检索结果-内蒙古大学图书馆

Parallel Learning:Overview and Perspective for Computational Learning Across Syn2Real and Sim2Real

IEEE/CAA Journal of Automatica Sinica 2023年第3期10卷 603-631页

作者： Qinghai Miao Yisheng Lv Min Huang Xiao Wang Fei-Yue Wang School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China School of Artificial Intelligence Anhui UniversityHefei 266114China Qingdao Academy of Intelligent Industries Qingdao 230031China State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China IEEE

The virtual-to-real paradigm,i.e.,training models on virtual data and then applying them to solve real-world problems,has attracted more and more attention from various domains by successfully alleviating the data shortage problem in machine *** summarize the advances in recent years,this survey comprehensively reviews the literature,from the viewport of parallel ***,an extended parallel learning framework is proposed to cover main domains including computer vision,natural language processing,robotics,and autonomous ***,a multi-dimensional taxonomy is designed to organize the literature in a hierarchical ***,the related virtual-toreal works are analyzed and compared according to the three principles of parallel learning known as description,prediction,and prescription,which cover the methods for constructing virtual worlds,generating labeled data,domain transferring,model training and testing,as well as optimizing the strategies to guide the task-oriented data generator for better learning *** issues remained in virtual-to-real are ***,the future research directions from the viewpoint of parallel learning are suggested.

关键词： Machine learning parallel learning parallel systems sim-to-real syn-to-real virtual-to-real

来源：评论

学校读者我要写书评

暂无评论

Multi-Level Features Fusion for Zero-Shot Object Pose Estimation 26

Multi-Level Features Fusion for Zero-Shot Object Pose Estima...

引用

26th International Conference on Industrial Technology, ICIT 2025

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

ISBN: (纸本)9798331521950

Driven by advancements in industrial production and artificial intelligence, the need for pose estimation of new ob-jects in areas like robotic manipulation and virtual reality is increasing. We introduce a zero-shot object pose estimation approach that identifies the poses of objects excluded from the training dataset, removing the requirement for re-modeling. The method is built around a multi-level features fusion framework de-signed to enhance generalization. First, a trainable feature extraction module filters and selects multi-level features extracted by the backbone network. Unlike traditional convolutional ker-nels, we incorporate a dynamic convolution kernel to enhance the feature extraction capability. Second, in the feature fusion module, we adopt a dynamic weight generation strategy to perform weighted fusion of multi-level features. This method enhances template matching by effectively describing similarities between unseen objects (those absent from the training set) and templates, leveraging robust and adaptive feature representations to narrow the gap with seen objects. Experimental results demonstrate that our approach achieves state-of-the-art performance on two popu-lar benchmark datasets, LineMod and LineMod-Occlusion, proves that our method has better generalization than previous models. © 2025 IEEE.

关键词： Industrial robots

来源：评论

学校读者我要写书评

暂无评论

Alarm Prediction with Variational Output Dimension for Alarm Floods Using Transformer 43

Alarm Prediction with Variational Output Dimension for Alarm...

引用

43rd Chinese control Conference, CCC 2024

作者： Pang, Long Jiang, Wenbin Hu, Wenkai Wang, Zhuang Cao, Weihua China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China

ISBN: (纸本)9789887581581

Industrial alarm systems play crucial roles in assessing the production status and ensuring process safety. However, the presence of alarm floods can make alarm systems partially or fully fail, and thus would cause serious consequences. Alarm prediction, as an advanced approach to address alarm floods, offers operators decision supports when an alarm flood occurs. Existing alarm prediction methods requires that the output alarm sequences are of a fixed dimension, making such methods unable to adapt to the changing alarm rate. Accordingly, this paper proposes an alarm prediction model based on Transformer. The proposed model can predict alarm sequences with variational dimensions and can also achieve remarkable accuracy. The effectiveness of the proposed method is demonstrated by a case study with data from the Vinyl Acetate Monomer (VAM) simulation model. © 2024 Technical Committee on control Theory, Chinese Association of automation.

关键词： Polyvinyl acetates

来源：评论

学校读者我要写书评

暂无评论

Road Underground Target Detection in Ground Penetrating Radar Images Based on YOLO Models

Road Underground Target Detection in Ground Penetrating Rada...

引用

2023 China automation Congress, CAC 2023

作者： Li, Ting Xue, Wei Yang, Xinya Wu, Dongchang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

ISBN: (纸本)9798350303759

Ground penetrating radar (GPR) is extensively employed for subsurface road target detection, offering benefits such as convenience, nondestructive testing, rapid data acquisition, and superior resolution. Despite these advantages, interpreting GPR data often depends on the expertise of professionals, resulting in low detection efficiency and low accuracy. To address these challenges, this study introduces an intelligent detection technique for GPR images, utilizing an enhanced YOLOv5 framework. First, considering the problems of the small amount of GPR image datasets and the unclear characteristics caused by the complex underground media, a Dense-C3 module is built by utilizing the structure of DenseNet to enhance the network's capability for extracting features. Subsequently, a channel and spatial hybrid attention module is introduced into the backbone for feature refinement and improving the efficiency. Finally, the multi-class focal loss function is devised to enhance the precision in cases of imbalanced sample classes. Experimental results show that the proposed model surpasses the original YOLOv5 model and various contemporary advanced models. © 2023 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Efficient Mobile Deployment of Lightweight CNN-Transformer Model for Crop Disease Diagnosis in Smart Agriculture 4

Efficient Mobile Deployment of Lightweight CNN-Transformer M...

引用

4th Asia Conference on Information Engineering, ACIE 2024

作者： Lv, Zirong China University of Geosciences Hubei Key Lab. of Adv. Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education School of Automation Wuhan China

ISBN: (纸本)9798350371925

Crop disease diagnosis is of great significance for crop yield and agricultural production. Deep learning methods have become a major research direction for solving crop disease diagnosis. However, recent studies have shown that deploying complex neural network models on mobile devices poses a significant challenge to mobile hardware performance. To address this issue, this paper proposes a lightweight network model based on the Transformer and deploys it on mobile devices. Compared to other lightweight network models, our approach significantly reduces computational complexity using Transformer modules and exhibits a particular advantage in recognition accuracy. It achieves a recognition rate of 97.76% for ten categories of tomato diseases, while the model size is only 3.86 MB. Furthermore, we deploy the model on embedded devices and apply it to tomato crop recognition, enabling farmers to monitor crop conditions in real-time and realizing smart agriculture. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Multimodal Multilevel Attention for Semi-Supervised Skeleton-Based Gesture Recognition

SSRN

引用

SSRN 2024年

作者： Liu, Jinting Gan, Ming-Gang He, Yuxuan Guo, Jia Hu, Kang State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China

Although skeleton-based gesture recognition based on supervised learning has made promising achievements, the reliance on large amounts of annotation for training poses a significant cost. This paper addresses semi-supervised gesture recognition, aiming to learn feature representations effectively from unlabeled data. To resolve this problem, we propose a novel multimodal multilevel attention network to achieve semi-supervised learning. This model uses an attention mechanism to polymerize multimodal and multilevel complementary semantic information of the hand skeleton, designing a multimodal multilevel contrastive loss to measure the similarity of features for semi-supervised learning. Specifically, our method explores the relationships between joint, bone, and motion to learn more discriminative feature representations. Considering the hierarchy of the hand skeleton, the skeleton data is divided into multilevel (i.e., hand-level, finger-level, and joint-level) to capture complementary semantic information. Furthermore, a multimodal contrastive loss measure similarity among multilevel representations. The proposed method outperforms the semi-supervised skeleton-based gesture recognition tasks, according to extensive experimentation on two challenging datasets from SHREC-17 and DHG 14/28 datasets. © 2024, The Authors. All rights reserved.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Pre-trained Language Model - Based Real-time Formation Lithology Identification Method for Drilling Process

Pre-trained Language Model - Based Real-time Formation Litho...

引用

2024 China automation Congress, CAC 2024

作者： Liu, Jianyang Gan, Chao Cao, Weihua 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

ISBN: (纸本)9798350368604

Geological exploration is essential for economic and social progress, with lithology identification being a key technology that improves exploration precision and resource development efficiency. This paper presents a real-time identification method of formation lithology in drilling process based on pre-training language model, which is divided into three stages. In this first stage, the drilling data undergoes rigorous cleaning, feature selection, and normalization to eliminate noise and anomalies. In the second stage, key model inputs such as weight on bit (WOB), rate of penetration (ROP), rotation speed (RPM), torque, and pump volume (P) are identified through detailed drilling mechanism analysis. In the last stage, a real-time identification method of formation lithology in drilling process based on pre-training language model is proposed, which realizes high-precision real-time identification in drilling process. The effectiveness of the proposed method is proved by comparison with common methods. © 2024 IEEE.

关键词： Lithology

来源：评论

学校读者我要写书评

暂无评论

Gesture Recognition Using FMCW Radar Based on Deep Neural Network

Gesture Recognition Using FMCW Radar Based on Deep Neural Ne...

引用

2023 China automation Congress, CAC 2023

作者： Wang, Rui Xue, Wei Peng, Jiao Yang, Xinya School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

ISBN: (纸本)9798350303759

In recent years, radar based gesture recognition technology has attracted more and more attention. Among different types of radars, frequency modulated continuous wave (FMCW) radar has the greatest application potential due to its high range and velocity resolution and low cost. However, insufficient gesture information extraction and interference signals affect the performance of FMCW radar gesture recognition. To address the problems, a gesture recognition method based on multi-dimensional features and deep neural network is proposed in this paper. First, the range-time map (RTM) and velocity-time map (VTM) of the gesture are constructed from the range-Doppler map (RDM) with two-dimensional fast Fourier transform (2D-FFT). Then, the angle-time map (ATM) is constructed with the multiple signal classification (MUSIC) algorithm. Subsequently, RTM, VTM and ATM are normalized and adaptively filtered to suppress interference signals, and the three maps are fused to construct the range-velocity-angle-time map (RV ATM) of the gesture. Finally, an improved VGG16 network with self-attention mechanism module is used for feature extraction and recognition. The experimental results show that the proposed method achieves an average accuracy of 98.3% for six gestures, and the improved VGG16 network outperforms other traditional convolutional neural networks. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

3D Point Cloud-Based Lithium Battery Surface Defects Detection Using Region Growing Proposal Approach 8th

3D Point Cloud-Based Lithium Battery Surface Defects Detecti...

引用

8th International Workshop on Advanced Computational Intelligence and intelligent Informatics, IWACIII 2023

作者： Rehman, Zia Ur Wang, Xin Alsumeri, Abdulrahman Abdo Ali Khan, Malak Abid Ali Ma, Hongbin State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9789819975891

Detecting the lithium battery surface defects is a difficult task due to the illumination reflection from the surface. To overcome the issue related to labeling and training big data by using 2D techniques, a 3D point cloud-based technique has been proposed in this paper. The 3D point cloud-based defect detection of lithium batteries used feature-based techniques to downscale the point clouds to reduce the computational cost, extracting the normals of the points and calculating their differences to detect the defects of the battery which assure the quality of the product. This paper offers a novel strategy using 3D point clouds to get beyond the labeling and training challenges involved with conventional 2D approaches. This 3D point cloud-based approach for lithium battery fault identification makes use of feature-based methods to improve the point cloud data and lessen the computing burden. In our work, the experiments show that the feature-based technique precisely detects the affected surface of the battery. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Lithium batteries

来源：评论

学校读者我要写书评

暂无评论

Non-Convex Operating Zone Establishment and Alarm Limit Design for Multivariate Alarm systems Based on Grid Clustering 43

Non-Convex Operating Zone Establishment and Alarm Limit Desi...

引用

43rd Chinese control Conference, CCC 2024

作者： Wei, Yujie Hu, Wenkai Li, Yupeng Cao, Weihua China University of Geosciences School of Automation 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

ISBN: (纸本)9789887581581

Alarm systems are core components in large complex industrial facilities to ensure safe and efficient operation. Traditional univariate alarm system design methods ignore the correlation of process variables and thus may generate massive false alarms and missed alarms. An effective way of designing a multivariate alarm system is to establish the normal operating zones (NOZs) based on historical data under normal conditions. These NOZs serve as the basis for setting alarm limits in multivariate alarm systems. Given that the actual correlations between related variables are frequently unknown, a robust modeling approach is necessary to effectively handle both convex and non-convex NOZs. Thus, this paper presents a systematic method for nonconvex operating zone establishment and alarm limit design for multivariate alarm systems. A multivariate non-convex NOZ is established based on grid clustering. Then, the multidimensional grid boundary is extracted and used to determine the alarm limits for real-time samples. A numerical example is used to demonstrate the effectiveness of the proposed method. © 2024 Technical Committee on control Theory, Chinese Association of automation.

关键词： Alarm systems

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：