检索结果-内蒙古大学图书馆

Semantic feature space construction for unsupervised few-shot image classification

Journal of Supercomputing 2025年第6期81卷 1-45页

作者： Wang, Zhicheng Wang, Longge Yu, Junyang Li, Han Wang, Tingyu Wu, Jinhu College of Software Henan University Kaifeng475004 China Henan Province Intelligent Data Processing Research Engineering Research Center Henan Kaifeng475004 China

Unsupervised few-shot learning faces challenges such as "sampling bias" and "class collision," which make it difficult to extract effective features from limited samples and map them into a separable feature space, thus weakening the model’s generalization ability. To address this issue, this paper proposes a novel unsupervised few-shot learning method—Enhanced Contrastive Self-supervised Learning (ECSL). ECSL includes a multi-task training framework, a General Feature Enhancement (GFE) module, a Projection Distance Metric Algorithm (PDMA), and an Adjustable Loss function (AL). The method aims to enhance the model’s understanding of samples through complex task collaboration, enabling it to extract more generalized semantic information and thereby establish an effective mapping from samples to a separable feature space. Experimental results show that ECSL outperforms existing methods such as PsCo and CPNWCP on the miniImageNet and tieredImageNet datasets. In the 5-way 1-shot task, ECSL improves classification accuracy by 2.10% and 2.11%, respectively, compared to CPNWCP, and in the 5-way 5-shot task, it improves by 0.66% and 1.55%. These results show significant competitiveness among unsupervised few-shot learning methods, particularly in the miniImageNet 5-way 1-shot experiment, where ECSL even exceeds traditional supervised methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Screening and Artifact Detection of RFI in Sentinel-1A Time-Series Images Combining Change Detection Techniques With Structural Similarity Index

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 10864-10881页

作者： Zhang, Zhizheng Shu, Gaofeng Huang, Yabo Wu, Lin Li, Ning College of Computer and Information Engineering Henan University Kaifeng475004 China Henan Key Laboratory of Big Data Analysis and Processing Kaifeng475004 China Henan Province Engineering Research Center of Spatial Information Processing Kaifeng475004 China

As a wideband radar system, spaceborne synthetic aperture radar (SAR) is susceptible from other high-power radiation sources, which can cause radio frequency interference (RFI) artifacts in the acquired images. Given that RFI significantly impacts data processing and image interpretation, screening and artifact detection of RFI have become top priorities for spaceborne SAR systems, which generate massive data daily. However, current image-level methods mostly rely on the acquisition of relevant prior knowledge, which makes efficient screening of large-scale products difficult when the scenario changes. In this article, a novel screening and detection method based on change detection techniques is proposed. Due to the time-varying feature of RFI artifacts in time-series SAR images, local areas affected by RFI can be masked through change detection operator. The screening step is performed by quantifying and analyzing the feature differences between RFI artifacts and ground-truth information in local areas. Therefore, an RFI-free background is constructed based on the results, enabling effective artifacts detection of RFI-containing images. Experimental results of Sentinel-1A Level-2 products verify the effectiveness and robustness of the proposed method. © 2008-2012 IEEE.

关键词： Radio interference

来源：评论

学校读者我要写书评

暂无评论

A numerical magnitude aware multi-channel hierarchical encoding network for math word problem solving

引用

Neural Computing and Applications 2025年第3期37卷 1651-1672页

作者： Xu, Junjie Chen, Yuzhong Xiao, Lingsheng Liao, Hongmiao Zhong, Jiayuan Dong, Chen College of Computer and Data Science Fuzhou University Fujian Province Fuzhou350108 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fujian Province Fuzhou350108 China

Math word problem (MWP) represents a critical research area within reading comprehension, where accurate comprehension of math problem text is crucial for generating math expressions. However, current approaches still grapple with unresolved challenges in grasping the sensitivity of math problem text and delineating distinct roles across various clause types, and enhancing numerical representation. To address these challenges, this paper proposes a Numerical Magnitude Aware Multi-Channel Hierarchical Encoding Network (NMA-MHEA) for math expression generation. Firstly, NMA-MHEA implements a multi-channel hierarchical context encoding module to learn context representations at three different channels: intra-clause channel, inter-clause channel, and context-question interaction channel. NMA-MHEA constructs hierarchical constituent-dependency graphs for different levels of sentences and employs a Hierarchical Graph Attention Neural Network (HGAT) to learn syntactic and semantic information within these graphs at the intra-clause and inter-clause channels. NMA-MHEA then refines context clauses using question information at the context-question interaction channel. Secondly, NMA-MHEA designs a number encoding module to enhance the relative magnitude information among numerical values and type information of numerical values. Experimental results on two public benchmark datasets demonstrate that NMA-MHEA outperforms other state-of-the-art models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Missing Traffic data Imputation based on Tensor Completion and Graph Network Fusion

引用

Transportation research Record 2025年

作者： Xia, Chengliang Yin, Xiang Yu, Junyang Liang, Xiaoli Chen, Lei School of Software Henan University Henan Kaifeng China Intelligent Data Processing Engineering Research Center of Henan Province Henan University Henan Kaifeng China

During traffic data acquisition, missing data often arise owing to equipment failures and network disruptions. Despite extensive research on traffic data imputation, two primary limitations persist: First, existing methods struggle to fully integrate the spatiotemporal correlations and low-rank structures inherent in traffic data. Second, current research has mostly focused on missing completely at random (MCAR), with limited attention on other missing data patterns. We propose an innovative method, tensor completion and graph network fusion (TCGNF), to address these challenges for missing traffic data imputation. This method initially utilizes tensor completion for the preliminary imputation of missing data. Subsequently, it constructs the road network by leveraging the Pearson correlation coefficient from historical road data and the physical distances between detectors. The method then uses graph sampling and aggregation (GraphSAGE) to extract spatiotemporal data features from the two road networks and fuse them. Finally, these features are trained in generative adversarial networks (GANs) for accurate data imputation. Extensive experiments were conducted on two publicly accessible traffic datasets to validate the efficacy of the TCGNF model. The outcomes of these experiments indicate that the TCGNF model demonstrates superior generalization capabilities, significantly outperforming other state-of-the-art data imputation models concerning overall performance. © The Author(s) 2025.

关键词： data reduction

来源：评论

学校读者我要写书评

暂无评论

TPE for JPEG images with Dynamic M-ary Decomposition and Adaptive Threshold Constraints

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Ma, Yakun Chai, Xiuli Long, Guoqiang Gan, Zhihua Zhang, Yushu Henan University School of Artificial Intelligence Henan Engineering Research Center for Industrial Internet of Things Zhengzhou450046 China Henan University School of Software Intelligent Data Processing Engineering Research Center of Henan Province Institute of Intelligent Network System Kaifeng475004 China Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing211106 China

Traditional JPEG image encryption that prioritizes solely confidentiality fails to account for the pressing usability requirements of cloud-based environments, thus boosting the boom in thumbnail-preserving encryption (TPE) to balance image privacy and usability. However, existing TPE schemes for JPEG images face numerous challenges, such as insufficient security, inability to achieve lossless decryption, and high file extension. To address these challenges, we propose a TPE scheme based on dynamic M-ary decomposition and adaptive threshold constraints (TPE-MDTC). First, the valid ranges of quantized DC coefficients for JPEG images are determined. Then, a sum-preserving encryption method for quantized DC coefficients with compliance threshold constraints is designed using the bit-plane permutation to preserve thumbnails with high accuracy. Next, the introduction of dynamic M-ary decomposition effectively changes bit statistical characteristics preserved by bit-plane permutation, enhancing the ciphertext security. Finally, a quantized AC encryption method with RV (Run/Value) pair global permutation is proposed, effectively modifying the unit block features, thereby significantly improving the security and attack resistance of encrypted images. Experimental results show that the proposed TPE-MDTC scheme can reconstruct the original JPEG images without loss, and the generated ciphertext images exhibit significant advantages over previous schemes regarding file extension and security. © 1991-2012 IEEE.

关键词： Ciphertext

来源：评论

学校读者我要写书评

暂无评论

SPDGrNet: A Lightweight and Efficient Image Classification Network for Zea mays Diseases

引用

Journal of Crop Health 2025年第3期77卷 1-12页

作者： Xu, Laixiang Cao, Bingxu Su, Jing feng Zhang, Fengyue Song, Hongyun Zhao, Junmin School of Computer and Data Science Research Center of Smart City and Big Data Engineering of Henan Province Henan University of Urban Construction Pingdingshan China School of Information Engineering Luohe Vocational Technology College Luohe China Institute of Technology University of Technology Luohe Luohe China School of Computer and Data Science Innovation Laboratory of Smart Traffic and Big Data Development of Hainan Province Henan University of Urban Construction Pingdingshan China School of Computer and Data Science Henan University of Urban Construction Pingdingshan China School of Computer and Data Science Research Center of Smart City and Big Data Engineering of Henan Province Research Center of Intelligent Campus Application Engineering of Henan Province Innovation Laboratory of Smart Traffic and Big Data Development of Hainan Province Henan University of Urban Construction Pingdingshan China

Controlling diseases on the foliage of cultivated plants has a major impact on crop yield and quality. Leaf symptoms and environmental information are the basis of crop disease and pest identification. Due to the complexity and diversity of disease leaf symptoms and environmental information, the accuracy of crop disease detection methods has decreased. Aiming at low disease identification efficiency and difficult feature modeling, we propose a new deep learning algorithm and obtain ideal results. We used improved convolutional neural networks (CNNs) SPDNet and GrNet (SPDGrNet) to perform Zea mays disease identification. The proposed research and analysis focus on four categories of Zea mays symptoms: healthy, leaf blight, southern leaf blight and grey spot. The experimental results and analysis confirm that the proposed approach outperforms other excellent plant disease recognition algorithms and achieves an overall classification accuracy of 98.96%. When compared to AlexNet, VGG-16, Inception-V4, ShuffleNet-V3, and Efficient-B7, the proposed model achieves accuracy improvements of 27.78%, 19.05%, 14.59%, 10.28%, and 7.06%, respectively, with corresponding accuracies of 71.18%, 79.91%, 84.37%, 88.68%, and 91.9%. The proposed model has outstanding generalization ability in open-source databases, such as the PlantifyDr, Plant Pathology, and New Plant Diseases dataset. The suggested strategy can provide ideas for transplanting models into mobile disease detection equipment. This is very helpful in the intelligent development of agricultural systems and crop leaf disease analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Out-of-Distribution Fault Diagnosis of Industrial Cyber-Physical Systems Based on Orthogonal Anchor Clustering With Adaptive Balance

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical Systems 2025年 3卷 48-60页

作者： Liu, Ruonan Hu, Puyuan Zhao, Siheng Sun, Zhijian Han, Te Pang, Zhibo Zhang, Weidong Shanghai Jiao Tong University Department of Automation Shanghai200240 China National Key Laboratory of Marine Engine Science and Technology Shanghai201108 China Crossocean of Suzhou Technology Suzhou215121 China Beijing Institute of Technology Center for Energy and Environmental Policy Research School of Management Beijing100081 China ABB Corporate Research Sweden Department of Automation Technology Vasteras722 26 Sweden KTH Royal Institute of Technology Department of Intelligent Systems Stockholm114 28 Sweden Henan University Henan Key Laboratory of Big Data Analysis and Processing School of Computer and Information Engineering Kaifeng475001 China Shanghai Jiaotong University Department of Automation Shanghai200240 China

Given the critical role of rotating machinery in industrial cyber-physical systems (ICPS), ensuring their reliable operation is essential for the stability and safety of ICPS. Deep neural networks have demonstrated competitive results for intelligent fault diagnosis, which are usually trained via the historical data of all fault modes. However, in real engineering, it is usually difficult to collect samples and exhaust all failures during the training stage. As a result, out-of-distribution fault diagnosis (OOD-FD) becomes a more realistic problem that requires the methods to not only accurately diagnose the known faults, but also effectively recognize unknown ones. Therefore, a novel orthogonal anchor clustering with focal attention (FA-OAC) is proposed in this paper for OOD-FD. Firstly, an orthogonal anchor clustering (OAC) algorithm is proposed to fix the class center of each fault mode orthogonally and distinguish the known and unknown faults at the class level. Then, because the identifiability of different fault modes changes a lot in OOD-FD, the focal attention mechanism is applied to dynamically adjust the attention to different fault modes according to the distance loss of OAC, thus addressing the identifiability imbalance problem. To verify the effectiveness of the proposed method, different OOD-FD tasks are designed based on two rotating machinery datasets. The experimental results and comparison with state-of-the-art fault diagnosis methods have demonstrated that the proposed method has improved the OOD-FD performance greatly and therefore provides an effective tool in real engineering. © 2023 IEEE.

关键词： Rotating machinery

来源：评论

学校读者我要写书评

暂无评论

LMP-GAN: Out-Of-Distribution Detection For Non-Control data Malware Attacks

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 PP页

作者： Wood, David Kapp, David Kebede, Temesgen Hirakawa, Keigo Wuhan University School of Computer Science China Wuhan University National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering China Zhongguancun Academy China Wuhan University State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing China Sun Yat-sen University School of Geography and Planning China Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates Chongqing University College of Computer Science China The University of Tokyo Japan RIKEN Center for Advanced Intelligence Project Japan Intelligent Science & Technology Academy Limited CASIC China iFlytek Company Ltd. National Engineering Research Center of Speech and Language Information Processing China Nanyang Technological University College of Computing & Data Science Singapore Henan Academy of Sciences Aerospace Information Research Institute China

Anomaly detection is a common application of machine learning. Out-of-distribution (OOD) detection in particular is a semi-supervised anomaly detection technique where the detection method is trained only on the inlier (in-distribution) samples - unlike the fully supervised variant, the distribution of the outlier samples are never explicitly modeled in OOD detection tasks. In this work, we design a novel GAN-based OOD detection network specifically designed to protect a cyber-physical signal systems from novel Trojan malware called non-control data (NCD) attack that evades conventional malware detection techniques. Inspired in part by the classical locally most powerful (LMP) test in statistical inferences, the proposed LMP-GAN trains the OOD detector (discriminator) by generating OOD samples that are aimed at making maximal alteration to the inlier samples while evading detection. We experimentally compare the results to the state-of-the-art anomaly detection methods to demonstrate the benefits and the appropriateness of the LMP-GAN OOD detector. © 2025 IEEE.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

research on traffic flow prediction based on adaptive spatio-temporal perceptual graph neural network for traffic prediction 24

Research on traffic flow prediction based on adaptive spatio...

引用

4th International Conference on Artificial Intelligence, Big data and Algorithms, CAIBDA 2024

作者： Liang, Qian Yin, Xiang Xia, Chengliang Chen, Ye School of Software Henan University Kaifeng Henan China Henan University Henan Province Intelligent Data Processing Engineering Research Center Kaifeng Henan China

ISBN: (纸本)9798400710247

Accurate traffic prediction is essential for path planning, people flow monitoring, and urban traffic control in the age of artificial intelligence and big data. Even though academics both domestically and internationally have conducted extensive research on traffic flow prediction in recent years, there are still two main obstacles that need to be overcome: first, the methods currently in use do not fully account for the data correlation between neighboring time nodes;second, because the majority of the research focuses on static spatial analysis, it is challenging to capture the dynamic spatial dependence between nodes. This paper suggests a novel solution, the adaptive spatio-temporal perceptual graph neural network, to address these issues and increase the precision of traffic flow prediction. Through the use of an adaptive graph convolution module, a local spatio-temporal fusion graph, a Pearson correlation coefficient adjacency matrix, and a spatio-temporal perceptual distance metric, the method is able to capture spatio-temporal dynamics and dependencies between neighboring time points and traffic nodes. We used two datasets related to public transportation as the basis for an experimental investigation. The experimental findings demonstrate that our model performs better than baseline models. © 2024 Copyright held by the owner/author(s).

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年

作者： Wang, Di Hu, Meiqi Jin, Yao Miao, Yuchun Yang, Jiaqi Xu, Yichu Qin, Xiaolei Ma, Jiaqi Sun, Lingyu Li, Chenxing Fu, Chuan Chen, Hongruixuan Han, Chengxi Yokoya, Naoto Zhang, Jing Xu, Minqiang Liu, Lin Zhang, Lefei Wu, Chen Du, Bo Tao, Dacheng Zhang, Liangpei Wuhan University School of Computer Science China Wuhan University National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering China Zhongguancun Academy China Wuhan University State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing China Sun Yat-sen University School of Geography and Planning China Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates Chongqing University College of Computer Science China The University of Tokyo Japan RIKEN Center for Advanced Intelligence Project Japan Intelligent Science & Technology Academy Limited CASIC China iFlytek Company Ltd. National Engineering Research Center of Speech and Language Information Processing China Nanyang Technological University College of Computing & Data Science Singapore Henan Academy of Sciences Aerospace Information Research Institute China

Accurate hyperspectral image (HSI) interpretation is critical for providing valuable insights into various earth observation-related applications such as urban planning, precision agriculture, and environmental monitoring. However, existing HSI processing methods are predominantly task-specific and scene-dependent, which severely limits their ability to transfer knowledge across tasks and scenes, thereby reducing the practicality in real-world applications. To address these challenges, we present HyperSIGMA, a vision transformer-based foundation model that unifies HSI interpretation across tasks and scenes, scalable to over one billion parameters. To overcome the spectral and spatial redundancy inherent in HSIs, we introduce a novel sparse sampling attention (SSA) mechanism, which effectively promotes the learning of diverse contextual features and serves as the basic block of HyperSIGMA. HyperSIGMA integrates spatial and spectral features using a specially designed spectral enhancement module. In addition, we construct a large-scale hyperspectral dataset, HyperGlobal-450 K, for pre-training, which contains about 450 K hyperspectral images, significantly surpassing existing datasets in scale. Extensive experiments on various high-level and low-level HSI tasks demonstrate HyperSIGMA's versatility and superior representational capability compared to current state-of-the-art methods. Moreover, HyperSIGMA shows significant advantages in scalability, robustness, cross-modal transferring capability, real-world applicability, and computational efficiency. The code and models will be released at HyperSIGMA. © 1979-2012 IEEE.

关键词： Hyperspectral imaging

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：