检索结果-内蒙古大学图书馆

arXiv 2023年

作者： He, Yingjie Li, Yuanman Chen, Changsheng Li, Xia Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen University China

The recently developed deep algorithms achieve promising progress in the field of image copy-move forgery detection (CMFD). However, they have limited generalizability in some practical scenarios, where the copy-move objects may not appear in the training images or cloned regions are from the background. To address the above issues, in this work, we propose a novel end-to-end CMFD framework by integrating merits from both conventional and deep methods. Specifically, we design a deep cross-scale patchmatch method tailored for CMFD to localize copy-move regions. In contrast to existing deep models, our scheme aims to seek explicit and reliable point-to-point matching between source and target regions using features extracted from high-resolution scales. Further, we develop a manipulation region location branch for source/target separation. The proposed CMFD framework is completely differentiable and can be trained in an end-to-end manner. Extensive experimental results demonstrate the high generalizability of our method to different copy-move contents, and the proposed scheme achieves significantly better performance than existing approaches. Copyright © 2023, The Authors. All rights reserved.

关键词： Cloning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Parameter Design with Frequency and Clock Drift Constraints in Microgrids∗ 63

Optimizing Parameter Design with Frequency and Clock Drift C...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Yu, Chang Lu, Xiaoqing Wuhan University of Science and Technology School of Information Science and Engineering Wuhan430081 China Huazhong University of Science and Technology Ministry of Education Key Laboratory of Image Processing and Intelligent Control Wuhan430074 China Wuhan University School of Electrical Engineering and Automation Wuhan430000 China

ISBN: (纸本)9798350316339

Microgrids subjected to secondary cooperative control encounter significant challenges, including operational constraints and clock drifts, adversely affecting their stability and efficiency. This paper provides conditions that assure optimal microgrid performance in both transient and steady-state scenarios, focusing on the effects of clock drifts and fluctuations in load. Furthermore, we introduce a novel approach for designing secondary control parameters, specifically engineered to minimize steady-state discrepancies attributable to clock drifts while ensuring adherence to standards for transient operations. Comprehensive experimental validations corroborate the effectiveness of our proposed solutions. © 2024 IEEE.

关键词： Microgrids

来源：评论

学校读者我要写书评

暂无评论

DMAM-ECG: A Diffusion Model with Self-Attention Module for ECG Signal Denoising

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第3期9卷 1278-1296页

作者： Hu, Zheng-Dong Hong, Yang Huang, Jia-Yan Chen, Kai-Hong Zhao, Wan-Qi Grau, Antoni Guerra, Edmundo Wang, Chuan-Sheng Zhang, Fu-Quan New Engineering Industry College Putian University Putian351100 China School of Mathematics and Data Science Minjiang University Fuzhou350108 China The University of Sheffield SheffieldS10 2TN United Kingdom Department of Automatic Control Technical Polytechnic University of Catalonia Barcelona08034 Spain Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350108 China

Electrocardiogram (ECG) is the most common and non-invasive auxiliary diagnostic technique for heart disease. However, the ECG signal is susceptible to various noises during the collection process, which will impact subsequent analysis and diagnosis. Therefore, ECG signal denoising has become the primary task after signal acquisition. ECG signal denoising aims to remove noise interference from the collected noisy signals for clarify abnormal waveforms in it, and thus diagnose diseases more accurately. In this paper, to obtain high-quality and high-fidelity denoised ECG signals, we propose a novel diffusion model with self-attention module for ECG signal denoising (DMAM-ECG). Specifically, the DMAM-ECG contains two main branches used to extract features of input noise signal observations and potential variables, respectively. Each branch consists of 6 designed Convolution-Instancenormal-LeakyReLU Filter Blocks (CIL-Filter Blocks). Meanwhile, DMAM-ECG introduces the self-Attention Module Fusion Blocks (SAM-Fusion Blocks) to further extract features for the first branch, and then fuse the output features with the second branch. Besides, we use a multi-shot reconstruction strategy to further improve signal denoising. Quantitative and qualitative results on the QT database show that the proposed DMAM-ECG performs better than the existing 5 state-of-the-art ECG signal denoising methods, especially for strong noise interference ECG signal removal. To sum up, our DMAM-ECG introduces self-attention module into the diffusion model to improve the grasp of global information and achieve high-quality information preservation for extremely noise removal of ECG signal. In particular, it uses only 3-shot reconstruction gets much better denoised results than that of the best baseline with 10-shot. The code of the proposed DMAM-ECG is available at https://***/luvletterh/DMAM-ECG. © 2024, Taiwan Ubiquitous information CO LTD. All rights reserved.

关键词： Signal denoising

来源：评论

学校读者我要写书评

暂无评论

Named Entity recognition of Electronic Medical Records based on BERT-BiLSTM-Biaffine Model

Named Entity Recognition of Electronic Medical Records based...

引用

2023 Asia-Pacific Conference on Image processing, Electronics and Computers, IPEC 2023

作者： Wang, Peng Gu, Jinguang Institute of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Prov. Key Laboratory of Intelligent Information Processing and Real Time Industrial Systems Wuhan University of Science and Technology Wuhan China

In the case of the specific task of identifying named entities within electronic medical record, it is hard to determine the boundary of nested entities, and existing NER systems have insufficient decoding performance. Based on the pre training model BERT, this paper introduces a novel network structure called Biaffine Layer using a bidirectional LSTM layer. The network uses a dual affine attention mechanism for semantic information learning, which can better interact with the semantic information of entity heads and entity tails, thereby achieving better recognition results for entities. Due to the sparsity of named entity datasets and the uneven distribution of entity categories, traditional binary cross entropy loss functions require multiple rounds of training to decode entities. In this paper, we have modified the binary cross entropy loss function to make the proposed model faster decode the entities that need to be identified. The model performs well, according to the experimental findings. The approach suggested in this paper offers a fresh approach to the NER issue raised by electronic medical records, and it is anticipated to considerably boost the effectiveness and caliber of clinical medical research. © Published under licence by IOP Publishing Ltd.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

A Multi-scale Framework for Out-of-Distribution Detection in Dermoscopic Images 1

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Huang, Zhongzheng Wang, Tao Cai, Yuanzheng Liang, Lingyu College of Computer and Data Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering and International Digital Economy College Minjiang University Fuzhou350108 China The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University Wuyishan354300 China Fujian Yilian-Health Nursing Information Technology Co. Ltd. Fuzhou350003 China School of Electronic and Information Engineering South China University of Technology Guangzhou510641 China

ISBN: (数字)9783031200960

ISBN: (纸本)9783031200953

The automatic detection of skin diseases via dermoscopic images can improve the efficiency in diagnosis and help doctors make more accurate judgments. However, conventional skin disease recognition systems may produce high confidence for out-of-distribution (OOD) data, which may become a major security vulnerability in practical applications. In this paper, we propose a multi-scale detection framework to detect out-of-distribution skin disease image data to ensure the robustness of the system. Our framework extracts features from different layers of the neural network. In the early layers, rectified activation is used to make the output features closer to the well-behaved distribution, and then an one-class SVM is trained to detect OOD data;in the penultimate layer, an adapted Gram matrix is used to calculate the features after rectified activation, and finally the layer with the best performance is chosen to compute a normality score. Experiments show that the proposed framework achieves superior performance when compared with other state-of-the-art methods in the task of skin disease recognition. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Multi-Branch Spatial-Temporal Attention Graph Convolution Network for Skeleton-based Action recognition 41

Multi-Branch Spatial-Temporal Attention Graph Convolution Ne...

引用

第41届中国控制会议

作者： Daoshuai Wang Dewei Li Yaonan Guan Gang Wang Haibin Shao Department 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

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Skeleton-based human action reco gnition has attracted considerable research interest due to its robustness to dynamic environments and complex *** based on graph neural networks have achieved great success in this ***,most of these graph neural network based methods adopt a single-branch or two-stream structure with limited input *** to the separation of space and time,many methods cannot pay attention to the critical information of human skeleton sequence,and multi-scale spatial-temporal dependent attention modeling becomes the key to *** paper proposes a novel multi-branch Spatio-temporal attention graph convolutional neural network(MB-STAGCN) to recognize human actions from skeleton *** proposed model adopts a multi-branch structure,fuses three-stream features,and then inputs them into the backbone network to extract features from multiple perspectives to a greater ***,we design a new temporal convolutional block for multi-scale extraction of information in the backbone *** also propose an attention block named Spatio-temporal Concat Attention(STCatAtt) to capture critical *** on benchmark datasets show remarkable performance for human action reco gnition,demonstrating the effectiveness of our method.

关键词： Skeleton-based human action recognition MB-STAGCN STCatAtt

来源：评论

学校读者我要写书评

暂无评论

On Privacy-Preserving Task Assignment for Heterogeneous Users in Mobile Crowdsensing 26

On Privacy-Preserving Task Assignment for Heterogeneous User...

引用

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Zhang, Ji Li, Peng Huang, Weiyi Nie, Lei Bao, Haizhou Liu, Qin Wuhan University of Science and Technology School of Computer Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System China Wuhan University School of Cyber Science and Engineering China

ISBN: (纸本)9798350331684

Task assignment is a key challenge in mobile crowd-sensing because of the varying capabilities of crowd users. Location-based task assignment schemes require users to upload their location to an untrusted platform, which raises many privacy concerns. However, stronger privacy preservation may lead to lower system utility. It is challenging to maximize system utility under privacy preservation for users. In this paper, we propose a privacy-preserving task assignment for heterogeneous users (PTAH) problem in mobile crowdsensing. Specifically, we divide users into two groups: private users with location privacy requirements and public users without location privacy requirements. We first design a privacy-preserving mechanism to obfuscate the actual location of private users. Then we construct a relationship graph based on the locations between users and tasks. We prove that the PTAH problem is an NP-hard problem, so to maximize the system utility, we propose an approximation algorithm based on the greedy algorithm. Then we propose a multi-thread cooperative simulated annealing algorithm to search for a better approximate solution. Finally, we conducted simulations based on the widely-used real-world Roma dataset. The results show that our proposed algorithm consistently outperforms other baseline algorithms. © 2023 IEEE.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Dehazing Quality Evaluation Algorithm Integrating Dark Channel Theory and Image Depth Estimation

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第2期9卷 1119-1133页

作者： Huang, Jia-Yan Xu, Xin-Xin Luo, Shao-Ye Zhao, Wan-Qi Fan, Hao-Yi Grau, Antoni Guerra, Edmundo Wang, Chuan-Sheng Zhang, Fu-Quan New Engineering Industry College Putian University Putian351100 China The University of Sheffield SheffieldS10 2TN United Kingdom School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou450001 China Department of Automatic Control Technical Polytechnic University of Catalonia Barcelona08034 Spain Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350108 China

Image dehazing is an important research topic and hotspot in the fields of image processing and computer vision. Therefore, evaluating the performance of image dehazing algorithms has become an import research issue. However, current image quality assessment (IQA) algorithms only judge the final dehazed image and do not give an analysis of the capabilities of the image dehazing algorithm. In order to fill this gap, we propose an image dehazing quality assessment method that integrated the dark channel prior with image depth estimation. The proposed method first uses the dark channel prior to estimate the absolute amount of haze removed from each pixel as an indication of the performance of dehazing. Then, a dual-scale variance ratio method is introduced to estimate the scene depth of the image. Finally, the relative dehazing is calculated from the obtained absolute dehazing and the image depth to represent the capability of the dehazing algorithm. The method proposed in this paper first introduces the concepts of relative and absolute dehazing quantities, along with pioneering a pixel-level evaluation of dehazing outcomes. Extensive experiments show that the algorithm proposed in this paper is more in line with human subjective judgment than other IQA algorithms. © 2024, Taiwan Ubiquitous information CO LTD. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Structured Sparse Coding With the Group Log-regularizer for key Frame Extraction

引用

IEEE/CAA Journal of Automatica Sinica 2022年第10期9卷 1818-1830页

作者： Zhenni Li Yujie Li Benying Tan Shuxue Ding Shengli Xie the School of Automation Guangdong University of TechnologyGuangzhou 510006 the Guangdong-Hong Kong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangdong University of Technology(GDUT)Guangzhou 510006China the School of Artificial Intelligence Guilin University of Electronic TechnologyGuilin 541004China the National Institute of Advanced Industrial Science and Technology TsukubaIbaraki 305-8560Japan IEEE the Key Laboratory of Intelligent Information Processing and System Integration of Io T(GDUT) Ministry of Education Guangdong Key Laboratory of IoT Information Technology(GDUT) Guangzhou 510006China

key frame extraction based on sparse coding can reduce the redundancy of continuous frames and concisely express the entire ***,how to develop a key frame extraction algorithm that can automatically extract a few frames with a low reconstruction error remains a *** this paper,we propose a novel model of structured sparse-codingbased key frame extraction,wherein a nonconvex group log-regularizer is used with strong sparsity and a low reconstruction *** automatically extract key frames,a decomposition scheme is designed to separate the sparse coefficient matrix by *** rows enforced by the nonconvex group log-regularizer become zero or nonzero,leading to the learning of the structured sparse coefficient *** solve the nonconvex problems due to the log-regularizer,the difference of convex algorithm(DCA)is employed to decompose the log-regularizer into the difference of two convex functions related to the l1 norm,which can be directly obtained through the proximal ***,an efficient structured sparse coding algorithm with the group log-regularizer for key frame extraction is developed,which can automatically extract a few frames directly from the video to represent the entire video with a low reconstruction *** results demonstrate that the proposed algorithm can extract more accurate key frames from most Sum Me videos compared to the stateof-the-art ***,the proposed algorithm can obtain a higher compression with a nearly 18% increase compared to sparse modeling representation selection(SMRS)and an 8% increase compared to SC-det on the VSUMM dataset.

关键词： Difference of convex algorithm(DCA) group logregularizer key frame extraction structured sparse coding

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Team Personality Tourism Route Design Based on Fuzzy APACA

Multi-Objective Team Personality Tourism Route Design Based ...

引用

Emerging Technology (INCET), International Conference for

作者： Xiaoling Song Huanhuan Peng Key Laboratory of Intelligent Information Processing Control of Chongqing Municipal Institutions of Higher Education Chongqing Three Gorges University

ISBN: (数字)9798350361155

ISBN: (纸本)9798350361162

In order to solve the challenge of multi-objective team personalized tourism route design, in view of the shortcomings of the existing divide and conquer algorithms, this study proposes an innovative personalized tourism route design method based on fuzzy APACA. This new scheme uses the principles of gradient descent theory to accurately identify and locate key influencing factors, and accordingly carries out a sensible classification of indicators to reduce possible interference. At the same time, by using the unique mechanism of fuzzy APACA, this scheme cleverly constructs the design strategy of tourism routes. The empirical results show that this scheme shows a significant improvement compared with the traditional divide and conquer algorithm in terms of key performance indicators such as the accuracy of personalized tourism route design and the processing efficiency of key factors, showing its obvious strong advantages. In the multi-objective team, the personalized tourism route design plays a crucial role, which can accurately predict and optimize the growth trend and output results of the multi-objective team's personalized tourism route design. However, in the face of complex simulation tasks, traditional divide-and-conquer algorithms show some inherent shortcomings, especially when dealing with multi-level challenges, their performance is often unsatisfactory. To overcome this, this study introduces a new idea of fuzzy APACA optimization for the design of personalized tourism routes, and accurately controls the influencing parameters through gradient descent theory, which is used as the road map for index allocation, and then uses fuzzy APACA to innovate and construct a system scheme. The test results clearly point out that in the context of the evaluation criteria, the new scheme has been significantly optimized in terms of accuracy and processing speed for a variety of challenges, showing stronger performance superiority. Therefore, in the design of multi-

关键词： Accuracy Roads key performance indicator Interference Prediction algorithms Market research Classification algorithms

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：