检索结果-内蒙古大学图书馆

2021 IEEE International Conference on Artificial Intelligence and computer Applications, ICAICA 2021

作者： Zhao, Chenyang Ke, Wei Wang, Tingting Nanjing Normal University Jiangsu Key Laboratory on Optoelectronic Technology in School of Computer and Electronic Information School of Artificial Intelligence Nanjing China Nanjing University of Information Science Technology Jiangsu Key Lab of Meteorological Observation and Information Processing Nanjing China

ISBN: (纸本)9781665418676

This paper presents a sparsity-based multi-target localization method for multiple-input multiple-output (MIMO) radar systems using distributed antennas. Since targets usually lie at some points within the localization domain, we are able to exploit this sparsity to convert the radar localization problem into a distributed recovery solution. Based on this natural sparsity, in this paper we introduce a block-sparse illustration model for distributed MIMO radar and propose a completely unique block-sparse recovery algorithmic rule supported approximate l0 norm diminution. The novelty of this technique is using l0 norm to push inter-block sparsity within the signals and also the optimisation problem is resolved by an ordered procedure in conjunction with a conjugate-gradient technique for quick reconstruction. Moreover, the amount of targets doesn't be well-known in advance. The effectiveness of this technique is incontestable by simulation results that obtain better localization performance and reduce computation complexness for giant sized data. © 2021 IEEE.

关键词： MIMO radar

来源：评论

学校读者我要写书评

暂无评论

Image Segmentation via Fischer-Burmeister Total Variation and Thresholding

引用

Advances in Applied Mathematics and Mechanics 2022年第4期14卷 960-988页

作者： TingtingWu Yichen Zhao Zhihui Mao Li Shi Zhi Li Yonghua Zeng School of Science Nanjing University of Posts and TelecommunicationsNanjingJiangsu 210023China The Department of Computer Science and Technology Shanghai Key Laboratory of Multidimensional Information ProcessingEast China Normal UniversityShanghai 200241China College of Field Engineering PLA Army Engineering UniversityNanjingJianhsu 210007China

Image segmentation is a significant problem in image *** this paper,we propose a new two-stage scheme for segmentation based on the Fischer-Burmeister total variation(FBTV).The first stage of our method is to calculate a smooth solution from the FBTV Mumford-Shah ***,we design a new difference of convex algorithm(DCA)with the semi-proximal alternating direction method of multipliers(sPADMM)*** the second stage,we make use of the smooth solution and the K-means method to obtain the segmentation *** simulate images more accurately,a useful operator is introduced,which enables the proposed model to segment not only the noisy or blurry images but the images with missing pixels *** demonstrate the proposed method produces more preferable results comparing with some state-of-the-art methods,especially on the images with missing pixels.

关键词： Image segmentation Fischer-Burmeister total variation difference of convex algorithm sPADMM K-means method.

来源：评论

学校读者我要写书评

暂无评论

Asymptotics-Aware Multi-View Subspace Clustering

引用

IEEE Transactions on Multimedia 2025年

作者： Xu, Yesong Chen, Shuo Li, Jun Yang, Jian Anhui Polytechnic University School of Computer and Information Wuhu241000 China RIKEN Center for Advanced Intelligence Project Tokyo103-0027 Japan Nanjing University of Science and Technology PCA Laboratory Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing210094 China Nanjing University of Science and Technology Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing210094 China

Recently, multi-view subspace clustering has attracted extensive attention due to the rapid increase of multi-view data in many real-world applications. The main goal of this task is to learn a common representation of multiple subspaces from the given multi-view data, and most existing methods usually directly merge multiple groups of features by the single-step integration. However, there may exist large disparities among different views of the data, and thus the conventional single-step practice can hardly obtain a generally consistent feature representation for the multi-view data. To overcome this challenge, we present a novel approach dubbed "Asymptotics-Aware Multi-view Subspace Clustering (A2 MSC)"to pursue a consistent feature representation in a multi-step way, which iteratively conducts the data recovery to gradually reduce the differences between pairwise views. Specifically, we construct an asymptotic learning rule to update the feature representation, and the iteration result converges to a consistent feature vector for characterizing each instance of the original multi-view data. After that, we utilize such a new feature representation to learn a clustering-oriented similarity matrix via minimizing a self-expressive objective, and we also design the corresponding optimization algorithm to solve it with convergence guarantees. Theoretically, we prove that the learned asymptotic representation effectively integrates multiple views, thereby ensuring the effective handling of multi-view data. Empirically, extensive experimental results demonstrate the superiority of our proposed A2 MSC over the state-of-the-art multi-view subspace clustering approaches. © 2025 IEEE.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Applications for COVID-19 Analysis:A State-of-the-Art Survey

引用

computer Modeling in Engineering & Sciences 2021年第10期129卷 65-98页

作者： Wenqian Li Xing Deng Haijian Shao Xia Wang School of Computer Jiangsu University of Science and TechnologyZhenjiang212003China School of Automation Key Laboratory of Measurement and Control for CSEMinistry of EducationSoutheast UniversityNanjing210096China School of Information Science and Technology Nantong UniversityNantong226019China

The COVID-19 has resulted in catastrophic situation and the deaths of millions of people all over the *** this paper,the predictions of epidemiological propagation models,such as SIR and SEIR,are introduced to analyze the earlier COVID-19 *** deep learning methods combined with transfer learning are familiar with classification-detection approaches based on chest X-ray and CT images are presented in ***,deep learning approaches have also been applied to lung ultrasound(LUS),which has been shown to be more sensitive than chest X-ray and CT images in detecting *** the absence of a vaccine,the machine learning-related approaches are applied to analyze vaccine candidates in the realm of biology and *** telehealth system played a major role in combating the pandemic from all aspects and reducing contact with patients during this *** language processing-related methods are utilized to analyze tweets related to the COVID-19 epidemic on social media,and further analyze public sentiment and subject modeling,so as to arrange corresponding measures to appease public *** particular,this survey is to summarize and analyze the contributions made in various fields during the COVID-19 pandemic by considering both the contribution of deep learning in chest X-ray and CT images,as well as the application of the latest LUS during the COVID-19 *** and the importance of public sentiment analysis during a pandemic were also described in detail.

关键词： COVID-19 epidemiological propagation models deep learning transfer learning classification-detection lung ultrasound telehealth system

来源：评论

学校读者我要写书评

暂无评论

DBSSL: A Scheme to Detect Backdoor Attacks in Self-Supervised Learning Models

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Huang, Yuxian Yang, Geng Yuan, Dong Yu, Shui Nanjing University of Posts and Telecommunication College of Computer Science and Software China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing China University of Sydney School of Electrical and Information Engineering Australia University of Technology Sydney School of Computer Science Australia

Recently, self-supervised learning has garnered significant attention for its ability to extract high-quality features from unlabeled data. However, existing research indicates that backdoor attacks can pose significant threats to self-supervised learning. Additionally, due to the substantial training overhead, traditional backdoor detection methods in supervised learning, such as meta-learning, are not well-suited for self-supervised learning. Current backdoor detection methods for self-supervised learning can only defend against backdoor attacks triggered by patch. To address this challenge, we proposes DBSSL, a scheme that can efficiently detect backdoor attacks in self-supervised learning models. In DBSSL, we connect backdoor attacks with adversarial attacks and use adversarial perturbations for detection. Specifically, we first conduct targeted adversarial attacks on the samples, classifying them into different classes. Then, we employ the Z-Score method to analyze these adversarial perturbations. If outliers are present, we can infer that the self-supervised learning model has been backdoored. Unlike previous works, our scheme is better suited for downstream users with constrained computation resources and exhibits excellent detection capabilities for backdoor attacks caused by patch -type or global triggers. Abundant theoretical analysis has demonstrated the feasibility of our scheme. Moreover, extensive experiments show that our method performs well in detecting prevalent backdoor attacks in self-supervised learning, achieving detection accuracy exceeding 95%. © 2004-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Method for Automatic Identification of Natural Fracture Based on Machine Learning: A Case Study on the Dahebian Block of the Liupanshui Basin in Guizhou Province 13th

A Method for Automatic Identification of Natural Fracture Ba...

引用

13th International Field Exploration and Development Conference, IFEDC 2023

作者： Zhao, Wei-Guang Sang, Shu-Xun Cheng, De-Qiang Han, Si-Jie Zhou, Xiao-Zhi Zhang, Jin-Chao Zhao, Fu-Ping School of Resources and Geosciences China University of Mining and Technology Xuzhou221116 China Jiangsu Key Laboratory of Coal-Based Greenhouse Gas Controland Utilization China University of Mining and Technology Xuzhou221008 China Carbon Neutrality Institute China University of Mining and Technology Xuzhou221008 China Artificial Intelligence Research Institute China University of Mining and Technology Xuzhou221116 China School of Information and Control Engineering China University of Mining and Technology Xuzhou221116 China Key Laboratory of Coalbed Methane Resources and Reservoir Formation Process Ministry of Education China University of Mining and Technology Xuzhou221116 China Key Laboratory of Unconventional Natural Gas Evaluation and Development in Complex Tectonic Areas Ministry of Natural Resources Guiyang550009 China Guizhou Engineering Research Institute of Oil & Gas Exploration and Development Guiyang550009 China

ISBN: (纸本)9789819702718

Natural fractures are effective storage spaces and important seepage channels for oil and gas reservoirs. Accurately identifying natural fractures in reservoirs is crucial for the exploration and development of oil and gas resources. This article combines conventional and imaging logging data and uses machine learning to automatically identify natural fractures in reservoirs. The fracture labels of conventional logging come from imaging logging. Conventional logging data is decomposed through multi-scale wavelet to extract components that reflect fracture information, and further build the original data set. The AdaBoost model is trained based on a modified dataset of balanced samples for automatic fractures recognition in logging. The research results indicate that the approximate component and high-frequency component reflect the fluctuation of the formation and noise information respectively, and have little impact on the reservoir fractures identification;The medium frequency component can reflect the characteristic information of fractures and can be used for model training;After hyper-parameter optimization, the AdaBoost model has high accuracy and generalization ability, and can still accurately identify the types and distribution of natural fractures from the actual unbalanced logging data. This research has important guiding significance for the accurate characterization and construction of reservoir. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Text-Driven Human Image Generation with Texture and Pose Control

SSRN

引用

SSRN 2024年

作者： Jin, Zhedong Xia, Guiyu Yang, Paike Wang, Mengxiang Sun, Yubao Liu, Qingshan Jiangsu Key Laboratory of Big Data Analysis Technology School of Automation Nanjing University of Information Science and Technology Nanjing210044 China Nanjing University of Information Science and Technology Nanjing210044 China School of Computer and Software Nanjing University of Information Science and Technology Nanjing210044 China

Generating high-quality and diverse human images solely based on textual prompts is a challenging task in computer vision and computer graphics. Existing models do not have stable generation capabilities, and their control over image generation is insufficient, requiring an additional densepose map to provide pose information. In this work, we present a text-driven human image generation model, which enables control over texture and pose through textual input. The framework consists of three stages: 1) generating a pose map from the pose description which achieves control over the pose information of the generated human image. 2) converting the pose map to a parsing map based on the shape description, and 3) generating the final image by using textual descriptions of clothes texture along with a quality enhancement network. For the texture learning stage, we construct a texture-aware codebook using FSQ, learning vector representations for different clothes fabrics and patterns. Furthermore, we fine-tune the diffusion model to equip it with the capability of image denoising and image refining, thus improving the quality of the generated images. Extensive experimental results demonstrate our model's ability of generating realistic human body images that align with the semantics of the input text. © 2024, The Authors. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

An image classification algorithm for MSWI based on ResNet and attention mechanism

An image classification algorithm for MSWI based on ResNet a...

引用

Chinese Control and Decision Conference, CCDC

作者： Jian Zhang Jianbo Yu Gang Yu Rongcheng Sun Jian Tang School of Computer Science Nanjing University of Information Science & Technology Nanjing China NUIST-TianChang Research Institute Nanjing University of Information Science & Technology Nanjing China State & Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing China Faculty of Information Technology Beijing University of Technology Beijing China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

The municipal solid waste incineration has great advantages for resource recovery and utilization, and the stability of its combustion state is of great significance to the control process. However, the problem of low accuracy still exists in the classification of the images of municipal solid waste incineration (MSWI). For this reason, this paper proposes an image classification algorithm for MSWI based on attention module. The framework of ResNet is employed to improve the depth and accuracy of the network, which solves the problem of insufficient depth of the traditional network while suffering from the deficiency of slow convergence speed. Consequently, the attention module is embedded to solve the problem of different importance of different parts in the incineration flame image. The results show that the algorithm improves the recognition accuracy of municipal solid waste incineration flame images to 96.7%, and the convergence speed is significantly improved compared to other basic neural network models.

关键词： Waste management Training Waste materials Accuracy Image recognition Incineration Fires

来源：评论

学校读者我要写书评

暂无评论

Recognition of Combustion Conditions in MSWI process based on Hierarchical-Split ResNet

Recognition of Combustion Conditions in MSWI Process based o...

引用

Chinese Control and Decision Conference, CCDC

作者： Jian Zhang Rongcheng Sun Gang Yu Jianbo Yu Jian Tang School of Computer Science Nanjing University of Information Science & Technology Nanjing China NUIST-TianChang Research Institute Nanjing University of Information Science & Technology Nanjing China State & Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing China Faculty of Information Technology Beijing University of Technology Beijing China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

Municipal solid waste incineration (MSWI) has significant advantages in the treatment of municipal solid waste, however, the instability of the solid waste combustion state can lead to a reduction in the operational efficiency of the whole system. In addition, the judgement of the MSWI state mainly relies on the operators' own experience to control the combustion, leading to the identification results with substantially subjective and arbitrary. In order to address these challenging problems, a Hierarchical-Split residual neural network is proposed for MSWI process combustion state recognition, which is modeled by collecting combustion images, combining the experience of field experts and the incinerator grate structure, and classifying the combustion state into four categories: normal burning, partial burning, channelling burning, and smothering. Aiming at the problem of incomplete image information extracted by the traditional single-scale convolution, the Hierarchical-Split feature extraction module is utilized not only to enhance the ability of the model to extract feature information, but also to improve the recognition accuracy of the model. Finally, the proposed method is validated by taking the flame data of a municipal waste treatment plant in Beijing as an example. The experimental results show that the method effectively improves the generalization and robustness, and has good recognition accuracy.

关键词： Waste management Waste materials Accuracy Image recognition Incineration Fires Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A spectrum-enhanced attention model for semantic segmentation of remote sensing images

A spectrum-enhanced attention model for semantic segmentatio...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Li, Xin Xu, Feng Tao, Feifei Tong, Yao Lyu, Xin Zhong, Jianyi Kaup, André College of Computer Science and Software Engineering Hohai University Nanjing China Key Laboratory of Water Big Data Technology Ministry of Water Resources Hohai University Nanjing China School of Computer Engineering Jiangsu Ocean University Lianyungang China School of Artificial Intelligence and Information Technology Nanjing University of Chinese Medicine Nanjing China Multimedia Communications and Signal Processing Friedrich-Alexander University Erlangen-Nuremberg Erlangen Germany

ISBN: (纸本)9798350368741

Semantic segmentation of remote sensing images (RSIs) is essential for applications such as environmental monitoring, urban planning, and disaster management. Convolutional Neural Networks (CNNs) and their variants struggle to capture comprehensive spectral context for learning discriminative representations. In this paper, we propose a Spectrum-Enhanced Network (SPENet) that leverages the Frequency Transformer Block (FTB) to capture rich spectral context. FTB integrates Spectrum-Enhanced Attention (SEA) with Multi-Head Frequency Self-Attention (MH-FSA), incorporating more informative contextual cues. Specifically, SEA aggregates spectral statistics through covariance matrix normalization before applying channel-wise attention. By projecting feature maps onto the frequency domain, MH-FSA provides the network with a broader context, extending beyond the low-frequency focus of standard self-attention mechanisms. Extensive experiments on the ISPRS Potsdam and LoveDA datasets show that SPENet significantly outperforms state-of-the-art methods. Besides, the proposed SEA module notably rises average F1-score/overall accuracy/mean insert over union wiht more than 2.5/2.6%/2.3%, as demonstrated by ablation study. © 2025 IEEE.

关键词： frequency transformer remote sensing images Semantic segmentation spectrum enhancement

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：