检索结果-内蒙古大学图书馆

42nd Chinese control Conference, CCC 2023

作者： Liu, Yixian Liu, Jiao Li, Hongchao School of Artificial Intelligence Hebei University of Technology Tianjin China Hebei University of Technology Control Engineering Technology Innovation Center of Hebei Province Tianjin300401 China

ISBN: (纸本)9789887581543

This paper studies the asymptotical stability for a class of discrete-time switched positive neural networks with mixed delays. The time-varying delays and distribution delays which exist during neuron transmission are taken into consideration. The nonnegative state space of the first quadrant is divided into several subspaces, where the overlapping region is constructed to deal with the chattering behavior caused by frequent switching. Then hysteresis switching rule is designed by using the single copositive Lyapunov function (SCLF) and multiple copositive Lyapunov functions (MCLFs) methods, respectively. The sufficient conditions for the system's stability are given in the form of linear inequalities. At the end of this paper, two numerical examples demonstrate the effectiveness of this approach. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

Investigations into the flow dynamics of mixed biomass particles in a fluidized bed through Hilbert-Huang transformation and data-driven modelling

引用

Particuology 2024年第12期95卷 115-123页

作者： Bojian Qi Yong Yan Wenbiao Zhang School of Computer and Artificial Intelligence Beijing Technology and Business UniversityBeijing100048China International Research Center for Carbon Neutralization Hangzhou Beihang International Innovation InstituteBeihang UniversityHangzhou311115China School of Control and Computer Engineering North China Electric Power UniversityBeijing102206China

Flow dynamics of binary particles are investigated to realize the monitoring and optimization of fluidized *** is a challenge to accurately classify the mass fraction of mixed biomass,considering the limitations of existing *** data collected from an electrostatic sensor array is *** correlation,empirical mode decomposition(EMD),Hilbert-Huang transform(HHT)are applied to process the *** a higher mass fraction of the wood sawdust,the segregation behavior occurs,and the high energy region of HHT spectrum ***,two data-driven models are trained based on a hybrid wavelet scattering transform and bidirectional long short-term memory(ST-BiLSTM)network and a EMD and BiLSTM(EMD-BiLSTM)network to identify the mass fractions of the mixed biomass,with accuracies of 92%and 99%.The electrostatic sensing combined with the EMD-BiLSTM model is effective to classify the mass fraction of the mixed biomass.

关键词： Fluidized beds Biomass Hilbert-Huang transformation Bidirectional long short-term memory network Electrostatic sensors

来源：评论

学校读者我要写书评

暂无评论

Pressure Ulcer Stage Evaluation Algorithm Based on Multi-Scale Attention Residual Network 8

Pressure Ulcer Stage Evaluation Algorithm Based on Multi-Sca...

引用

8th International Symposium on Computer Science and Intelligent control, ISCSIC 2024

作者： Geng, Yanli Sun, Hao Li, Zelei Yang, Shucai Hebei University of Technology Enginneering Research Center of Intelligent Rehabilitation Device Detection Technology Ministry of Education School of Artificial Intelligence Control Engineering Technology Innovation Center of Hebei Province Tianjin China Tianjin Magic Technology Co. Ltd. Tianjin China

ISBN: (纸本)9798350380286

Pressure ulcer, alternatively referred to as a pressure injury, mostly occurs in long-term bedridden patients. This issue has emerged as a significant global health concern. Accurate diagnosis is the key to the treatment of pressure sores in clinical application scenarios. Conventional contact-based artificial pressure ulcer detection methods can cause discomfort to patients and potentially elevate the risk of infection. In response to these problems, a pressure ulcer stage evaluation algorithm based on multi-scale attention residual network was proposed. The residual network was used as the basic framework, the stage 0 was improved to enhance the network's nonlinear expressive capacity, and the residual structure was improved to enhanced the model's generalization capability, the FPN feature pyramid was added to fuse the high-level features with the underlying features to achieve feature pyramid feature extraction. The incorporation of the attention mechanism enhanced the model's overall performance and recognition accuracy. The pressure damage stage dataset was used in an experiment to validate the model's performance. The experimental outcomes demonstrate that the proposed method could achieve the precision, recall, F1-score and accuracy of the algorithm of 82.64 %, 83.26 %, 0.83 and 82.37% respectively. Compared with other deep learning models, this proposed algorithm can improve the accuracy and identify the pressure ulcer effectively. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

MFF6D: Multi-Scale Feature Fusion Network for 6D Object Pose Estimation and Refinement 42

MFF6D: Multi-Scale Feature Fusion Network for 6D Object Pose...

引用

42nd Chinese control Conference, CCC 2023

作者： An, Yunnan Yang, Dedong Ge, Haoran Li, Yangyang School of Artificial Intelligence Hebei University of Technology Tianjin300401 China Control Engineering Technology Innovation Center of Hebei Province Hebei University of Technology Tianjin300401 China

ISBN: (纸本)9789887581543

Due to insufficient correlation between features at different scales, the multi-scale 6D object pose estimation remains a challenge. To fully correlate the multi-scale features of different modes, we propose a high-efficiency Multi-scale Feature Fusion Network for 6D object pose estimate. Our method utilizes two independent branches to extract appearance features and geometric features respectively, and a multi-scale architecture to focus on semantically rich regions in different scales. In addition, we also propose adaptive channel attention to refine multi-scale features by constraining the average and maximum pooling layers with a trainable parameter. We evaluate our model on the well-known YCB-Video and LineMOD datasets. Our method achieves 94.3% of the AUC on the YCB-Video dataset and 98.3% of the ADD on the LineMOD dataset. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： 6D pose estimation adaptive channel attention Multi-scale Feature Fusion

来源：评论

学校读者我要写书评

暂无评论

Dynamic Signal State Estimation of Electromagnetic Flowmeter Measurement Based on Variance Compensation Kalman Filter 42

Dynamic Signal State Estimation of Electromagnetic Flowmeter...

引用

42nd Chinese control Conference, CCC 2023

作者： Zhai, Xinyu Zhang, Wei School of Artificial Intelligence Hebei University of Technology Tianjin300401 China Control Engineering Technology Innovation Center of Hebei Province Hebei University of Technology Tianjin300401 China

ISBN: (纸本)9789887581543

Electromagnetic flowmeter is widely applied in single-phase flow, solid-liquid two-phase flow and solid-liquid-gas three-phase flow measurement due to the advantages of high accuracy and high stability. However, existing electromagnetic flowmeter inherit the shortcomings of limited applicability and slow dynamic response speed. In order to solve the problem above, this paper make several modifications on the traditional Kalman filter to form an adaptive algorithm. The traditional Kalman filter method is difficult to track the changing flow signal. In order to solve the problem that the flow state changes with the flow state in electromagnetic flowmeter, the adaptive estimation considering the change of real-time flow state is introduced, which provides a solution to remove invalid signal more effectively, make rapid changes according to the change of flow state, and reduce the actual error of filtering. The adaptive Kalman estimation model under continuous flow condition is established, which makes the scope of application wider, improves the signal-to-noise ratio and greatly improves the signal accuracy. Through simulation, the results obtained by Kalman filter are more close to the real value than the measured value, indicating that the variance compensation adaptive Kalman filter has the effect of eliminating noise. At the same time, with the passage of time, the filtering gain K slowly decreases until it becomes stable to a constant. When the adaptive Kalman gain is stable, the adaptive Kalman filtering is equivalent to low-pass filtering, and the system reaches steady state. The adaptive Kalman filtering solves the problem that the traditional Kalman filtering method is difficult to track the changing flow signal. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

LGEGAN: A Lightweight Evolutionary Generative Adversarial Network with Statistic Global Information 42

LGEGAN: A Lightweight Evolutionary Generative Adversarial Ne...

引用

42nd Chinese control Conference, CCC 2023

作者： Cao, Bin Lei, Huan School of Artificial Intelligence Hebei University of Technology Tianjin300401 China Hebei University of Technology Control Engineering Technology Innovation Center of Hebei Province Tianjin300401 China

ISBN: (纸本)9789887581543

Generative Adversarial Networks (GANs) have been applied in many fields. However, the existing GANs and their variants encounter many problems, including pattern collapse, training instability and falling into local optimal. Therefore, we construct a lightweight evolutionary generative adversarial network (LGEGAN) with statistic global information. To solve the problem that shallow convolutional neural networks are difficult to capture long-range feature dependence and the training process is prone to pattern collapse, LGEGAN is different from EGAN in that we add an improved self-attention mechanism to the generator network. To solve the problem of instability in the training process, we add spectral normalization to LGEGAN, which increases the stability of each generation of training process. Finally, to efficiently evolve individuals who adapt to the environment in a short time and solve the problem of falling into local optimal, different from EGAN, we construct a novel selection operator and apply it to the selection stage of LGEGAN's evolution of the generator. In the experiments, we evaluate the LGEGAN from four aspects: the quality and diversity of generated images, the collapse of patterns, the stability of training and the robustness of the architecture. The experimental results indicate that the performance of LGEGAN is better than that of EGAN, MOEGAN, SMOEGAN, LRGAN, ProbGAN and the other generative adversarial network models. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Container Detection Network Model Based on YOLOv5s 42

A Lightweight Container Detection Network Model Based on YOL...

引用

42nd Chinese control Conference, CCC 2023

作者： Liu, Yang Chen, He School of Artificial Intelligence Hebei University of Technology Tianjin300401 China Hebei University of Technology Control Engineering Technology Innovation Center of Hebei Province Tianjin300401 China

ISBN: (纸本)9789887581543

The real-time detection and identification of the container are an essential prerequisite for realizing automated port. However, most of the existing container detection algorithms suffer many challenges, such as excessive computational cost and undesired detection accuracy. To deal with these challenges, an improved lightweight YOLOv5s network is proposed for container detection in this paper. Firstly, Ghost and C3Ghost modules are introduced into YOLOv5s network to reduce the number of model parameters and improve the performance of feature expression. Secondly, the C3 module in the original neck structure of YOLOv5s network is replaced by CN3 module to enrich the features of neck network and decrease the loss of semantic information during neural network feature extraction. Finally, the weighted bidirectional feature pyramid network (BiFPN) is used to replace the feature fusion method of the original YOLOv5s, and a small target detection layer is added to improve the model's ability in detecting small targets. To verify the validity of the proposed Lite-YOLOv5s model, the trained network model is evaluated on the test set of Container Posing. The results show that, compared with the original YOLOv5s model, the detection accuracy of the proposed model is improved by 1.7%, and the number of model parameters is reduced by 42.67%. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Cloud-Based Dynamic Event-Triggered Predictive control for Networked Multi-Agent Systems 42

Cloud-Based Dynamic Event-Triggered Predictive Control for N...

引用

42nd Chinese control Conference, CCC 2023

作者： Yu, Yang Ding, Sanbo School of Artificial Intelligence Hebei University of Technology Tianjin300401 China Hebei University of Technology Control Engineering Technology Innovation Center of Hebei Province Tianjin300401 China

ISBN: (纸本)9789887581543

This article concentrates on the cloud-based dynamic event-triggered predictive control for networked multi-agent systems (NMASs). Since each agent communicates with the cloud by network, a cloud-based predictive control scheme is introduced to compensate for network-induced delays actively. The adverse effects caused by delays are eliminated effectively for NMASs. A dynamic event-triggered mechanism (DETM) is proposed to schedule the inter-agent communication. Each agent broadcasts its own information intermittently, which reduces the communication burden and resource consumption significantly. A distributed consensus protocol which integrates cloud-based predictive control scheme and DETM is developed in detail. The sufficient conditions of closed-loop asymptotic stability and leader-following consensus are derived by Lyapunov method. The effectiveness of represented method is indicated by numerical simulation. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Backstepping Fast Terminal Sliding Mode control Strategy With GPIO For Double Pendulum Cranes 42

Hierarchical Backstepping Fast Terminal Sliding Mode Control...

引用

42nd Chinese control Conference, CCC 2023

作者： Fan, Zhenyue Chen, He Li, Zhaoqi School of Artificial Intelligence Hebei University of Technology Tianjin300401 China Hebei University of Technology Control Engineering Technology Innovation Center of Hebei Province Tianjin300401 China

ISBN: (纸本)9789887581543

In the field of cranes, the double pendulum effects may occur when the payload is large, and the hook mass is a non-negligible factor. Under these effects, the dynamic model of the system will be more complex, which brings many difficulties to the design of the controller. To achieve trolley positioning, suppress double pendulum effects, and improve anti-disturbances ability, this article presents a hierarchical backstepping fast terminal sliding mode control strategy for the double pendulum cranes. First, to design the observers and controller, the double pendulum crane system is divided into three subsystems. A generalized proportional integral observer (GPIO) is designed for each subsystem, which can estimate potential model uncertainties and unknown external disturbances of the system. According to the estimates of the GPIO, we design a first layer fast terminal sliding surface for each subsystem, and equivalent control law is designed using the idea of backstepping. Meanwhile, using the advantages of backstepping control makes the structure of the system more clear and brings convenience to the design of the Lyapunov function. Based on the first layer of sliding surfaces, we design a second layer sliding surface. Then, an ultimate control law is designed to ensure the stability of the entire system. In the end, the effectiveness of this control strategy is validated through simulation results on MATLAB/Simulink. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Backstepping

来源：评论

学校读者我要写书评

暂无评论

Lung Nodule Segmentation Based on Complementary Context-Aware Networks 42

Lung Nodule Segmentation Based on Complementary Context-Awar...

引用

42nd Chinese control Conference, CCC 2023

作者： Liu, Weipeng Qi, Yedong Li, Jian Ren, Ziwen Hebei University of Technology School of Artificial Intelligence Tianjin300401 China Control Engineering Technology Innovation Center of Hebei Province Hebei University of Technology Tianjin300401 China

ISBN: (纸本)9789887581543

Accurate lung nodule segmentation in computer assisted diagnosis (CAD) has emerged as the key to diagnosis and treatment for lung disorders brought on by lung nodule, which pose a severe threat to people's lives and health. However, since medical images are 3D data, the spatial semantic content is very complex, and it is difficult to extract target features accurately. Furthermore, the small CT area of the lungs occupied by pulmonary nodules, the complex background and low contrast make it difficult to create a successful automatic segmentation framework for the pulmonary nodule segmentation task. In this study, we develop a coarse-to-fine 3D segmentation framework to apply the segmentation task of lung nodules in lung computed tomography (CT) images. Furthermore, we propose a novel Complementary Context-Aware (CCA) attention module, which can capture long-range dependencies in different directions in 3D space and complex spatial context information to further improve segmentation accuracy. To test the effectiveness of our model, we conduct extensive experiments and validation using the lung dataset from the Medical Segmentation Decathlon (MSD). Experimental results show that our lung nodule segmentation model achieves excellent segmentation results and outperforms other advanced 3D segmentation networks. The proposed CCA attention method can effectively obtain the spatial context information in the volume data, highlight the target features, and improve the segmentation accuracy. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Computerized tomography

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：