检索结果-内蒙古大学图书馆

Adaptive Circular Receptive Field for Remote Sensing Image Target Detection

IEEE ACCESS 2025年 13卷 30155-30166页

作者： Wen, Ning Ge, Yun Yang, Xiaoyu Yu, Meigen Wang, Ting Nanchang Hangkong Univ Sch Software Nanchang 330063 Jiangxi Peoples R China Nanchang Hangkong Univ Sch Civil Engn & Architecture Nanchang 330063 Jiangxi Peoples R China Huihang Jiangxi Digital Technol Co Ltd Nanchang 330038 Jiangxi Peoples R China

Remote sensing images contain a variety of targets. The circular and square-like targets are very common. However, general methods are prone to incorporating background information and have problems with rotation angles when detecting circular and square-like targets. The Adaptive Circular Receptive Field Network (ACRFNet) is proposed to address these problems. Firstly, a radius detection head based on the center point is designed, which predicts the center point and radius of the target to obtain a bounding circle. Compared with the rectangular bounding box, the bounding circle contains less background information and has rotation invariance, achieving in more accurate localization. Secondly, in order to better extract the features of circular targets and cope with scale changes, a multi-scale feature fusion method based on adaptive circular convolution is proposed. Adaptive circular receptive fields replace the ordinary convolution of square receptive fields, and a feature pyramid structure is introduced to enrich the semantic information of the feature map. Finally, in order to reasonably evaluate the performance of the model, Circle IOU is used to calculate mAP to fit the bounding circle. The experimental results on the NWPU VHR-10 and DIOR datasets demonstrate that the model has significantly improved detection accuracy for circular and square-like targets and has better generalization for other types of targets.

关键词： Feature extraction Remote sensing Object detection Convolution Kernel Heating systems Detectors classification algorithms Accuracy Semantics Remote sensing image target detection bounding circle adaptive circular receptive field

来源：评论

学校读者我要写书评

暂无评论

Optimized Subset Selection for Matrices and its Application in Hyperspectral Band Selection

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 6464-6479页

作者： Xiao, Songyi Zhu, Liangliang Zhu, Xinwen Geng, Xiurui Chinese Acad Sci Aerosp Informat Res Inst Beijing 100094 Peoples R China Chinese Acad Sci Key Lab Technol Geospatial Informat Proc & Applica Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 100049 Peoples R China Chinese Acad Sci Key Lab Target Cognit & Applicat Technol Beijing 100190 Peoples R China Hefei Univ Technol Sch Comp Sci & Informat Engn Hefei 230009 Peoples R China

When spectral bands are considered as scatter points in the image space, hyperspectral band selection can be transformed into the column subset selection problem for matrices. We consider the problem of finding the submatrix of maximum volume of a matrix X is an element of R-NxL (N >> L) within the column space perspective. To solve this problem, we present a novel determinant formula that utilizes the scalar product of arbitrary-order antisymmetric tensors in wedge product form, providing a fresh perspective for interpreting the volume gradient. Based on the variant of this formula, we can mitigate the local extremum problem inherent in existing subset selection algorithms to a certain extent. Subsequently, we introduce exterior algebra theory into the remote sensing community and develop a hyperspectral band selection algorithm via higher order joint volume gradient. To address bias in the volume criterion and reduce algorithmic complexity, we integrate a general subspace partitioning framework that accounts for spectral information. In addition, we propose a method for automatically determining the optimal number of bands. Experiments conducted on both publicly available and Gaofen-5 satellite hyperspectral datasets demonstrate the superiority and stability of our proposed algorithms in terms of classification accuracy and computational efficiency.

关键词： Hyperspectral imaging Partitioning algorithms classification algorithms Vectors Optimization Greedy algorithms Approximation algorithms Accuracy Tensors Symmetric matrices Band selection (BS) column subset selection problem (CSSP) Gaofen-5 (GF-5) local extremum problem wedge product

来源：评论

学校读者我要写书评

暂无评论

Imbalanced Data Problem in Machine Learning: A Review

引用

IEEE ACCESS 2025年 13卷 13686-13699页

作者： Altalhan, Manahel Algarni, Abdulmohsen Alouane, Monia Turki-Hadj King Khalid Univ Dept Comp Sci Abha 61421 Saudi Arabia

One of the prominent challenges encountered in real-world data is an imbalance, characterized by unequal distribution of observations across different target classes, which complicates achieving accurate model classifications. This survey delves into various machine learning techniques developed to address the difficulties posed by imbalanced data. It discusses data-level methods such as oversampling and undersampling, algorithm-level solutions including ensemble learning and specific algorithm adjustments, cost-sensitive algorithms, and hybrid strategies that combine multiple approaches. Moreover, this paper emphasizes the crucial role of evaluation methods like Precision, F1 Score, Recall, G-mean, and AUC in measuring the effectiveness of these strategies under imbalanced conditions. A detailed review of recent research articles helps pinpoint persistent gaps in generalizability, scalability, and robustness across these methods, underscoring the necessity for ongoing improvements. The survey seeks to offer an extensive overview of current approaches that improve the efficiency and effectiveness of machine learning models dealing with imbalanced datasets, thus equipping researchers with the insights needed to develop robust and effective models ready for real-world application.

关键词： Data models Machine learning classification algorithms Machine learning algorithms Training Reviews Fraud Surveys Ensemble learning Data augmentation Imbalanced data machine learning balance techniques evaluation methods

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Approaches for Handling Concept Drifts in Data Processed With Machine Learning

引用

IEEE ACCESS 2025年 13卷 61109-61121页

作者： Pereira, Emanuel Valerio da Silva, Wendley Souza Univ Fed Ceara Comp Engn Dept BR-60020181 Sobral Brazil

In the realm of machine learning models, the pursuit of achieving favorable metrics is undeniably significant. However, these models confront phenomena that can diminish their effectiveness if left unaddressed-notably, the phenomenon of concept drift. Concept drift materializes when unforeseen alterations in the statistical properties of the target variable transpire over time. This article introduces a comprehensive analysis of classical treatment methods, examining the behavior of machine learning models across diverse datasets. Various concept drift detection algorithms are employed, facilitating a holistic assessment. The study encompasses a comparative exploration of different classification algorithms within the scikit-multiflow framework. These algorithms integrate adaptive strategies to contend with concept drifts. Through this generalized analysis, the performance of distinct classification algorithms is contrasted. The overarching aim is to facilitate the selection of optimal classification methods aligned with specific types of concept drift. Ultimately, this study provides a pivotal toolkit for the judicious selection of classification methods, enhancing model adaptability in the presence of concept drifts. In addition to shedding light on the behavior of machine learning models under concept drift, the findings empower practitioners and researchers to make informed decisions to optimize model robustness.

关键词： Concept drift Adaptation models Data models Stochastic processes Measurement Analytical models Accuracy Feature extraction classification algorithms Random variables Classifiers concept drift data stream evaluation machine learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Heart-Kidney Interaction for Cancer Detection Through Physiological Process Simulation as a Decision Support System

引用

IEEE ACCESS 2025年 13卷 79169-79179页

作者： Jaddi, Najmeh Sadat Abdullah, Salwani Othman, Zalinda Yahya, Yazrina Nazri, Mohd Zakree Ahmad Goh, Say Leng Alvankarian, Fatemeh Alvankarian, Jafar Iranian eUniv Fac Comp Engn Tehran *** Iran Univ Kebangsaan Malaysia Fac Informat Sci & Technol Ctr Artificial Intelligence Technol Bangi 43600 Selangor Malaysia Univ Kebangsaan Malaysia Fac Informat Sci & Technol Ctr Software Technol & Management Bangi 43600 Selangor Malaysia Univ Malaysia Sabah Kampus Antarabangsa Labuan Fac Comp & Informat Optimisat & Analyt Res Grp Labuan 87000 Malaysia Univ Maryland Dept Elect & Comp Engn College Pk MD 20742 USA Tehran Univ Sci & Technol Pk RayanMiniFab Tehran *** Iran

A decision support system (DSS) is a computer-based tool used to improve decision-making capabilities for any organization by analyzing the available data. The heart-kidney (HK) model proposed in this paper, as a DSS, simulates the physiological processes of the heart and kidneys in the human body to support cancer detection. The first part of the HK algorithm is inspired by the functions of the heart, where blood molecules (solutions) are sent to the heart, simulating the processes of oxygenation and the pumping of oxygenated blood to the kidneys as a local search. The solutions generated by the heart are then fed into the kidney-inspired algorithm (KA), which performs filtration, reabsorption, secretion, and excretion. The heart component enhances the KA's local search capability, guiding the algorithm toward optimal solutions. The HK model is evaluated on eight test functions, with results compared to those of the heart algorithm and KA alone. Additionally, the HK algorithm's effectiveness as a decision support system is tested on benchmark classification and time series prediction problems, with statistical analysis against existing methods in the literature. Finally, the HK algorithm is applied to cancer detection from microRNA data, demonstrating its potential in optimizing decision-making processes in healthcare.

关键词： Blood classification algorithms Filtration Decision support systems Prediction algorithms Kidney Heart rate Medical services Cancer detection Time series analysis Heart-kidney algorithm decision support system cancer detection classification and time series prediction optimization techniques

来源：评论

学校读者我要写书评

暂无评论

Gradient-Guided Local Search for Large-Scale Hypervolume Subset Selection

引用

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION 2025年第2期29卷 519-533页

作者： Nan, Yang Shu, Tianye Ishibuchi, Hisao Shang, Ke Southern Univ Sci & Technol Dept Comp Sci & Engn Shenzhen 518055 Peoples R China Shenzhen Univ Natl Engn Lab Big Data Syst Comp Technol Shenzhen 518060 Peoples R China

The use of an unbounded archive (UA) has attracted much attention in the filed of evolutionary multiobjective optimization (EMO) since a solution set selected from the UA is often better than the final population. The size of the UA is very large (e.g., 1 000 000) since it is unbounded and it stores all the examined nondominated solutions during the execution of an EMO algorithm. Thus, an algorithm which can efficiently select a high-quality subset from a large-scale candidate set (e.g., UA) is needed. In this article, we propose a gradient-guided local search hypervolume subset selection (GL-HSS) algorithm to efficiently select a high-quality subset from a large-scale candidate set. In each iteration of GL-HSS, the gradient of the hypervolume (HV) contribution of each selected solution is used to guide the local search. As a result, the proposed algorithm can quickly improve the HV of the selected subset. Experimental results show that, compared to the existing subset selection algorithms, the proposed GL-HSS algorithm can efficiently select high-quality subsets from various large-scale candidate sets.

关键词： Approximation algorithms classification algorithms Search problems Optimization Vectors Evolutionary computation Minimization Time complexity Size measurement Indexes Evolutionary multiobjective optimization (EMO) hypervolume subset selection (HSS) local search (LS) many-objective optimization

来源：评论

学校读者我要写书评

暂无评论

Leveraging Mixture Alignment for Multi-Source Domain Adaptation

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2025年 34卷 885-898页

作者： Dayal, Aveen Shrusti, S. Cenkeramaddi, Linga Reddy Mohan, C. Krishna Kumar, Abhinav Indian Inst Technol Hyderabad Dept Artificial Intelligence Hyderabad 502285 India Indian Inst Technol Hyderabad Dept Comp Sci & Engn Hyderabad 502285 India Univ Agder Dept Informat & Commun Technol N-4879 Grimstad Norway

In a conventional Domain Adaptation (DA) setting, we only have one source and target domain, whereas, in many real-world applications, data is often collected from several related sources in different conditions. This has led to a more practical and challenging knowledge transfer problem called Multi-source Domain Adaptation (MDA). Several methodologies, such as prototype matching, explicit distance discrepancy, adversarial learning, etc., have been considered to tackle the MDA problem in recent years. Among them, the adversarial-based learning framework is a popular methodology for transferring knowledge from multiple sources to target domains using a min-max optimization strategy. Despite the advances in adversarial-based methods, several limitations exist, such as the need for a classifier-aware discrepancy metric to align the domains and the need to consider target samples' consistency and semantic information while aligning the domains. To mitigate these issues, in this work, we propose a novel adversarial learning MDA algorithm, MDAMA, which aligns the target domain with a mixture distribution that consists of source domains. MDAMA uses margin-based discrepancy and augmented intermediate distributions to align the domains effectively. We also propose consistency of target samples by confidence thresholding and transfer of semantic information from multiple source domains to the augmented target domain to further improve the performance of the target domain. We extensively experiment with the MDAMA algorithm on popular real-world MDA datasets such as OfficeHome, Office31, PACS, Office-Caltech, and DomainNet. We evaluate the MDAMA model on these benchmark datasets and demonstrate top performance in all of them.

关键词： Measurement Adaptation models Semantics Accuracy Visualization Training Prototypes Indexes classification algorithms Benchmark testing Adversarial learning consistency regularization multi-source domain adaptation

来源：评论

学校读者我要写书评

暂无评论

Synthetic Zero-Sequence Signal-Based Intelligent Location Method for Single-Phase Ground Fault in Distribution Networks

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Guo, Mou-Fa Lin, Hongxin Lin, Jiahao Hong, Qiteng Fuzhou Univ Coll Elect Engn & Automat Fuzhou 350108 Peoples R China Fujian Key Lab New Energy Generat & Power Convers Fuzhou 350108 Peoples R China Univ Strathclyde Dept Elect & Elect Engn Glasgow City G1 1XQ Scotland

Distribution system structures are intricate and variable, with single-phase ground (SPG) fault occurring frequently. Existing section location methods for SPG faults are often influenced by manually set thresholds, resulting in low accuracy. This article analyzes the relationship between the zero-sequence voltage (ZSV) and zero-sequence current (ZSC) synthesized from three-phase voltage and current under the condition of no zero-sequence transformer installed on the line and proposes an SPG fault section threshold-free location method based on Swin-Transformer (S-T). First, Fourier transform-based data processing methods correct phase errors caused by current transformers (CTs) and eliminate the dc bias in synthesized ZSCs. Second, the synthesized ZSC waveform and the derivative of ZSC (DZSV) waveform are overlaid on the same image, with the enclosed areas shaded to highlight the relationship between the two electrical quantities. Finally, the transformer model is used to classify the differentiated images between the SPG fault section and sound section to achieve threshold-free fault location. The proposed method has been tested and validated on an industrial prototype in a 10-kV full-scale test system and deployed in the actual distribution network. Experimental results demonstrate that the method can accurately locate fault sections even under conditions of noise interference and inaccurate trigger timing.

关键词： Feature extraction Current transformers Transient analysis Grounding Capacitance Distribution networks classification algorithms Adaptation models Threshold voltage Data mining Distribution network fault section location single-phase ground (SPG) fault synthesized zero sequence transformer

来源：评论

学校读者我要写书评

暂无评论

Compact Workspace Decomposition Based on a Bottom-Up Approach

引用

IEEE ACCESS 2025年 13卷 3917-3928页

作者： Skorobogatov, Georgy Calvo, Toni Barrado, Cristina Salami, Esther Tech Univ Catalonia Comp Architecture Dept Castelldefels 08860 Spain

In this paper, we present an algorithm that addresses the challenge of dividing a workspace among multiple UAVs. The workspace can be any convex or non-convex polygon and may contain holes of various shapes that represent no-fly zones. The UAVs can be heterogeneous, with different levels of autonomy, speed, and range. The goal of the workspace division is to obtain areas whose sizes are best matched to the capabilities of the UAVs while maximizing compactness. The algorithm decomposes the polygon representing the workspace into a triangular grid, followed by an iterative process of accumulating adjacent triangles while maximizing the compactness of the resulting regions. The performance of the algorithm and the quality of the partitions generated by the algorithm are compared to existing methods. Results show that this approach outperforms others in several metrics, achieving a 5% to 10% improvement in compactness, while maintaining reasonable performance, with a time overhead of up to approximately two seconds when splitting a polygon into ten parts.

关键词： Partitioning algorithms Autonomous aerial vehicles Drones Robots Clustering algorithms classification algorithms Shape Approximation algorithms Sensors Area measurement UAV multi-robot systems workspace division polygon partition

来源：评论

学校读者我要写书评

暂无评论

Adaptive and Low-Cost Traffic Engineering: A Traffic Matrix Clustering Perspective

引用

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2025年第2期43卷 510-523页

作者： Liu, Yi Geng, Nan Xu, Mingwei Yang, Yuan Dong, Enhuan Liu, Chenyi Gan, Qiaoyin Li, Qing Wu, Jianping Tsinghua Univ Dept Comp Sci & Technol Beijing 100084 Peoples R China Tsinghua Univ Inst Network Sci & Cyberspace Beijing 100084 Peoples R China Tsinghua Univ Dept Comp Sci & Technol Beijing 100084 Peoples R China Chinese Acad Sci Inst Comp Technol Beijing 100190 Peoples R China Peng Cheng Lab Shenzhen 518066 Peoples R China

Traffic engineering (TE) has attracted extensive attention over the years. Operators expect to design a TE scheme that accommodates traffic dynamics well and achieves good TE performance with little overhead. Some approaches like oblivious routing compute an optimal static routing based on a large traffic matrix (TM) range, which usually leads to much performance loss. Many approaches compute routing solutions based on one or a few representative TMs obtained from observed historical TMs. However, they may suffer from performance degradation for unexpected TMs and usually induce much overhead of system operating. In this paper, we propose ALTE, an adaptive and low-cost TE scheme based on TM classification. We develop a novel clustering algorithm to properly group a set of historical TMs into several clusters and compute a candidate routing solution for each TM cluster. A machine learning classifier is trained to infer the proper candidate routing solution online based on the features extracted from some easily measured statistics. We implement a system prototype of ALTE and do extensive simulations and experiments using both real and synthetic traffic traces. The results show that ALTE achieves near-optimal performance for dynamic traffic and introduces little overhead of routing updates.

关键词： Routing Real-time systems Feature extraction Computational modeling Clustering algorithms Quality of service Optimization models classification algorithms Transforms Topology Traffic engineering traffic matrix classification machine learning

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：