检索结果-内蒙古大学图书馆

Feature Selection and classification Optimization of Transformer Oil Odor Data With Recursive Feature Elimination Using Grid Search and Cross-Validation

引用

IEEE ACCESS 2025年 13卷 21043-21051页

作者： Tozlu, Bilge Han Hitit Univ Engn Fac Dept Elect & Elect Engn TR-19200 Corum Turkiye

Power transformers are vital for transmitting, distributing, and using energy produced in electrical energy systems. The failure of a distribution transformer can cause significant financial losses to society and cause irreparable problems. Therefore, power transformers' reliability, continuous monitoring, and fault-free operation are critical. In this study, an electronic nose system was developed to detect the duration of oil usage in power transformers based on its smell. In the system designed with eleven inexpensive gas sensors, a total of 200 transformer oil odors with four different usage periods were analyzed. Four features were selected from eighty-eight features using the Recursive Feature Elimination method with Grid Search and Cross-Validation, and they were classified with six different classifiers. With the Extra Trees algorithm, the most successful classifier, classification performance of 0.9810 CA, 0.9810 SE, 0.9937 SF was achieved without feature selection, and 0.9610 CA, 0.9610 SE, 0.9870 SF was achieved by selecting features. Dielectric breakdown voltage tests of the oils in the study were also performed, and the results supported the results of the electronic nose system. According to the results obtained, it can be concluded that transformer oil maintenance can be performed economically, practically, and reliably with the proposed system.

关键词： ExtraTreesClassifier feature selection recursive feature elimination electronic nose dielectric breakdown voltage test classification algorithms transformers oil ExtraTreesClassifier feature selection recursive feature elimination electronic nose dielectric breakdown voltage test classification algorithms transformers oil

来源：评论

学校读者我要写书评

暂无评论

Actuator Fault Tolerant Control in Switched Systems: A Comprehensive Approach Integrating Clustering, classification, and LMI-Based Compensation

引用

IEEE ACCESS 2025年 13卷 44090-44106页

作者： Yahia, Salwa Bedoui, Saida Abderrahim, Kamel Univ Gabes Lab Numer Control Ind Proc Tunis 1053 Tunisia

This paper presents a new strategy to address the challenges associated with the design of fault tolerant tolerant control (FTC) in stochastic switched systems. In fact, the problem of predicting the switched mode in discrete behavior is based on a set of input-output database. To address this, the proposed methodologies incorporate a combination of clustering and classification techniques to determine the number of sub-models. The estimated actuator fault is then compensated by controller generated for each sub model. The controller gains are given by solving the Linear Matrix Inequality (LMIs), which is derived based on the general Lyapunov function. The fast convergence of the actuator fault, which is estimated using the proposed data-driven method, minimizes the instability time of the switched system after fault occurrence and attenuates the disturbance. Finally, the effectiveness of the proposed method against actuator faults is validated through two numerical analyses. The first example shows a faulty stochastic switched system with two modes and the second example shows a practical application of a double cart system with elastic coupling.

关键词： Switches Control systems Fault tolerant systems Fault tolerance Switched systems Noise Estimation Switching systems Switching circuits classification algorithms Switched system classification fault-tolerant control actuator fault switching mode Lyapunov

来源：评论

学校读者我要写书评

暂无评论

An Analytic Hierarchy Model for classification algorithms Selection in Credit Risk Analysis

引用

MATHEMATICAL PROBLEMS IN ENGINEERING 2014年第1期2014卷 1-7页

作者： Kou, Gang Wu, Wenshuai Southwestern Univ Finance & Econ Sch Business Adm Chengdu 611130 Peoples R China Southwestern Univ Finance & Econ Collaborat Innovat Ctr Financial Secur Chengdu 611130 Peoples R China Univ Elect Sci & Technol China Sch Management & Econ Chengdu 610054 Peoples R China

This paper proposes an analytic hierarchy model (AHM) to evaluate classification algorithms for credit risk analysis. The proposed AHM consists of three stages: data mining stage, multicriteria decision making stage, and secondary mining stage. For verification, 2 public-domain credit datasets, 10 classification algorithms, and 10 performance criteria are used to test the proposed AHM in the experimental study. The results demonstrate that the proposed AHM is an efficient tool to select classification algorithms in credit risk analysis, especially when different evaluation algorithms generate conflicting results.

关键词： ANALYTIC hierarchy process classification algorithms CREDIT risk MULTIPLE criteria decision making DATA mining

来源：评论

学校读者我要写书评

暂无评论

Deep Metric Learning Based on Brownian Covariance Representation for Few-Shot Hyperspectral Image classification

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Dong, Yanni Zhu, Bei Yang, Xiaochen Ma, Xin Wuhan Univ Sch Resource & Environm Sci Wuhan 430079 Peoples R China China Univ Geosci Sch Geophys & Geomat Wuhan 430074 Peoples R China Univ Glasgow Sch Math & Stat Glasgow G12 8QQ Scotland Wuhan Univ State Key Lab Informat Engn Surveying Mapping & Re Wuhan 430079 Peoples R China

Currently, few-shot learning (FSL) is widely used in image classification hyperspectral image classification (HSIC), owing to its exceptional proficiency in achieving good performance with few training samples. Although the FSL has made good progress, there are still some problems to be solved. On the one hand, existing methods rely on linear distance to learn metrics, which cannot capture the subtle similarities and differences between scarce prior samples. On the other hand, many current methods directly superimpose the features of spatial and spectral information, without deeply fusing the internal relationship between these two kinds of information. To address the aforementioned issues, a deep metric learning method based on Brownian distance covariance (DML-BDC) is proposed for few-shot HSIC. A dual-channel Brownian distance covariance feature extraction network is designed, which uses the Brownian covariance representation to model and fuse the spatial and spectral information and uses two different feature extractors to achieve the effect of information complementarity. Then, a metric loss based on Gaussian kernel distance is proposed to learn the complex nonlinear structure and subtle similarities and differences between support samples. Experiments on three benchmark datasets show that DML-BDC has advantages over the existing mainstream methods in terms of classification accuracy, generalization, and model complexity.

关键词： Measurement Feature extraction Training Hyperspectral imaging Data mining Image classification Adaptation models Kernel classification algorithms Overfitting Covariance representation (CR) deep metric learning (DML) few-shot hyperspectral image classification (HSIC)

来源：评论

学校读者我要写书评

暂无评论

CDFNet: Cross-Domain Feature Fusion Network for PolSAR Terrain classification

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Wang, Shuang Sun, Zhuangzhuang Bian, Tianquan Guo, Yuwei Dai, Linwei Guo, Yanhe Jiao, Licheng Xidian Univ Int Res Ctr Intelligent Percept & Computat Sch Artificial Intelligence Key Lab Intelligent Percept & Image Understanding Xian 710071 Shaanxi Peoples R China

The scarcity of labeled data and domain shift among polarimetric synthetic aperture radar (PolSAR) images degrades the performance of the supervised-learning-based algorithm. Some unsupervised domain adaptation (UDA) algorithms have been proposed to address this problem and achieve good performance. The existing UDA algorithms for PolSAR terrain classification focus on the feature distribution shift problem but ignore the label shift problem in UDA task. In addition, feature alignment-based algorithms generate pseudo labels for target domain which introduce label noise and compromising the UDA performance. To alleviate the problems above, we present a cross-domain feature fusion network (CDFNet) for PolSAR terrain classification. Specifically, a domain-balanced sampling (DBS) module is proposed to obtain a nearly balanced training dataset to alleviate the label shift problem. Then, a cross-domain feature fusion (CDF) module is presented to achieve class-wise feature alignment with no additional label noise introduction. Experimental results on four PolSAR datasets demonstrate that our algorithm outperforms state-of-the-art UDA algorithms in terms of target domain performance.

关键词： classification algorithms Feature extraction Scattering Imaging Training Noise Mathematical models Covariance matrices Representation learning Matrix decomposition Feature fusion land cover classification polarimetric synthetic aperture radar (PolSAR) unsupervised domain adaptation (UDA)

来源：评论

学校读者我要写书评

暂无评论

classification of Seabed Sediment by Combining Airborne LiDAR Bathymetry and Multispectral Remote Sensing Images

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 9023-9032页

作者： Su, Dianpeng Gao, Han Yang, Anxiu Wang, Juan Mai, Xiaozheng Liu, Xudong Yang, Fanlin Wu, Ziyin Shandong Univ Sci & Technol Coll Geodesy & Geomat Qingdao 266590 Peoples R China Minist Nat Resources Key Lab Ocean Geomat Qingdao 266590 Peoples R China Chinese Acad Sci Shanghai Inst Opt & Fine Mech Shanghai 201800 Peoples R China Minist Nat Resources Inst Oceanog 2 Key Lab Submarine Geosci Hangzhou 310012 Peoples R China Minist Nat Resources Key Lab Ecol Prewarning Protect & Restorat Bohai Sea Qingdao 310012 Peoples R China Minist Nat Resources Topog surveying Bridge 7 Haikou 570203 Peoples R China

The classification of seabed sediment plays an important role in marine ecological environment protection and other related fields. To fully explore the application ability of marine geographic information in seabed sediment classification, this article makes a contribution to overcome the low accuracy and reliability shortcomings of using single data source and traditional classifiers. Based on extracted multisource features, the scale-invariant feature transform - random sample consensus model is applied to realize feature-level fusion between airborne LiDAR bathymetry (ALB) data and multispectral remote sensing images. Furthermore, a dual-branch convolutional neural network (CNN) classifier is constructed to classify the seabed sediment into five categories (coral reef, sand, gravel, coastal zone, and vegetation). To verify the effectiveness of fused data in seabed sediment classification, experiments were conducted using multispectral remote sensing images and ALB data. Experimental results show that the overall classification accuracy and the Kappa coefficient of the dual CNN classifier constructed in this article are 98.2% and 0.977, respectively. In addition, the classification results using multisource fusion data are higher than those using single-source data, indicating the accuracy and effectiveness of multisource fusion features for classification. The research results can provide effective technical support for seabed sediment classification.

关键词： Feature extraction Sediments Remote sensing Laser radar Accuracy Natural resources Soft sensors Data mining classification algorithms Geomagnetism Airborne LiDAR bathymetry (ALB) multisource feature extraction and fusion multispectral remote sensing images seabed sediment classification

来源：评论

学校读者我要写书评

暂无评论

Electromyography Signals in Embedded Systems: A Review of Processing and classification Techniques

引用

BIOMIMETICS 2025年第3期10卷 166-166页

作者： Castruita-Lopez, Jose Felix Aviles, Marcos Toledo-Perez, Diana C. Macias-Socarras, Idalberto Rodriguez-Resendiz, Juvenal Univ Autonoma Queretaro Fac Ingn Santiago De Queretaro 76240 Mexico Univ Estatal Peninsula Santa Elena UPSE Fac Ciencias Agr Santa Elena 240204 Ecuador

This article provides an overview of the implementation of electromyography (EMG) signal classification algorithms in various embedded system architectures. They address the specifications used for implementation in different devices, such as the number of movements and the type of classification method. Architectures analyzed include microcontrollers, DSP, FPGA, SoC, and neuromorphic computers/chips in terms of precision, processing time, energy consumption, and cost. This analysis highlights the capabilities of each technology for real-time wearable applications such as smart prosthetics and gesture control devices, as well as the importance of local inference in artificial intelligence models to minimize execution times and resource consumption. The results show that the choice of device depends on the required system specifications, the robustness of the model, the number of movements to be classified, and the limits of knowledge concerning design and budget. This work provides a reference for selecting technologies for developing embedded biomedical solutions based on EMG.

关键词： embedded systems EMG artificial intelligence classification algorithms FPGA SoC

来源：评论

学校读者我要写书评

暂无评论

Model Input-Output Configuration Search With Embedded Feature Selection for Sensor Time-Series and Image classification

引用

IEEE ACCESS 2025年 13卷 58960-58977页

作者： Hoang, Anh Tuan Viharos, Zsolt Janos Ctr Excellence Hungarian Acad Sci MTA Ctr Excellence Prod Informat & Control EPIC HUN REN Inst Comp Sci & Control H-1111 Budapest Hungary Eotvos Lorand Univ Doctoral Sch Informat H-1117 Budapest Hungary John von Neumann Univ Fac Econ & Business H-6000 Kecskemet Hungary

Machine learning is a powerful tool for extracting valuable information and making various predictions from diverse datasets. Traditional machine learning algorithms rely on well-defined input and output variables;however, there are scenarios where the separation between the input and output variables and the underlying, associated input and output layers of the model are unknown. Feature Selection (FS) and Neural Architecture Search (NAS) have emerged as promising solutions in such scenarios. This paper proposes MICS-EFS, a Model Input-Output Configuration Search with Embedded Feature Selection. The methodology explores internal dependencies in the complete input parameter space for classification tasks involving both 1D sensor time-series and 2D image data. MICS-EFS employs a modified encoder-decoder model and the Sequential Forward Search (SFS) algorithm, combining input-output configuration search with embedded feature selection. Experimental results demonstrate MICS-EFS's superior performance compared to other FS algorithms. Across all tested datasets, MICS-EFS delivered an average accuracy improvement of 1.5% over baseline models, with the accuracy gains ranging from 0.5% to 5.9%. Moreover, the algorithm reduced feature dimensionality to just 2-5% of the original data, significantly enhancing computational efficiency. These results highlight the potential of MICS-EFS to improve model accuracy and efficiency in various machine learning tasks. Furthermore, the proposed method has been validated in a real-world industrial application focused on machining processes, underscoring its effectiveness and practicality in addressing complex input-output challenges.

关键词： Feature extraction Computational modeling Computer architecture Accuracy Machine learning algorithms Training Neural networks classification algorithms Autoencoders Feature selection input output configuration search machine learning neural network architectures optimal model structure optimal model structure

来源：评论

学校读者我要写书评

暂无评论

Dense-ShuffleGCANet: An Attention-Driven Deep Learning Approach for Diabetic Foot Ulcer classification Using Refined Spatio-Dimensional Features

引用

IEEE ACCESS 2025年 13卷 5507-5521页

作者： Ajay, Armaano Bisht, Akshaj Singh Karthik, R. Vellore Inst Technol Sch Comp Sci & Engn SCOPE Chennai 600127 India Vellore Inst Technol CCPS Chennai 600127 India

Diabetic foot ulcers (DFU) are a common and serious complication of diabetes, often leading to severe health implications like limb amputation if left untreated. Timely intervention and treatment are crucial in mitigating the impact of DFU on patients' well-being. However, manual identification of DFUs remains a challenge due to their heterogeneous visual characteristics, leading to several undiagnosed cases and avoidable complications. Deep learning provides an efficient solution to the challenge by automating the process of DFU detection, thereby alleviating the burden on the healthcare industry. This research introduces a novel model, Dense-ShuffleGCANet, for DFU detection by leveraging DenseNet-169, Channel-Centric Depth-wise Group Shuffle (CCDGS) block, and triplet attention. The architecture of DenseNet-169 is modified to integrate the CCDGS block and triplet attention, enabling the model to efficiently capture long-range dependencies and utilise cross-channel features. These improvements enable the effective extraction of both channel-wise and spatial features. The proposed Dense-ShuffleGCANet model achieved an accuracy of 86.09% and an F1-score of 85.77% on the DFUC2021 dataset, outperforming state-of-the-art architectures.

关键词： Accuracy Feature extraction Diabetes Computer architecture Computational modeling Transformers classification algorithms Optimization Medical services CNN deep learning DenseNet diabetic foot ulcer triplet attention triplet attention

来源：评论

学校读者我要写书评

暂无评论

MKD-Net: A Novel Neuro Evolutionary Approach for Blockchain-Based Secure Medical Image classification Using Multi-Kernel DLM

引用

IEEE ACCESS 2025年 13卷 29900-29913页

作者： Vishwakarma, Virendra P. Yadav, Abhay Kumar USICT Guru Gobind Singh Indraprastha Univ New Delhi 110078 India

In the era of digital healthcare, secure and accurate classification of medical images is of utmost importance, particularly in situations of data imbalance. Owing to advancements in the domain of nature-inspired optimization and human brain simulations, this paper presents a novel approach to a neuro-evolutionary algorithm for medical image classification. In the proposed methodology, we develop a non-iterative learning-based neural network that can handle class imbalance with the help of class-specific regularizations, named multi-kernel deep neural networks (MKD-Net). Multiple kernels are employed in the proposed MKD-Net for different data representations in the classification of heterogeneous data. The MKD-Net parameters are optimized using the Enhanced-JAYA algorithm. ResNet-50, known for its incomparable feature drawing ability, has been used in MKD-Net as an input image feature extractor. Experimental evaluations conducted on benchmark medical image datasets demonstrate that MKD-Net achieves superior classification performance, particularly in imbalanced datasets. Key metrics such as classification accuracy, sensitivity, specificity, precision, and F1-score consistently improve over traditional models. Specifically, the proposed MKD-Net obtained accurate classification on ATT and ALL-IDB1 datasets;97.44% and 97.46% accuracy on ALL-IDB2 and CoVid datasets respectively. Moreover, the integration with blockchain provide secure feature storage and also ensures data integrity, traceability, and enhanced privacy. By combining advanced feature extraction, optimization, and security mechanisms, MKD-Net sets a new benchmark in medical image classification, showcasing its potential for scalable and secure healthcare applications.

关键词： Accuracy Medical diagnostic imaging Feature extraction Blockchains Image classification Face recognition Deep learning Optimization Leukemia classification algorithms Data Imbalance medical image classification multi-kernel deep learning model neuro-evolution ResNet-50

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：