检索结果-内蒙古大学图书馆

Efficient Attention Transformer Network With Self-Similarity Feature Enhancement for Hyperspectral Image Classification

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 11469-11486页

作者： Wang, Yuyang Shu, Zhenqiu Yu, Zhengtao Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming China

Recently, Transformer has gained widespread application in hyperspectral image classification (HSIC) tasks due to its powerful global modeling ability. However, the inherent high-dimensional property of hyperspectral images (HSIs) leads to a sharp increase in the number of parameters and expensive computational costs. Moreover, self-attention operations in Transformer-based HSIC methods may introduce irrelevant spectral-spatial information, and thus may consequently impact the classification performance. To mitigate these issues, in this paper, we introduce an efficient deep network, named efficient attention Transformer network (EATN), for practice HSIC tasks. Specifically, we propose two self-similarity descriptors based on the original HSI patch to enhance spatial feature representations. The center self-similarity descriptor emphasizes pixels similar to the central pixel. In contrast, the neighborhood self-similarity descriptor explores the similarity relationship between each pixel and its neighboring pixels within the patch. Then we embed these two self-similarity descriptors into the original patch for subsequent feature extraction and classification. Furthermore, we design two efficient feature extraction modules based on the preprocessed patches, called spectral interactive Transformer (SIT) module and spatial conv-attention (SCA) module, to reduce the computational costs of the classification framework. Extensive experiments on four benchmark datasets show that our proposed EATN method outperforms other state-of-the-art HSI classification approaches. The source code of this work will be released later. © 2025 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Spatial-Frequency Complementary Transformer and Multi-Scale Attention Refinement for Image Inpainting

引用

Journal of Shanghai Jiaotong University (Science) 2025年 1-15页

作者： Ren, Shuangde Li, Huafeng Zhang, Yafei Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China

The ability to capture long-range contextual information is crucial for image inpainting networks when dealing with complex semantic scenes and large areas of damage. Therefore, Transformers and frequency-based learning methods have gained wide attention due to their powerful global modeling capabilities. However, these methods only learn global features within a single domain, ignoring the complementarity of modeling global dependencies in both spatial and frequency domains. To address this issue, a spatial-frequency complementary Transformer is proposed, which combines the advantages of spatial global learning for global structure generation and frequency global learning for repetitive texture inpainting. This solution enhances the network’s performance in complex semantic scenes and large areas of damage. For spatial global learning, deformable convolution v4 (DCNv4) is introduced to image inpainting for the first time. By utilizing its sparse and efficient global modeling capabilities, a more lightweight inpainting is realized, and the occurrence of blurring and artifacts in the inpainting results is minimized. Additionally, a multi-scale attention refinement module is proposed to enhance the network’s ability to inpaint local detail. Extensive experiments on three benchmark datasets demonstrate that the proposed method outperforms existing advanced inpainting models while maintaining lower parameter counts and a faster inference speed. © Shanghai Jiao Tong University 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Parallel Seeds:From Foundation Models to Foundation Intelligence for Agricultural Sustainability

引用

IEEE/CAA Journal of Automatica Sinica 2025年第3期12卷 481-484页

作者： Laiyi Fu Shunkang Ling Danyang Wu Mengzhen Kang Fei-Yue Wang Hequan Sun the Shool of Automation Science and Engineering Faculty of Electronic and Information Engineering Xi'an Jiaotong University the College of Information Engineering Northwest A&F University IEEE the State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences

THE development of agriculture faces significant challenges due to population growth, climate change, land depletion, and environmental pollution, threatening global food security [1]. This necessitates the development of sustainable agriculture, where a fundamental step is crop breeding to improve agronomic or economic traits, e.g., increasing yields of crops while decreasing resource usage and minimizing pollution to the environment [2].

关键词：

来源：评论

学校读者我要写书评

暂无评论

Secure MIMO Communication via Pilot-Based Codebook Artificial Noise: Unknown Eavesdropper Channel

引用

IEEE Communications Letters 2025年第5期29卷 1013-1017页

作者： Gu, Yebo Zhao, Tao Shen, Tao Wang, Bo Kunming University of Science and Technology Faculty of Information Engineering and Automation China China Telecom Heilongjiang Branch Harbin150001 China

Pilot-Based Codebook Artificial Noise (PCAN), which plays a crucial role in ensuring secure communication, is an emerging physical layer security technique. PCAN faces a significant challenge due to the unknown eavesdropper channel. To address this issue, this letter re-models the eavesdropper channel using random matrix theory. By applying the η-transform and Shannon-transform, the asymptotic expression for the eavesdropper channel capacity is derived under the condition of an unknown eavesdropper channel. The simulation result shows that when the number of transmitter antennas equals the number of eavesdropper antennas and the system dimension is large, the model can effectively characterize the eavesdropper channel *** this framework, the secrecy capacity is optimized using the Difference of Convex functions - Successive Convex Approximation (DC-SCA) algorithm, providing a new approach to improve the performance of PCAN. © 1997-2012 IEEE.

关键词： Eigenvalues and eigenfunctions Optimization Channel capacity MIMO Eavesdropping Vectors Transmitting antennas Receiving antennas Physical layer security Limiting

来源：评论

学校读者我要写书评

暂无评论

Explainable Climate-Based Time Series Modeling for Predicting Chemical Compositions in Tobacco Leaves

引用

IEEE Access 2025年 13卷 76352-76369页

作者： He, Hong Zhang, Yunwei Li, Bin Tao, Chengjin Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming650500 China Yunnan Tobacco Leaf Company Kunming650218 China

The quality of tobacco leaves significantly influences cigarette flavor and market value, with chemical composition serving as a critical quality indicator. However, existing tobacco quality prediction studies mainly rely on physical leaf samples, resulting in significant time lags and limited applicability for early decision-making. To address this, we construct a 153×6 climate factor matrix covering the tobacco growth period (May 1 to September 30), incorporating daily maximum temperature, minimum temperature, mean temperature, precipitation, mean sunlight intensity, and atmospheric pressure. Notably, atmospheric pressure is introduced for the first time to enhance model generalizability. We develop and compare five predictive models: multiple linear regression (MLR), eXtreme Gradient Boosting (XGBoost), long short-term memory (LSTM), gated recurrent unit (GRU), and convolutional neural network combined with LSTM (CNN+LSTM). The models are trained and validated using climate and chemical composition data from 98 tobacco-growing counties in Yunnan Province (2013-2021). Experimental results demonstrate that the CNN+LSTM model achieves superior predictive accuracy, effectively capturing complex spatiotemporal interactions in climate factors. The mean absolute percentage errors (MAPE) for total sugar, reducing sugar, and total nitrogen remain within 10%-20%, while nicotine and potassium exhibit errors in the range of 20%-30%. Furthermore, Integrated Gradients (IG) analysis is employed to interpret the CNN+LSTM model, revealing the contribution of individual climate factors to chemical accumulation patterns. Our approach improves on the time lag issue of existing studies, helps producers plan resources in advance, and provides a data-driven approach for optimizing tobacco cultivation and quality management. © 2013 IEEE.

关键词： Reliability

来源：评论

学校读者我要写书评

暂无评论

Calibration and validation of the CMADS-Driven SWAT model in the distributed hydrological simulation of the Baihe River Basin in Nanyang

引用

ISH Journal of Hydraulic engineering 2025年第1期31卷 97-107页

作者： BiYing, Xu Abd Rahman, Nor Faiza Tai, Vin Cent Faculty of Automation Engineering Henan Polytechnic Institute Henan Nanyang China Centre for Sustainable Design Modelling and Simulation Faculty of Engineering Built Environment & Information Technology SEGi University Petaling Jaya Selangor Malaysia

The China Meteorological Assimilation Driving Dataset for the SWAT model (CMADS) has gained widespread use for its accuracy. This study focuses on the Baihe River Basin in Nanyang, using the SWAT tool and CMADS dataset to construct two distributed hydrological models of different scales. The accuracy and effectiveness of these models were evaluated. Parameter uncertainty analysis on a monthly and annual scale was conducted usingSUFI-2 algorithm. The goal was to assess the applicability of the CMADS-driven SWAT model in theBasin by calibrating and validating flow data at both monthly and annual scales. The results form the calibration period (2009–2013) showedmonthly R2 and NSE values were 0.81 and 0.8, while the annual values were 0.91 and 0.9. During validation(2014–2016), the annual R2 and NSE values were 0.89 and 0.86, and the monthly values were 0.76 and 0.76, with reasonable values for the P-factor, R-factor, and percentage bias (PBIAS), indicating good model applicability. Seasonal variations in rainfall, surface runoff, water yield, evapotranspiration (ET), and potential evapotranspiration (PET) were analyzed. The results demonstrate that surface runoff and water yield is closely related to precipitation, while ET is largely controlled by land use types, providing insights for water resource management. © 2024 Indian Society for Hydraulics.

关键词： SWAT

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Survival Prediction Model for Melanoma 24

Machine Learning-Based Survival Prediction Model for Melanom...

引用

5th International Symposium on Artificial Intelligence for Medicine Science, ISAIMS 2024

作者： Jing, Zijie Wang, Jianghong Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Kunming China

ISBN: (纸本)9798400717826

The high growth rate of melanoma poses a huge challenge to healthcare delivery worldwide. At this stage, rapid and accurate diagnosis and timely treatment of melanoma is crucial. In this study, we utilized multiple metrics to predict survival in melanoma patients. We built multiple models of different types of machine learning, deep learning, and integrated learning, of which the best results were Logistic regression, Long short-term memory, and Categorical boosting, with AUCs of 0.9267, 0.9365, and 0.9417, respectively. We performed interpretability analyses of these models to improve the models’ applicability in the clinic. The conclusions obtained from the analysis have important implications for the treatment of melanoma. This study represents a significant advancement in the use of machine learning methods to predict the survival status of individuals with melanoma, providing a new way of thinking about melanoma treatment and prognosis. © 2024 Copyright held by the owner/author(s).

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Secure and Efficient Privacy Scheme for Location-Based Services in Cloud Environments 24

A Secure and Efficient Privacy Scheme for Location-Based Ser...

引用

9th International Conference on Cloud Computing and Internet of Things, CCIOT 2024

作者： Pu, Tongyu Zeng, Kai Bai, Fenhua Zhang, Chi Zhang, Xiaohui Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Kunming China

ISBN: (纸本)9798400717161

Preserving privacy has become crucial in the field of location-based services (LBS) to leverage their full potential while protecting users from untrustworthy LBS providers. Given that LBS users typically use resource-constrained mobile devices, many existing privacy-preserving methods focus on anonymization. However, these methods have certain limitations regarding privacy protection and efficiency. This paper introduces a novel Privacy-preserving LBS scheme to address these issues. We develop an efficient query mechanism where users send encrypted distance queries to the server. The server then employs a PFR-tree and homomorphic encryption to filter Points of Interest (POIs) in a hierarchical manner. The PFR-tree quickly eliminates irrelevant regions based on their locations, minimizing unnecessary computations and enhancing query efficiency. Experimental results indicate that this PFR-tree-based scheme significantly reduces query time compared to traditional methods without a PFR tree, especially as the number of POIs increases, demonstrating superior performance and efficiency in scenarios with many POIs. This approach effectively meets privacy protection needs for indoor navigation in cloud environments while maintaining high efficiency and security. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

MCFF-Net: Multi-Scale Contextual Feature Fusion Network for Polyp Segmentation

引用

Journal of Shanghai Jiaotong University (Science) 2025年 1-13页

作者： Ma, Lei Yan, Jiangkai Shao, Dangguo Li, Jingtao Wang, Jiawei Yan, Yukun Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Yunnan Provincial Key Laboratory of Artificial Intelligence Kunming650500 China

In clinical practice, technologies for automatically segmenting polyps might greatly improve the speed and accuracy of medical diagnosis, significantly reducing the chances of patients developing colorectal cancer. Nevertheless, the segmentation of polyps presents a considerable challenge due to their low contrast, presence of occlusion, and intricate background disturbances. In this paper, we propose an innovative approach for segmenting polyps, called multi-scale contextual feature fusion network for polyp segmentation (MCFF-Net). Specifically, MCFF-Net includes three modules: feature enhancement module (FEM), global-local feature fusion module (GLFF), and cross-scale feature fusion module (CFFM). Among them, FEM is used to improve the features at each scale. Building on this, the CFFM enables comprehensive interaction among the information across various scales, enhancing the diversity of the feature scales extracted. Moreover, the GLFF fuses global-local features to generate a rough object localization map. This map further modulates the fusion features from the CFFM, facilitating more precise segmentation. On five publicly available datasets, our approach not only segments various polyp types but also surpasses existing methods in terms of accuracy and generalizability. © Shanghai Jiao Tong University 2024.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Characterization of ultraviolet communication in a mixed aerosol environment

引用

Optoelectronics Letters 2025年第2期21卷 77-84页

作者： ZHAO Taifei SUN Yuxin WANG Wuxin ZHANG Haijun PAN Feixiang WU Hao Artificial Intelligence Key Laboratory of Sichuan Province Sichuan University of Science&EngineeringZigong 643000China Faculty of Automation and Information Engineering Xi’an University of TechnologyXi’an 710048China

Wireless ultraviolet (UV) has strong scattering characteristics and can communicate through non-direct *** UV signals are transmitted in the atmosphere,they are affected by the absorption and scattering effects of atmospheric particles and atmospheric turbulence,resulting in attenuation of UV signal energy and reduced reliability of the communication *** paper focuses on the channel model of UV non-direct-view single scattering communication,and simulates and analyzes the communication characteristics of UV light in atmospheric turbulence and mixed aerosol environment under horizontal,vertical and oblique range communication *** results show that at equal relative humidity,the wireless UV non-directive scattering communication performance for vertical communication scenarios is more affected by the mixed aerosol environment and the communication performance is worse.

关键词： communication scattering ultraviolet

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：