检索结果-内蒙古大学图书馆

9th IEEE Joint International Information Technology and Artificial Intelligence Conference, ITAIC 2020

作者： Chen, Siyu Li, Wei Huazhong University of Science and Technology School of Artificial Intelligence and Automation Wuhan430074 China Image Processing and Intelligent Control Key Laboratory Education Ministry of China Wuhan430074 China

In recent years, Deep Neural Network (DNN) has been widely used in the domain of computer vision, but its further development is restricted because of the lack of train samples. Fine-tuning is one of deep transfer learning methods to solve this problem. Nowdays, some existing Fine-tuning approaches assume that if the fine-tuned network could be as close to the pre-trained network as possible, the source knowledge would be fully utilized to improve the study effect. Although these approaches work pretty well, the assumptions on which they are based have not been systematically proved. Due to the complexity of DNNs, offering a reasonable and accurate explanation of the performance of the network is significant for designing new algorithms. In this paper, we design a series of experiments with or without transfer learning respectively, to characterize the relationship between network differences and network performance. The results show that there is an obvious negative correlation between them under certain circumstances. This conclusion can not only provide a more reasonable explanation for the relevant transfer learning algorithm, but also provide support and in-spiration for the future work. © 2020 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Surface Defect Detection Based on Deep Learning and Collaborative Cloud-edge Computation 7

Surface Defect Detection Based on Deep Learning and Collabor...

引用

7th International Conference on Computer and Communications, ICCC 2021

作者： He, Shunjie Yang, Bo Zhu, Dafeng Li, Cheng Shanghai Jiao Tong University Department of Automation Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Engineering Research Center of Industrial Intelligent Control and Management Shanghai200240 China

ISBN: (纸本)9781665409506

Surface defect detection is a fundamental step of quality management. Nowadays, surface defect detection system based on machine vision technology has made great progress which can gradually replace the human inspector. With the help of convolutional neural networks, the accuracy and stability of the surface defect detection algorithm are improving rapidly. However, it is difficult to process the images which have small defect areas and complex backgrounds. Furthermore, lacking defective samples and limited computation resources are also tough problems. To deal with these problems, a two-stage algorithm combined with object detection and classification networks is proposed. Transform learning and data augmentation are used to deal with the problem of lacking defect samples. Besides, a detection system based on collaborative cloud-edge computation is designed to improve the performance of the algorithm. The result shows that the proposed method has high performance and low requirements of computation resources. © 2021 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Distributed Observer Design over Directed Switching Topologies

arXiv

引用

arXiv 2024年

作者： Xu, Haotian Liu, Shuai Wang, Bohui Wang, Jingcheng School of Control Science and Engineering Shandong University Jinan250061 China The School of Aerospace Science and Technology Xidian University Xi’an710071 China Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China

The distributed observer design problem holds significant importance in cases in which the output information of a system is decentralized across different subsystems. Each subsystem has a local observer and access to one part of the measurement outputs and information exchanged through communication networks. This paper focuses on the design of distributed observer with jointly connected directed switching networks. The problem presents challenges due to passive switching modes and the open-loop unboundedness that results from local observability. To overcome these challenges, we develop a network transformation mapping method whereby each local observer can classify itself into an independent subgraph based on independent judgment. Next, an observable decomposition and reorganization method is developed for the digraph case to ensure that each subgraph possesses independent dynamic properties. Asymptotic omniscience is then proven using a developed recursive proof method. This paper includes many previous results as special cases, because most are only suitable for undirected switching topologies or fast-switching cases. An adaptive coupling gain design is proposed to simplify the calculation and verification of conditions that guarantee asymptotic omniscience. Finally, simulation results with the power system show the validity of the developed theory. © 2024, CC BY.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Locating and Sizing Charging Station in Multi-Period to Promote Electric Vehicles Adoption in Urban Areas

SSRN

引用

SSRN 2023年

作者： Hu, Dandan Huang, Liu Liu, Chen Liu, Zhi-Wei The School of Management South-central Minzu University Wuhan430074 China The School of Engineering RMIT University MelbourneVIC3001 Australia The School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China The Key Laboratory of Image Processing and Intelligent Control Ministry of Education Huazhong University of Science and Technology Wuhan430074 China

The layout of public fast charging stations often fails to meet the charging demand of electric vehicle (EV) users, resulting in charging anxiety. To address this issue and promote the widespread use of EVs in urban areas, this paper presents a multiperiod locating and sizing optimization model under dynamic demand. The model incorporates GPS trajectory extraction data to identify potential charging demand points and considers the mobile load characteristics of EVs for fusion modeling. A multiperiod change formula is proposed to reflect the interaction between public fast charging stations and EV market penetration, incorporating charging opportunity and waiting time satisfaction as measures of charging service quality. To solve the model, a heuristic algorithm combining genetic algorithm (GA) and k-medoids clustering algorithm is designed. We apply the model to an actual case of Shenzhen and find that increasing investment in charging infrastructure can boost EV market penetration in the later planning period. Moreover, the gap between charging opportunity and waiting time satisfaction tends to narrow as the planning progresses. Our findings highlight the importance of optimizing the location and size of public fast charging stations to improve the charging service quality and promote the adoption of EVs. © 2023, The Authors. All rights reserved.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Inferring Topology of Networked Dynamical Systems by Active Excitations

arXiv

引用

arXiv 2022年

作者： Li, Yushan He, Jianping Chen, Cailian Guan, Xinping Dept. of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China

Topology inference for networked dynamical systems (NDSs) has received considerable attention in recent years. The majority of pioneering works have dealt with inferring the topology from abundant observations of NDSs, so as to approximate the real one asymptotically. Leveraging the characteristic that NDSs will react to various disturbances and the disturbance’s influence will consistently spread, this paper focuses on inferring the topology by a few active excitations. The key challenge is to distinguish different influences of system noises and excitations from the exhibited state deviations, where the influences will decay with time and the exciatation cannot be arbitrarily large. To practice, we propose a one-shot excitation based inference method to infer h-hop neighbors of a node. The excitation conditions for accurate one-hop neighbor inference are first derived with probability guarantees. Then, we extend the results to h-hop neighbor inference and multiple excitations cases, providing the explicit relationships between the inference accuracy and excitation magnitude. Specifically, the excitation based inference method is not only suitable for scenarios where abundant observations are unavailable, but also can be leveraged as auxiliary means to improve the accuracy of existing methods. Simulations are conducted to verify the analytical results. Copyright © 2022, The Authors. All rights reserved.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation for Deep Learning Based a Utomaticmo Dulation Recognition

SSRN

引用

SSRN 2023年

作者： Ma, Hongbin Feng, Zhixi Yang, Shuyuan Wang, Min Wu, Tao Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University Xi’an710071 China Key Laboratory of Radar Signal Processing Xidian University Xi’an710071 China Xidian University China Institute School of Artificial Intelligence Xidian University TaiBai road 2# Shannxi Province Xi’an China

Data augmentation, as a strategy to expand training datasets, can be utilized to improve the accuracy of Deep Learning(DL)-based models to a certain extent. However, existing data augmentation methods for the DL-based Automatic Modulation Recognition (AMR) task lack a theoretical basis, and the availability of these methods to different types of AMR models has not been evaluated. In this paper, we first model the transformation process from an information source to a modulation signal and analyze the parameters that influence the difference between modulation signals for the theoretical basis of data augmentation in the AMR field. Then we propose nine signal augmentation methods to generate argumentation signals by modifying the influence parameters in the amplitude domain, the time domain, and the frequency domain. Finally, we conduct a series of experiments on the public RML2016.10a and RML2016.10b datasets to evaluate the effectiveness of the proposed methods andanalyze the availability of these methods to Convolutional Neural Network (CNN)-based AMR models, and hybrid AMR models based on CNN and Recurrent Neural Network. © 2023, The Authors. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Taming Consistency Distillation for Accelerated Human image Animation

arXiv

引用

arXiv 2025年

作者： Wang, Xiang Zhang, Shiwei Yuan, Hangjie Wei, Yujie Zhang, Yingya Gao, Changxin Wang, Yuehuan Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Alibaba Group China Fudan University China

Recent advancements in human image animation have been propelled by video diffusion models, yet their reliance on numerous iterative denoising steps results in high inference costs and slow speeds. An intuitive solution involves adopting consistency models, which serve as an effective acceleration paradigm through consistency distillation. However, simply employing this strategy in human image animation often leads to quality decline, including visual blurring, motion degradation, and facial distortion, particularly in dynamic regions. In this paper, we propose the DanceLCM approach complemented by several enhancements to improve visual quality and motion continuity at low-step regime: (1) segmented consistency distillation with an auxiliary light-weight head to incorporate supervision from real video latents, mitigating cumulative errors resulting from single full-trajectory generation;(2) a motion-focused loss to centre on motion regions, and explicit injection of facial fidelity features to improve face authenticity. Extensive qualitative and quantitative experiments demonstrate that DanceLCM achieves results comparable to state-of-the-art video diffusion models with a mere 2-4 inference steps, significantly reducing the inference burden without compromising video quality. The code and models will be made publicly available. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Retinal Vessel Segmentation Based on UNet and Edge Detection

Retinal Vessel Segmentation Based on UNet and Edge Detection

引用

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Peixin Yan Zuoyong Li Rong Hu Xinrong Cao College of Computer Science and Mathematics Fujian University of Technology Fuzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Colloge of Computer and Control Engineering Minjiang University Fuzhou China

Retinal vessel segmentation is important for the diagnosis of many diseases. The segmentation of microscopic vessels is one of the challenges because of the complex structure of retinal vessels, which makes it challenging to tell the vessels apart from the background. In order to improve the segmentation performance of retinal vessels, we use the edge detection method of HED to optimize the segmentation effect of UNet. Using Hybrid Dilated Convolution not only increases the perceptual field, but also avoids the loss of information continuity caused by the continuous use of dilated convolution. The Pyramid Pooling Module is used at the end of the encoder to compensate for the information loss caused by downsampling. Finally, the output of edge detection and image segmentation is combined as the final result. The model is evaluated in two mainstream datasets DRIVE and CHASE_DB1, and the experimental results show that the proposed model can improve the performance of retinal vessel segmentation.

关键词： Training image segmentation Convolution image edge detection Microscopy Feature extraction Retinal vessels

来源：评论

学校读者我要写书评

暂无评论

A Multi-Kernel Principal Component Analysis Method for Quality-Related Fault Detection

A Multi-Kernel Principal Component Analysis Method for Quali...

引用

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Lingxia Mu Biyu Lei Ding Liu School of Automation and Information Engineering Xi’an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an University of Technology Xi’an China

ISBN: (纸本)9781665465373

In this paper, a multi-kernel principal component analysis (MKPCA) method for quality-related fault detection is proposed. The initial space is firstly mapped to a new space. The correlated information between the new space and output quality is then obtained by the kernel function. Meanwhile, with consideration of the advantage of global function and local function, a weight factor which combines them together is introduced to construct a multi-kernel function. In this way, the algorithm achieves better learning ability. The new space is projected to two mutually orthogonal subspaces, i.e., quality-related part and quality-unrelated part. In each subspace, fault information is expressed by different statistical indicators. The numerical example is presented to evaluate the performance of the MKPCA. The results show better reliability and high fault detection rate through proper spatial decomposition and kernel function construction.

关键词： Correlation Automation Fault detection Feature extraction Eigenvalues and eigenfunctions Reliability Matrix decomposition

来源：评论

学校读者我要写书评

暂无评论

Insulator Defect Detection Based on YOLOv4-tiny with Improved Feature Fusion

Insulator Defect Detection Based on YOLOv4-tiny with Improve...

引用

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Yuning Zhong Rong Hu Zuoyong Li Yuanzheng Cai College of Computer Science and Mathematics Fujian University of Technology Fuzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou China

Insulator exposed to a wild environment for long-term running usually suffers from the damage of natural calamities that makes them become one of the most fragile components in the whole power system. In this case, even a slight fault will seriously affect the power supply safety of the power grid. Therefore, it is critical to find and identify the faulty insulator efficiently and accurately. However, an insulator is quite a small component in comparison with a huge power system which makes it hard to visible with naked eyes. This characteristic leads to poor recognition accuracy for existing detection methods. In order to solve the above problems, we propose an insulator defect detection algorithm based on an improved YOLOv4-tiny model. It differs from existing insulator detection models, our algorithm applies the effective channel attention network to the feature extraction network of YOLOv4-tiny, which significantly enhances the feature extraction ability of the backbone network. These two-way features of the pyramid can be fully fused in the two-way feature fusion stages seamlessly. Experimental results show that compared with, our proposed algorithm outperforms Faster RCNN and YOLOv3 in average classification accuracy, missed detection, and false detection.

关键词： Fault diagnosis Power supplies Education Insulators Feature extraction Power grids Safety

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：