检索结果-内蒙古大学图书馆

Multitask Twin Pinball Kernel Matrix Classifier for Pattern classification

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Chen, Chunan Pan, Haiyang Tong, Jinyu Wang, Yinghan Cheng, Jian Zheng, Jinde Anhui Univ Technol Sch Mech Engn Maanshan 243002 Peoples R China Cihu Econ Dev Bur Maanshan 243002 Peoples R China

Given the sensitivity of traditional matrix classifiers to noisy signals, a new classification method called multitask twin pinball kernel matrix classifier (MTTPKMC) is proposed. MTTPKMC first designs a feature mapping kernel (FMK) to protect the structural information of matrix samples and then introduces a pinball constraint term to reduce the sensitivity of the model to noise. In addition, the proposed algorithm is integrated with multitask learning (MTL) framework to fully utilize the correlation information between tasks, thereby further improving the classification performance of the model. To validate the effectiveness of the MTTPKMC method described above, experimental verification is conducted on two mechanical fault datasets, and the results show that the proposed method has superior diagnostic performance.

关键词： Support vector machines Multitasking Kernel Training Data mining Sensitivity classification algorithms Vectors Production Noise Fault diagnosis gear multitask learning (MTL) multitask twin pinball kernel matrix classifier (MTTPKMC) rolling bearing support matrix machine (SMM)

来源：评论

学校读者我要写书评

暂无评论

Bidirectional Stacking Ensemble Curriculum Learning for Hyperspectral Image Imbalanced classification With Noisy Labels

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Wang, Yixin Li, Hao Gong, Maoguo Wu, Yue Gong, Peiran Qin, A. K. Xing, Lining Zhang, Mingyang Xidian Univ Sch Elect Engn Key Lab Collaborat Intelligence Syst Minist Educ Xian 710071 Shaanxi Peoples R China Inner Mongolia Normal Univ Acad Artificial Intelligence Coll Math Sci Minist Educ Hohhot 010028 Peoples R China Xidian Univ Sch Comp Sci & Technol Xian 710071 Peoples R China Swinburne Univ Technol Dept Comp Technol Hawthorn Vic 3122 Australia

Hyperspectral imaging has demonstrated substantial advantages in enhancing classification performance in remote sensing applications due to its abundant spectral information. To address the challenges of label noise and class imbalance in the hyperspectral image (HSI) classification, we propose an end-to-end feature-guided network (FGN) for HSIs. Instead of merely combining spatial and channel attention, the FGN leverages feature-level attention interactions to enhance contextual understanding, leading to better feature extraction, especially for underrepresented classes. Furthermore, a bidirectional loss for curriculum learning (CL) is proposed to rank the HSI training data in descending or ascending order. The top and bottom loss regularizers are designed to make the proposed model suitable for noisy and imbalanced HSI data distributions. In the phase of selecting the pace parameter, a stacking ensemble CL (SECL) model is established to avoid the outliers and noisy HSI data involved in the CL training process. A novel instruction matrix based on sample weights is designed for base classifiers. The outputs of the base models, combined with the expected labels, form the input-output pairs for training the second-level classifier. Experiments conducted on multiple hyperspectral imbalanced datasets with noisy labels demonstrate the superior performance of our method.

关键词： Noise measurement Training Training data Stacking Noise Hyperspectral imaging Ensemble learning Data models classification algorithms Annotations Curriculum learning (CL) ensemble learning hyperspectral image (HSI) classification imbalanced distribution

来源：评论

学校读者我要写书评

暂无评论

Spectral-Temporal-Spatial Feature Optimization for Dioscorea Polystachya Turczaninow classification Using Time Series Sentinel-2 Data

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Chen, Zhulin Shi, Tingting Jiang, Haiying Yuan, Bo Cui, Yuran Qiao, Shijiao Jia, Kun Beijing Normal Univ Adv Interdisciplinary Inst Satellite Applicat Beijing 100875 Peoples R China Chinese Acad Forestry Inst Forest Resource Informat Tech Beijing 100091 Peoples R China China Acad Chinese Med Sci Natl Resource Ctr Chinese Mat Med State Key Lab Breeding Base Dao DiHerbs Beijing 100700 Peoples R China Harbin Engn Univ Coll Comp Sci & Technol Harbin 150001 Peoples R China Chinese Res Inst Environm Sci Beijing 100012 Peoples R China

Dioscorea polystachya Turczaninow is one of the most famous traditional Chinese Materia Medica. However, there is a lack of large-scale classification method, which is crucial for its growth status monitoring and yield estimation. This study proposed a reliable D. polystachya Turczaninow classification model based on spectral-temporal-spatial feature optimization using time series Sentinel-2 data. First, 16 monotemporal classification models were developed using five vegetation indices (VIs) and random forest (RF) algorithm. Then, temporal feature optimization was conducted by identifying the most effective time phase combinations based on Sentinel-2 time series normalized difference vegetation index (NDVI) data, Gaussian mixture modeling algorithm, and F1 score of D. polystachya Turczaninow in each monotemporal model. Next, spectral features were optimized by replacing NDVI with the optimal VI corresponding to each time phase, thus constructing a multi-VI-based time series dataset. Finally, the spatial feature optimization was conducted using the 3-D convolutional neural network (3-D CNN) algorithm and the multi-VI-based time series Sentinel-2 data. Following the comprehensive feature optimization, the final D. polystachya Turczaninow classification model was determined. The results found that Sentinel-2 data acquired during the rhizome enlargement stage played a crucial role in classifying the D. polystachya Turczaninow. By using the optimized features, the classification model achieved the D. polystachya Turczaninow F1 score of 95.00%, which improved by 11.49% compared to only using the time series NDVI data. This spectral, temporal, and spatial feature optimization method also has the potential to the development of large-scale, dynamic, and accurate mapping for other crops.

关键词： Crops Vegetation mapping Data models Time series analysis Normalized difference vegetation index Accuracy classification algorithms Training Indexes Convolutional neural networks classification Dioscorea polystachya Turczaninow feature optimization remote sensing time series Sentinel-2

来源：评论

学校读者我要写书评

暂无评论

MMD-MLP: LiDAR-Guided Hyperspectral Data classification Using Local-Global Directional-MLP With Multiresolution Multiscale Representation

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Luo, Fulin Hua, Yiyan Fu, Chuan Guo, Tan Duan, Yule Shi, Guangyao Chongqing Univ Coll Comp Sci Chongqing 400044 Peoples R China Xidian Univ State Key Lab Integrated Serv Networks Xian 710071 Peoples R China Chongqing Univ Posts & Telecommun Sch Commun & Informat Engn Chongqing 400065 Peoples R China Henan Univ Technol Coll Informat Sci & Engn Zhengzhou 450001 Peoples R China Chongqing Univ Posts & Telecommun Sch Comp Sci & Technol Chongqing 400065 Peoples R China

Hyperspectral images (HSIs) are rich in spectral information and are widely used in the field of land-cover classification. However, existing deep learning methods ignore the combination of multiscale and multiresolution information, while not making better use of light detection and ranging (LiDAR) elevation information to assist in the enhancement of HSI data. To solve the problem above, we proposed a multiresolution, multiscale local-global directional MLP (MMD-MLP) for HSI classification with a LiDAR-guided feature enhancement module in this article. The algorithm first introduced a local-global-directed MLP structure, which effectively combines local and global features. Second, a multiresolution and multiscale feature extraction strategy is invented for the accurate acquisition of the detailed information and features of different land covers under different scale sizes. Subsequently, a LiDAR-guided feature enhancement module, which introduces the elevation information from LiDAR for improving the feature representation of HSI, adopts a cross-attention mechanism to reduce the semantic gap to improve the features of HSI. The proposed algorithm was evaluated on multiple hyperspectral-LiDAR datasets, and the results demonstrate that it achieves state-of-the-art (SOTA) performance. The code will be available at https://***/sanxian-svg/MMD-MLP.

关键词： Feature extraction Laser radar Transformers Hyperspectral imaging Data mining classification algorithms Training Three-dimensional displays Tensors Shape classification hyperspectral image (HSI) light detection and ranging (LiDAR) multilayer perceptions

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Normal White Blood Cell Multi-classification Optimization

引用

IEEE ACCESS 2025年 13卷 17662-17672页

作者： Gil, Taeyeon Lee, Sukjun Lee, Onseok Soonchunhyang Univ Grad Sch Dept Software Convergence Asan 31538 Chungcheongnam South Korea Cheongju Univ Coll Hlth & Med Sci Dept Biomed Lab Sci Cheongju 28503 Chungcheongbug South Korea Soonchunhyang Univ Coll Software Convergence Dept Med IT Engn Asan 31538 Chungcheongnam South Korea

Clinically, the proportion and classification of white blood cell (WBC)s are currently established using manual methods, which rely on subjective judgment. Therefore, many studies are being conducted to automate the classification of WBC types. Several studies have employed deep learning (DL) or machine learning (ML) methods;no significant difference in performance between the two methods has been demonstrated. However, if the feature extraction and selection processes are optimized when using ML for WBC classification, its performance is improved. Therefore, in this study, we proposed an ML-based optimization system for five normal WBC classifications. Open datasets, Raabin-WBC, and private data were used. WBCs were segmented into nucleus, cytoplasm, and cell regions using U-Net, a DL model. The nucleus showed high segmentation performance with an average accuracy of 98.58% and a Dice coefficient of 0.9233, whereas the cells achieved an average accuracy of 99.47% and a Dice coefficient of 0.9324. Among the five multiple classifiers, the support vector machine achieved the highest accuracy of 97.36% and was chosen for WBC classification. Features used for WBC classification were determined through three experiments, resulting in a final selection of 108 features combining intensity histogram, hue saturation value, and CIE La * b * features. When using the selected features, the classification accuracy was 98.22%, indicating a high performance. Segmentation and classification of WBCs were performed using a graphical user interface and required approximately 137 s. The proposed system in this study is expected to enhance the efficiency of the existing PBS tests.

关键词： Feature extraction Accuracy Lymphocytes classification algorithms Support vector machines Convolutional neural networks Image segmentation Blood Eosinophils Deep learning Peripheral blood smear normal white blood cells feature selection multiple classifiers graphical user interface

来源：评论

学校读者我要写书评

暂无评论

Sustainable Environmental Monitoring: Multistage Fusion Algorithm for Remotely Sensed Underwater Super-Resolution Image Enhancement and classification

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 3640-3653页

作者： Ghaban, Wad Ahmad, Jawad Siddique, Ali Akbar Alshehri, Mohammad S. Saghir, Anila Saeed, Faisal Ghaleb, Baraq Rehman, Mujeeb Ur Univ Tabuk Appl Coll Tabuk 47512 Saudi Arabia Prince Mohammad bin Fahd Univ Cybersecur Ctr Al Khobar 31952 Saudi Arabia Iqra Univ Dept Comp Sci Karachi 75300 Pakistan Najran Univ Coll Comp Sci & Informat Syst Dept Comp Sci Najran 61441 Saudi Arabia Sir Syed Univ Engn & Technol Dept Telecommun Engn Karachi 75300 Pakistan Birmingham City Univ Coll Comp Birmingham B4 7XG England Edinburgh Napier Univ Sch Comp Engn & Built Environm Edinburgh EH105DT Scotland Montfort Univ Inst Artificial Intelligence Sch Comp Sci & Informat Leicester LE1 9BH England

Oceans and seas cover more than 70% of the Earth's surface. If compared with the land mass there are a lot of unexplored locations, a wealth of natural resources, and diverse ocean creatures that are inaccessible to us humans. Underwater rovers and vehicles play a vital role in discovering these resources, yet limited visibility in deep waters and technological constraints impede underwater exploration. To address these issues, advanced image super-resolution and enhancement techniques are crucial for reliable resource identification, species recognition, and underwater ecosystem study. This will ultimately bridge the current gap in environmental monitoring by facilitating resource tracking and underwater waste assessment. This article proposes a novel multistage fusion algorithm for underwater image super-resolution, designed to enhance the quality and spatial resolution of low-resolution underwater images toward a more accurate object characterization. The effectiveness of the proposed super-resolution technique is demonstrated using multiple performance metrics including accuracy, f1-score, recall, and precision. By enhancing the spatial resolution of underwater images, our approach meets the increasing demand for detailed and accurate information in underwater earth observation applications.

关键词： Remote sensing Superresolution Image enhancement Spatial resolution Image quality Image color analysis Computer science Accuracy Colored noise classification algorithms Image classification image enhancement image processing image recognition remote sensing

来源：评论

学校读者我要写书评

暂无评论

Deep Fourier-Based Task-Aware Metric Network for Few-Shot SAR Target classification

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Zheng, Jia Li, Ming Chen, Hongmeng Zhang, Peng Wu, Yan Xidian Univ Natl Key Lab Radar Signal Proc Xian 710071 Peoples R China Beijing Inst Radio Measurement Beijing 100854 Peoples R China Xidian Univ Sch Elect Engn Remote Sensing Image Proc & Fus Grp Xian 710071 Peoples R China

The downsampling operations in convolutional neural networks (CNNs) lead to the loss of high-frequency texture features in images, posing challenges for synthetic aperture radar (SAR) automatic target recognition (ATR). To this end, some algorithms introduce the Fourier transform to retain and restore high-frequency information. However, these algorithms are prone to overfitting with a small number of SAR samples. Additionally, the similarity of different SAR target backgrounds further complicates distinguishing between targets and backgrounds during metric learning. To address these issues, a novel few-shot learning (FSL) method for SAR target classification, namely, the deep Fourier-based task-aware metric network, is proposed. First, we propose a frequency-domain feature extraction module. This module uses a fast Fourier transform (FFT) to convert the input image into the frequency domain, and then performs convolution on the amplitude and phase information to extract and enhance features. Then, the inverse FFT and convolution operations are applied to generate the final frequency-domain feature representation. Furthermore, we propose a parameter-free contrast metric module that identifies and reduces background-related features by calculating the similarity between the query sample and both the target and nontarget classes. This module fully considers the context of the entire task support set, effectively improving the model's recognition accuracy. Finally, to address the issue of increased sensitivity to noise and outliers due to unimportant local descriptors during the metric process, we design a weighted k-nearest neighbor (k-NN) method to enhance the model's focus on important information, thereby improving classification accuracy. The experimental results on two public SAR datasets demonstrate that our proposed algorithm achieves higher classification accuracy than other FSL algorithms and exhibits discriminative feature representation and metric capabilit

关键词： Measurement Synthetic aperture radar Feature extraction classification algorithms Radar polarimetry Target recognition Frequency-domain analysis Accuracy Fast Fourier transforms Training Automatic target classification contrastive metric module few-shot learning (FSL) Fourier transform synthetic aperture radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

Artifacts Extraction From Video Head Impulse Test Data Using Time Series classification Methods and VOR Gain Analysis

引用

IEEE ACCESS 2025年 13卷 56520-56530页

作者： Baydadaev, Shokhrukh Usmankhujaev, Saidrasul Sung Kim, Kyu Woo Kwon, Jang Inha Univ Dept Elect & Comp Engn Incheon 22212 South Korea Inha Univ Coll Med Dept Otorhinolaryngol Inchon 22332 South Korea

The video head impulse test (vHIT) has become an essential tool in the examination of patients with dizziness and other balance disorders, providing significant data on all six semicircular canals. The clinical interpretation of the vestibulo-ocular reflex (VOR) dynamic function of the human brain in vertigo and balance disorders using the vHIT method poses a considerable challenge. We utilize VOR gain measurements to ascertain the health of the patient's vestibular system. However, all methods have inherent limitations due to the presence of noise and artifacts in the data, which can significantly affect the gain values of normal and abnormal impulses, leading to inaccuracies. This paper presents a comprehensive study, where we have created a dataset using vHIT data from 5,782 clinical patients from the Department of Otorhinolaryngology, College of Medicine, Inha University. We apply time series classification (TSC) algorithms to identify and filter artifact-affected impulses, ensuring more reliable VOR gain calculations. The encoder model achieved a classification accuracy of 94%, surpassing previous approaches such as SSNHLV (92%) and AI-based stroke (88%) classification. Statistical analysis confirms the significance of our method, with p-values (<0.05) demonstrating a clear distinction between normal, abnormal, and artifact impulses. By improving impulse classification, our approach enhances the precision of VOR gain calculations, contributing to more accurate clinical diagnoses of vestibular disorders.

关键词： Deep learning Accuracy Magnetic heads Head Time series analysis Gain measurement Data mining classification algorithms Statistical analysis Otorhinolaryngology Video head impulse test (vHIT) vestibulo-ocular reflex (VOR) VOR gain video-oculography (VOG) device time-series classification (TSC)

来源：评论

学校读者我要写书评

暂无评论

MDSC-Net: Multi-Modal Discriminative Sparse Coding Driven RGB-D classification Network

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2025年 27卷 442-454页

作者： Xu, Jingyi Deng, Xin Fu, Yibing Xu, Mai Li, Shengxi Beihang Univ Sch Elect & Informat Engn Beijing 100191 Peoples R China Beihang Univ Shen Yuan Honors Coll Beijing 100191 Peoples R China

In this paper, we propose a novel sparsity-driven deep neural network to solve the RGB-D image classification problem. Different from existing classification networks, our network architecture is designed by drawing inspirations from a new proposed multi-modal discriminative sparse coding (MDSC) model. The key feature of this model is that it can gradually separate the discriminative and non-discriminative features in RGB-D images in a coarse-to-fine manner. Only the discriminative features are integrated and refined for classification, while the non-discriminative features are discarded, to improve the classification accuracy and efficiency. Derived from the MDSC model, the proposed network is composed of three modules, i.e., the shared feature extraction (SFE) module, discriminative feature refinement (DFR) module, and classification module. The architecture of each module is derived from the optimization solution in the MDSC model. To the best of our knowledge, this is the first time a fully sparsity-driven network has been proposed for RGB-D image classification. Extensive results verify the effectiveness of our method on different RGB-D image datasets.

关键词： Feature extraction Image coding Image classification Dictionaries Optimization classification algorithms Deep learning Convolutional neural networks Accuracy Encoding Convolutional sparse coding RGB-D image classification Discriminative features

来源：评论

学校读者我要写书评

暂无评论

PDCNet: A Polarimetric Data-Enhanced Contrastive Learning Network for PolSAR Land Cover classification

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 10010-10025页

作者： Ren, Bo Hua, Chaoyue Hou, Biao Lv, Jian Yang, Chen Jiao, Licheng Chanussot, Jocelyn Xidian Univ Minist Educ China Key Lab Intelligent Percept & Image Understanding Xian 710071 Peoples R China Univ Grenoble Alpes Inria CNRS Grenoble INPLJK F-38000 Grenoble France

Polarimetric synthetic aperture radar (PolSAR) has rich polarization information, offering an efficient and reliable means of collecting information. However, how to effectively leverage these complex data to extract polarization features remains a key challenge. Recently, contrastive learning has been successful in computer vision, with fewer labeled and a large amount of unlabeled data. Inspired by it, a polarimetric data-enhanced contrastive learning network (PDCNet) for PolSAR land cover classification is proposed. The design process for polarimetric contrastive learning involves the construction of positive samples, the establishment of a PolSAR-based network architecture for contrastive learning, and the formulation of the loss function. The proposed method first constructs positive sample pairs for contrastive learning by leveraging the linear relationship between the coherency matrix (T-matrix) and the covariance matrix (C-matrix). In addition, since both of them are 3 X 3 complex conjugate symmetric matrices, we design an adaptive contrastive learning network to extract real and complex information. Specifically, the encoder of PDCNet is designed as an extraction module for a real-convolutional composite complex convolutional network. Thirdly, a loss function is designed to effectively compute the real and complex high-level semantics of the T- and C-matrix's features separately. We conducted experiments with labels of different quantities in four data sets. The results indicate that our proposed model outperforms state-of-the-art contrastive learning models.

关键词： Feature extraction Contrastive learning Convolutional neural networks Vectors Scattering Land surface Synthetic aperture radar Data mining classification algorithms Training Complex convolutional networks contrastive learning land cover classification polarimetric synthetic aperture radar (PolSAR) positive pairs

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：