检索结果-内蒙古大学图书馆

Chinese Control Conference (CCC)

作者： Jiajun Chu Weihua Cao Chao Gan Yulong Yang School of Automation China University of Geosciences Wuhan P. R. China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan P. R. China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan P. R. China

Deep-sea unmanned exploration equipment is an important tool for exploring and developing the resources in the ocean, and it can survey the deep-sea environment more visually with the help of visual images. However, the complex and variable environment and the low resolution of the underwater lens lead to the poor resolution of the images acquired by the equipment. In this paper, we propose a residual-dense connected method applied to unmanned deep-sea exploration equipment to improve it's image resolution. The method uses dense connections within the residual structure to improve the model detail information acquisition to ensure accuracy and model stability of model. Secondly, through the study of the model performance, a high precision residual-dense connected model with less computational effort is designed. Finally, the model is trained and tested using environmental images in deep-sea conditions, and it is demonstrated that the method can be applied to deep-sea unmanned exploration equipment for fast, accurate, and stable image super-resolution processing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CMFN: Cross-Modal Fusion Network for Irregular Scene Text Recognition

arXiv

引用

arXiv 2024年

作者： Zheng, Jinzhi Ji, Ruyi Zhang, Libo Wu, Yanjun Zhao, Chen Intelligent Software Research Center Institute of Software Chinese Academy of Sciences Beijing100190 China The Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing100190 China

Scene text recognition, as a cross-modal task involving vision and text, is an important research topic in computer vision. Most existing methods use language models to extract semantic information for optimizing visual recognition. However, the guidance of visual cues is ignored in the process of semantic mining, which limits the performance of the algorithm in recognizing irregular scene text. To tackle this issue, we propose a novel cross-modal fusion network (CMFN) for irregular scene text recognition, which incorporates visual cues into the semantic mining process. Specifically, CMFN consists of a position self-enhanced encoder, a visual recognition branch and an iterative semantic recognition branch. The position self-enhanced encoder provides character sequence position encoding for both the visual recognition branch and the iterative semantic recognition branch. The visual recognition branch carries out visual recognition based on the visual features extracted by CNN and the position encoding information provided by the position self-enhanced encoder. The iterative semantic recognition branch, which consists of a language recognition module and a cross-modal fusion gate, simulates the way that human recognizes scene text and integrates cross-modal visual cues for text recognition. The experiments demonstrate that the proposed CMFN algorithm achieves comparable performance to stateof- the-art algorithms, indicating its effectiveness. © 2024, CC BY.

关键词： Optical character recognition

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

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

引用

IEEE International Conference on Industrial Technology (ICIT)

作者： Chengao Bao Luefeng Chen Min Li Min Wu Witold Pedrycz Kaoru Hirota School of Automation China University of Geosciences Wuhan China the Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems School of Automation and the Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education China University of Geosciences Wuhan China Department of Electrical and Computer Engineering University of Alberta Edmonton Canada Tokyo Institute of Technology Yokohama Japan Tokyo Institute of Technology Tokyo Japan

ISBN: (数字)9798331521950

ISBN: (纸本)9798331521967

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.

关键词： Emotion recognition Visualization Accuracy Service robots Semantics Human-robot interaction Speech recognition Feature extraction Data mining Facial features

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

Bit Bounce Detection for Drilling Process Based on Multi-Feature Graph and Graph Convolutional Network

Bit Bounce Detection for Drilling Process Based on Multi-Fea...

引用

Annual Conference of Industrial Electronics Society

作者： Peng Zhang Wenkai Hu Weihua Cao Min Wu Jiandong Wang School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan China College of Electrical Engineering and Automation Shandong University of Science and Technology Qingdao Shandong Province China

Prompt detection of bit bounce can prevent serious incidents and is of great importance for safe and efficient deep geological drilling. In the early stage of bit bounce, signal changes are relatively weak. In addition, there are differences in the topological relationships of samples at different time instances in normal state and bit bounce. These factors present a challenge to timely and accurate bit bounce detection. Therefore, this paper proposes a bit bounce detection method based on multi-feature graph and graph convolution networks. A multi-feature graph construction method using process variables, mean value, Mahalanobis distance, and Euclidean distance is proposed, and a two-layer graph convolutional network is designed to realize deep feature extraction and incident detection. The effectiveness and superiority of the proposed method are demonstrated by a real drilling industrial case.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition via Environmental Context and Human Body

Emotion Recognition via Environmental Context and Human Body

引用

Industrial Cyber-Physical systems (ICPS)

作者： Cheng-Shan Jiang Zhen-Tao Liu School of Automation China University of Geosciences Wuhan P. R. China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan P. R. China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan P. R. China

To promote the humanized interactive experience of the intelligent device and system, emotional intelligence has become a popular research field in the human-machine interaction. The previous research on emotion recognition based on computer vision has mostly been carried out by analysing facial expression or body posture, and psychological studies show that scene context also contributes some important information on emotion recognition. In addition, most context-aware emotion recognition studies focus on exploring the relevance analysis of environmental semantics, but the influence of feature encoder on semantic information embedding has not been fully discussed. In this paper, we proposed a Global Semantic Feature Enhancement-Dual Stream Densely Connected Network (GSFE-DSDCN) to enhance global semantic information learning from the perspectives of dimension and spatial. Densely connected pattern is introduced to concatenate the shallow and deep layers output, which fuses the semantic information of low-dimensional geometric features and high-dimensional abstract context features together. The Global Multi-Scale Feature Recalibration (GMSFR) module expands the receptive field in spatial, which effectively improves the global semantic features extraction capability of feature encoder. We evaluate the proposed method on the EMOTIC data set, and experimental results are shown to be competitive with the state-of-the-art algorithms.

关键词： Human computer interaction Emotion recognition Computer vision Fuses Biological system modeling Semantics Psychology

来源：评论

学校读者我要写书评

暂无评论

Exponential Stability Analysis for Delayed Neural Networks via A Cubic Function Negative-Determination Lemma

Exponential Stability Analysis for Delayed Neural Networks v...

引用

Chinese Control Conference (CCC)

作者： Wen-Xuan Zhao Yun-Fan Liu Yu-Long Fan Chuan-Ke Zhang School of Automation China University of Geosciences Wuhan P. R. China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan P. R. China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan P. R. China

This paper concerns with the exponential stability of delayed neural networks via Lyapunov-Krasovskii functional (LKF) method. Initially, an improved augmented delay-product-type LKF containing an additional double integral state is established, which introduces more delayed states and has less conservatism. In the LKF's derivative, the function has high order of delay due to the existence of exponent. Thus, in order to obtain tractable linear matrix inequalities, three state vectors are used to reduce the order of the function to cubic. Secondly, to achieve the negative-definiteness requirement, a negative-determination lemma for cubic functions with less conservatism is employed. Then, a less conservative delay-dependent stability criterion for neural networks with time-varying delays is established. Finally, the validity of the proposed delay-dependent stability criterion is illustrated by two numerical examples.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stability Analysis for Amplidyne Electrical systems with Time-Varying Delay via a Negative-Determination Quadratic Function Lemma

Stability Analysis for Amplidyne Electrical Systems with Tim...

引用

Chinese Control Conference (CCC)

作者： Hong-Jian Huang Hong-Zhang Wang Yu-Long Fan Ke-You Xie Chuan-Ke Zhang School of Automation China University of Geosciences Wuhan P. R. China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan P. R. China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan P. R. China

In this paper, the stability of Amplidyne Electrical systems (AESs) with a time-varying delay is studied. Firstly, the model of AESs with a time-varying delay is established. Secondly, an augmented Lyapunov-Krasovskii functional (LKF) is constructed. Then, a less conservative delay-dependent stability criterion for AESs with a time-varying delay is obtained by utilizing the generalized reciprocally convex combination and an advanced negative-determination quadratic function lemma. Finally, the superiority and effectiveness of the proposed criterion is verified by a numerical example.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generating Waste Heat Energy from CPU Based on Thermoelectric Power Generator

Generating Waste Heat Energy from CPU Based on Thermoelectri...

引用

Chinese Automation Congress (CAC)

作者： Kun Qian Yeyun Cai Kun Xu Fang Deng School of Automation Beijing Institute of Technology Beijing China Key Laboratory of Intelligent Control and Decision of Complex Systems

ISBN: (纸本)9781665426480

Heat dissipation is extremely important for electronic component such as CPU or GPU of the computer. Now most researchers only design optimal heat sink for CPU for better heat dissipation, while few of them consider waste heat recycling of CPU. The CPU can be used as the heat source, while the original system has fan and heat sink as the cooling system. Thus, the original CPU working condition is very suitable for thermoelectric power generation and will bring great benefit to system itself. However, adding thermoelectric generator will increase the temperature of CPU, which will decrease the performance of the computer. It is necessary to reduce the hot side temperature while generating energy as much as possible. To achieve this, this paper designed a kind of intelligent waste heat generation system based on thermoelectric power generator. Three different shape heat sinks are designed, contrasted, and tested. By building experimental platform and establishing simulation model, the power of thermoelectric power generation and temperature change of the three heat sink structures are compared. The fin shaped heat sink is considered has the best output performance while keeping the hot side temperature within the acceptance range. The maximum output power is 10.67mW, and the maximum hot side temperature is 72°C during the experiment.

关键词： Temperature distribution Shape Cogeneration Generators Central Processing Unit Waste heat Trigeneration

来源：评论

学校读者我要写书评

暂无评论

Weighted Sparse Partial Least Squares for Joint Sample and Feature Selection

arXiv

引用

arXiv 2023年

作者： Min, Wenwen Xu, Taosheng Ding, Chris The Yunnan Key Laboratory of Intelligent Systems and Computing School of Information Science and Engineering Yunnan University Yunnan Kunming650091 China The Institute of Intelligent Machines Hefei Institutes of Physical Science Chinese Academy of Sciences Anhui Hefei230031 China The School of Data Science The Chinese University of Hong Kong Shenzhen China

Sparse Partial Least Squares (sPLS) is a common dimensionality reduction technique for data fusion, which projects data samples from two views by seeking linear combinations with a small number of variables with the maximum variance. However, sPLS extracts the combinations between two data sets with all data samples so that it cannot detect latent subsets of samples. To extend the application of sPLS by identifying a specific subset of samples and remove outliers, we propose an ∞/0-norm constrained weighted sparse PLS (∞/0-wsPLS) method for joint sample and feature selection, where the ∞/0-norm constrains are used to select a subset of samples. We prove that the ∞/0-norm constrains have the Kurdyka-Lojasiewicz property so that a globally convergent algorithm is developed to solve it. Moreover, multi-view data with a same set of samples can be available in various real problems. To this end, we extend the ∞/0-wsPLS model and propose two multi-view wsPLS models for multi-view data fusion. We develop an efficient iterative algorithm for each multi-view wsPLS model and show its convergence property. As well as numerical and biomedical data experiments demonstrate the efficiency of the proposed methods. © 2023, CC BY.

关键词： Data fusion

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：