute of Technology Beijing 100081 China Key Lab of Intelligent Control and Decision of Complex Systems Beijing 100081 China

This paper investigates the consensus tracking problem of leader-follower multi-agent systems. Different from most existing works, dynamics of all the agents are assumed completely unknown, whereas some input-output data about the agents are available. It is well known from the Willems et al. Fundamental Lemma that when inputs of a linear time-invariant (LTI) system are persistently exciting, all possible trajectories of the system can be represented in terms of a finite set of measured input-output data. Building on this idea, the present paper proposes a purely data-driven distributed consensus control policy which allows all the follower agents to track the leader agent’s trajectory. It is shown that for a linear discrete-time multi-agent system, the corresponding controller can be designed to ensure the global synchronization with local data. Even if the data are corrupted by noises, the proposed approach is still applicable under certain conditions. Numerical examples corroborate the practical merits of the theoretical results.

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：