检索结果-内蒙古大学图书馆

Feature Selection-Based Multiview Concentration for Multivariate Time Series classification and Its Application

IEEE SENSORS JOURNAL 2024年第4期24卷 4798-4806页

作者： He, Changchun Huo, Xin Zhu, Chao Chen, Songlin Harbin Inst Technol Control & Simulat Ctr Harbin 150080 Peoples R China Shanghai Rising Digital Co Ltd Shanghai 201210 Peoples R China

In this article, a feature selection-based multiview concentration (FS-MVC) algorithm is proposed for multivariate time series classification (MTSC). The data-driven excavator fault diagnosis task is used as an application case of the MTSC algorithm. The three steps of FS-MVC comprise multidimensional feature extraction, multiview concentration, and multiview ensemble. In multidimensional feature extraction, the multivariate time series (MTSs) are mapped to multiple spaces by various series transformations to extract dimension-dependent and dimension-independent features. A new time series pooling feature is extracted, which denotes the power of proportion of positive values (PPPV) in the feature map generated by the convolution operation. The ensemble-group feature selection framework is introduced into the MTSC task to remove redundant features and generate multiviews through feature vector concentration in multiview concentration. In multiview ensemble, each view feature is input into the corresponding classifier, and then, the final prediction label is obtained by the hard voting ensemble. Feature diversity is improved via the series transformations and dimension-dependent and dimension-independent PPPV features, while feature stability is enhanced significantly by the ensemble-group feature selection framework. Finally, the superiority of FS-MVC over other state-of-the-art MTSC algorithms is demonstrated in both contrast experiments on the public UEA MTS and the practical excavator datasets.

关键词： Feature extraction Time series analysis Fault diagnosis Sensors classification algorithms Task analysis Rockets Fault diagnosis feature extraction feature selection multivariate time series classification (MTSC)

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Image classification Using Spectral-Spatial Dual Random Fields With Gaussian and Markov Processes

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 4199-4212页

作者： Zhang, Yaqiu Liu, Lizhi Yang, Xinnian Hubei Univ Automot Technol Sch Elect & Informat Engn Shiyan 442002 Peoples R China Liaoning Tech Univ Sch Geomat Fuxin 123000 Peoples R China Tarim Univ Coll Landscape & Forestry Xinjiang 843399 Peoples R China Inner Mongolia Agr Univ Coll Forestry Hohhot 010019 Peoples R China Hubei Univ Automot Technol Sch Intelligent Connected Vehicle Shiyan 442002 Peoples R China

This article presents a novel hyperspectral image (HSI) classification approach that integrates the sparse inducing variational Gaussian process (SIVGP) with a spatially adaptive Markov random field (SAMRF), termed G-MDRF. Variational inference is employed to obtain a sparse approximation of the posterior distribution, modeling the spectral field within the latent function space. Subsequently, SAMRF is utilized to model the spatial prior within the function space, while the alternating direction method of multipliers (ADMM) is employed to enhance computational efficiency. Experimental results on three datasets with varying complexity show that the proposed algorithm improves computational efficiency by approximately 152 times and accuracy by about 7%-26% compared to the current popular Gaussian process methods. Compared to classical random field methods, G-MDRF rapidly achieves a convergent solution with only one ten-thousandth to one hundred-thousandth of the iterations, improving accuracy by about 5%-18%. Particularly, when the number of classes in the dataset increases and the scene becomes more complex, the proposed method demonstrates a greater advantage in both computational efficiency and classification accuracy compared to existing methods.

关键词： Computational modeling Uncertainty Atmospheric modeling Vectors Indexes Markov random fields classification algorithms Bayes methods Accuracy Random variables Gaussian processes (GPs) hyperspectral image (HSI) classification Markov random field (MRF) stochastic processes

来源：评论

学校读者我要写书评

暂无评论

Environmentally-Robust Defect classification With Domain Augmentation Framework

引用

IEEE ACCESS 2024年 12卷 122684-122694页

作者： Lee, Sungho Shim, Jaewoong Seoul Natl Univ Sci & Technol Dept Data Sci Seoul 01811 South Korea

Visual defect classification is a critical process in manufacturing systems, aiming to achieve high-quality production and reduce costs. Although deep learning-based defect classification models have achieved significant success, their performance can be significantly diminished due to 'environment shifts'-variations in manufacturing environments across multiple production lines. To address this challenge, we propose a domain augmentation framework to construct an environmentally-robust defect classification model, delivering high performance across various manufacturing environments using a training dataset from only a single production line. In our framework, each environment is treated as a separate domain, and multiple augmented domains are created using image transformation functions. Subsequently, a defect classification model is trained using a multi-source domain generalization (DG) method with these augmented domains. This approach mitigates the single-source DG problem to a multi-source DG problem, enabling the adoption of multi-source DG methods, which leads to performance improvements. The effectiveness of the proposed framework is demonstrated through experiments on a dataset provided by a Korean manufacturing company.

关键词： Training Production Data models Training data Costs Manufacturing systems Image augmentation Visual analytics Defect detection classification algorithms Visual defect classification environment shift domain generalization image augmentation manufacturing system

来源：评论

学校读者我要写书评

暂无评论

A Sparse 2-D Magnetic Inversion Method for Subsurface Target classification

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2025年 22卷

作者： Mu, Yaxin Chen, Luzhao Liu, Xin Beijing Informat Sci & Technol Univ Sch Informat & Commun Engn Beijing 100101 Peoples R China Beijing Automat Control Equipment Inst Beijing 100074 Peoples R China Beijing Inst Satellite Informat Engn State Key Lab Space Ground Integrated Informat Tec Beijing 100095 Peoples R China

Magnetic inversion plays an important role in target classification and recognition. However, traditional magnetic susceptibility inversion methods often fall into local minima, and require high storage space and computing power. This letter proposes a novel 2-D magnetic inversion method for compact ferrous targets, the 3-D object is projected onto a 2-D inversion plane and a linear inversion model based on the modulus of magnetic moment on a 2-D horizontal slice is created. The compact anomaly target is composed of multiple nonzero uniformly connected grids in spatial domain, so the target is sparse in the gradient domain, because the nonzero elements on the inversion plane are only located at the boundary of the target. Using the sparseness, total variation compressed sensing (TV-CS) framework is employed to solve the 2-D magnetic inversion problem, achieving rapid classification and identification of hidden targets. In addition, numerical simulations have been performed, and experimental results indicate that the proposed algorithm is able to accurately delineate targets of different shapes and distinguish between solid and hollow targets. For a compact 3-D target, the 2-D magnetic inversion time is 0.096 s with a spatial resolution of 0.5 m, and 2.36 s with a spatial resolution of 0.1 m.

关键词： Solid modeling Three-dimensional displays Target recognition Shape Magnetic domains Solids classification algorithms Spatial resolution Compressed sensing Magnetic susceptibility Compressed sensing (CS) magnetic anomaly detection magnetic inversion subsurface target

来源：评论

学校读者我要写书评

暂无评论

Dark Side of the Web: Dark Web classification Based on TextCNN and Topic Modeling Weight

引用

IEEE ACCESS 2024年 12卷 36361-36371页

作者： Shin, Gun-Yoon Jang, Younghoan Kim, Dong-Wook Park, Sungjin Park, A-Ran Kim, Younghwan Han, Myung-Mook Gachon Univ Dept AI Software Seongnam Si 13120 South Korea Cyber Warfare LIG Nex1 Seongnam Si 13488 South Korea

The Dark Web is an internet domain that ensures user anonymity and has increasingly become a focal point for illegal activities and a repository for information on cyberattacks owing to the challenges in tracking its users. This study examined the classification of the Dark Web in relation to these cyber threats. We processed Dark Web texts to extract vector types suitable for machine learning classification. Traditional methods utilizing the entirety of Dark Web texts to generate features result in vectors including all words found on the Dark Web. However, this approach incorporates extraneous information in the vectors, diminishing learning effectiveness and extending processing duration. The research aimed to optimize the classification process by selectively focusing on keywords within each class, thereby curtailing word vector dimensions. This optimization was facilitated by leveraging the anonymity characteristic of the Dark Web and employing topic-modeling-based weight generation. These methods enabled the creation of word vectors with a constrained feature set, enhancing the distinction of Dark Web classes. To further improve classification performance, we integrated TextCNN with topic modeling weights. For validation, we employed two datasets and compared the performance of the model with other text classification algorithms, where the proposed model demonstrated superior effectiveness in Dark Web classification.

关键词： Dark Web Feature extraction Data models Analytical models Text categorization Graph neural networks classification algorithms Dark web dark web analysis text classification topic modeling model explanation

来源：评论

学校读者我要写书评

暂无评论

Time Series classification Using Federated Convolutional Neural Networks and Image-Based Representations

引用

IEEE ACCESS 2025年 13卷 56180-56194页

作者： Silva, Felipe A. R. Orang, Omid Javier Erazo-Costa, Fabricio Silva, Petronio C. L. Barros, Pedro H. Ferreira, Ricardo P. M. Gadelha Guimaraes, Frederico Univ Fed Minas Gerais Grad Program Elect Engn BR-31270901 Belo Horizonte MG Brazil Univ Fed Minas Gerais Dept Comp Sci BR-31270901 Belo Horizonte MG Brazil Univ Fed Ouro Preto UFOP Dept Elect Engn BR-35931008 Joao Monlevade MG Brazil Inst Fed Norte Minas Gerais IFNMG BR-39480000 Januaria MG Brazil Univ Fed Minas Gerais Dept Mech Engn BR-31270901 Belo Horizonte MG Brazil

Time series classification (TSC) has numerous applications across various domains. This research introduces a federated hybrid TSC method that combines image-based time series representation techniques with Convolutional Neural Networks (CNNs) in a decentralized framework. Specifically, three image representation techniques-Motif representation of numerical time series (NMotif), Motif representation of fuzzy time series (FTSMotif), and Polar-are utilized to convert raw data into image representations, which are then used as inputs for CNNs. Federated Learning (FL) enables collaborative training across distributed clients while ensuring data privacy. The method's effectiveness is evaluated using 40 datasets from the UCR Archive. The results show that the FL model surpasses traditional baselines by up to 1.9% while enabling collaborative learning and preserving privacy. Although centralized state-of-the-art (SOTA) models such as Rocket and ResNet achieve higher overall accuracy, the proposed approach offers a competitive and practical alternative for real-world scenarios where centralized training is infeasible due to privacy constraints. These findings highlight the potential of our proposed federated image-based TSC as a scalable and privacy-aware solution for time series analysis.

关键词： Time series analysis Convolutional neural networks Accuracy Fuzzy logic Data privacy classification algorithms Training Servers Image representation Federated learning Time series classification convolutional neural networks image-based representation federated learning privacy-preserving

来源：评论

学校读者我要写书评

暂无评论

A CNN-Based Approach for Classical Music Recognition and Style Emotion classification

引用

IEEE ACCESS 2025年 13卷 20647-20666页

作者： Shi, Yawen Henan Univ Sci & Technol Sch Art & Design Luoyang 471000 Henan Peoples R China

Music recognition refers to the process of automatically recognizing and classifying the musical content in audio signals using computer technology and algorithms. Music recognition technology can help people recognize information such as the music title, artist, musical style, rhythm, and the emotions conveyed by the music in the audio, thus enabling applications like automated music information retrieval and recommendation systems. Classical music, due to its vast quantity, diverse types, and time span covering several centuries, presents challenges that existing music recognition software and traditional music recognition algorithms cannot effectively address. In this study, The model based on convolutional neural networks (CNNs) is proposed, allowing people to recognize the classical music title, style, and emotions contained in a piece of music. The proposed model is particularly beneficial for individuals who are interested in classical music but lack extensive knowledge about it, as it provides essential information about the pieces. By extracting multidimensional features from classical music, the model can recognize the title, style, and emotions expressed. To improve the model's recognition accuracy, various noises are introduced to the dataset. Meanwhile, in this study, a novel loss function has been devised to more effectively assess the model's performance. For searching for optimal performance of the model, a novel optimization algorithm also be proposed to find optimal hyperparameters of loss function. The experiment results show average title recognition accuracy is 0.98, average style recognition accuracy is 0.89 and average emotion recognition accuracy is 0.93. These results adequately demonstrate that the proposal model significantly enhances the model's ability to accurately recognize the titles, styles, and emotions of classical music, achieving high recognition rates even in noisy environments.

关键词： Emotion recognition Accuracy Feature extraction Multiple signal classification classification algorithms Noise Deep learning Recommender systems Proposals Heuristic algorithms CNN deep learning music recognition music retrieval optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Low-Resolution Aerial Imagery classification by Actively Learning Human Perception and Manifold-Regularized Feature Selection

引用

IEEE ACCESS 2024年 12卷 31107-31116页

作者： Xu, Kunpeng Liu, Dongmei Wang, Zhiming Xuzhou Coll Ind Technol Xuzhou 221116 Jiangsu Peoples R China Jiangxi Vocat & Tech Coll Ind & Trade Nanchang 330000 Jiangxi Peoples R China Anhui Univ Coll AI Hefei 230009 Peoples R China

There are plenty of high- and low-altitude earth observation satellites asynchronously capture massive-scale aerial images everyday. In practice, high-altitude satellites take low-resolution (LR) aerial pictures, each covers a considerably large area. Comparatively, low-altitude satellites capture high-resolution (HR) aerial photos, each depicts a relatively small area. Effectively identifying the LR aerial images' semantic categories is an indispensable module in many AI systems. However, it is also a challenging task due to: 1) the inefficiency to label adequate training samples, and 2) the difficulty to describe how humans preserving the world. To handle these problems, this work presents a so-called active perception learning coupled with a manifold-regularized feature selection (MRFS), aiming at acquiring perceptual and discriminative visual representation to classify LR aerial photos. Particularly, by stimulating how humans sequentially perceiving different salient regions, we deploy an active learning paradigm to divide an LR aerial image into a few attractive regions as well as a rich set of non-attractive regions. Theoretically, the active learning technique ensures that the selected attractive regions can maximally reconstruct each LR aerial image, which well mimics human visual perception. Subsequently, a novel MRFS is designed to select high quality features from the actively detected attractive regions. MRFS has many advantages: 1) it is built upon a semi-supervised architecture that a small proportion of labeled samples are required;2) a linear classifier based on the selected features can be learned in the unified MRFS framework;3) the labeled/unlabeled sample distribution are optimally preserved during feature selection (FS). Plenty of empirical results shown the superiority of the proposed classification pipeline.

关键词： Visualization Semantics Image resolution Support vector machines Image reconstruction Training Manifold learning Satellite images Machine learning classification algorithms Manifold regularizer selecting features low-resolution aerial imaging machine learning classification

来源：评论

学校读者我要写书评

暂无评论

Nighttime Visibility classification Based on Stable Light Sources

引用

IEEE ACCESS 2024年 12卷 129870-129879页

作者： Liang, Zhuoran Cao, Yu Wang, Zhilei Li, Yongqiang Chen, Zan Sun, Ting Hangzhou Meteorol Bur Hangzhou 310051 Zhejiang Peoples R China Zhejiang Univ Technol Coll Informat Engn Hangzhou 310014 Zhejiang Peoples R China Zhejiang Int Studies Univ Sch Culture & Tourism Hangzhou 310000 Zhejiang Peoples R China

To enhance the accuracy of existing nighttime visibility estimation methods, this study proposes a classification algorithm for nighttime visibility levels based on stable light sources. Initially, a target detection network identifies all stable streetlights in the image and extracts the light source blocks. Subsequently, these blocks undergo fog classification through a classification network. The blocks we then sorted by brightness values and assigned corresponding weights. Finally, the classification results and weights are combined to categorize the nighttime image visibility levels. Experimental results show that the accuracy of our nighttime visibility classification algorithm reaches 77.6% on real-world datasets, outperforming existing methods and demonstrating good generalization across different scenes.

关键词： Light sources Feature extraction Estimation Brightness Surveillance Image color analysis classification algorithms Night images visibility classification light source block generalization

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Fault classification Algorithm for Real Fault Data in Transmission Lines

引用

IEEE ACCESS 2024年 12卷 121156-121168页

作者： Lim, Se-Heon Kim, Taegeun Lee, Kyeong-Yeong Song, Kyung-Min Yoon, Sung-Guk Soongsil Univ Dept Elect Engn Seoul 06978 South Korea

Fault classification in power transmission lines is important in distance relaying for identifying the accurate phases implicated in the fault occurrence. Generally, the accuracy of fault classification algorithms is evaluated by simulation data, which shows quite different characteristics from real fault data. Also, most of the previous works on fault classification used a single-stage method such as a rule-based algorithm or machine learning-based algorithm. Because of the diverse characteristics of real fault data, the performance of the single-stage method is limited. To address these issues, this paper proposes a novel two-stage algorithm that combines the strengths of rule-based and machine-learning algorithms to improve the accuracy of real fault data. A case study using real fault data shows that the proposed two-stage algorithm outperforms other conventional single-stage algorithms.

关键词： classification algorithms Artificial neural networks Accuracy Random forests Machine learning algorithms Reviews Prediction algorithms Root mean square Power transmission lines Two-stage algorithm rule-based artificial neural network root mean square

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：