检索结果-内蒙古大学图书馆

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Dai, Zhigang Chen, Junying Mian, Ajmal South China University of Technology Key Laboratory of Big Data and Intelligent Robot Ministry of Education School of Software Engineering Guangzhou China The University of Western Australia Department of Computer Science Perth Australia

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Fine-grained visual categorization is challenged by limited training data by localizing discriminative regions and learning diverse features. We propose an effective regularization method that simultaneously imposes spatial consistency and feature diversity on CNN feature maps from a unified perspective. The former guides different feature map channels to concentrate collaboratively on the discriminative areas while the latter ensures that the feature maps are diverse. The proposed method does not require additional supervision, and leverages the covariance matrix of multi-channel feature maps to regularize the loss at the last convolutional layer where the semantic information is the richest. This allows the influence to be backpropagated to update all convolutional layers. We perform experiments using four network architectures for transfer learning from two source domains to three target domains, and demonstrate that our regularization method improves accuracy in all different settings. The proposed regularization method achieves state-of-the-art performance on CUB-200-2011, Stanford-Cars, and Stanford-Dogs datasets with 89.8%, 94.6%, and 88.5% accuracy, respectively. © 2022 IEEE.

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Degradation Modeling and Remaining Useful Life Prediction Method Based on Uncertain Random Process

Two-Stage Degradation Modeling and Remaining Useful Life Pre...

引用

Prognostics and System Health Management Conference (PHM-Qingdao)

作者： Xuerui Cao Kaixiang Peng Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China

Remaining useful life (RUL) prediction is the foundation and core of prognosis and health management to improve the reliability of the device. For a category of devices with two-stage degradation characteristics, the aleatory and epistemic uncertainty caused by inherent fluctuations within the system and insufficient sample knowledge is ignored frequently. Therefore, this paper proposes a novel two-stage degradation model and RUL prediction method considering aleatory and epistemic uncertainty. Firstly, a two-stage uncertain random process is established to characterize the degradation trajectory of the device, and the analytical expression of the RUL is derived under the concept of the first hitting time. Afterwards, the modified information criterion is employed to detect the change-point. Meanwhile, the stochastic uncertainty maximum likelihood estimation algorithm and Bayesian update are used to achieve parameter identification. Finally, the practicability of the proposed method is verified by Monte Carlo simulation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

datasets of Visualization for Machine Learning

arXiv

引用

arXiv 2024年

作者： Liu, Can Jiang, Ruike Tan, Shaocong Yu, Jiacheng Yang, Chaofan Shao, Hanning Yuan, Xiaoru Key Laboratory of Machine Perception Ministry of Education School of Intelligence Science and Technology Peking University China National Engineering Laboratory for Big Data Analysis and Application Peking University China

datasets of visualization play a crucial role in automating data-driven visualization pipelines, serving as the foundation for supervised model training and algorithm benchmarking. In this paper, we survey the literature on visualization datasets and provide a comprehensive overview of existing visualization datasets, including their data types, formats, supported tasks, and openness. We propose a what-why-how model for visualization datasets, considering the content of the dataset (what), the supported tasks (why), and the dataset construction process (how). This model provides a clear understanding of the diversity and complexity of visualization datasets. Additionally, we highlight the challenges faced by existing visualization datasets, including the lack of standardization in data types and formats and the limited availability of large-scale datasets. To address these challenges, we suggest future research directions. © 2024, CC BY.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Visual Design Of Artificial Pancreas Glucose Control Method

Visual Design Of Artificial Pancreas Glucose Control Method

引用

Complex Systems and Intelligent Science (CSIS-IAC), International Annual Conference on

作者： Ying Zhou Rui Zhuo Song Li Na Xia Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China

The number of diabetic patients is predicted to increase and the age of diabetic patients is slowly becoming younger. Diabetes is generally categorized into the following types: type I diabetes, type II diabetes, gestational diabetes, and other types of diabetes caused by pancreatic disease, endocrine disease, medications, and other factors. The traditional method of treating diabetes involves injecting insulin using a device outside the body. This method is physically and psychologically harmful to the diabetic. Therefore, this paper focuses on the glycemic control of patients with type I diabetes who have completely lost their insulin secretion, and whose pancreas is unable to secrete insulin. Therefore, it is necessary to use a blood glucose sensor to measure the blood glucose concentration in the patient's body. Then the measured blood glucose concentration in the diabetic patient's body is fed back to the computer terminal. Finally the controller is utilized for regulation. This paper focuses on the regulation of blood glucose in the body of type I diabetic patients and combines a fuzzy controller and a PID controller to regulate the blood glucose concentration in type I diabetic patients. In this paper, the blood glucose-insulin metabolism models of healthy people and diabetic patients are firstly established. Then the parameter values of the PID controller are adjusted through several trials to build a fuzzy rule base. Then the fuzzy controller is designed so that the diabetic's blood glucose can be successfully tracked to the healthy person's blood glucose changes. In this way, the purpose of regulating the blood glucose concentration of diabetic patients is realized. In addition, on the basis of realizing the control of blood glucose concentration. In this paper, the GUI toolbox of MATLAB is also used to design the visualization interface for the simulation process and the results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fault detection for rolling bearings by multi-sensor information fusion method with adaptive weights

Fault detection for rolling bearings by multi-sensor informa...

引用

data Driven Control and Learning Systems (DDCLS)

作者： Hao Wu YingHao Zhao Xu Yang Jian Huang Jiarui Cui Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China

Driven by the increasing needs for production safety, a fault detection method based on multi-sensor fusion with adaptive weight coefficients is proposed in this paper to make full use of multi-measuring points information. To this end, considering the different information among multi-measuring points, the variance contribution rate (VCR) of vibration signals are used to design adaptive weight coefficients for data fusion to fully utilize the information contained in each vibration signal. On this basis, the least atoms contain time domain and frequency domain are extracted based on dictionary sparse representation (DSR) algorithm to represent the feature information of the original signal to weaken the influence of the curse of dimensionality. Finally, K-nearest neighbor distance is used in sparse residual space (SRS) for fault detection (K-SRS). The effectiveness of the proposed method is demonstrated by the rolling bearings data, and results show the advantage of our proposed approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Interference Characterization and Mitigation for Multi-Beam ISAC Systems in Vehicular Networks

引用

IEEE Transactions on Wireless Communications 2024年第10期23卷 14729-14742页

作者： Wang, Yi Zhang, Qixun Zhang, J. Andrew Wei, Zhiqing Feng, Zhiyong Peng, Jinlin The School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu611731 China University of Electronic Science and Technology of China Quzhou324003 China The Key Laboratory of Universal Wireless Communications Ministry of Education Beijing University of Posts and Telecommunications Beijing100876 China The Global Big Data Technologies Centre University of Technology Sydney SydneyNSW2007 Australia The Artificial Intelligence Research Center National Innovation Institute of Defense Technology Beijing100071 China

— Millimeter-wave Integrated Sensing and Communications (ISAC) with multi-beam design holds significant promise for vehicular networks, offering multi-target omnidirectional sensing and high-capacity communication services concurrently. Nonetheless, the considerable challenge of potential mutual interference arises due to the high mobility and density of transmitters in such networks. To address this challenge effectively, we propose leveraging inter-vehicle communication to schedule communication and sensing signals for vehicles, thereby enhancing networked sensing capabilities. We first introduce an analytical framework to characterize the mutual interference among multiple vehicles. Subsequently, we evaluate the effectiveness of our proposed interference mitigation method in terms of interference probability, duration, and the achievable detectable density. Additionally, recognizing the different performance requirements of communication and sensing functions, we investigate a joint resource allocation problem catering to both aspects. Simulation results demonstrate a notable enhancement in the proposed ISAC-based interference mitigation, with a 58% reduction in interference probability compared to benchmarking schemes. © 2002-2012 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

A Survey on Smart Grid and its Applications

A Survey on Smart Grid and its Applications

引用

Complex Systems and Intelligent Science (CSIS-IAC), International Annual Conference on

作者： Yufan Zhao Ruizhuo Song Lina Xia Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China

Environmental issues have become an important challenge for human development, the application of renewable energy will greatly alleviate this problem. The introduction of renewable energy into the existing power grid will has many impacts such as energy distribution, communications and security issues, it is bound to intelligently upgrade the existing power grid. By querying relevant literature, this study summarizes and reviews the current research on smart grids from the above perspectives. At the same time, from the perspective of two emerging technologies, Internet of Things (IoT) and artificial intelligence, the application of smart grid to two emerging technologies is summarized. Finally, the possible development directions of smart grid are discussed and summarized.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Survey of Few-shot Learning-based Compound Fault Diagnosis Methods for Industrial Processes

A Survey of Few-shot Learning-based Compound Fault Diagnosis...

引用

Industrial Cyber-Physical Systems (ICPS)

作者： Liang Ma Fuzhong Shi Zijing Wu Kaixiang Peng Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China

Once the fault occurs in the industrial processes, the fault maybe always compound faults which take place in different locations, forms, and degrees. How to diagnose the multiple faults with coupling and propagation characteristics, enhance the reliability of the system, and ensure the reliable operation of industrial processes is very important. In this paper, a survey on mechanism and manifestation of symptoms for compound faults is given. Meanwhile, difficulties and research status of compound fault diagnosis methods, especially the few-shot learning-based methods are analyzed and discussed. Moreover, the advantages, disadvantages, and research directions are mentioned.

关键词： Surveys Fault diagnosis Learning systems Couplings Materials reliability Cyber-physical systems Compounds

来源：评论

学校读者我要写书评

暂无评论

Verifying Diagnosability of Discrete Event System with Logical Formula

引用

Chinese Journal of Electronics 2020年第2期29卷 304-311页

作者： GENG Xuena OUYANG Dantong HAN Cheng College of Computer Science and Technology Changchun University of Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering for Ministry of Education Jilin University

Diagnosability is an important property in the field of fault diagnosis. In this paper, a novel approach based on logical formula is proposed to verify diagnosability of Discrete event systems(DESs). CNFFSM is defined to represent a new model for DES. Each transition in DES can be described as a clause. According to CNF-FSM, we construct a CNF-diagnoser. Based on the resolution principle and CNF-diagnoser, an algorithm is presented to test whether the failure events can be detected or not in a finite number of observable *** algorithm can be applied in both off-line diagnosis and on-line diagnosis. Experimental results show that our algorithm can solve the diagnosability problem efficiently.

关键词： Fault diagnosis Diagnosability Discrete event system Finite state machine Conjunctive normal form

来源：评论

学校读者我要写书评

暂无评论

Shortcut Learning in In-Context Learning: A Survey

arXiv

引用

arXiv 2024年

作者： Song, Rui Li, Yingji Shi, Lida Giunchiglia, Fausto Xu, Hao College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University China Department of Information Engineering and Computer Science University of Trento Italy

Shortcut learning refers to the phenomenon where models employ simple, non-robust decision rules in practical tasks, which hinders their generalization and robustness. With the rapid development of Large Language Models (LLMs) in recent years, an increasing number of studies have shown the impact of shortcut learning on LLMs. This paper provides a novel perspective to review relevant research on shortcut learning in In-Context Learning (ICL). It conducts a detailed exploration of the types of shortcuts in ICL tasks, their causes, available benchmarks, and strategies for mitigating shortcuts. Based on the corresponding observations, we summarize the unresolved issues in existing research and attempts to outline the future research landscape of shortcut learning. © 2024, CC BY.

关键词： Contrastive Learning

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：